This pullreq has a few miscellaneous fixes, plus the non-controversial (and largely reviewed) parts of my series removing deprecated arm boards. (The rest of that series I will send out a v2 for once this lands.) -- PMM The following changes since commit 718780d20470c66a3a36d036b29148d5809dc855: Merge tag 'pull-nvme-20241001' of https://gitlab.com/birkelund/qemu into staging (2024-10-01 11:34:07 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20241001 for you to fetch changes up to be025ce676d0f8fd094d17b34e87305a1c8fb595: hw: Remove omap2 specific defines and enums (2024-10-01 16:08:02 +0100) ---------------------------------------------------------------- target-arm queue: * MAINTAINERS: Update STM32L4x5 and B-L475E-IOT01A maintainers * hw/arm/xlnx: Connect secondary CGEM IRQs * m25p80: Add SFDP table for mt35xu01g flash * target/arm: Avoid target_ulong for physical address lookups * hw/ssi/xilinx_spips: Fix flash erase assert in dual parallel configuration * hw: fix memory leak in IRQState allocation * hw/sd/sdcard: Fix handling of disabled boot partitions * arm: Remove deprecated board models ---------------------------------------------------------------- Ard Biesheuvel (1): target/arm: Avoid target_ulong for physical address lookups Inès Varhol (1): MAINTAINERS: Update STM32L4x5 and B-L475E-IOT01A maintainers Jan Luebbe (1): hw/sd/sdcard: Fix handling of disabled boot partitions Kinsey Moore (1): hw/arm/xlnx: Connect secondary CGEM IRQs Matheus Tavares Bernardino (1): hw: fix memory leak in IRQState allocation Peter Maydell (47): hw/arm: Remove deprecated akita, borzoi, spitz, terrier, tosa boards hw/input: Drop ADS7846 device hw/display: Remove tc6393xb device hw/arm/KConfig: Replace ZAURUS with ZAURUS_SCOOP hw/arm: Remove 'cheetah' machine hw/arm: Remove 'connex' and 'verdex' machines hw/arm: Remove 'mainstone' machine hw/misc: Remove MAINSTONE_FPGA device hw/arm: Remove 'z2' machine hw/arm: Remove STRONGARM->PXA2XX dependency hw/timer/pxa2xx_timer: Remove use of pxa.h header hw/arm: Remove pxa2xx.c hw/sd: Remove pxa2xx_mmci.c hw/input: Remove pxa2xx_keypad hw/display: Remove pxa2xx_lcd.c hw/dma: Remove pxa2xx_dma hw/pcmcia: Remove pxa2xx pcmcia device hw/arm: Remove pxa2xx_gpio hw/arm: Remove pxa2xx_pic hw/timer: Remove pxa27x-timer hw/arm: Remove 'n800' and 'n810' machines hw/misc: Remove cbus hw/display: Remove Blizzard display device hw/input: Remove tsc2005 touchscreen controller hw/input: Remove tsc210x device hw/rtc: Remove twl92230 device hw/input: Remove lm832x device hw/block: Remove OneNAND device hw/usb: Remove tusb6010 USB controller hw/usb: Remove MUSB USB host controller docs: Document removal of old Arm boards hw/arm: Remove omap2.c hw/gpio: Remove TYPE_OMAP2_GPIO hw/char: Remove omap2_uart hw/intc: Remove omap2-intc device hw/sd: Remove omap2_mmc device hw/misc: Remove omap_sdrc device hw/misc: Remove omap_gpmc hw/timer: Remove omap_gptimer hw/timer: Remove omap_synctimer hw/ssi: Remove omap_mcspi hw/misc: Remove omap_tap device hw/display: Remove omap_dss hw/misc: Remove omap_l4 device hw/misc/omap_clk: Remove OMAP2-specifics hw/dma: Remove omap_dma4 device hw: Remove omap2 specific defines and enums Shiva sagar Myana (2): m25p80: Add SFDP table for mt35xu01g flash hw/ssi/xilinx_spips: Fix flash erase assert in dual parallel configuration MAINTAINERS | 99 +- docs/about/deprecated.rst | 15 - docs/about/removed-features.rst | 14 + docs/system/arm/gumstix.rst | 21 - docs/system/arm/mainstone.rst | 25 - docs/system/arm/nseries.rst | 33 - docs/system/arm/palm.rst | 23 - docs/system/arm/xscale.rst | 35 - docs/system/target-arm.rst | 5 - configs/devices/arm-softmmu/default.mak | 7 - hw/block/m25p80_sfdp.h | 1 + include/hw/arm/omap.h | 350 +--- include/hw/arm/pxa.h | 197 --- include/hw/arm/xlnx-versal.h | 1 + include/hw/arm/xlnx-zynqmp.h | 1 + include/hw/block/flash.h | 3 - include/hw/display/blizzard.h | 21 - include/hw/display/tc6393xb.h | 21 - include/hw/input/lm832x.h | 28 - include/hw/input/tsc2xxx.h | 41 - include/hw/misc/cbus.h | 31 - include/hw/usb/hcd-musb.h | 49 - target/arm/internals.h | 4 +- hw/arm/gumstix.c | 141 -- hw/arm/mainstone.c | 175 -- hw/arm/nseries.c | 1473 ----------------- hw/arm/omap2.c | 2715 ------------------------------- hw/arm/palm.c | 324 ---- hw/arm/pxa2xx.c | 2393 --------------------------- hw/arm/pxa2xx_gpio.c | 365 ----- hw/arm/pxa2xx_pic.c | 359 ---- hw/arm/spitz.c | 1284 --------------- hw/arm/tosa.c | 327 ---- hw/arm/xlnx-versal.c | 12 +- hw/arm/xlnx-zynqmp.c | 11 +- hw/arm/z2.c | 355 ---- hw/block/m25p80.c | 3 +- hw/block/m25p80_sfdp.c | 37 + hw/block/onenand.c | 872 ---------- hw/char/omap_uart.c | 113 -- hw/core/irq.c | 19 +- hw/display/blizzard.c | 1026 ------------ hw/display/omap_dss.c | 1093 ------------- hw/display/pxa2xx_lcd.c | 1451 ----------------- hw/display/tc6393xb.c | 568 ------- hw/dma/omap_dma.c | 451 +---- hw/dma/pxa2xx_dma.c | 591 ------- hw/gpio/omap_gpio.c | 557 ------- hw/input/ads7846.c | 186 --- hw/input/lm832x.c | 528 ------ hw/input/pxa2xx_keypad.c | 331 ---- hw/input/tsc2005.c | 571 ------- hw/input/tsc210x.c | 1241 -------------- hw/intc/omap_intc.c | 276 ---- hw/misc/cbus.c | 619 ------- hw/misc/mst_fpga.c | 269 --- hw/misc/omap_clk.c | 527 +----- hw/misc/omap_gpmc.c | 898 ---------- hw/misc/omap_l4.c | 162 -- hw/misc/omap_sdrc.c | 167 -- hw/misc/omap_tap.c | 117 -- hw/pcmcia/pxa2xx.c | 248 --- hw/rtc/twl92230.c | 882 ---------- hw/sd/omap_mmc.c | 63 - hw/sd/pxa2xx_mmci.c | 594 ------- hw/sd/sd.c | 7 - hw/ssi/omap_spi.c | 380 ----- hw/ssi/xilinx_spips.c | 4 +- hw/timer/omap_gptimer.c | 512 ------ hw/timer/omap_synctimer.c | 110 -- hw/timer/pxa2xx_timer.c | 25 - hw/usb/hcd-musb.c | 1553 ------------------ hw/usb/tusb6010.c | 850 ---------- target/arm/ptw.c | 16 +- tests/qtest/libqos/arm-n800-machine.c | 92 -- hw/arm/Kconfig | 89 +- hw/arm/meson.build | 9 - hw/block/Kconfig | 3 - hw/block/meson.build | 1 - hw/display/Kconfig | 3 - hw/display/meson.build | 4 - hw/dma/meson.build | 1 - hw/gpio/Kconfig | 3 + hw/gpio/meson.build | 2 +- hw/input/Kconfig | 13 - hw/input/meson.build | 5 - hw/input/trace-events | 3 - hw/misc/meson.build | 6 - hw/pcmcia/meson.build | 1 - hw/rtc/Kconfig | 4 - hw/rtc/meson.build | 1 - hw/sd/meson.build | 1 - hw/sd/trace-events | 4 - hw/ssi/meson.build | 1 - hw/timer/Kconfig | 3 + hw/timer/meson.build | 4 +- hw/usb/Kconfig | 8 - hw/usb/meson.build | 2 - tests/avocado/machine_arm_n8x0.py | 49 - tests/qtest/libqos/meson.build | 1 - 100 files changed, 146 insertions(+), 29043 deletions(-) delete mode 100644 docs/system/arm/gumstix.rst delete mode 100644 docs/system/arm/mainstone.rst delete mode 100644 docs/system/arm/nseries.rst delete mode 100644 docs/system/arm/palm.rst delete mode 100644 docs/system/arm/xscale.rst delete mode 100644 include/hw/arm/pxa.h delete mode 100644 include/hw/display/blizzard.h delete mode 100644 include/hw/display/tc6393xb.h delete mode 100644 include/hw/input/lm832x.h delete mode 100644 include/hw/input/tsc2xxx.h delete mode 100644 include/hw/misc/cbus.h delete mode 100644 include/hw/usb/hcd-musb.h delete mode 100644 hw/arm/gumstix.c delete mode 100644 hw/arm/mainstone.c delete mode 100644 hw/arm/nseries.c delete mode 100644 hw/arm/omap2.c delete mode 100644 hw/arm/palm.c delete mode 100644 hw/arm/pxa2xx.c delete mode 100644 hw/arm/pxa2xx_gpio.c delete mode 100644 hw/arm/pxa2xx_pic.c delete mode 100644 hw/arm/spitz.c delete mode 100644 hw/arm/tosa.c delete mode 100644 hw/arm/z2.c delete mode 100644 hw/block/onenand.c delete mode 100644 hw/display/blizzard.c delete mode 100644 hw/display/omap_dss.c delete mode 100644 hw/display/pxa2xx_lcd.c delete mode 100644 hw/display/tc6393xb.c delete mode 100644 hw/dma/pxa2xx_dma.c delete mode 100644 hw/input/ads7846.c delete mode 100644 hw/input/lm832x.c delete mode 100644 hw/input/pxa2xx_keypad.c delete mode 100644 hw/input/tsc2005.c delete mode 100644 hw/input/tsc210x.c delete mode 100644 hw/misc/cbus.c delete mode 100644 hw/misc/mst_fpga.c delete mode 100644 hw/misc/omap_gpmc.c delete mode 100644 hw/misc/omap_l4.c delete mode 100644 hw/misc/omap_sdrc.c delete mode 100644 hw/misc/omap_tap.c delete mode 100644 hw/pcmcia/pxa2xx.c delete mode 100644 hw/rtc/twl92230.c delete mode 100644 hw/sd/pxa2xx_mmci.c delete mode 100644 hw/ssi/omap_spi.c delete mode 100644 hw/timer/omap_gptimer.c delete mode 100644 hw/timer/omap_synctimer.c delete mode 100644 hw/usb/hcd-musb.c delete mode 100644 hw/usb/tusb6010.c delete mode 100644 tests/qtest/libqos/arm-n800-machine.c delete mode 100755 tests/avocado/machine_arm_n8x0.py From: Inès Varhol <ines.varhol@telecom-paris.fr> It has been a learning experience to contribute to QEMU for our end-of-studies project. For a few months now, Arnaud and I aren't actively involved anymore as we lack time and access to the hardware. Therefore it's high time to update the maintainers file: from now on, Samuel Tardieu who is behind the project will be taking up the role of maintainer. This commit updates maintainers and the list of files, and places the two devices in alphabetical order. Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Signed-off-by: Samuel Tardieu <sam@rfc1149.net> Message-id: 20240921104751.43671-1-ines.varhol@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 41 +++++++++++++++++++++-------------------- 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/timer/armv7m_systick.h F: include/hw/misc/armv7m_ras.h F: tests/qtest/test-arm-mptimer.c +B-L475E-IOT01A IoT Node +M: Samuel Tardieu <sam@rfc1149.net> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/b-l475e-iot01a.c +F: hw/display/dm163.c +F: tests/qtest/dm163-test.c + Exynos M: Igor Mitsyanko <i.mitsyanko@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> @@ -XXX,XX +XXX,XX @@ F: include/hw/input/gamepad.h F: include/hw/timer/stellaris-gptm.h F: docs/system/arm/stellaris.rst +STM32L4x5 SoC Family +M: Samuel Tardieu <sam@rfc1149.net> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/stm32l4x5_soc.c +F: hw/char/stm32l4x5_usart.c +F: hw/misc/stm32l4x5_exti.c +F: hw/misc/stm32l4x5_syscfg.c +F: hw/misc/stm32l4x5_rcc.c +F: hw/gpio/stm32l4x5_gpio.c +F: include/hw/*/stm32l4x5_*.h +F: tests/qtest/stm32l4x5* + STM32VLDISCOVERY M: Alexandre Iooss <erdnaxe@crans.org> L: qemu-arm@nongnu.org @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Maintained F: hw/arm/olimex-stm32-h405.c -STM32L4x5 SoC Family -M: Arnaud Minier <arnaud.minier@telecom-paris.fr> -M: Inès Varhol <ines.varhol@telecom-paris.fr> -L: qemu-arm@nongnu.org -S: Maintained -F: hw/arm/stm32l4x5_soc.c -F: hw/char/stm32l4x5_usart.c -F: hw/misc/stm32l4x5_exti.c -F: hw/misc/stm32l4x5_syscfg.c -F: hw/misc/stm32l4x5_rcc.c -F: hw/gpio/stm32l4x5_gpio.c -F: include/hw/*/stm32l4x5_*.h - -B-L475E-IOT01A IoT Node -M: Arnaud Minier <arnaud.minier@telecom-paris.fr> -M: Inès Varhol <ines.varhol@telecom-paris.fr> -L: qemu-arm@nongnu.org -S: Maintained -F: hw/arm/b-l475e-iot01a.c - SmartFusion2 M: Subbaraya Sundeep <sundeep.lkml@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> -- 2.34.1 From: Kinsey Moore <kinsey.moore@oarcorp.com> The Cadence GEM peripherals as configured for Zynq MPSoC and Versal platforms have two priority queues with separate interrupt sources for each. If the interrupt source for the second priority queue is not connected, they work in polling mode only. This change connects the second interrupt source for platforms where it is available. This patch has been tested using the lwIP stack with a Xilinx-supplied driver from their embeddedsw repository. Signed-off-by: Kinsey Moore <kinsey.moore@oarcorp.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 1 + include/hw/arm/xlnx-zynqmp.h | 1 + hw/arm/xlnx-versal.c | 12 +++++++++++- hw/arm/xlnx-zynqmp.c | 11 ++++++++++- 4 files changed, 23 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ struct Versal { struct { PL011State uart[XLNX_VERSAL_NR_UARTS]; CadenceGEMState gem[XLNX_VERSAL_NR_GEMS]; + OrIRQState gem_irq_orgate[XLNX_VERSAL_NR_GEMS]; XlnxZDMA adma[XLNX_VERSAL_NR_ADMAS]; VersalUsb2 usb; CanBusState *canbus[XLNX_VERSAL_NR_CANFD]; diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { MemoryRegion mr_unimp[XLNX_ZYNQMP_NUM_UNIMP_AREAS]; CadenceGEMState gem[XLNX_ZYNQMP_NUM_GEMS]; + OrIRQState gem_irq_orgate[XLNX_ZYNQMP_NUM_GEMS]; CadenceUARTState uart[XLNX_ZYNQMP_NUM_UARTS]; XlnxZynqMPCANState can[XLNX_ZYNQMP_NUM_CAN]; SysbusAHCIState sata; diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_gems(Versal *s, qemu_irq *pic) char *name = g_strdup_printf("gem%d", i); DeviceState *dev; MemoryRegion *mr; + OrIRQState *or_irq; object_initialize_child(OBJECT(s), name, &s->lpd.iou.gem[i], TYPE_CADENCE_GEM); + or_irq = &s->lpd.iou.gem_irq_orgate[i]; + object_initialize_child(OBJECT(s), "gem-irq-orgate[*]", + or_irq, TYPE_OR_IRQ); dev = DEVICE(&s->lpd.iou.gem[i]); qemu_configure_nic_device(dev, true, NULL); object_property_set_int(OBJECT(dev), "phy-addr", 23, &error_abort); object_property_set_int(OBJECT(dev), "num-priority-queues", 2, &error_abort); + object_property_set_int(OBJECT(or_irq), + "num-lines", 2, &error_fatal); + qdev_realize(DEVICE(or_irq), NULL, &error_fatal); + qdev_connect_gpio_out(DEVICE(or_irq), 0, pic[irqs[i]]); + object_property_set_link(OBJECT(dev), "dma", OBJECT(&s->mr_ps), &error_abort); sysbus_realize(SYS_BUS_DEVICE(dev), &error_fatal); @@ -XXX,XX +XXX,XX @@ static void versal_create_gems(Versal *s, qemu_irq *pic) mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); memory_region_add_subregion(&s->mr_ps, addrs[i], mr); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[irqs[i]]); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, qdev_get_gpio_in(DEVICE(or_irq), 0)); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 1, qdev_get_gpio_in(DEVICE(or_irq), 1)); g_free(name); } } diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zynqmp.c +++ b/hw/arm/xlnx-zynqmp.c @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_init(Object *obj) for (i = 0; i < XLNX_ZYNQMP_NUM_GEMS; i++) { object_initialize_child(obj, "gem[*]", &s->gem[i], TYPE_CADENCE_GEM); + object_initialize_child(obj, "gem-irq-orgate[*]", + &s->gem_irq_orgate[i], TYPE_OR_IRQ); } for (i = 0; i < XLNX_ZYNQMP_NUM_UARTS; i++) { @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) &error_abort); object_property_set_int(OBJECT(&s->gem[i]), "num-priority-queues", 2, &error_abort); + object_property_set_int(OBJECT(&s->gem_irq_orgate[i]), + "num-lines", 2, &error_fatal); + qdev_realize(DEVICE(&s->gem_irq_orgate[i]), NULL, &error_fatal); + qdev_connect_gpio_out(DEVICE(&s->gem_irq_orgate[i]), 0, gic_spi[gem_intr[i]]); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->gem[i]), errp)) { return; } sysbus_mmio_map(SYS_BUS_DEVICE(&s->gem[i]), 0, gem_addr[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gem[i]), 0, - gic_spi[gem_intr[i]]); + qdev_get_gpio_in(DEVICE(&s->gem_irq_orgate[i]), 0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gem[i]), 1, + qdev_get_gpio_in(DEVICE(&s->gem_irq_orgate[i]), 1)); } for (i = 0; i < XLNX_ZYNQMP_NUM_UARTS; i++) { -- 2.34.1 From: Shiva sagar Myana <Shivasagar.Myana@amd.com> Add the SFDP table for the Micron Xccela mt35xu01g flash. Signed-off-by: Shiva sagar Myana <Shivasagar.Myana@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20240829120117.616861-1-Shivasagar.Myana@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/block/m25p80_sfdp.h | 1 + hw/block/m25p80.c | 3 ++- hw/block/m25p80_sfdp.c | 37 +++++++++++++++++++++++++++++++++++++ 3 files changed, 40 insertions(+), 1 deletion(-) diff --git a/hw/block/m25p80_sfdp.h b/hw/block/m25p80_sfdp.h index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80_sfdp.h +++ b/hw/block/m25p80_sfdp.h @@ -XXX,XX +XXX,XX @@ #define M25P80_SFDP_MAX_SIZE (1 << 24) uint8_t m25p80_sfdp_n25q256a(uint32_t addr); +uint8_t m25p80_sfdp_mt35xu01g(uint32_t addr); uint8_t m25p80_sfdp_mt35xu02g(uint32_t addr); uint8_t m25p80_sfdp_mx25l25635e(uint32_t addr); diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -XXX,XX +XXX,XX @@ static const FlashPartInfo known_devices[] = { { INFO("n25q512ax3", 0x20ba20, 0x1000, 64 << 10, 1024, ER_4K) }, { INFO("mt25ql512ab", 0x20ba20, 0x1044, 64 << 10, 1024, ER_4K | ER_32K) }, { INFO_STACKED("mt35xu01g", 0x2c5b1b, 0x104100, 128 << 10, 1024, - ER_4K | ER_32K, 2) }, + ER_4K | ER_32K, 2), + .sfdp_read = m25p80_sfdp_mt35xu01g }, { INFO_STACKED("mt35xu02gbba", 0x2c5b1c, 0x104100, 128 << 10, 2048, ER_4K | ER_32K, 4), .sfdp_read = m25p80_sfdp_mt35xu02g }, diff --git a/hw/block/m25p80_sfdp.c b/hw/block/m25p80_sfdp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80_sfdp.c +++ b/hw/block/m25p80_sfdp.c @@ -XXX,XX +XXX,XX @@ static const uint8_t sfdp_n25q256a[] = { }; define_sfdp_read(n25q256a); +static const uint8_t sfdp_mt35xu01g[] = { + 0x53, 0x46, 0x44, 0x50, 0x06, 0x01, 0x01, 0xff, + 0x00, 0x06, 0x01, 0x10, 0x30, 0x00, 0x00, 0xff, + 0x84, 0x00, 0x01, 0x02, 0x80, 0x00, 0x00, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xe5, 0x20, 0x8a, 0xff, 0xff, 0xff, 0xff, 0x3f, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0xee, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, + 0xff, 0xff, 0x00, 0x00, 0x0c, 0x20, 0x11, 0xd8, + 0x0f, 0x52, 0x00, 0x00, 0x24, 0x5a, 0x99, 0x00, + 0x8b, 0x8e, 0x03, 0xe1, 0xac, 0x01, 0x27, 0x38, + 0x7a, 0x75, 0x7a, 0x75, 0xfb, 0xbd, 0xd5, 0x5c, + 0x00, 0x00, 0x70, 0xff, 0x81, 0xb0, 0x38, 0x36, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0x43, 0x0e, 0xff, 0xff, 0x21, 0xdc, 0x5c, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, +}; + +define_sfdp_read(mt35xu01g); + static const uint8_t sfdp_mt35xu02g[] = { 0x53, 0x46, 0x44, 0x50, 0x06, 0x01, 0x01, 0xff, 0x00, 0x06, 0x01, 0x10, 0x30, 0x00, 0x00, 0xff, -- 2.34.1 From: Ard Biesheuvel <ardb@kernel.org> target_ulong is typedef'ed as a 32-bit integer when building the qemu-system-arm target, and this is smaller than the size of an intermediate physical address when LPAE is being used. Given that Linux may place leaf level user page tables in high memory when built for LPAE, the kernel will crash with an external abort as soon as it enters user space when running with more than ~3 GiB of system RAM. So replace target_ulong with vaddr in places where it may carry an address value that is not representable in 32 bits. Fixes: f3639a64f602ea ("target/arm: Use softmmu tlbs for page table walking") Cc: qemu-stable@nongnu.org Reported-by: Arnd Bergmann <arnd@arndb.de> Tested-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Message-id: 20240927071051.1444768-1-ardb+git@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 4 ++-- target/arm/ptw.c | 16 ++++++++-------- 2 files changed, 10 insertions(+), 10 deletions(-) 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 @@ typedef struct GetPhysAddrResult { * * for PSMAv5 based systems we don't bother to return a full FSR format * value. */ -bool get_phys_addr(CPUARMState *env, target_ulong address, +bool get_phys_addr(CPUARMState *env, vaddr address, MMUAccessType access_type, ARMMMUIdx mmu_idx, GetPhysAddrResult *result, ARMMMUFaultInfo *fi) __attribute__((nonnull)); @@ -XXX,XX +XXX,XX @@ bool get_phys_addr(CPUARMState *env, target_ulong address, * Similar to get_phys_addr, but use the given security space and don't perform * a Granule Protection Check on the resulting address. */ -bool get_phys_addr_with_space_nogpc(CPUARMState *env, target_ulong address, +bool get_phys_addr_with_space_nogpc(CPUARMState *env, vaddr address, MMUAccessType access_type, ARMMMUIdx mmu_idx, ARMSecuritySpace space, GetPhysAddrResult *result, diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ typedef struct S1Translate { } S1Translate; static bool get_phys_addr_nogpc(CPUARMState *env, S1Translate *ptw, - target_ulong address, + vaddr address, MMUAccessType access_type, GetPhysAddrResult *result, ARMMMUFaultInfo *fi); static bool get_phys_addr_gpc(CPUARMState *env, S1Translate *ptw, - target_ulong address, + vaddr address, MMUAccessType access_type, GetPhysAddrResult *result, ARMMMUFaultInfo *fi); @@ -XXX,XX +XXX,XX @@ static ARMCacheAttrs combine_cacheattrs(uint64_t hcr, */ static bool get_phys_addr_disabled(CPUARMState *env, S1Translate *ptw, - target_ulong address, + vaddr address, MMUAccessType access_type, GetPhysAddrResult *result, ARMMMUFaultInfo *fi) @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_disabled(CPUARMState *env, } static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw, - target_ulong address, + vaddr address, MMUAccessType access_type, GetPhysAddrResult *result, ARMMMUFaultInfo *fi) @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw, } static bool get_phys_addr_nogpc(CPUARMState *env, S1Translate *ptw, - target_ulong address, + vaddr address, MMUAccessType access_type, GetPhysAddrResult *result, ARMMMUFaultInfo *fi) @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_nogpc(CPUARMState *env, S1Translate *ptw, } static bool get_phys_addr_gpc(CPUARMState *env, S1Translate *ptw, - target_ulong address, + vaddr address, MMUAccessType access_type, GetPhysAddrResult *result, ARMMMUFaultInfo *fi) @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_gpc(CPUARMState *env, S1Translate *ptw, return false; } -bool get_phys_addr_with_space_nogpc(CPUARMState *env, target_ulong address, +bool get_phys_addr_with_space_nogpc(CPUARMState *env, vaddr address, MMUAccessType access_type, ARMMMUIdx mmu_idx, ARMSecuritySpace space, GetPhysAddrResult *result, @@ -XXX,XX +XXX,XX @@ bool get_phys_addr_with_space_nogpc(CPUARMState *env, target_ulong address, return get_phys_addr_nogpc(env, &ptw, address, access_type, result, fi); } -bool get_phys_addr(CPUARMState *env, target_ulong address, +bool get_phys_addr(CPUARMState *env, vaddr address, MMUAccessType access_type, ARMMMUIdx mmu_idx, GetPhysAddrResult *result, ARMMMUFaultInfo *fi) { -- 2.34.1 From: Shiva sagar Myana <Shivasagar.Myana@amd.com> Ensure that the FIFO is checked for emptiness before popping data from it. Previously, the code directly popped the data from the FIFO without checking, which could cause an assertion failure: ../util/fifo8.c:67: fifo8_pop: Assertion `fifo->num > 0' failed. Signed-off-by: Shiva sagar Myana <Shivasagar.Myana@amd.com> Message-id: 20240924112035.1320865-1-Shivasagar.Myana@amd.com Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> [PMM: tweaked commit message] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/xilinx_spips.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/xilinx_spips.c +++ b/hw/ssi/xilinx_spips.c @@ -XXX,XX +XXX,XX @@ static void xilinx_spips_flush_txfifo(XilinxSPIPS *s) } else if (s->snoop_state == SNOOP_STRIPING || s->snoop_state == SNOOP_NONE) { for (i = 0; i < num_effective_busses(s); ++i) { - tx_rx[i] = fifo8_pop(&s->tx_fifo); + if (!fifo8_is_empty(&s->tx_fifo)) { + tx_rx[i] = fifo8_pop(&s->tx_fifo); + } } stripe8(tx_rx, num_effective_busses(s), false); } else if (s->snoop_state >= SNOOP_ADDR) { -- 2.34.1 From: Matheus Tavares Bernardino <quic_mathbern@quicinc.com> At e72a7f65c1 (hw: Move declaration of IRQState to header and add init function, 2024-06-29), we've changed qemu_allocate_irq() to use a combination of g_new() + object_initialize() instead of IRQ(object_new()). The latter sets obj->free, so that that the memory is properly cleaned when the object is finalized, but the former doesn't. Fixes: e72a7f65c1 (hw: Move declaration of IRQState to header and add init function) Signed-off-by: Matheus Tavares Bernardino <quic_mathbern@quicinc.com> Reviewed-by: BALATON Zoltan <balaton@eik.bme.hu> Reviewed-by: Brian Cain <bcain@quicinc.com> Message-id: 1723deb603afec3fa69a75970cef9aac62d57d62.1726674185.git.quic_mathbern@quicinc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/irq.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/hw/core/irq.c b/hw/core/irq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/irq.c +++ b/hw/core/irq.c @@ -XXX,XX +XXX,XX @@ void qemu_set_irq(qemu_irq irq, int level) irq->handler(irq->opaque, irq->n, level); } +static void init_irq_fields(IRQState *irq, qemu_irq_handler handler, + void *opaque, int n) +{ + irq->handler = handler; + irq->opaque = opaque; + irq->n = n; +} + void qemu_init_irq(IRQState *irq, qemu_irq_handler handler, void *opaque, int n) { object_initialize(irq, sizeof(*irq), TYPE_IRQ); - irq->handler = handler; - irq->opaque = opaque; - irq->n = n; + init_irq_fields(irq, handler, opaque, n); } qemu_irq *qemu_extend_irqs(qemu_irq *old, int n_old, qemu_irq_handler handler, @@ -XXX,XX +XXX,XX @@ qemu_irq *qemu_allocate_irqs(qemu_irq_handler handler, void *opaque, int n) qemu_irq qemu_allocate_irq(qemu_irq_handler handler, void *opaque, int n) { - IRQState *irq; - - irq = g_new(IRQState, 1); - qemu_init_irq(irq, handler, opaque, n); - + IRQState *irq = IRQ(object_new(TYPE_IRQ)); + init_irq_fields(irq, handler, opaque, n); return irq; } -- 2.34.1 From: Jan Luebbe <jlu@pengutronix.de> The enable bits in the EXT_CSD_PART_CONFIG ext_csd register do *not* specify whether the boot partitions exist, but whether they are enabled for booting. Existence of the boot partitions is specified by a EXT_CSD_BOOT_MULT != 0. Currently, in the case of boot-partition-size=1M and boot-config=0, Linux detects boot partitions of 1M. But as sd_bootpart_offset always returns 0, all reads/writes are mapped to the same offset in the backing file. Fix this bug by calculating the offset independent of which partition is enabled for booting. This bug is unlikely to affect many users with QEMU's current set of boards, because only aspeed sets boot-partition-size, and it also sets boot-config to 8. So to run into this a user would have to manually mark the boot partition non-booting from within the guest. Cc: qemu-stable@nongnu.org Signed-off-by: Jan Luebbe <jlu@pengutronix.de> Message-id: 20240906164834.130257-1-jlu@pengutronix.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: added note to commit message about effects of bug] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/sd.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ static uint32_t sd_blk_len(SDState *sd) */ static uint32_t sd_bootpart_offset(SDState *sd) { - bool partitions_enabled; unsigned partition_access; if (!sd->boot_part_size || !sd_is_emmc(sd)) { return 0; } - partitions_enabled = sd->ext_csd[EXT_CSD_PART_CONFIG] - & EXT_CSD_PART_CONFIG_EN_MASK; - if (!partitions_enabled) { - return 0; - } - partition_access = sd->ext_csd[EXT_CSD_PART_CONFIG] & EXT_CSD_PART_CONFIG_ACC_MASK; switch (partition_access) { -- 2.34.1 The Sharp XScale-based PDA board models akita, borzoi, spitz, terrier, and tosa were all deprecated in 9.0, so our deprecation cycle permits removing them for the 9.2 release. Remove the source files for the board models themselves, and their documentation. There were no tests for these boards. We will move the text describing the dropped boards from deprecated.rst to removed-features.rst when we've cleaned up all the boards it lists. Device models used only by removed board models will be removed in separate commits. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-2-peter.maydell@linaro.org --- MAINTAINERS | 3 - docs/system/arm/xscale.rst | 35 - docs/system/target-arm.rst | 1 - configs/devices/arm-softmmu/default.mak | 2 - hw/arm/spitz.c | 1284 ----------------------- hw/arm/tosa.c | 327 ------ hw/arm/Kconfig | 23 - hw/arm/meson.build | 2 - 8 files changed, 1677 deletions(-) delete mode 100644 docs/system/arm/xscale.rst delete mode 100644 hw/arm/spitz.c delete mode 100644 hw/arm/tosa.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes F: hw/arm/mainstone.c -F: hw/arm/spitz.c -F: hw/arm/tosa.c F: hw/arm/z2.c F: hw/*/pxa2xx* F: hw/display/tc6393xb.c @@ -XXX,XX +XXX,XX @@ F: include/hw/adc/max111x.h F: include/hw/arm/pxa.h F: include/hw/arm/sharpsl.h F: include/hw/display/tc6393xb.h -F: docs/system/arm/xscale.rst F: docs/system/arm/mainstone.rst SABRELITE / i.MX6 diff --git a/docs/system/arm/xscale.rst b/docs/system/arm/xscale.rst deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/system/arm/xscale.rst +++ /dev/null @@ -XXX,XX +XXX,XX @@ -Sharp XScale-based PDA models (``akita``, ``borzoi``, ``spitz``, ``terrier``, ``tosa``) -======================================================================================= - -The Sharp Zaurus are PDAs based on XScale, able to run Linux ('SL series'). - -The SL-6000 (\"Tosa\"), released in 2005, uses a PXA255 System-on-chip. - -The SL-C3000 (\"Spitz\"), SL-C1000 (\"Akita\"), SL-C3100 (\"Borzoi\") and -SL-C3200 (\"Terrier\") use a PXA270. - -The clamshell PDA models emulation includes the following peripherals: - -- Intel PXA255/PXA270 System-on-chip (ARMv5TE core) - -- NAND Flash memory - not in \"Tosa\" - -- IBM/Hitachi DSCM microdrive in a PXA PCMCIA slot - not in \"Akita\" - -- On-chip OHCI USB controller - not in \"Tosa\" - -- On-chip LCD controller - -- On-chip Real Time Clock - -- TI ADS7846 touchscreen controller on SSP bus - -- Maxim MAX1111 analog-digital converter on |I2C| bus - -- GPIO-connected keyboard controller and LEDs - -- Secure Digital card connected to PXA MMC/SD host - -- Three on-chip UARTs - -- WM8750 audio CODEC on |I2C| and |I2S| buses diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/orangepi arm/palm arm/raspi - arm/xscale arm/collie arm/sx1 arm/stellaris diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ # CONFIG_ZYNQ=n # CONFIG_MAINSTONE=n # CONFIG_GUMSTIX=n -# CONFIG_SPITZ=n -# CONFIG_TOSA=n # CONFIG_Z2=n # CONFIG_NPCM7XX=n # CONFIG_COLLIE=n diff --git a/hw/arm/spitz.c b/hw/arm/spitz.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/spitz.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * PXA270-based Clamshell PDA platforms. - * - * Copyright (c) 2006 Openedhand Ltd. - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GNU GPL v2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "hw/arm/pxa.h" -#include "hw/arm/boot.h" -#include "sysemu/runstate.h" -#include "sysemu/sysemu.h" -#include "hw/pcmcia.h" -#include "hw/qdev-properties.h" -#include "hw/i2c/i2c.h" -#include "hw/irq.h" -#include "hw/ssi/ssi.h" -#include "hw/block/flash.h" -#include "qemu/timer.h" -#include "qemu/log.h" -#include "hw/arm/sharpsl.h" -#include "ui/console.h" -#include "hw/audio/wm8750.h" -#include "audio/audio.h" -#include "hw/boards.h" -#include "hw/sysbus.h" -#include "hw/adc/max111x.h" -#include "migration/vmstate.h" -#include "exec/address-spaces.h" -#include "qom/object.h" -#include "audio/audio.h" - -enum spitz_model_e { spitz, akita, borzoi, terrier }; - -struct SpitzMachineClass { - MachineClass parent; - enum spitz_model_e model; - int arm_id; -}; - -struct SpitzMachineState { - MachineState parent; - PXA2xxState *mpu; - DeviceState *mux; - DeviceState *lcdtg; - DeviceState *ads7846; - DeviceState *max1111; - DeviceState *scp0; - DeviceState *scp1; - DeviceState *misc_gpio; -}; - -#define TYPE_SPITZ_MACHINE "spitz-common" -OBJECT_DECLARE_TYPE(SpitzMachineState, SpitzMachineClass, SPITZ_MACHINE) - -#define zaurus_printf(format, ...) \ - fprintf(stderr, "%s: " format, __func__, ##__VA_ARGS__) - -/* Spitz Flash */ -#define FLASH_BASE 0x0c000000 -#define FLASH_ECCLPLB 0x00 /* Line parity 7 - 0 bit */ -#define FLASH_ECCLPUB 0x04 /* Line parity 15 - 8 bit */ -#define FLASH_ECCCP 0x08 /* Column parity 5 - 0 bit */ -#define FLASH_ECCCNTR 0x0c /* ECC byte counter */ -#define FLASH_ECCCLRR 0x10 /* Clear ECC */ -#define FLASH_FLASHIO 0x14 /* Flash I/O */ -#define FLASH_FLASHCTL 0x18 /* Flash Control */ - -#define FLASHCTL_CE0 (1 << 0) -#define FLASHCTL_CLE (1 << 1) -#define FLASHCTL_ALE (1 << 2) -#define FLASHCTL_WP (1 << 3) -#define FLASHCTL_CE1 (1 << 4) -#define FLASHCTL_RYBY (1 << 5) -#define FLASHCTL_NCE (FLASHCTL_CE0 | FLASHCTL_CE1) - -#define TYPE_SL_NAND "sl-nand" -OBJECT_DECLARE_SIMPLE_TYPE(SLNANDState, SL_NAND) - -struct SLNANDState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - DeviceState *nand; - uint8_t ctl; - uint8_t manf_id; - uint8_t chip_id; - ECCState ecc; -}; - -static uint64_t sl_read(void *opaque, hwaddr addr, unsigned size) -{ - SLNANDState *s = (SLNANDState *) opaque; - int ryby; - - switch (addr) { -#define BSHR(byte, from, to) ((s->ecc.lp[byte] >> (from - to)) & (1 << to)) - case FLASH_ECCLPLB: - return BSHR(0, 4, 0) | BSHR(0, 5, 2) | BSHR(0, 6, 4) | BSHR(0, 7, 6) | - BSHR(1, 4, 1) | BSHR(1, 5, 3) | BSHR(1, 6, 5) | BSHR(1, 7, 7); - -#define BSHL(byte, from, to) ((s->ecc.lp[byte] << (to - from)) & (1 << to)) - case FLASH_ECCLPUB: - return BSHL(0, 0, 0) | BSHL(0, 1, 2) | BSHL(0, 2, 4) | BSHL(0, 3, 6) | - BSHL(1, 0, 1) | BSHL(1, 1, 3) | BSHL(1, 2, 5) | BSHL(1, 3, 7); - - case FLASH_ECCCP: - return s->ecc.cp; - - case FLASH_ECCCNTR: - return s->ecc.count & 0xff; - - case FLASH_FLASHCTL: - nand_getpins(s->nand, &ryby); - if (ryby) - return s->ctl | FLASHCTL_RYBY; - else - return s->ctl; - - case FLASH_FLASHIO: - if (size == 4) { - return ecc_digest(&s->ecc, nand_getio(s->nand)) | - (ecc_digest(&s->ecc, nand_getio(s->nand)) << 16); - } - return ecc_digest(&s->ecc, nand_getio(s->nand)); - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "sl_read: bad register offset 0x%02" HWADDR_PRIx "\n", - addr); - } - return 0; -} - -static void sl_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - SLNANDState *s = (SLNANDState *) opaque; - - switch (addr) { - case FLASH_ECCCLRR: - /* Value is ignored. */ - ecc_reset(&s->ecc); - break; - - case FLASH_FLASHCTL: - s->ctl = value & 0xff & ~FLASHCTL_RYBY; - nand_setpins(s->nand, - s->ctl & FLASHCTL_CLE, - s->ctl & FLASHCTL_ALE, - s->ctl & FLASHCTL_NCE, - s->ctl & FLASHCTL_WP, - 0); - break; - - case FLASH_FLASHIO: - nand_setio(s->nand, ecc_digest(&s->ecc, value & 0xff)); - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "sl_write: bad register offset 0x%02" HWADDR_PRIx "\n", - addr); - } -} - -enum { - FLASH_128M, - FLASH_1024M, -}; - -static const MemoryRegionOps sl_ops = { - .read = sl_read, - .write = sl_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void sl_flash_register(PXA2xxState *cpu, int size) -{ - DeviceState *dev; - - dev = qdev_new(TYPE_SL_NAND); - - qdev_prop_set_uint8(dev, "manf_id", NAND_MFR_SAMSUNG); - if (size == FLASH_128M) - qdev_prop_set_uint8(dev, "chip_id", 0x73); - else if (size == FLASH_1024M) - qdev_prop_set_uint8(dev, "chip_id", 0xf1); - - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, FLASH_BASE); -} - -static void sl_nand_init(Object *obj) -{ - SLNANDState *s = SL_NAND(obj); - SysBusDevice *dev = SYS_BUS_DEVICE(obj); - - s->ctl = 0; - - memory_region_init_io(&s->iomem, obj, &sl_ops, s, "sl", 0x40); - sysbus_init_mmio(dev, &s->iomem); -} - -static void sl_nand_realize(DeviceState *dev, Error **errp) -{ - SLNANDState *s = SL_NAND(dev); - DriveInfo *nand; - - /* FIXME use a qdev drive property instead of drive_get() */ - nand = drive_get(IF_MTD, 0, 0); - s->nand = nand_init(nand ? blk_by_legacy_dinfo(nand) : NULL, - s->manf_id, s->chip_id); -} - -/* Spitz Keyboard */ - -#define SPITZ_KEY_STROBE_NUM 11 -#define SPITZ_KEY_SENSE_NUM 7 - -static const int spitz_gpio_key_sense[SPITZ_KEY_SENSE_NUM] = { - 12, 17, 91, 34, 36, 38, 39 -}; - -static const int spitz_gpio_key_strobe[SPITZ_KEY_STROBE_NUM] = { - 88, 23, 24, 25, 26, 27, 52, 103, 107, 108, 114 -}; - -/* Eighth additional row maps the special keys */ -static int spitz_keymap[SPITZ_KEY_SENSE_NUM + 1][SPITZ_KEY_STROBE_NUM] = { - { 0x1d, 0x02, 0x04, 0x06, 0x07, 0x08, 0x0a, 0x0b, 0x0e, 0x3f, 0x40 }, - { -1 , 0x03, 0x05, 0x13, 0x15, 0x09, 0x17, 0x18, 0x19, 0x41, 0x42 }, - { 0x0f, 0x10, 0x12, 0x14, 0x22, 0x16, 0x24, 0x25, -1 , -1 , -1 }, - { 0x3c, 0x11, 0x1f, 0x21, 0x2f, 0x23, 0x32, 0x26, -1 , 0x36, -1 }, - { 0x3b, 0x1e, 0x20, 0x2e, 0x30, 0x31, 0x34, -1 , 0x1c, 0x2a, -1 }, - { 0x44, 0x2c, 0x2d, 0x0c, 0x39, 0x33, -1 , 0x48, -1 , -1 , 0x38 }, - { 0x37, 0x3d, -1 , 0x45, 0x57, 0x58, 0x4b, 0x50, 0x4d, -1 , -1 }, - { 0x52, 0x43, 0x01, 0x47, 0x49, -1 , -1 , -1 , -1 , -1 , -1 }, -}; - -#define SPITZ_GPIO_AK_INT 13 /* Remote control */ -#define SPITZ_GPIO_SYNC 16 /* Sync button */ -#define SPITZ_GPIO_ON_KEY 95 /* Power button */ -#define SPITZ_GPIO_SWA 97 /* Lid */ -#define SPITZ_GPIO_SWB 96 /* Tablet mode */ - -/* The special buttons are mapped to unused keys */ -static const int spitz_gpiomap[5] = { - SPITZ_GPIO_AK_INT, SPITZ_GPIO_SYNC, SPITZ_GPIO_ON_KEY, - SPITZ_GPIO_SWA, SPITZ_GPIO_SWB, -}; - -#define TYPE_SPITZ_KEYBOARD "spitz-keyboard" -OBJECT_DECLARE_SIMPLE_TYPE(SpitzKeyboardState, SPITZ_KEYBOARD) - -struct SpitzKeyboardState { - SysBusDevice parent_obj; - - qemu_irq sense[SPITZ_KEY_SENSE_NUM]; - qemu_irq gpiomap[5]; - int keymap[0x80]; - uint16_t keyrow[SPITZ_KEY_SENSE_NUM]; - uint16_t strobe_state; - uint16_t sense_state; - - uint16_t pre_map[0x100]; - uint16_t modifiers; - uint16_t imodifiers; - uint8_t fifo[16]; - int fifopos, fifolen; - QEMUTimer *kbdtimer; -}; - -static void spitz_keyboard_sense_update(SpitzKeyboardState *s) -{ - int i; - uint16_t strobe, sense = 0; - for (i = 0; i < SPITZ_KEY_SENSE_NUM; i ++) { - strobe = s->keyrow[i] & s->strobe_state; - if (strobe) { - sense |= 1 << i; - if (!(s->sense_state & (1 << i))) - qemu_irq_raise(s->sense[i]); - } else if (s->sense_state & (1 << i)) - qemu_irq_lower(s->sense[i]); - } - - s->sense_state = sense; -} - -static void spitz_keyboard_strobe(void *opaque, int line, int level) -{ - SpitzKeyboardState *s = (SpitzKeyboardState *) opaque; - - if (level) - s->strobe_state |= 1 << line; - else - s->strobe_state &= ~(1 << line); - spitz_keyboard_sense_update(s); -} - -static void spitz_keyboard_keydown(SpitzKeyboardState *s, int keycode) -{ - int spitz_keycode = s->keymap[keycode & 0x7f]; - if (spitz_keycode == -1) - return; - - /* Handle the additional keys */ - if ((spitz_keycode >> 4) == SPITZ_KEY_SENSE_NUM) { - qemu_set_irq(s->gpiomap[spitz_keycode & 0xf], (keycode < 0x80)); - return; - } - - if (keycode & 0x80) - s->keyrow[spitz_keycode >> 4] &= ~(1 << (spitz_keycode & 0xf)); - else - s->keyrow[spitz_keycode >> 4] |= 1 << (spitz_keycode & 0xf); - - spitz_keyboard_sense_update(s); -} - -#define SPITZ_MOD_SHIFT (1 << 7) -#define SPITZ_MOD_CTRL (1 << 8) -#define SPITZ_MOD_FN (1 << 9) - -#define QUEUE_KEY(c) s->fifo[(s->fifopos + s->fifolen ++) & 0xf] = c - -static void spitz_keyboard_handler(void *opaque, int keycode) -{ - SpitzKeyboardState *s = opaque; - uint16_t code; - int mapcode; - switch (keycode) { - case 0x2a: /* Left Shift */ - s->modifiers |= 1; - break; - case 0xaa: - s->modifiers &= ~1; - break; - case 0x36: /* Right Shift */ - s->modifiers |= 2; - break; - case 0xb6: - s->modifiers &= ~2; - break; - case 0x1d: /* Control */ - s->modifiers |= 4; - break; - case 0x9d: - s->modifiers &= ~4; - break; - case 0x38: /* Alt */ - s->modifiers |= 8; - break; - case 0xb8: - s->modifiers &= ~8; - break; - } - - code = s->pre_map[mapcode = ((s->modifiers & 3) ? - (keycode | SPITZ_MOD_SHIFT) : - (keycode & ~SPITZ_MOD_SHIFT))]; - - if (code != mapcode) { -#if 0 - if ((code & SPITZ_MOD_SHIFT) && !(s->modifiers & 1)) { - QUEUE_KEY(0x2a | (keycode & 0x80)); - } - if ((code & SPITZ_MOD_CTRL) && !(s->modifiers & 4)) { - QUEUE_KEY(0x1d | (keycode & 0x80)); - } - if ((code & SPITZ_MOD_FN) && !(s->modifiers & 8)) { - QUEUE_KEY(0x38 | (keycode & 0x80)); - } - if ((code & SPITZ_MOD_FN) && (s->modifiers & 1)) { - QUEUE_KEY(0x2a | (~keycode & 0x80)); - } - if ((code & SPITZ_MOD_FN) && (s->modifiers & 2)) { - QUEUE_KEY(0x36 | (~keycode & 0x80)); - } -#else - if (keycode & 0x80) { - if ((s->imodifiers & 1 ) && !(s->modifiers & 1)) - QUEUE_KEY(0x2a | 0x80); - if ((s->imodifiers & 4 ) && !(s->modifiers & 4)) - QUEUE_KEY(0x1d | 0x80); - if ((s->imodifiers & 8 ) && !(s->modifiers & 8)) - QUEUE_KEY(0x38 | 0x80); - if ((s->imodifiers & 0x10) && (s->modifiers & 1)) - QUEUE_KEY(0x2a); - if ((s->imodifiers & 0x20) && (s->modifiers & 2)) - QUEUE_KEY(0x36); - s->imodifiers = 0; - } else { - if ((code & SPITZ_MOD_SHIFT) && - !((s->modifiers | s->imodifiers) & 1)) { - QUEUE_KEY(0x2a); - s->imodifiers |= 1; - } - if ((code & SPITZ_MOD_CTRL) && - !((s->modifiers | s->imodifiers) & 4)) { - QUEUE_KEY(0x1d); - s->imodifiers |= 4; - } - if ((code & SPITZ_MOD_FN) && - !((s->modifiers | s->imodifiers) & 8)) { - QUEUE_KEY(0x38); - s->imodifiers |= 8; - } - if ((code & SPITZ_MOD_FN) && (s->modifiers & 1) && - !(s->imodifiers & 0x10)) { - QUEUE_KEY(0x2a | 0x80); - s->imodifiers |= 0x10; - } - if ((code & SPITZ_MOD_FN) && (s->modifiers & 2) && - !(s->imodifiers & 0x20)) { - QUEUE_KEY(0x36 | 0x80); - s->imodifiers |= 0x20; - } - } -#endif - } - - QUEUE_KEY((code & 0x7f) | (keycode & 0x80)); -} - -static void spitz_keyboard_tick(void *opaque) -{ - SpitzKeyboardState *s = (SpitzKeyboardState *) opaque; - - if (s->fifolen) { - spitz_keyboard_keydown(s, s->fifo[s->fifopos ++]); - s->fifolen --; - if (s->fifopos >= 16) - s->fifopos = 0; - } - - timer_mod(s->kbdtimer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + - NANOSECONDS_PER_SECOND / 32); -} - -static void spitz_keyboard_pre_map(SpitzKeyboardState *s) -{ - int i; - for (i = 0; i < 0x100; i ++) - s->pre_map[i] = i; - s->pre_map[0x02 | SPITZ_MOD_SHIFT] = 0x02 | SPITZ_MOD_SHIFT; /* exclam */ - s->pre_map[0x28 | SPITZ_MOD_SHIFT] = 0x03 | SPITZ_MOD_SHIFT; /* quotedbl */ - s->pre_map[0x04 | SPITZ_MOD_SHIFT] = 0x04 | SPITZ_MOD_SHIFT; /* # */ - s->pre_map[0x05 | SPITZ_MOD_SHIFT] = 0x05 | SPITZ_MOD_SHIFT; /* dollar */ - s->pre_map[0x06 | SPITZ_MOD_SHIFT] = 0x06 | SPITZ_MOD_SHIFT; /* percent */ - s->pre_map[0x08 | SPITZ_MOD_SHIFT] = 0x07 | SPITZ_MOD_SHIFT; /* ampersand */ - s->pre_map[0x28] = 0x08 | SPITZ_MOD_SHIFT; /* ' */ - s->pre_map[0x0a | SPITZ_MOD_SHIFT] = 0x09 | SPITZ_MOD_SHIFT; /* ( */ - s->pre_map[0x0b | SPITZ_MOD_SHIFT] = 0x0a | SPITZ_MOD_SHIFT; /* ) */ - s->pre_map[0x29 | SPITZ_MOD_SHIFT] = 0x0b | SPITZ_MOD_SHIFT; /* tilde */ - s->pre_map[0x03 | SPITZ_MOD_SHIFT] = 0x0c | SPITZ_MOD_SHIFT; /* at */ - s->pre_map[0xd3] = 0x0e | SPITZ_MOD_FN; /* Delete */ - s->pre_map[0x3a] = 0x0f | SPITZ_MOD_FN; /* Caps_Lock */ - s->pre_map[0x07 | SPITZ_MOD_SHIFT] = 0x11 | SPITZ_MOD_FN; /* ^ */ - s->pre_map[0x0d] = 0x12 | SPITZ_MOD_FN; /* equal */ - s->pre_map[0x0d | SPITZ_MOD_SHIFT] = 0x13 | SPITZ_MOD_FN; /* plus */ - s->pre_map[0x1a] = 0x14 | SPITZ_MOD_FN; /* [ */ - s->pre_map[0x1b] = 0x15 | SPITZ_MOD_FN; /* ] */ - s->pre_map[0x1a | SPITZ_MOD_SHIFT] = 0x16 | SPITZ_MOD_FN; /* { */ - s->pre_map[0x1b | SPITZ_MOD_SHIFT] = 0x17 | SPITZ_MOD_FN; /* } */ - s->pre_map[0x27] = 0x22 | SPITZ_MOD_FN; /* semicolon */ - s->pre_map[0x27 | SPITZ_MOD_SHIFT] = 0x23 | SPITZ_MOD_FN; /* colon */ - s->pre_map[0x09 | SPITZ_MOD_SHIFT] = 0x24 | SPITZ_MOD_FN; /* asterisk */ - s->pre_map[0x2b] = 0x25 | SPITZ_MOD_FN; /* backslash */ - s->pre_map[0x2b | SPITZ_MOD_SHIFT] = 0x26 | SPITZ_MOD_FN; /* bar */ - s->pre_map[0x0c | SPITZ_MOD_SHIFT] = 0x30 | SPITZ_MOD_FN; /* _ */ - s->pre_map[0x33 | SPITZ_MOD_SHIFT] = 0x33 | SPITZ_MOD_FN; /* less */ - s->pre_map[0x35] = 0x33 | SPITZ_MOD_SHIFT; /* slash */ - s->pre_map[0x34 | SPITZ_MOD_SHIFT] = 0x34 | SPITZ_MOD_FN; /* greater */ - s->pre_map[0x35 | SPITZ_MOD_SHIFT] = 0x34 | SPITZ_MOD_SHIFT; /* question */ - s->pre_map[0x49] = 0x48 | SPITZ_MOD_FN; /* Page_Up */ - s->pre_map[0x51] = 0x50 | SPITZ_MOD_FN; /* Page_Down */ - - s->modifiers = 0; - s->imodifiers = 0; - s->fifopos = 0; - s->fifolen = 0; -} - -#undef SPITZ_MOD_SHIFT -#undef SPITZ_MOD_CTRL -#undef SPITZ_MOD_FN - -static int spitz_keyboard_post_load(void *opaque, int version_id) -{ - SpitzKeyboardState *s = (SpitzKeyboardState *) opaque; - - /* Release all pressed keys */ - memset(s->keyrow, 0, sizeof(s->keyrow)); - spitz_keyboard_sense_update(s); - s->modifiers = 0; - s->imodifiers = 0; - s->fifopos = 0; - s->fifolen = 0; - - return 0; -} - -static void spitz_keyboard_register(PXA2xxState *cpu) -{ - int i; - DeviceState *dev; - SpitzKeyboardState *s; - - dev = sysbus_create_simple(TYPE_SPITZ_KEYBOARD, -1, NULL); - s = SPITZ_KEYBOARD(dev); - - for (i = 0; i < SPITZ_KEY_SENSE_NUM; i ++) - qdev_connect_gpio_out(dev, i, qdev_get_gpio_in(cpu->gpio, spitz_gpio_key_sense[i])); - - for (i = 0; i < 5; i ++) - s->gpiomap[i] = qdev_get_gpio_in(cpu->gpio, spitz_gpiomap[i]); - - if (!graphic_rotate) - s->gpiomap[4] = qemu_irq_invert(s->gpiomap[4]); - - for (i = 0; i < 5; i++) - qemu_set_irq(s->gpiomap[i], 0); - - for (i = 0; i < SPITZ_KEY_STROBE_NUM; i ++) - qdev_connect_gpio_out(cpu->gpio, spitz_gpio_key_strobe[i], - qdev_get_gpio_in(dev, i)); - - timer_mod(s->kbdtimer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL)); - - qemu_add_kbd_event_handler(spitz_keyboard_handler, s); -} - -static void spitz_keyboard_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - SpitzKeyboardState *s = SPITZ_KEYBOARD(obj); - int i, j; - - for (i = 0; i < 0x80; i ++) - s->keymap[i] = -1; - for (i = 0; i < SPITZ_KEY_SENSE_NUM + 1; i ++) - for (j = 0; j < SPITZ_KEY_STROBE_NUM; j ++) - if (spitz_keymap[i][j] != -1) - s->keymap[spitz_keymap[i][j]] = (i << 4) | j; - - spitz_keyboard_pre_map(s); - - qdev_init_gpio_in(dev, spitz_keyboard_strobe, SPITZ_KEY_STROBE_NUM); - qdev_init_gpio_out(dev, s->sense, SPITZ_KEY_SENSE_NUM); -} - -static void spitz_keyboard_realize(DeviceState *dev, Error **errp) -{ - SpitzKeyboardState *s = SPITZ_KEYBOARD(dev); - s->kbdtimer = timer_new_ns(QEMU_CLOCK_VIRTUAL, spitz_keyboard_tick, s); -} - -/* LCD backlight controller */ - -#define LCDTG_RESCTL 0x00 -#define LCDTG_PHACTRL 0x01 -#define LCDTG_DUTYCTRL 0x02 -#define LCDTG_POWERREG0 0x03 -#define LCDTG_POWERREG1 0x04 -#define LCDTG_GPOR3 0x05 -#define LCDTG_PICTRL 0x06 -#define LCDTG_POLCTRL 0x07 - -#define TYPE_SPITZ_LCDTG "spitz-lcdtg" -OBJECT_DECLARE_SIMPLE_TYPE(SpitzLCDTG, SPITZ_LCDTG) - -struct SpitzLCDTG { - SSIPeripheral ssidev; - uint32_t bl_intensity; - uint32_t bl_power; -}; - -static void spitz_bl_update(SpitzLCDTG *s) -{ - if (s->bl_power && s->bl_intensity) - zaurus_printf("LCD Backlight now at %u/63\n", s->bl_intensity); - else - zaurus_printf("LCD Backlight now off\n"); -} - -static inline void spitz_bl_bit5(void *opaque, int line, int level) -{ - SpitzLCDTG *s = opaque; - int prev = s->bl_intensity; - - if (level) - s->bl_intensity &= ~0x20; - else - s->bl_intensity |= 0x20; - - if (s->bl_power && prev != s->bl_intensity) - spitz_bl_update(s); -} - -static inline void spitz_bl_power(void *opaque, int line, int level) -{ - SpitzLCDTG *s = opaque; - s->bl_power = !!level; - spitz_bl_update(s); -} - -static uint32_t spitz_lcdtg_transfer(SSIPeripheral *dev, uint32_t value) -{ - SpitzLCDTG *s = SPITZ_LCDTG(dev); - int addr; - addr = value >> 5; - value &= 0x1f; - - switch (addr) { - case LCDTG_RESCTL: - if (value) - zaurus_printf("LCD in QVGA mode\n"); - else - zaurus_printf("LCD in VGA mode\n"); - break; - - case LCDTG_DUTYCTRL: - s->bl_intensity &= ~0x1f; - s->bl_intensity |= value; - if (s->bl_power) - spitz_bl_update(s); - break; - - case LCDTG_POWERREG0: - /* Set common voltage to M62332FP */ - break; - } - return 0; -} - -static void spitz_lcdtg_realize(SSIPeripheral *ssi, Error **errp) -{ - SpitzLCDTG *s = SPITZ_LCDTG(ssi); - DeviceState *dev = DEVICE(s); - - s->bl_power = 0; - s->bl_intensity = 0x20; - - qdev_init_gpio_in_named(dev, spitz_bl_bit5, "bl_bit5", 1); - qdev_init_gpio_in_named(dev, spitz_bl_power, "bl_power", 1); -} - -/* SSP devices */ - -#define CORGI_SSP_PORT 2 - -#define SPITZ_GPIO_LCDCON_CS 53 -#define SPITZ_GPIO_ADS7846_CS 14 -#define SPITZ_GPIO_MAX1111_CS 20 -#define SPITZ_GPIO_TP_INT 11 - -#define TYPE_CORGI_SSP "corgi-ssp" -OBJECT_DECLARE_SIMPLE_TYPE(CorgiSSPState, CORGI_SSP) - -/* "Demux" the signal based on current chipselect */ -struct CorgiSSPState { - SSIPeripheral ssidev; - SSIBus *bus[3]; - uint32_t enable[3]; -}; - -static uint32_t corgi_ssp_transfer(SSIPeripheral *dev, uint32_t value) -{ - CorgiSSPState *s = CORGI_SSP(dev); - int i; - - for (i = 0; i < 3; i++) { - if (s->enable[i]) { - return ssi_transfer(s->bus[i], value); - } - } - return 0; -} - -static void corgi_ssp_gpio_cs(void *opaque, int line, int level) -{ - CorgiSSPState *s = (CorgiSSPState *)opaque; - assert(line >= 0 && line < 3); - s->enable[line] = !level; -} - -#define MAX1111_BATT_VOLT 1 -#define MAX1111_BATT_TEMP 2 -#define MAX1111_ACIN_VOLT 3 - -#define SPITZ_BATTERY_TEMP 0xe0 /* About 2.9V */ -#define SPITZ_BATTERY_VOLT 0xd0 /* About 4.0V */ -#define SPITZ_CHARGEON_ACIN 0x80 /* About 5.0V */ - -static void corgi_ssp_realize(SSIPeripheral *d, Error **errp) -{ - DeviceState *dev = DEVICE(d); - CorgiSSPState *s = CORGI_SSP(d); - - qdev_init_gpio_in(dev, corgi_ssp_gpio_cs, 3); - s->bus[0] = ssi_create_bus(dev, "ssi0"); - s->bus[1] = ssi_create_bus(dev, "ssi1"); - s->bus[2] = ssi_create_bus(dev, "ssi2"); -} - -static void spitz_ssp_attach(SpitzMachineState *sms) -{ - void *bus; - - sms->mux = ssi_create_peripheral(sms->mpu->ssp[CORGI_SSP_PORT - 1], - TYPE_CORGI_SSP); - - bus = qdev_get_child_bus(sms->mux, "ssi0"); - sms->lcdtg = ssi_create_peripheral(bus, TYPE_SPITZ_LCDTG); - - bus = qdev_get_child_bus(sms->mux, "ssi1"); - sms->ads7846 = ssi_create_peripheral(bus, "ads7846"); - qdev_connect_gpio_out(sms->ads7846, 0, - qdev_get_gpio_in(sms->mpu->gpio, SPITZ_GPIO_TP_INT)); - - bus = qdev_get_child_bus(sms->mux, "ssi2"); - sms->max1111 = qdev_new(TYPE_MAX_1111); - qdev_prop_set_uint8(sms->max1111, "input1" /* BATT_VOLT */, - SPITZ_BATTERY_VOLT); - qdev_prop_set_uint8(sms->max1111, "input2" /* BATT_TEMP */, 0); - qdev_prop_set_uint8(sms->max1111, "input3" /* ACIN_VOLT */, - SPITZ_CHARGEON_ACIN); - ssi_realize_and_unref(sms->max1111, bus, &error_fatal); - - qdev_connect_gpio_out(sms->mpu->gpio, SPITZ_GPIO_LCDCON_CS, - qdev_get_gpio_in(sms->mux, 0)); - qdev_connect_gpio_out(sms->mpu->gpio, SPITZ_GPIO_ADS7846_CS, - qdev_get_gpio_in(sms->mux, 1)); - qdev_connect_gpio_out(sms->mpu->gpio, SPITZ_GPIO_MAX1111_CS, - qdev_get_gpio_in(sms->mux, 2)); -} - -/* CF Microdrive */ - -static void spitz_microdrive_attach(PXA2xxState *cpu, int slot) -{ - PCMCIACardState *md; - DriveInfo *dinfo; - - dinfo = drive_get(IF_IDE, 0, 0); - if (!dinfo || dinfo->media_cd) - return; - md = dscm1xxxx_init(dinfo); - pxa2xx_pcmcia_attach(cpu->pcmcia[slot], md); -} - -/* Wm8750 and Max7310 on I2C */ - -#define AKITA_MAX_ADDR 0x18 -#define SPITZ_WM_ADDRL 0x1b -#define SPITZ_WM_ADDRH 0x1a - -#define SPITZ_GPIO_WM 5 - -static void spitz_wm8750_addr(void *opaque, int line, int level) -{ - I2CSlave *wm = (I2CSlave *) opaque; - if (level) - i2c_slave_set_address(wm, SPITZ_WM_ADDRH); - else - i2c_slave_set_address(wm, SPITZ_WM_ADDRL); -} - -static void spitz_i2c_setup(MachineState *machine, PXA2xxState *cpu) -{ - /* Attach the CPU on one end of our I2C bus. */ - I2CBus *bus = pxa2xx_i2c_bus(cpu->i2c[0]); - - /* Attach a WM8750 to the bus */ - I2CSlave *i2c_dev = i2c_slave_new(TYPE_WM8750, 0); - DeviceState *wm = DEVICE(i2c_dev); - - if (machine->audiodev) { - qdev_prop_set_string(wm, "audiodev", machine->audiodev); - } - i2c_slave_realize_and_unref(i2c_dev, bus, &error_abort); - - spitz_wm8750_addr(wm, 0, 0); - qdev_connect_gpio_out(cpu->gpio, SPITZ_GPIO_WM, - qemu_allocate_irq(spitz_wm8750_addr, wm, 0)); - /* .. and to the sound interface. */ - cpu->i2s->opaque = wm; - cpu->i2s->codec_out = wm8750_dac_dat; - cpu->i2s->codec_in = wm8750_adc_dat; - wm8750_data_req_set(wm, cpu->i2s->data_req, cpu->i2s); -} - -static void spitz_akita_i2c_setup(PXA2xxState *cpu) -{ - /* Attach a Max7310 to Akita I2C bus. */ - i2c_slave_create_simple(pxa2xx_i2c_bus(cpu->i2c[0]), "max7310", - AKITA_MAX_ADDR); -} - -/* Other peripherals */ - -/* - * Encapsulation of some miscellaneous GPIO line behaviour for the Spitz boards. - * - * QEMU interface: - * + named GPIO inputs "green-led", "orange-led", "charging", "discharging": - * these currently just print messages that the line has been signalled - * + named GPIO input "adc-temp-on": set to cause the battery-temperature - * value to be passed to the max111x ADC - * + named GPIO output "adc-temp": the ADC value, to be wired up to the max111x - */ -#define TYPE_SPITZ_MISC_GPIO "spitz-misc-gpio" -OBJECT_DECLARE_SIMPLE_TYPE(SpitzMiscGPIOState, SPITZ_MISC_GPIO) - -struct SpitzMiscGPIOState { - SysBusDevice parent_obj; - - qemu_irq adc_value; -}; - -static void spitz_misc_charging(void *opaque, int n, int level) -{ - zaurus_printf("Charging %s.\n", level ? "off" : "on"); -} - -static void spitz_misc_discharging(void *opaque, int n, int level) -{ - zaurus_printf("Discharging %s.\n", level ? "off" : "on"); -} - -static void spitz_misc_green_led(void *opaque, int n, int level) -{ - zaurus_printf("Green LED %s.\n", level ? "off" : "on"); -} - -static void spitz_misc_orange_led(void *opaque, int n, int level) -{ - zaurus_printf("Orange LED %s.\n", level ? "off" : "on"); -} - -static void spitz_misc_adc_temp(void *opaque, int n, int level) -{ - SpitzMiscGPIOState *s = SPITZ_MISC_GPIO(opaque); - int batt_temp = level ? SPITZ_BATTERY_TEMP : 0; - - qemu_set_irq(s->adc_value, batt_temp); -} - -static void spitz_misc_gpio_init(Object *obj) -{ - SpitzMiscGPIOState *s = SPITZ_MISC_GPIO(obj); - DeviceState *dev = DEVICE(obj); - - qdev_init_gpio_in_named(dev, spitz_misc_charging, "charging", 1); - qdev_init_gpio_in_named(dev, spitz_misc_discharging, "discharging", 1); - qdev_init_gpio_in_named(dev, spitz_misc_green_led, "green-led", 1); - qdev_init_gpio_in_named(dev, spitz_misc_orange_led, "orange-led", 1); - qdev_init_gpio_in_named(dev, spitz_misc_adc_temp, "adc-temp-on", 1); - - qdev_init_gpio_out_named(dev, &s->adc_value, "adc-temp", 1); -} - -#define SPITZ_SCP_LED_GREEN 1 -#define SPITZ_SCP_JK_B 2 -#define SPITZ_SCP_CHRG_ON 3 -#define SPITZ_SCP_MUTE_L 4 -#define SPITZ_SCP_MUTE_R 5 -#define SPITZ_SCP_CF_POWER 6 -#define SPITZ_SCP_LED_ORANGE 7 -#define SPITZ_SCP_JK_A 8 -#define SPITZ_SCP_ADC_TEMP_ON 9 -#define SPITZ_SCP2_IR_ON 1 -#define SPITZ_SCP2_AKIN_PULLUP 2 -#define SPITZ_SCP2_BACKLIGHT_CONT 7 -#define SPITZ_SCP2_BACKLIGHT_ON 8 -#define SPITZ_SCP2_MIC_BIAS 9 - -static void spitz_scoop_gpio_setup(SpitzMachineState *sms) -{ - DeviceState *miscdev = sysbus_create_simple(TYPE_SPITZ_MISC_GPIO, -1, NULL); - - sms->misc_gpio = miscdev; - - qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_CHRG_ON, - qdev_get_gpio_in_named(miscdev, "charging", 0)); - qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_JK_B, - qdev_get_gpio_in_named(miscdev, "discharging", 0)); - qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_LED_GREEN, - qdev_get_gpio_in_named(miscdev, "green-led", 0)); - qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_LED_ORANGE, - qdev_get_gpio_in_named(miscdev, "orange-led", 0)); - qdev_connect_gpio_out(sms->scp0, SPITZ_SCP_ADC_TEMP_ON, - qdev_get_gpio_in_named(miscdev, "adc-temp-on", 0)); - qdev_connect_gpio_out_named(miscdev, "adc-temp", 0, - qdev_get_gpio_in(sms->max1111, MAX1111_BATT_TEMP)); - - if (sms->scp1) { - qdev_connect_gpio_out(sms->scp1, SPITZ_SCP2_BACKLIGHT_CONT, - qdev_get_gpio_in_named(sms->lcdtg, "bl_bit5", 0)); - qdev_connect_gpio_out(sms->scp1, SPITZ_SCP2_BACKLIGHT_ON, - qdev_get_gpio_in_named(sms->lcdtg, "bl_power", 0)); - } -} - -#define SPITZ_GPIO_HSYNC 22 -#define SPITZ_GPIO_SD_DETECT 9 -#define SPITZ_GPIO_SD_WP 81 -#define SPITZ_GPIO_ON_RESET 89 -#define SPITZ_GPIO_BAT_COVER 90 -#define SPITZ_GPIO_CF1_IRQ 105 -#define SPITZ_GPIO_CF1_CD 94 -#define SPITZ_GPIO_CF2_IRQ 106 -#define SPITZ_GPIO_CF2_CD 93 - -static int spitz_hsync; - -static void spitz_lcd_hsync_handler(void *opaque, int line, int level) -{ - PXA2xxState *cpu = (PXA2xxState *) opaque; - qemu_set_irq(qdev_get_gpio_in(cpu->gpio, SPITZ_GPIO_HSYNC), spitz_hsync); - spitz_hsync ^= 1; -} - -static void spitz_reset(void *opaque, int line, int level) -{ - if (level) { - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); - } -} - -static void spitz_gpio_setup(PXA2xxState *cpu, int slots) -{ - qemu_irq lcd_hsync; - qemu_irq reset; - - /* - * Bad hack: We toggle the LCD hsync GPIO on every GPIO status - * read to satisfy broken guests that poll-wait for hsync. - * Simulating a real hsync event would be less practical and - * wouldn't guarantee that a guest ever exits the loop. - */ - spitz_hsync = 0; - lcd_hsync = qemu_allocate_irq(spitz_lcd_hsync_handler, cpu, 0); - pxa2xx_gpio_read_notifier(cpu->gpio, lcd_hsync); - pxa2xx_lcd_vsync_notifier(cpu->lcd, lcd_hsync); - - /* MMC/SD host */ - pxa2xx_mmci_handlers(cpu->mmc, - qdev_get_gpio_in(cpu->gpio, SPITZ_GPIO_SD_WP), - qdev_get_gpio_in(cpu->gpio, SPITZ_GPIO_SD_DETECT)); - - /* Battery lock always closed */ - qemu_irq_raise(qdev_get_gpio_in(cpu->gpio, SPITZ_GPIO_BAT_COVER)); - - /* Handle reset */ - reset = qemu_allocate_irq(spitz_reset, cpu, 0); - qdev_connect_gpio_out(cpu->gpio, SPITZ_GPIO_ON_RESET, reset); - - /* PCMCIA signals: card's IRQ and Card-Detect */ - if (slots >= 1) - pxa2xx_pcmcia_set_irq_cb(cpu->pcmcia[0], - qdev_get_gpio_in(cpu->gpio, SPITZ_GPIO_CF1_IRQ), - qdev_get_gpio_in(cpu->gpio, SPITZ_GPIO_CF1_CD)); - if (slots >= 2) - pxa2xx_pcmcia_set_irq_cb(cpu->pcmcia[1], - qdev_get_gpio_in(cpu->gpio, SPITZ_GPIO_CF2_IRQ), - qdev_get_gpio_in(cpu->gpio, SPITZ_GPIO_CF2_CD)); -} - -/* Board init. */ -#define SPITZ_RAM 0x04000000 -#define SPITZ_ROM 0x00800000 - -static struct arm_boot_info spitz_binfo = { - .loader_start = PXA2XX_SDRAM_BASE, - .ram_size = 0x04000000, -}; - -static void spitz_common_init(MachineState *machine) -{ - SpitzMachineClass *smc = SPITZ_MACHINE_GET_CLASS(machine); - SpitzMachineState *sms = SPITZ_MACHINE(machine); - enum spitz_model_e model = smc->model; - PXA2xxState *mpu; - MemoryRegion *rom = g_new(MemoryRegion, 1); - - /* Setup CPU & memory */ - mpu = pxa270_init(spitz_binfo.ram_size, machine->cpu_type); - sms->mpu = mpu; - - sl_flash_register(mpu, (model == spitz) ? FLASH_128M : FLASH_1024M); - - memory_region_init_rom(rom, NULL, "spitz.rom", SPITZ_ROM, &error_fatal); - memory_region_add_subregion(get_system_memory(), 0, rom); - - /* Setup peripherals */ - spitz_keyboard_register(mpu); - - spitz_ssp_attach(sms); - - sms->scp0 = sysbus_create_simple("scoop", 0x10800000, NULL); - if (model != akita) { - sms->scp1 = sysbus_create_simple("scoop", 0x08800040, NULL); - } else { - sms->scp1 = NULL; - } - - spitz_scoop_gpio_setup(sms); - - spitz_gpio_setup(mpu, (model == akita) ? 1 : 2); - - spitz_i2c_setup(machine, mpu); - - if (model == akita) - spitz_akita_i2c_setup(mpu); - - if (model == terrier) - /* A 6.0 GB microdrive is permanently sitting in CF slot 1. */ - spitz_microdrive_attach(mpu, 1); - else if (model != akita) - /* A 4.0 GB microdrive is permanently sitting in CF slot 0. */ - spitz_microdrive_attach(mpu, 0); - - spitz_binfo.board_id = smc->arm_id; - arm_load_kernel(mpu->cpu, machine, &spitz_binfo); - sl_bootparam_write(SL_PXA_PARAM_BASE); -} - -static void spitz_common_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->block_default_type = IF_IDE; - mc->ignore_memory_transaction_failures = true; - mc->init = spitz_common_init; - mc->deprecation_reason = "machine is old and unmaintained"; - - machine_add_audiodev_property(mc); -} - -static const TypeInfo spitz_common_info = { - .name = TYPE_SPITZ_MACHINE, - .parent = TYPE_MACHINE, - .abstract = true, - .instance_size = sizeof(SpitzMachineState), - .class_size = sizeof(SpitzMachineClass), - .class_init = spitz_common_class_init, -}; - -static void akitapda_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - SpitzMachineClass *smc = SPITZ_MACHINE_CLASS(oc); - - mc->desc = "Sharp SL-C1000 (Akita) PDA (PXA270)"; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); - smc->model = akita; - smc->arm_id = 0x2e8; -} - -static const TypeInfo akitapda_type = { - .name = MACHINE_TYPE_NAME("akita"), - .parent = TYPE_SPITZ_MACHINE, - .class_init = akitapda_class_init, -}; - -static void spitzpda_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - SpitzMachineClass *smc = SPITZ_MACHINE_CLASS(oc); - - mc->desc = "Sharp SL-C3000 (Spitz) PDA (PXA270)"; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); - smc->model = spitz; - smc->arm_id = 0x2c9; -} - -static const TypeInfo spitzpda_type = { - .name = MACHINE_TYPE_NAME("spitz"), - .parent = TYPE_SPITZ_MACHINE, - .class_init = spitzpda_class_init, -}; - -static void borzoipda_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - SpitzMachineClass *smc = SPITZ_MACHINE_CLASS(oc); - - mc->desc = "Sharp SL-C3100 (Borzoi) PDA (PXA270)"; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); - smc->model = borzoi; - smc->arm_id = 0x33f; -} - -static const TypeInfo borzoipda_type = { - .name = MACHINE_TYPE_NAME("borzoi"), - .parent = TYPE_SPITZ_MACHINE, - .class_init = borzoipda_class_init, -}; - -static void terrierpda_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - SpitzMachineClass *smc = SPITZ_MACHINE_CLASS(oc); - - mc->desc = "Sharp SL-C3200 (Terrier) PDA (PXA270)"; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c5"); - smc->model = terrier; - smc->arm_id = 0x33f; -} - -static const TypeInfo terrierpda_type = { - .name = MACHINE_TYPE_NAME("terrier"), - .parent = TYPE_SPITZ_MACHINE, - .class_init = terrierpda_class_init, -}; - -static void spitz_machine_init(void) -{ - type_register_static(&spitz_common_info); - type_register_static(&akitapda_type); - type_register_static(&spitzpda_type); - type_register_static(&borzoipda_type); - type_register_static(&terrierpda_type); -} - -type_init(spitz_machine_init) - -static bool is_version_0(void *opaque, int version_id) -{ - return version_id == 0; -} - -static const VMStateDescription vmstate_sl_nand_info = { - .name = "sl-nand", - .version_id = 0, - .minimum_version_id = 0, - .fields = (const VMStateField[]) { - VMSTATE_UINT8(ctl, SLNANDState), - VMSTATE_STRUCT(ecc, SLNANDState, 0, vmstate_ecc_state, ECCState), - VMSTATE_END_OF_LIST(), - }, -}; - -static Property sl_nand_properties[] = { - DEFINE_PROP_UINT8("manf_id", SLNANDState, manf_id, NAND_MFR_SAMSUNG), - DEFINE_PROP_UINT8("chip_id", SLNANDState, chip_id, 0xf1), - DEFINE_PROP_END_OF_LIST(), -}; - -static void sl_nand_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->vmsd = &vmstate_sl_nand_info; - device_class_set_props(dc, sl_nand_properties); - dc->realize = sl_nand_realize; - /* Reason: init() method uses drive_get() */ - dc->user_creatable = false; -} - -static const TypeInfo sl_nand_info = { - .name = TYPE_SL_NAND, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(SLNANDState), - .instance_init = sl_nand_init, - .class_init = sl_nand_class_init, -}; - -static const VMStateDescription vmstate_spitz_kbd = { - .name = "spitz-keyboard", - .version_id = 1, - .minimum_version_id = 0, - .post_load = spitz_keyboard_post_load, - .fields = (const VMStateField[]) { - VMSTATE_UINT16(sense_state, SpitzKeyboardState), - VMSTATE_UINT16(strobe_state, SpitzKeyboardState), - VMSTATE_UNUSED_TEST(is_version_0, 5), - VMSTATE_END_OF_LIST(), - }, -}; - -static void spitz_keyboard_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->vmsd = &vmstate_spitz_kbd; - dc->realize = spitz_keyboard_realize; -} - -static const TypeInfo spitz_keyboard_info = { - .name = TYPE_SPITZ_KEYBOARD, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(SpitzKeyboardState), - .instance_init = spitz_keyboard_init, - .class_init = spitz_keyboard_class_init, -}; - -static const VMStateDescription vmstate_corgi_ssp_regs = { - .name = "corgi-ssp", - .version_id = 2, - .minimum_version_id = 2, - .fields = (const VMStateField[]) { - VMSTATE_SSI_PERIPHERAL(ssidev, CorgiSSPState), - VMSTATE_UINT32_ARRAY(enable, CorgiSSPState, 3), - VMSTATE_END_OF_LIST(), - } -}; - -static void corgi_ssp_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - SSIPeripheralClass *k = SSI_PERIPHERAL_CLASS(klass); - - k->realize = corgi_ssp_realize; - k->transfer = corgi_ssp_transfer; - dc->vmsd = &vmstate_corgi_ssp_regs; -} - -static const TypeInfo corgi_ssp_info = { - .name = TYPE_CORGI_SSP, - .parent = TYPE_SSI_PERIPHERAL, - .instance_size = sizeof(CorgiSSPState), - .class_init = corgi_ssp_class_init, -}; - -static const VMStateDescription vmstate_spitz_lcdtg_regs = { - .name = "spitz-lcdtg", - .version_id = 1, - .minimum_version_id = 1, - .fields = (const VMStateField[]) { - VMSTATE_SSI_PERIPHERAL(ssidev, SpitzLCDTG), - VMSTATE_UINT32(bl_intensity, SpitzLCDTG), - VMSTATE_UINT32(bl_power, SpitzLCDTG), - VMSTATE_END_OF_LIST(), - } -}; - -static void spitz_lcdtg_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - SSIPeripheralClass *k = SSI_PERIPHERAL_CLASS(klass); - - k->realize = spitz_lcdtg_realize; - k->transfer = spitz_lcdtg_transfer; - dc->vmsd = &vmstate_spitz_lcdtg_regs; -} - -static const TypeInfo spitz_lcdtg_info = { - .name = TYPE_SPITZ_LCDTG, - .parent = TYPE_SSI_PERIPHERAL, - .instance_size = sizeof(SpitzLCDTG), - .class_init = spitz_lcdtg_class_init, -}; - -static const TypeInfo spitz_misc_gpio_info = { - .name = TYPE_SPITZ_MISC_GPIO, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(SpitzMiscGPIOState), - .instance_init = spitz_misc_gpio_init, - /* - * No class_init required: device has no internal state so does not - * need to set up reset or vmstate, and does not have a realize method. - */ -}; - -static void spitz_register_types(void) -{ - type_register_static(&corgi_ssp_info); - type_register_static(&spitz_lcdtg_info); - type_register_static(&spitz_keyboard_info); - type_register_static(&sl_nand_info); - type_register_static(&spitz_misc_gpio_info); -} - -type_init(spitz_register_types) diff --git a/hw/arm/tosa.c b/hw/arm/tosa.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/tosa.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* vim:set shiftwidth=4 ts=4 et: */ -/* - * PXA255 Sharp Zaurus SL-6000 PDA platform - * - * Copyright (c) 2008 Dmitry Baryshkov - * - * Code based on spitz platform by Andrzej Zaborowski <balrog@zabor.org> - * This code is licensed under the GNU GPL v2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "sysemu/runstate.h" -#include "hw/arm/pxa.h" -#include "hw/arm/boot.h" -#include "hw/arm/sharpsl.h" -#include "hw/pcmcia.h" -#include "hw/boards.h" -#include "hw/display/tc6393xb.h" -#include "hw/i2c/i2c.h" -#include "hw/irq.h" -#include "hw/ssi/ssi.h" -#include "hw/sysbus.h" -#include "hw/misc/led.h" -#include "exec/address-spaces.h" -#include "qom/object.h" - -#define TOSA_RAM 0x04000000 -#define TOSA_ROM 0x00800000 - -#define TOSA_GPIO_USB_IN (5) -#define TOSA_GPIO_nSD_DETECT (9) -#define TOSA_GPIO_ON_RESET (19) -#define TOSA_GPIO_CF_IRQ (21) /* CF slot0 Ready */ -#define TOSA_GPIO_CF_CD (13) -#define TOSA_GPIO_TC6393XB_INT (15) -#define TOSA_GPIO_JC_CF_IRQ (36) /* CF slot1 Ready */ - -#define TOSA_SCOOP_GPIO_BASE 1 -#define TOSA_GPIO_IR_POWERDWN (TOSA_SCOOP_GPIO_BASE + 2) -#define TOSA_GPIO_SD_WP (TOSA_SCOOP_GPIO_BASE + 3) -#define TOSA_GPIO_PWR_ON (TOSA_SCOOP_GPIO_BASE + 4) - -#define TOSA_SCOOP_JC_GPIO_BASE 1 -#define TOSA_GPIO_BT_LED (TOSA_SCOOP_JC_GPIO_BASE + 0) -#define TOSA_GPIO_NOTE_LED (TOSA_SCOOP_JC_GPIO_BASE + 1) -#define TOSA_GPIO_CHRG_ERR_LED (TOSA_SCOOP_JC_GPIO_BASE + 2) -#define TOSA_GPIO_TC6393XB_L3V_ON (TOSA_SCOOP_JC_GPIO_BASE + 5) -#define TOSA_GPIO_WLAN_LED (TOSA_SCOOP_JC_GPIO_BASE + 7) - -#define DAC_BASE 0x4e -#define DAC_CH1 0 -#define DAC_CH2 1 - -static void tosa_microdrive_attach(PXA2xxState *cpu) -{ - PCMCIACardState *md; - DriveInfo *dinfo; - - dinfo = drive_get(IF_IDE, 0, 0); - if (!dinfo || dinfo->media_cd) - return; - md = dscm1xxxx_init(dinfo); - pxa2xx_pcmcia_attach(cpu->pcmcia[0], md); -} - -/* - * Encapsulation of some GPIO line behaviour for the Tosa board - * - * QEMU interface: - * + named GPIO inputs "leds[0..3]": assert to light LEDs - * + named GPIO input "reset": when asserted, resets the system - */ - -#define TYPE_TOSA_MISC_GPIO "tosa-misc-gpio" -OBJECT_DECLARE_SIMPLE_TYPE(TosaMiscGPIOState, TOSA_MISC_GPIO) - -struct TosaMiscGPIOState { - SysBusDevice parent_obj; -}; - -static void tosa_reset(void *opaque, int line, int level) -{ - if (level) { - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); - } -} - -static void tosa_misc_gpio_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - - qdev_init_gpio_in_named(dev, tosa_reset, "reset", 1); -} - -static void tosa_gpio_setup(PXA2xxState *cpu, - DeviceState *scp0, - DeviceState *scp1, - TC6393xbState *tmio) -{ - DeviceState *misc_gpio; - LEDState *led[4]; - - misc_gpio = sysbus_create_simple(TYPE_TOSA_MISC_GPIO, -1, NULL); - - /* MMC/SD host */ - pxa2xx_mmci_handlers(cpu->mmc, - qdev_get_gpio_in(scp0, TOSA_GPIO_SD_WP), - qemu_irq_invert(qdev_get_gpio_in(cpu->gpio, TOSA_GPIO_nSD_DETECT))); - - /* Handle reset */ - qdev_connect_gpio_out(cpu->gpio, TOSA_GPIO_ON_RESET, - qdev_get_gpio_in_named(misc_gpio, "reset", 0)); - - /* PCMCIA signals: card's IRQ and Card-Detect */ - pxa2xx_pcmcia_set_irq_cb(cpu->pcmcia[0], - qdev_get_gpio_in(cpu->gpio, TOSA_GPIO_CF_IRQ), - qdev_get_gpio_in(cpu->gpio, TOSA_GPIO_CF_CD)); - - pxa2xx_pcmcia_set_irq_cb(cpu->pcmcia[1], - qdev_get_gpio_in(cpu->gpio, TOSA_GPIO_JC_CF_IRQ), - NULL); - - led[0] = led_create_simple(OBJECT(misc_gpio), GPIO_POLARITY_ACTIVE_HIGH, - LED_COLOR_BLUE, "bluetooth"); - led[1] = led_create_simple(OBJECT(misc_gpio), GPIO_POLARITY_ACTIVE_HIGH, - LED_COLOR_GREEN, "note"); - led[2] = led_create_simple(OBJECT(misc_gpio), GPIO_POLARITY_ACTIVE_HIGH, - LED_COLOR_AMBER, "charger-error"); - led[3] = led_create_simple(OBJECT(misc_gpio), GPIO_POLARITY_ACTIVE_HIGH, - LED_COLOR_GREEN, "wlan"); - - qdev_connect_gpio_out(scp1, TOSA_GPIO_BT_LED, - qdev_get_gpio_in(DEVICE(led[0]), 0)); - qdev_connect_gpio_out(scp1, TOSA_GPIO_NOTE_LED, - qdev_get_gpio_in(DEVICE(led[1]), 0)); - qdev_connect_gpio_out(scp1, TOSA_GPIO_CHRG_ERR_LED, - qdev_get_gpio_in(DEVICE(led[2]), 0)); - qdev_connect_gpio_out(scp1, TOSA_GPIO_WLAN_LED, - qdev_get_gpio_in(DEVICE(led[3]), 0)); - - qdev_connect_gpio_out(scp1, TOSA_GPIO_TC6393XB_L3V_ON, tc6393xb_l3v_get(tmio)); - - /* UDC Vbus */ - qemu_irq_raise(qdev_get_gpio_in(cpu->gpio, TOSA_GPIO_USB_IN)); -} - -static uint32_t tosa_ssp_tansfer(SSIPeripheral *dev, uint32_t value) -{ - fprintf(stderr, "TG: %u %02x\n", value >> 5, value & 0x1f); - return 0; -} - -static void tosa_ssp_realize(SSIPeripheral *dev, Error **errp) -{ - /* Nothing to do. */ -} - -#define TYPE_TOSA_DAC "tosa_dac" -OBJECT_DECLARE_SIMPLE_TYPE(TosaDACState, TOSA_DAC) - -struct TosaDACState { - I2CSlave parent_obj; - - int len; - char buf[3]; -}; - -static int tosa_dac_send(I2CSlave *i2c, uint8_t data) -{ - TosaDACState *s = TOSA_DAC(i2c); - - s->buf[s->len] = data; - if (s->len ++ > 2) { -#ifdef VERBOSE - fprintf(stderr, "%s: message too long (%i bytes)\n", __func__, s->len); -#endif - return 1; - } - - if (s->len == 2) { - fprintf(stderr, "dac: channel %d value 0x%02x\n", - s->buf[0], s->buf[1]); - } - - return 0; -} - -static int tosa_dac_event(I2CSlave *i2c, enum i2c_event event) -{ - TosaDACState *s = TOSA_DAC(i2c); - - s->len = 0; - switch (event) { - case I2C_START_SEND: - break; - case I2C_START_RECV: - printf("%s: recv not supported!!!\n", __func__); - break; - case I2C_FINISH: -#ifdef VERBOSE - if (s->len < 2) - printf("%s: message too short (%i bytes)\n", __func__, s->len); - if (s->len > 2) - printf("%s: message too long\n", __func__); -#endif - break; - default: - break; - } - - return 0; -} - -static uint8_t tosa_dac_recv(I2CSlave *s) -{ - printf("%s: recv not supported!!!\n", __func__); - return 0xff; -} - -static void tosa_tg_init(PXA2xxState *cpu) -{ - I2CBus *bus = pxa2xx_i2c_bus(cpu->i2c[0]); - i2c_slave_create_simple(bus, TYPE_TOSA_DAC, DAC_BASE); - ssi_create_peripheral(cpu->ssp[1], "tosa-ssp"); -} - - -static struct arm_boot_info tosa_binfo = { - .loader_start = PXA2XX_SDRAM_BASE, - .ram_size = 0x04000000, -}; - -static void tosa_init(MachineState *machine) -{ - MemoryRegion *address_space_mem = get_system_memory(); - MemoryRegion *rom = g_new(MemoryRegion, 1); - PXA2xxState *mpu; - TC6393xbState *tmio; - DeviceState *scp0, *scp1; - - mpu = pxa255_init(tosa_binfo.ram_size); - - memory_region_init_rom(rom, NULL, "tosa.rom", TOSA_ROM, &error_fatal); - memory_region_add_subregion(address_space_mem, 0, rom); - - tmio = tc6393xb_init(address_space_mem, 0x10000000, - qdev_get_gpio_in(mpu->gpio, TOSA_GPIO_TC6393XB_INT)); - - scp0 = sysbus_create_simple("scoop", 0x08800000, NULL); - scp1 = sysbus_create_simple("scoop", 0x14800040, NULL); - - tosa_gpio_setup(mpu, scp0, scp1, tmio); - - tosa_microdrive_attach(mpu); - - tosa_tg_init(mpu); - - tosa_binfo.board_id = 0x208; - arm_load_kernel(mpu->cpu, machine, &tosa_binfo); - sl_bootparam_write(SL_PXA_PARAM_BASE); -} - -static void tosapda_machine_init(MachineClass *mc) -{ - mc->desc = "Sharp SL-6000 (Tosa) PDA (PXA255)"; - mc->init = tosa_init; - mc->block_default_type = IF_IDE; - mc->ignore_memory_transaction_failures = true; - mc->deprecation_reason = "machine is old and unmaintained"; -} - -DEFINE_MACHINE("tosa", tosapda_machine_init) - -static void tosa_dac_class_init(ObjectClass *klass, void *data) -{ - I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); - - k->event = tosa_dac_event; - k->recv = tosa_dac_recv; - k->send = tosa_dac_send; -} - -static const TypeInfo tosa_dac_info = { - .name = TYPE_TOSA_DAC, - .parent = TYPE_I2C_SLAVE, - .instance_size = sizeof(TosaDACState), - .class_init = tosa_dac_class_init, -}; - -static void tosa_ssp_class_init(ObjectClass *klass, void *data) -{ - SSIPeripheralClass *k = SSI_PERIPHERAL_CLASS(klass); - - k->realize = tosa_ssp_realize; - k->transfer = tosa_ssp_tansfer; -} - -static const TypeInfo tosa_ssp_info = { - .name = "tosa-ssp", - .parent = TYPE_SSI_PERIPHERAL, - .instance_size = sizeof(SSIPeripheral), - .class_init = tosa_ssp_class_init, -}; - -static const TypeInfo tosa_misc_gpio_info = { - .name = TYPE_TOSA_MISC_GPIO, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(TosaMiscGPIOState), - .instance_init = tosa_misc_gpio_init, - /* - * No class init required: device has no internal state so does not - * need to set up reset or vmstate, and has no realize method. - */ -}; - -static void tosa_register_types(void) -{ - type_register_static(&tosa_dac_info); - type_register_static(&tosa_ssp_info); - type_register_static(&tosa_misc_gpio_info); -} - -type_init(tosa_register_types) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config GUMSTIX select SMC91C111 select PXA2XX -config TOSA - bool - default y - depends on TCG && ARM - select ZAURUS # scoop - select MICRODRIVE - select PXA2XX - select LED - -config SPITZ - bool - default y - depends on TCG && ARM - select ADS7846 # touch-screen controller - select MAX111X # A/D converter - select WM8750 # audio codec - select MAX7310 # GPIO expander - select ZAURUS # scoop - select NAND # memory - select ECC # Error-correcting for NAND - select MICRODRIVE - select PXA2XX - config Z2 bool default y diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap2.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_peripherals.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2838_peripherals.c')) -system_ss.add(when: 'CONFIG_SPITZ', if_true: files('spitz.c')) system_ss.add(when: 'CONFIG_STRONGARM', if_true: files('strongarm.c')) system_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) -system_ss.add(when: 'CONFIG_TOSA', if_true: files('tosa.c')) system_ss.add(when: 'CONFIG_VERSATILE', if_true: files('versatilepb.c')) system_ss.add(when: 'CONFIG_VEXPRESS', if_true: files('vexpress.c')) system_ss.add(when: 'CONFIG_Z2', if_true: files('z2.c')) -- 2.34.1 The ADS7846 touchscreen controller device was used only by the XScale-based PDA machine types. Now that they have been removed, this device is not used in the tree and can be deleted. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20240903160751.4100218-3-peter.maydell@linaro.org --- MAINTAINERS | 1 - hw/input/ads7846.c | 186 ------------------------------------------- hw/input/Kconfig | 3 - hw/input/meson.build | 1 - 4 files changed, 191 deletions(-) delete mode 100644 hw/input/ads7846.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/*/pxa2xx* F: hw/display/tc6393xb.c F: hw/gpio/max7310.c F: hw/gpio/zaurus.c -F: hw/input/ads7846.c F: hw/misc/mst_fpga.c F: hw/adc/max111x.c F: include/hw/adc/max111x.h diff --git a/hw/input/ads7846.c b/hw/input/ads7846.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/input/ads7846.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI ADS7846 / TSC2046 chip emulation. - * - * Copyright (c) 2006 Openedhand Ltd. - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GNU GPL v2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/ssi/ssi.h" -#include "migration/vmstate.h" -#include "qemu/module.h" -#include "ui/console.h" -#include "qom/object.h" - -struct ADS7846State { - SSIPeripheral ssidev; - qemu_irq interrupt; - - int input[8]; - int pressure; - int noise; - - int cycle; - int output; -}; - -#define TYPE_ADS7846 "ads7846" -OBJECT_DECLARE_SIMPLE_TYPE(ADS7846State, ADS7846) - -/* Control-byte bitfields */ -#define CB_PD0 (1 << 0) -#define CB_PD1 (1 << 1) -#define CB_SER (1 << 2) -#define CB_MODE (1 << 3) -#define CB_A0 (1 << 4) -#define CB_A1 (1 << 5) -#define CB_A2 (1 << 6) -#define CB_START (1 << 7) - -#define X_AXIS_DMAX 3470 -#define X_AXIS_MIN 290 -#define Y_AXIS_DMAX 3450 -#define Y_AXIS_MIN 200 - -#define ADS_VBAT 2000 -#define ADS_VAUX 2000 -#define ADS_TEMP0 2000 -#define ADS_TEMP1 3000 -#define ADS_XPOS(x, y) (X_AXIS_MIN + ((X_AXIS_DMAX * (x)) >> 15)) -#define ADS_YPOS(x, y) (Y_AXIS_MIN + ((Y_AXIS_DMAX * (y)) >> 15)) -#define ADS_Z1POS(x, y) 600 -#define ADS_Z2POS(x, y) (600 + 6000 / ADS_XPOS(x, y)) - -static void ads7846_int_update(ADS7846State *s) -{ - if (s->interrupt) - qemu_set_irq(s->interrupt, s->pressure == 0); -} - -static uint32_t ads7846_transfer(SSIPeripheral *dev, uint32_t value) -{ - ADS7846State *s = ADS7846(dev); - - switch (s->cycle ++) { - case 0: - if (!(value & CB_START)) { - s->cycle = 0; - break; - } - - s->output = s->input[(value >> 4) & 7]; - - /* Imitate the ADC noise, some drivers expect this. */ - s->noise = (s->noise + 3) & 7; - switch ((value >> 4) & 7) { - case 1: s->output += s->noise ^ 2; break; - case 3: s->output += s->noise ^ 0; break; - case 4: s->output += s->noise ^ 7; break; - case 5: s->output += s->noise ^ 5; break; - } - - if (value & CB_MODE) - s->output >>= 4; /* 8 bits instead of 12 */ - - break; - case 1: - s->cycle = 0; - break; - } - return s->output; -} - -static void ads7846_ts_event(void *opaque, - int x, int y, int z, int buttons_state) -{ - ADS7846State *s = opaque; - - if (buttons_state) { - x = 0x7fff - x; - s->input[1] = ADS_XPOS(x, y); - s->input[3] = ADS_Z1POS(x, y); - s->input[4] = ADS_Z2POS(x, y); - s->input[5] = ADS_YPOS(x, y); - } - - if (s->pressure == !buttons_state) { - s->pressure = !!buttons_state; - - ads7846_int_update(s); - } -} - -static int ads7856_post_load(void *opaque, int version_id) -{ - ADS7846State *s = opaque; - - s->pressure = 0; - ads7846_int_update(s); - return 0; -} - -static const VMStateDescription vmstate_ads7846 = { - .name = "ads7846", - .version_id = 1, - .minimum_version_id = 1, - .post_load = ads7856_post_load, - .fields = (const VMStateField[]) { - VMSTATE_SSI_PERIPHERAL(ssidev, ADS7846State), - VMSTATE_INT32_ARRAY(input, ADS7846State, 8), - VMSTATE_INT32(noise, ADS7846State), - VMSTATE_INT32(cycle, ADS7846State), - VMSTATE_INT32(output, ADS7846State), - VMSTATE_END_OF_LIST() - } -}; - -static void ads7846_realize(SSIPeripheral *d, Error **errp) -{ - DeviceState *dev = DEVICE(d); - ADS7846State *s = ADS7846(d); - - qdev_init_gpio_out(dev, &s->interrupt, 1); - - s->input[0] = ADS_TEMP0; /* TEMP0 */ - s->input[2] = ADS_VBAT; /* VBAT */ - s->input[6] = ADS_VAUX; /* VAUX */ - s->input[7] = ADS_TEMP1; /* TEMP1 */ - - /* We want absolute coordinates */ - qemu_add_mouse_event_handler(ads7846_ts_event, s, 1, - "QEMU ADS7846-driven Touchscreen"); - - ads7846_int_update(s); - - vmstate_register_any(NULL, &vmstate_ads7846, s); -} - -static void ads7846_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - SSIPeripheralClass *k = SSI_PERIPHERAL_CLASS(klass); - - k->realize = ads7846_realize; - k->transfer = ads7846_transfer; - set_bit(DEVICE_CATEGORY_INPUT, dc->categories); -} - -static const TypeInfo ads7846_info = { - .name = TYPE_ADS7846, - .parent = TYPE_SSI_PERIPHERAL, - .instance_size = sizeof(ADS7846State), - .class_init = ads7846_class_init, -}; - -static void ads7846_register_types(void) -{ - type_register_static(&ads7846_info); -} - -type_init(ads7846_register_types) diff --git a/hw/input/Kconfig b/hw/input/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/input/Kconfig +++ b/hw/input/Kconfig @@ -XXX,XX +XXX,XX @@ config ADB bool -config ADS7846 - bool - config LM832X bool depends on I2C diff --git a/hw/input/meson.build b/hw/input/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/input/meson.build +++ b/hw/input/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(files('hid.c')) system_ss.add(when: 'CONFIG_ADB', if_true: files('adb.c', 'adb-mouse.c', 'adb-kbd.c')) -system_ss.add(when: 'CONFIG_ADS7846', if_true: files('ads7846.c')) system_ss.add(when: 'CONFIG_LM832X', if_true: files('lm832x.c')) system_ss.add(when: 'CONFIG_PCKBD', if_true: files('pckbd.c')) system_ss.add(when: 'CONFIG_PL050', if_true: files('pl050.c')) -- 2.34.1 The tc6393xb was used only by the XScale-based Zaurus machine types. Now they have been removed we can remove this device too. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-7-peter.maydell@linaro.org --- MAINTAINERS | 2 - include/hw/display/tc6393xb.h | 21 -- hw/display/tc6393xb.c | 568 ---------------------------------- hw/display/meson.build | 1 - 4 files changed, 592 deletions(-) delete mode 100644 include/hw/display/tc6393xb.h delete mode 100644 hw/display/tc6393xb.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Odd Fixes F: hw/arm/mainstone.c F: hw/arm/z2.c F: hw/*/pxa2xx* -F: hw/display/tc6393xb.c F: hw/gpio/max7310.c F: hw/gpio/zaurus.c F: hw/misc/mst_fpga.c @@ -XXX,XX +XXX,XX @@ F: hw/adc/max111x.c F: include/hw/adc/max111x.h F: include/hw/arm/pxa.h F: include/hw/arm/sharpsl.h -F: include/hw/display/tc6393xb.h F: docs/system/arm/mainstone.rst SABRELITE / i.MX6 diff --git a/include/hw/display/tc6393xb.h b/include/hw/display/tc6393xb.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/hw/display/tc6393xb.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Toshiba TC6393XB I/O Controller. - * Found in Sharp Zaurus SL-6000 (tosa) or some - * Toshiba e-Series PDAs. - * - * Copyright (c) 2007 Hervé Poussineau - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - */ - -#ifndef HW_DISPLAY_TC6393XB_H -#define HW_DISPLAY_TC6393XB_H - -typedef struct TC6393xbState TC6393xbState; - -TC6393xbState *tc6393xb_init(struct MemoryRegion *sysmem, - uint32_t base, qemu_irq irq); -qemu_irq tc6393xb_l3v_get(TC6393xbState *s); - -#endif diff --git a/hw/display/tc6393xb.c b/hw/display/tc6393xb.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/display/tc6393xb.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Toshiba TC6393XB I/O Controller. - * Found in Sharp Zaurus SL-6000 (tosa) or some - * Toshiba e-Series PDAs. - * - * Most features are currently unsupported!!! - * - * This code is licensed under the GNU GPL v2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "qemu/host-utils.h" -#include "hw/irq.h" -#include "hw/display/tc6393xb.h" -#include "exec/memory.h" -#include "hw/block/flash.h" -#include "ui/console.h" -#include "ui/pixel_ops.h" -#include "sysemu/blockdev.h" - -#define IRQ_TC6393_NAND 0 -#define IRQ_TC6393_MMC 1 -#define IRQ_TC6393_OHCI 2 -#define IRQ_TC6393_SERIAL 3 -#define IRQ_TC6393_FB 4 - -#define TC6393XB_NR_IRQS 8 - -#define TC6393XB_GPIOS 16 - -#define SCR_REVID 0x08 /* b Revision ID */ -#define SCR_ISR 0x50 /* b Interrupt Status */ -#define SCR_IMR 0x52 /* b Interrupt Mask */ -#define SCR_IRR 0x54 /* b Interrupt Routing */ -#define SCR_GPER 0x60 /* w GP Enable */ -#define SCR_GPI_SR(i) (0x64 + (i)) /* b3 GPI Status */ -#define SCR_GPI_IMR(i) (0x68 + (i)) /* b3 GPI INT Mask */ -#define SCR_GPI_EDER(i) (0x6c + (i)) /* b3 GPI Edge Detect Enable */ -#define SCR_GPI_LIR(i) (0x70 + (i)) /* b3 GPI Level Invert */ -#define SCR_GPO_DSR(i) (0x78 + (i)) /* b3 GPO Data Set */ -#define SCR_GPO_DOECR(i) (0x7c + (i)) /* b3 GPO Data OE Control */ -#define SCR_GP_IARCR(i) (0x80 + (i)) /* b3 GP Internal Active Register Control */ -#define SCR_GP_IARLCR(i) (0x84 + (i)) /* b3 GP INTERNAL Active Register Level Control */ -#define SCR_GPI_BCR(i) (0x88 + (i)) /* b3 GPI Buffer Control */ -#define SCR_GPA_IARCR 0x8c /* w GPa Internal Active Register Control */ -#define SCR_GPA_IARLCR 0x90 /* w GPa Internal Active Register Level Control */ -#define SCR_GPA_BCR 0x94 /* w GPa Buffer Control */ -#define SCR_CCR 0x98 /* w Clock Control */ -#define SCR_PLL2CR 0x9a /* w PLL2 Control */ -#define SCR_PLL1CR 0x9c /* l PLL1 Control */ -#define SCR_DIARCR 0xa0 /* b Device Internal Active Register Control */ -#define SCR_DBOCR 0xa1 /* b Device Buffer Off Control */ -#define SCR_FER 0xe0 /* b Function Enable */ -#define SCR_MCR 0xe4 /* w Mode Control */ -#define SCR_CONFIG 0xfc /* b Configuration Control */ -#define SCR_DEBUG 0xff /* b Debug */ - -#define NAND_CFG_COMMAND 0x04 /* w Command */ -#define NAND_CFG_BASE 0x10 /* l Control Base Address */ -#define NAND_CFG_INTP 0x3d /* b Interrupt Pin */ -#define NAND_CFG_INTE 0x48 /* b Int Enable */ -#define NAND_CFG_EC 0x4a /* b Event Control */ -#define NAND_CFG_ICC 0x4c /* b Internal Clock Control */ -#define NAND_CFG_ECCC 0x5b /* b ECC Control */ -#define NAND_CFG_NFTC 0x60 /* b NAND Flash Transaction Control */ -#define NAND_CFG_NFM 0x61 /* b NAND Flash Monitor */ -#define NAND_CFG_NFPSC 0x62 /* b NAND Flash Power Supply Control */ -#define NAND_CFG_NFDC 0x63 /* b NAND Flash Detect Control */ - -#define NAND_DATA 0x00 /* l Data */ -#define NAND_MODE 0x04 /* b Mode */ -#define NAND_STATUS 0x05 /* b Status */ -#define NAND_ISR 0x06 /* b Interrupt Status */ -#define NAND_IMR 0x07 /* b Interrupt Mask */ - -#define NAND_MODE_WP 0x80 -#define NAND_MODE_CE 0x10 -#define NAND_MODE_ALE 0x02 -#define NAND_MODE_CLE 0x01 -#define NAND_MODE_ECC_MASK 0x60 -#define NAND_MODE_ECC_EN 0x20 -#define NAND_MODE_ECC_READ 0x40 -#define NAND_MODE_ECC_RST 0x60 - -struct TC6393xbState { - MemoryRegion iomem; - qemu_irq irq; - qemu_irq *sub_irqs; - struct { - uint8_t ISR; - uint8_t IMR; - uint8_t IRR; - uint16_t GPER; - uint8_t GPI_SR[3]; - uint8_t GPI_IMR[3]; - uint8_t GPI_EDER[3]; - uint8_t GPI_LIR[3]; - uint8_t GP_IARCR[3]; - uint8_t GP_IARLCR[3]; - uint8_t GPI_BCR[3]; - uint16_t GPA_IARCR; - uint16_t GPA_IARLCR; - uint16_t CCR; - uint16_t PLL2CR; - uint32_t PLL1CR; - uint8_t DIARCR; - uint8_t DBOCR; - uint8_t FER; - uint16_t MCR; - uint8_t CONFIG; - uint8_t DEBUG; - } scr; - uint32_t gpio_dir; - uint32_t gpio_level; - uint32_t prev_level; - qemu_irq handler[TC6393XB_GPIOS]; - qemu_irq *gpio_in; - - struct { - uint8_t mode; - uint8_t isr; - uint8_t imr; - } nand; - int nand_enable; - uint32_t nand_phys; - DeviceState *flash; - ECCState ecc; - - QemuConsole *con; - MemoryRegion vram; - uint16_t *vram_ptr; - uint32_t scr_width, scr_height; /* in pixels */ - qemu_irq l3v; - unsigned blank : 1, - blanked : 1; -}; - -static void tc6393xb_gpio_set(void *opaque, int line, int level) -{ -// TC6393xbState *s = opaque; - - if (line > TC6393XB_GPIOS) { - printf("%s: No GPIO pin %i\n", __func__, line); - return; - } - - // FIXME: how does the chip reflect the GPIO input level change? -} - -static void tc6393xb_gpio_handler_update(TC6393xbState *s) -{ - uint32_t level, diff; - int bit; - - level = s->gpio_level & s->gpio_dir; - level &= MAKE_64BIT_MASK(0, TC6393XB_GPIOS); - - for (diff = s->prev_level ^ level; diff; diff ^= 1 << bit) { - bit = ctz32(diff); - qemu_set_irq(s->handler[bit], (level >> bit) & 1); - } - - s->prev_level = level; -} - -qemu_irq tc6393xb_l3v_get(TC6393xbState *s) -{ - return s->l3v; -} - -static void tc6393xb_l3v(void *opaque, int line, int level) -{ - TC6393xbState *s = opaque; - s->blank = !level; - fprintf(stderr, "L3V: %d\n", level); -} - -static void tc6393xb_sub_irq(void *opaque, int line, int level) { - TC6393xbState *s = opaque; - uint8_t isr = s->scr.ISR; - if (level) - isr |= 1 << line; - else - isr &= ~(1 << line); - s->scr.ISR = isr; - qemu_set_irq(s->irq, isr & s->scr.IMR); -} - -#define SCR_REG_B(N) \ - case SCR_ ##N: return s->scr.N -#define SCR_REG_W(N) \ - case SCR_ ##N: return s->scr.N; \ - case SCR_ ##N + 1: return s->scr.N >> 8; -#define SCR_REG_L(N) \ - case SCR_ ##N: return s->scr.N; \ - case SCR_ ##N + 1: return s->scr.N >> 8; \ - case SCR_ ##N + 2: return s->scr.N >> 16; \ - case SCR_ ##N + 3: return s->scr.N >> 24; -#define SCR_REG_A(N) \ - case SCR_ ##N(0): return s->scr.N[0]; \ - case SCR_ ##N(1): return s->scr.N[1]; \ - case SCR_ ##N(2): return s->scr.N[2] - -static uint32_t tc6393xb_scr_readb(TC6393xbState *s, hwaddr addr) -{ - switch (addr) { - case SCR_REVID: - return 3; - case SCR_REVID+1: - return 0; - SCR_REG_B(ISR); - SCR_REG_B(IMR); - SCR_REG_B(IRR); - SCR_REG_W(GPER); - SCR_REG_A(GPI_SR); - SCR_REG_A(GPI_IMR); - SCR_REG_A(GPI_EDER); - SCR_REG_A(GPI_LIR); - case SCR_GPO_DSR(0): - case SCR_GPO_DSR(1): - case SCR_GPO_DSR(2): - return (s->gpio_level >> ((addr - SCR_GPO_DSR(0)) * 8)) & 0xff; - case SCR_GPO_DOECR(0): - case SCR_GPO_DOECR(1): - case SCR_GPO_DOECR(2): - return (s->gpio_dir >> ((addr - SCR_GPO_DOECR(0)) * 8)) & 0xff; - SCR_REG_A(GP_IARCR); - SCR_REG_A(GP_IARLCR); - SCR_REG_A(GPI_BCR); - SCR_REG_W(GPA_IARCR); - SCR_REG_W(GPA_IARLCR); - SCR_REG_W(CCR); - SCR_REG_W(PLL2CR); - SCR_REG_L(PLL1CR); - SCR_REG_B(DIARCR); - SCR_REG_B(DBOCR); - SCR_REG_B(FER); - SCR_REG_W(MCR); - SCR_REG_B(CONFIG); - SCR_REG_B(DEBUG); - } - fprintf(stderr, "tc6393xb_scr: unhandled read at %08x\n", (uint32_t) addr); - return 0; -} -#undef SCR_REG_B -#undef SCR_REG_W -#undef SCR_REG_L -#undef SCR_REG_A - -#define SCR_REG_B(N) \ - case SCR_ ##N: s->scr.N = value; return; -#define SCR_REG_W(N) \ - case SCR_ ##N: s->scr.N = (s->scr.N & ~0xff) | (value & 0xff); return; \ - case SCR_ ##N + 1: s->scr.N = (s->scr.N & 0xff) | (value << 8); return -#define SCR_REG_L(N) \ - case SCR_ ##N: s->scr.N = (s->scr.N & ~0xff) | (value & 0xff); return; \ - case SCR_ ##N + 1: s->scr.N = (s->scr.N & ~(0xff << 8)) | (value & (0xff << 8)); return; \ - case SCR_ ##N + 2: s->scr.N = (s->scr.N & ~(0xff << 16)) | (value & (0xff << 16)); return; \ - case SCR_ ##N + 3: s->scr.N = (s->scr.N & ~(0xff << 24)) | (value & (0xff << 24)); return; -#define SCR_REG_A(N) \ - case SCR_ ##N(0): s->scr.N[0] = value; return; \ - case SCR_ ##N(1): s->scr.N[1] = value; return; \ - case SCR_ ##N(2): s->scr.N[2] = value; return - -static void tc6393xb_scr_writeb(TC6393xbState *s, hwaddr addr, uint32_t value) -{ - switch (addr) { - SCR_REG_B(ISR); - SCR_REG_B(IMR); - SCR_REG_B(IRR); - SCR_REG_W(GPER); - SCR_REG_A(GPI_SR); - SCR_REG_A(GPI_IMR); - SCR_REG_A(GPI_EDER); - SCR_REG_A(GPI_LIR); - case SCR_GPO_DSR(0): - case SCR_GPO_DSR(1): - case SCR_GPO_DSR(2): - s->gpio_level = (s->gpio_level & ~(0xff << ((addr - SCR_GPO_DSR(0))*8))) | ((value & 0xff) << ((addr - SCR_GPO_DSR(0))*8)); - tc6393xb_gpio_handler_update(s); - return; - case SCR_GPO_DOECR(0): - case SCR_GPO_DOECR(1): - case SCR_GPO_DOECR(2): - s->gpio_dir = (s->gpio_dir & ~(0xff << ((addr - SCR_GPO_DOECR(0))*8))) | ((value & 0xff) << ((addr - SCR_GPO_DOECR(0))*8)); - tc6393xb_gpio_handler_update(s); - return; - SCR_REG_A(GP_IARCR); - SCR_REG_A(GP_IARLCR); - SCR_REG_A(GPI_BCR); - SCR_REG_W(GPA_IARCR); - SCR_REG_W(GPA_IARLCR); - SCR_REG_W(CCR); - SCR_REG_W(PLL2CR); - SCR_REG_L(PLL1CR); - SCR_REG_B(DIARCR); - SCR_REG_B(DBOCR); - SCR_REG_B(FER); - SCR_REG_W(MCR); - SCR_REG_B(CONFIG); - SCR_REG_B(DEBUG); - } - fprintf(stderr, "tc6393xb_scr: unhandled write at %08x: %02x\n", - (uint32_t) addr, value & 0xff); -} -#undef SCR_REG_B -#undef SCR_REG_W -#undef SCR_REG_L -#undef SCR_REG_A - -static void tc6393xb_nand_irq(TC6393xbState *s) { - qemu_set_irq(s->sub_irqs[IRQ_TC6393_NAND], - (s->nand.imr & 0x80) && (s->nand.imr & s->nand.isr)); -} - -static uint32_t tc6393xb_nand_cfg_readb(TC6393xbState *s, hwaddr addr) { - switch (addr) { - case NAND_CFG_COMMAND: - return s->nand_enable ? 2 : 0; - case NAND_CFG_BASE: - case NAND_CFG_BASE + 1: - case NAND_CFG_BASE + 2: - case NAND_CFG_BASE + 3: - return s->nand_phys >> (addr - NAND_CFG_BASE); - } - fprintf(stderr, "tc6393xb_nand_cfg: unhandled read at %08x\n", (uint32_t) addr); - return 0; -} -static void tc6393xb_nand_cfg_writeb(TC6393xbState *s, hwaddr addr, uint32_t value) { - switch (addr) { - case NAND_CFG_COMMAND: - s->nand_enable = (value & 0x2); - return; - case NAND_CFG_BASE: - case NAND_CFG_BASE + 1: - case NAND_CFG_BASE + 2: - case NAND_CFG_BASE + 3: - s->nand_phys &= ~(0xff << ((addr - NAND_CFG_BASE) * 8)); - s->nand_phys |= (value & 0xff) << ((addr - NAND_CFG_BASE) * 8); - return; - } - fprintf(stderr, "tc6393xb_nand_cfg: unhandled write at %08x: %02x\n", - (uint32_t) addr, value & 0xff); -} - -static uint32_t tc6393xb_nand_readb(TC6393xbState *s, hwaddr addr) { - switch (addr) { - case NAND_DATA + 0: - case NAND_DATA + 1: - case NAND_DATA + 2: - case NAND_DATA + 3: - return nand_getio(s->flash); - case NAND_MODE: - return s->nand.mode; - case NAND_STATUS: - return 0x14; - case NAND_ISR: - return s->nand.isr; - case NAND_IMR: - return s->nand.imr; - } - fprintf(stderr, "tc6393xb_nand: unhandled read at %08x\n", (uint32_t) addr); - return 0; -} -static void tc6393xb_nand_writeb(TC6393xbState *s, hwaddr addr, uint32_t value) { -// fprintf(stderr, "tc6393xb_nand: write at %08x: %02x\n", -// (uint32_t) addr, value & 0xff); - switch (addr) { - case NAND_DATA + 0: - case NAND_DATA + 1: - case NAND_DATA + 2: - case NAND_DATA + 3: - nand_setio(s->flash, value); - s->nand.isr |= 1; - tc6393xb_nand_irq(s); - return; - case NAND_MODE: - s->nand.mode = value; - nand_setpins(s->flash, - value & NAND_MODE_CLE, - value & NAND_MODE_ALE, - !(value & NAND_MODE_CE), - value & NAND_MODE_WP, - 0); // FIXME: gnd - switch (value & NAND_MODE_ECC_MASK) { - case NAND_MODE_ECC_RST: - ecc_reset(&s->ecc); - break; - case NAND_MODE_ECC_READ: - // FIXME - break; - case NAND_MODE_ECC_EN: - ecc_reset(&s->ecc); - } - return; - case NAND_ISR: - s->nand.isr = value; - tc6393xb_nand_irq(s); - return; - case NAND_IMR: - s->nand.imr = value; - tc6393xb_nand_irq(s); - return; - } - fprintf(stderr, "tc6393xb_nand: unhandled write at %08x: %02x\n", - (uint32_t) addr, value & 0xff); -} - -static void tc6393xb_draw_graphic(TC6393xbState *s, int full_update) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - int i; - uint16_t *data_buffer; - uint8_t *data_display; - - data_buffer = s->vram_ptr; - data_display = surface_data(surface); - for (i = 0; i < s->scr_height; i++) { - int j; - for (j = 0; j < s->scr_width; j++, data_display += 4, data_buffer++) { - uint16_t color = *data_buffer; - uint32_t dest_color = rgb_to_pixel32( - ((color & 0xf800) * 0x108) >> 11, - ((color & 0x7e0) * 0x41) >> 9, - ((color & 0x1f) * 0x21) >> 2 - ); - *(uint32_t *)data_display = dest_color; - } - } - dpy_gfx_update_full(s->con); -} - -static void tc6393xb_draw_blank(TC6393xbState *s, int full_update) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - int i, w; - uint8_t *d; - - if (!full_update) - return; - - w = s->scr_width * surface_bytes_per_pixel(surface); - d = surface_data(surface); - for(i = 0; i < s->scr_height; i++) { - memset(d, 0, w); - d += surface_stride(surface); - } - - dpy_gfx_update_full(s->con); -} - -static void tc6393xb_update_display(void *opaque) -{ - TC6393xbState *s = opaque; - DisplaySurface *surface = qemu_console_surface(s->con); - int full_update; - - if (s->scr_width == 0 || s->scr_height == 0) - return; - - full_update = 0; - if (s->blanked != s->blank) { - s->blanked = s->blank; - full_update = 1; - } - if (s->scr_width != surface_width(surface) || - s->scr_height != surface_height(surface)) { - qemu_console_resize(s->con, s->scr_width, s->scr_height); - full_update = 1; - } - if (s->blanked) - tc6393xb_draw_blank(s, full_update); - else - tc6393xb_draw_graphic(s, full_update); -} - - -static uint64_t tc6393xb_readb(void *opaque, hwaddr addr, - unsigned size) -{ - TC6393xbState *s = opaque; - - switch (addr >> 8) { - case 0: - return tc6393xb_scr_readb(s, addr & 0xff); - case 1: - return tc6393xb_nand_cfg_readb(s, addr & 0xff); - }; - - if ((addr &~0xff) == s->nand_phys && s->nand_enable) { -// return tc6393xb_nand_readb(s, addr & 0xff); - uint8_t d = tc6393xb_nand_readb(s, addr & 0xff); -// fprintf(stderr, "tc6393xb_nand: read at %08x: %02hhx\n", (uint32_t) addr, d); - return d; - } - -// fprintf(stderr, "tc6393xb: unhandled read at %08x\n", (uint32_t) addr); - return 0; -} - -static void tc6393xb_writeb(void *opaque, hwaddr addr, - uint64_t value, unsigned size) { - TC6393xbState *s = opaque; - - switch (addr >> 8) { - case 0: - tc6393xb_scr_writeb(s, addr & 0xff, value); - return; - case 1: - tc6393xb_nand_cfg_writeb(s, addr & 0xff, value); - return; - }; - - if ((addr &~0xff) == s->nand_phys && s->nand_enable) - tc6393xb_nand_writeb(s, addr & 0xff, value); - else - fprintf(stderr, "tc6393xb: unhandled write at %08x: %02x\n", - (uint32_t) addr, (int)value & 0xff); -} - -static const GraphicHwOps tc6393xb_gfx_ops = { - .gfx_update = tc6393xb_update_display, -}; - -TC6393xbState *tc6393xb_init(MemoryRegion *sysmem, uint32_t base, qemu_irq irq) -{ - TC6393xbState *s; - DriveInfo *nand; - static const MemoryRegionOps tc6393xb_ops = { - .read = tc6393xb_readb, - .write = tc6393xb_writeb, - .endianness = DEVICE_NATIVE_ENDIAN, - .impl = { - .min_access_size = 1, - .max_access_size = 1, - }, - }; - - s = g_new0(TC6393xbState, 1); - s->irq = irq; - s->gpio_in = qemu_allocate_irqs(tc6393xb_gpio_set, s, TC6393XB_GPIOS); - - s->l3v = qemu_allocate_irq(tc6393xb_l3v, s, 0); - s->blanked = 1; - - s->sub_irqs = qemu_allocate_irqs(tc6393xb_sub_irq, s, TC6393XB_NR_IRQS); - - nand = drive_get(IF_MTD, 0, 0); - s->flash = nand_init(nand ? blk_by_legacy_dinfo(nand) : NULL, - NAND_MFR_TOSHIBA, 0x76); - - memory_region_init_io(&s->iomem, NULL, &tc6393xb_ops, s, "tc6393xb", 0x10000); - memory_region_add_subregion(sysmem, base, &s->iomem); - - memory_region_init_ram(&s->vram, NULL, "tc6393xb.vram", 0x100000, - &error_fatal); - s->vram_ptr = memory_region_get_ram_ptr(&s->vram); - memory_region_add_subregion(sysmem, base + 0x100000, &s->vram); - s->scr_width = 480; - s->scr_height = 640; - s->con = graphic_console_init(NULL, 0, &tc6393xb_gfx_ops, s); - - return s; -} diff --git a/hw/display/meson.build b/hw/display/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_BOCHS_DISPLAY', if_true: files('bochs-display.c')) system_ss.add(when: 'CONFIG_BLIZZARD', if_true: files('blizzard.c')) system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210_fimd.c')) system_ss.add(when: 'CONFIG_FRAMEBUFFER', if_true: files('framebuffer.c')) -system_ss.add(when: 'CONFIG_ZAURUS', if_true: files('tc6393xb.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_dss.c')) system_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_lcd.c')) -- 2.34.1 The ZAURUS KConfig symbol used to do multiple things: * pull in the tc6393xb display device * pull in the Zaurus SCOOP GPIO device * pull in hw/block/nand.c code * pull in hw/block/ecc.c code and was used by multiple machine types in the Zaurus family. Now that we've removed all the Zaurus machine types except "collie" (which is not currently deprecated), we can simplify this. "collie" doesn't need any of the above things except for the SCOOP GPIO device. Remove the does-lots-of-things ZAURUS KConfig symbol and instead have collie pull in ZAURUS_SCOOP, a new KConfig symbol which exists only to control the presence of the SCOOP GPIO device. Move the associated source file lines in MAINTAINERS into the Collie subsection, since this is now its only user. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-8-peter.maydell@linaro.org --- MAINTAINERS | 4 ++-- hw/arm/Kconfig | 7 +------ hw/gpio/Kconfig | 3 +++ hw/gpio/meson.build | 2 +- 4 files changed, 7 insertions(+), 9 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/arm/mainstone.c F: hw/arm/z2.c F: hw/*/pxa2xx* F: hw/gpio/max7310.c -F: hw/gpio/zaurus.c F: hw/misc/mst_fpga.c F: hw/adc/max111x.c F: include/hw/adc/max111x.h F: include/hw/arm/pxa.h -F: include/hw/arm/sharpsl.h F: docs/system/arm/mainstone.rst SABRELITE / i.MX6 @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Odd Fixes F: hw/arm/collie.c F: hw/arm/strongarm* +F: hw/gpio/zaurus.c +F: include/hw/arm/sharpsl.h F: docs/system/arm/collie.rst Stellaris 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 COLLIE default y depends on TCG && ARM select PFLASH_CFI01 - select ZAURUS # scoop + select ZAURUS_SCOOP select STRONGARM config SX1 @@ -XXX,XX +XXX,XX @@ config MSF2 select SSI select UNIMP -config ZAURUS - bool - select NAND - select ECC - config ARMSSE bool select ARM_V7M diff --git a/hw/gpio/Kconfig b/hw/gpio/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/Kconfig +++ b/hw/gpio/Kconfig @@ -XXX,XX +XXX,XX @@ config STM32L4X5_GPIO config PCF8574 bool depends on I2C + +config ZAURUS_SCOOP + bool diff --git a/hw/gpio/meson.build b/hw/gpio/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/meson.build +++ b/hw/gpio/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_MAX7310', if_true: files('max7310.c')) system_ss.add(when: 'CONFIG_PCA9552', if_true: files('pca9552.c')) system_ss.add(when: 'CONFIG_PCA9554', if_true: files('pca9554.c')) system_ss.add(when: 'CONFIG_PL061', if_true: files('pl061.c')) -system_ss.add(when: 'CONFIG_ZAURUS', if_true: files('zaurus.c')) +system_ss.add(when: 'CONFIG_ZAURUS_SCOOP', if_true: files('zaurus.c')) system_ss.add(when: 'CONFIG_IMX', if_true: files('imx_gpio.c')) system_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_gpio.c')) -- 2.34.1 The 'cheetah' machine has been deprecated since 9.0, so we can remove it for the 9.2 release. (tsc210x.c is also used by nseries, so move its MAINTAINER file line there; the nseries boards are also about to be removed.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-9-peter.maydell@linaro.org --- MAINTAINERS | 10 +- docs/system/arm/palm.rst | 23 -- docs/system/target-arm.rst | 1 - configs/devices/arm-softmmu/default.mak | 1 - hw/arm/palm.c | 324 ------------------------ hw/arm/Kconfig | 7 - hw/arm/meson.build | 1 - 7 files changed, 1 insertion(+), 366 deletions(-) delete mode 100644 docs/system/arm/palm.rst delete mode 100644 hw/arm/palm.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/arm/nseries.c F: hw/display/blizzard.c F: hw/input/lm832x.c F: hw/input/tsc2005.c +F: hw/input/tsc210x.c F: hw/misc/cbus.c F: hw/rtc/twl92230.c F: include/hw/display/blizzard.h @@ -XXX,XX +XXX,XX @@ F: include/hw/misc/cbus.h F: tests/avocado/machine_arm_n8x0.py F: docs/system/arm/nseries.rst -Palm -M: Peter Maydell <peter.maydell@linaro.org> -L: qemu-arm@nongnu.org -S: Odd Fixes -F: hw/arm/palm.c -F: hw/input/tsc210x.c -F: include/hw/input/tsc2xxx.h -F: docs/system/arm/palm.rst - Raspberry Pi M: Peter Maydell <peter.maydell@linaro.org> R: Philippe Mathieu-Daudé <philmd@linaro.org> diff --git a/docs/system/arm/palm.rst b/docs/system/arm/palm.rst deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/system/arm/palm.rst +++ /dev/null @@ -XXX,XX +XXX,XX @@ -Palm Tungsten|E PDA (``cheetah``) -================================= - -The Palm Tungsten|E PDA (codename \"Cheetah\") emulation includes the -following elements: - -- Texas Instruments OMAP310 System-on-chip (ARM925T core) - -- ROM and RAM memories (ROM firmware image can be loaded with - -option-rom) - -- On-chip LCD controller - -- On-chip Real Time Clock - -- TI TSC2102i touchscreen controller / analog-digital converter / - Audio CODEC, connected through MicroWire and |I2S| buses - -- GPIO-connected matrix keypad - -- Secure Digital card connected to OMAP MMC/SD host - -- Three on-chip UARTs diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/nuvoton arm/imx25-pdk arm/orangepi - arm/palm arm/raspi arm/collie arm/sx1 diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ # CONFIG_MUSICPAL=n # CONFIG_MPS3R=n # CONFIG_MUSCA=n -# CONFIG_CHEETAH=n # CONFIG_SX1=n # CONFIG_NSERIES=n # CONFIG_STELLARIS=n diff --git a/hw/arm/palm.c b/hw/arm/palm.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/palm.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * PalmOne's (TM) PDAs. - * - * Copyright (C) 2006-2007 Andrzej Zaborowski <balrog@zabor.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "audio/audio.h" -#include "sysemu/sysemu.h" -#include "sysemu/qtest.h" -#include "ui/console.h" -#include "hw/arm/omap.h" -#include "hw/boards.h" -#include "hw/arm/boot.h" -#include "hw/input/tsc2xxx.h" -#include "hw/irq.h" -#include "hw/loader.h" -#include "qemu/cutils.h" -#include "qom/object.h" -#include "qemu/error-report.h" - - -static uint64_t static_read(void *opaque, hwaddr offset, unsigned size) -{ - uint32_t *val = (uint32_t *)opaque; - uint32_t sizemask = 7 >> size; - - return *val >> ((offset & sizemask) << 3); -} - -static void static_write(void *opaque, hwaddr offset, uint64_t value, - unsigned size) -{ -#ifdef SPY - printf("%s: value %08lx written at " PA_FMT "\n", - __func__, value, offset); -#endif -} - -static const MemoryRegionOps static_ops = { - .read = static_read, - .write = static_write, - .valid.min_access_size = 1, - .valid.max_access_size = 4, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -/* Palm Tunsgten|E support */ - -/* Shared GPIOs */ -#define PALMTE_USBDETECT_GPIO 0 -#define PALMTE_USB_OR_DC_GPIO 1 -#define PALMTE_TSC_GPIO 4 -#define PALMTE_PINTDAV_GPIO 6 -#define PALMTE_MMC_WP_GPIO 8 -#define PALMTE_MMC_POWER_GPIO 9 -#define PALMTE_HDQ_GPIO 11 -#define PALMTE_HEADPHONES_GPIO 14 -#define PALMTE_SPEAKER_GPIO 15 -/* MPU private GPIOs */ -#define PALMTE_DC_GPIO 2 -#define PALMTE_MMC_SWITCH_GPIO 4 -#define PALMTE_MMC1_GPIO 6 -#define PALMTE_MMC2_GPIO 7 -#define PALMTE_MMC3_GPIO 11 - -static MouseTransformInfo palmte_pointercal = { - .x = 320, - .y = 320, - .a = { -5909, 8, 22465308, 104, 7644, -1219972, 65536 }, -}; - -static void palmte_microwire_setup(struct omap_mpu_state_s *cpu) -{ - uWireSlave *tsc; - - tsc = tsc2102_init(qdev_get_gpio_in(cpu->gpio, PALMTE_PINTDAV_GPIO)); - - omap_uwire_attach(cpu->microwire, tsc, 0); - omap_mcbsp_i2s_attach(cpu->mcbsp1, tsc210x_codec(tsc)); - - tsc210x_set_transform(tsc, &palmte_pointercal); -} - -static struct { - int row; - int column; -} palmte_keymap[0x80] = { - [0 ... 0x7f] = { -1, -1 }, - [0x3b] = { 0, 0 }, /* F1 -> Calendar */ - [0x3c] = { 1, 0 }, /* F2 -> Contacts */ - [0x3d] = { 2, 0 }, /* F3 -> Tasks List */ - [0x3e] = { 3, 0 }, /* F4 -> Note Pad */ - [0x01] = { 4, 0 }, /* Esc -> Power */ - [0x4b] = { 0, 1 }, /* Left */ - [0x50] = { 1, 1 }, /* Down */ - [0x48] = { 2, 1 }, /* Up */ - [0x4d] = { 3, 1 }, /* Right */ - [0x4c] = { 4, 1 }, /* Centre */ - [0x39] = { 4, 1 }, /* Spc -> Centre */ -}; - -static void palmte_button_event(void *opaque, int keycode) -{ - struct omap_mpu_state_s *cpu = opaque; - - if (palmte_keymap[keycode & 0x7f].row != -1) - omap_mpuio_key(cpu->mpuio, - palmte_keymap[keycode & 0x7f].row, - palmte_keymap[keycode & 0x7f].column, - !(keycode & 0x80)); -} - -/* - * Encapsulation of some GPIO line behaviour for the Palm board - * - * QEMU interface: - * + unnamed GPIO inputs 0..6: for the various miscellaneous input lines - */ - -#define TYPE_PALM_MISC_GPIO "palm-misc-gpio" -OBJECT_DECLARE_SIMPLE_TYPE(PalmMiscGPIOState, PALM_MISC_GPIO) - -struct PalmMiscGPIOState { - SysBusDevice parent_obj; -}; - -static void palmte_onoff_gpios(void *opaque, int line, int level) -{ - switch (line) { - case 0: - printf("%s: current to MMC/SD card %sabled.\n", - __func__, level ? "dis" : "en"); - break; - case 1: - printf("%s: internal speaker amplifier %s.\n", - __func__, level ? "down" : "on"); - break; - - /* These LCD & Audio output signals have not been identified yet. */ - case 2: - case 3: - case 4: - printf("%s: LCD GPIO%i %s.\n", - __func__, line - 1, level ? "high" : "low"); - break; - case 5: - case 6: - printf("%s: Audio GPIO%i %s.\n", - __func__, line - 4, level ? "high" : "low"); - break; - } -} - -static void palm_misc_gpio_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - - qdev_init_gpio_in(dev, palmte_onoff_gpios, 7); -} - -static const TypeInfo palm_misc_gpio_info = { - .name = TYPE_PALM_MISC_GPIO, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PalmMiscGPIOState), - .instance_init = palm_misc_gpio_init, - /* - * No class init required: device has no internal state so does not - * need to set up reset or vmstate, and has no realize method. - */ -}; - -static void palmte_gpio_setup(struct omap_mpu_state_s *cpu) -{ - DeviceState *misc_gpio; - - misc_gpio = sysbus_create_simple(TYPE_PALM_MISC_GPIO, -1, NULL); - - omap_mmc_handlers(cpu->mmc, - qdev_get_gpio_in(cpu->gpio, PALMTE_MMC_WP_GPIO), - qemu_irq_invert(omap_mpuio_in_get(cpu->mpuio) - [PALMTE_MMC_SWITCH_GPIO])); - - qdev_connect_gpio_out(cpu->gpio, PALMTE_MMC_POWER_GPIO, - qdev_get_gpio_in(misc_gpio, 0)); - qdev_connect_gpio_out(cpu->gpio, PALMTE_SPEAKER_GPIO, - qdev_get_gpio_in(misc_gpio, 1)); - qdev_connect_gpio_out(cpu->gpio, 11, qdev_get_gpio_in(misc_gpio, 2)); - qdev_connect_gpio_out(cpu->gpio, 12, qdev_get_gpio_in(misc_gpio, 3)); - qdev_connect_gpio_out(cpu->gpio, 13, qdev_get_gpio_in(misc_gpio, 4)); - omap_mpuio_out_set(cpu->mpuio, 1, qdev_get_gpio_in(misc_gpio, 5)); - omap_mpuio_out_set(cpu->mpuio, 3, qdev_get_gpio_in(misc_gpio, 6)); - - /* Reset some inputs to initial state. */ - qemu_irq_lower(qdev_get_gpio_in(cpu->gpio, PALMTE_USBDETECT_GPIO)); - qemu_irq_lower(qdev_get_gpio_in(cpu->gpio, PALMTE_USB_OR_DC_GPIO)); - qemu_irq_lower(qdev_get_gpio_in(cpu->gpio, 4)); - qemu_irq_lower(qdev_get_gpio_in(cpu->gpio, PALMTE_HEADPHONES_GPIO)); - qemu_irq_lower(omap_mpuio_in_get(cpu->mpuio)[PALMTE_DC_GPIO]); - qemu_irq_raise(omap_mpuio_in_get(cpu->mpuio)[6]); - qemu_irq_raise(omap_mpuio_in_get(cpu->mpuio)[7]); - qemu_irq_raise(omap_mpuio_in_get(cpu->mpuio)[11]); -} - -static struct arm_boot_info palmte_binfo = { - .loader_start = OMAP_EMIFF_BASE, - .ram_size = 0x02000000, - .board_id = 0x331, -}; - -static void palmte_init(MachineState *machine) -{ - MemoryRegion *address_space_mem = get_system_memory(); - struct omap_mpu_state_s *mpu; - int flash_size = 0x00800000; - static uint32_t cs0val = 0xffffffff; - static uint32_t cs1val = 0x0000e1a0; - static uint32_t cs2val = 0x0000e1a0; - static uint32_t cs3val = 0xe1a0e1a0; - int rom_size, rom_loaded = 0; - MachineClass *mc = MACHINE_GET_CLASS(machine); - MemoryRegion *flash = g_new(MemoryRegion, 1); - MemoryRegion *cs = g_new(MemoryRegion, 4); - - if (machine->ram_size != mc->default_ram_size) { - char *sz = size_to_str(mc->default_ram_size); - error_report("Invalid RAM size, should be %s", sz); - g_free(sz); - exit(EXIT_FAILURE); - } - - memory_region_add_subregion(address_space_mem, OMAP_EMIFF_BASE, - machine->ram); - - mpu = omap310_mpu_init(machine->ram, machine->cpu_type); - - /* External Flash (EMIFS) */ - memory_region_init_rom(flash, NULL, "palmte.flash", flash_size, - &error_fatal); - memory_region_add_subregion(address_space_mem, OMAP_CS0_BASE, flash); - - memory_region_init_io(&cs[0], NULL, &static_ops, &cs0val, "palmte-cs0", - OMAP_CS0_SIZE - flash_size); - memory_region_add_subregion(address_space_mem, OMAP_CS0_BASE + flash_size, - &cs[0]); - memory_region_init_io(&cs[1], NULL, &static_ops, &cs1val, "palmte-cs1", - OMAP_CS1_SIZE); - memory_region_add_subregion(address_space_mem, OMAP_CS1_BASE, &cs[1]); - memory_region_init_io(&cs[2], NULL, &static_ops, &cs2val, "palmte-cs2", - OMAP_CS2_SIZE); - memory_region_add_subregion(address_space_mem, OMAP_CS2_BASE, &cs[2]); - memory_region_init_io(&cs[3], NULL, &static_ops, &cs3val, "palmte-cs3", - OMAP_CS3_SIZE); - memory_region_add_subregion(address_space_mem, OMAP_CS3_BASE, &cs[3]); - - palmte_microwire_setup(mpu); - - qemu_add_kbd_event_handler(palmte_button_event, mpu); - - palmte_gpio_setup(mpu); - - /* Setup initial (reset) machine state */ - if (nb_option_roms) { - rom_size = get_image_size(option_rom[0].name); - if (rom_size > flash_size) { - fprintf(stderr, "%s: ROM image too big (%x > %x)\n", - __func__, rom_size, flash_size); - rom_size = 0; - } - if (rom_size > 0) { - rom_size = load_image_targphys(option_rom[0].name, OMAP_CS0_BASE, - flash_size); - rom_loaded = 1; - } - if (rom_size < 0) { - fprintf(stderr, "%s: error loading '%s'\n", - __func__, option_rom[0].name); - } - } - - if (!rom_loaded && !machine->kernel_filename && !qtest_enabled()) { - fprintf(stderr, "Kernel or ROM image must be specified\n"); - exit(1); - } - - /* Load the kernel. */ - arm_load_kernel(mpu->cpu, machine, &palmte_binfo); -} - -static void palmte_machine_init(MachineClass *mc) -{ - mc->desc = "Palm Tungsten|E aka. Cheetah PDA (OMAP310)"; - mc->init = palmte_init; - mc->ignore_memory_transaction_failures = true; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("ti925t"); - mc->default_ram_size = 0x02000000; - mc->default_ram_id = "omap1.dram"; - mc->deprecation_reason = "machine is old and unmaintained"; - - machine_add_audiodev_property(mc); -} - -DEFINE_MACHINE("cheetah", palmte_machine_init) - -static void palm_register_types(void) -{ - type_register_static(&palm_misc_gpio_info); -} - -type_init(palm_register_types) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ARM_VIRT select ACPI_CXL select ACPI_HMAT -config CHEETAH - bool - default y - depends on TCG && ARM - select OMAP - select TSC210X - config CUBIEBOARD bool default y diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_XEN', if_true: files( )) system_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmu-common.c')) -system_ss.add(when: 'CONFIG_CHEETAH', if_true: files('palm.c')) system_ss.add(when: 'CONFIG_COLLIE', if_true: files('collie.c')) system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4_boards.c')) system_ss.add(when: 'CONFIG_GUMSTIX', if_true: files('gumstix.c')) -- 2.34.1 The connex and verdex machines have been deprecated since 9.0 and so can be removed for the 9.2 release. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-10-peter.maydell@linaro.org --- MAINTAINERS | 8 -- docs/system/arm/gumstix.rst | 21 ---- docs/system/target-arm.rst | 1 - configs/devices/arm-softmmu/default.mak | 1 - hw/arm/gumstix.c | 141 ------------------------ hw/arm/Kconfig | 8 -- hw/arm/meson.build | 1 - 7 files changed, 181 deletions(-) delete mode 100644 docs/system/arm/gumstix.rst delete mode 100644 hw/arm/gumstix.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Maintained F: hw/rtc/goldfish_rtc.c F: include/hw/rtc/goldfish_rtc.h -Gumstix -M: Peter Maydell <peter.maydell@linaro.org> -R: Philippe Mathieu-Daudé <philmd@linaro.org> -L: qemu-arm@nongnu.org -S: Odd Fixes -F: hw/arm/gumstix.c -F: docs/system/arm/gumstix.rst - i.MX25 PDK M: Peter Maydell <peter.maydell@linaro.org> R: Jean-Christophe Dubois <jcd@tribudubois.net> diff --git a/docs/system/arm/gumstix.rst b/docs/system/arm/gumstix.rst deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/system/arm/gumstix.rst +++ /dev/null @@ -XXX,XX +XXX,XX @@ -Gumstix Connex and Verdex (``connex``, ``verdex``) -================================================== - -These machines model the Gumstix Connex and Verdex boards. -The Connex has a PXA255 CPU and the Verdex has a PXA270. - -Implemented devices: - - * NOR flash - * SMC91C111 ethernet - * Interrupt controller - * DMA - * Timer - * GPIO - * MMC/SD card - * Fast infra-red communications port (FIR) - * LCD controller - * Synchronous serial ports (SPI) - * PCMCIA interface - * I2C - * I2S diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/cubieboard arm/emcraft-sf2 arm/musicpal - arm/gumstix arm/mainstone arm/kzm arm/nseries diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ # CONFIG_VEXPRESS=n # CONFIG_ZYNQ=n # CONFIG_MAINSTONE=n -# CONFIG_GUMSTIX=n # CONFIG_Z2=n # CONFIG_NPCM7XX=n # CONFIG_COLLIE=n diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/gumstix.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Gumstix Platforms - * - * Copyright (c) 2007 by Thorsten Zitterell <info@bitmux.org> - * - * Code based on spitz platform by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GNU GPL v2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -/* - * Example usage: - * - * connex: - * ======= - * create image: - * # dd of=flash bs=1k count=16k if=/dev/zero - * # dd of=flash bs=1k conv=notrunc if=u-boot.bin - * # dd of=flash bs=1k conv=notrunc seek=256 if=rootfs.arm_nofpu.jffs2 - * start it: - * # qemu-system-arm -M connex -pflash flash -monitor null -nographic - * - * verdex: - * ======= - * create image: - * # dd of=flash bs=1k count=32k if=/dev/zero - * # dd of=flash bs=1k conv=notrunc if=u-boot.bin - * # dd of=flash bs=1k conv=notrunc seek=256 if=rootfs.arm_nofpu.jffs2 - * # dd of=flash bs=1k conv=notrunc seek=31744 if=uImage - * start it: - * # qemu-system-arm -M verdex -pflash flash -monitor null -nographic -m 289 - */ - -#include "qemu/osdep.h" -#include "qemu/units.h" -#include "qemu/error-report.h" -#include "hw/arm/pxa.h" -#include "net/net.h" -#include "hw/block/flash.h" -#include "hw/net/smc91c111.h" -#include "hw/boards.h" -#include "exec/address-spaces.h" -#include "sysemu/qtest.h" - -#define CONNEX_FLASH_SIZE (16 * MiB) -#define CONNEX_RAM_SIZE (64 * MiB) - -#define VERDEX_FLASH_SIZE (32 * MiB) -#define VERDEX_RAM_SIZE (256 * MiB) - -#define FLASH_SECTOR_SIZE (128 * KiB) - -static void connex_init(MachineState *machine) -{ - PXA2xxState *cpu; - DriveInfo *dinfo; - - cpu = pxa255_init(CONNEX_RAM_SIZE); - - dinfo = drive_get(IF_PFLASH, 0, 0); - if (!dinfo && !qtest_enabled()) { - error_report("A flash image must be given with the " - "'pflash' parameter"); - exit(1); - } - - /* Numonyx RC28F128J3F75 */ - pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0); - - /* Interrupt line of NIC is connected to GPIO line 36 */ - smc91c111_init(0x04000300, qdev_get_gpio_in(cpu->gpio, 36)); -} - -static void verdex_init(MachineState *machine) -{ - PXA2xxState *cpu; - DriveInfo *dinfo; - - cpu = pxa270_init(VERDEX_RAM_SIZE, machine->cpu_type); - - dinfo = drive_get(IF_PFLASH, 0, 0); - if (!dinfo && !qtest_enabled()) { - error_report("A flash image must be given with the " - "'pflash' parameter"); - exit(1); - } - - /* Micron RC28F256P30TFA */ - pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0); - - /* Interrupt line of NIC is connected to GPIO line 99 */ - smc91c111_init(0x04000300, qdev_get_gpio_in(cpu->gpio, 99)); -} - -static void connex_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Gumstix Connex (PXA255)"; - mc->init = connex_init; - mc->ignore_memory_transaction_failures = true; - mc->deprecation_reason = "machine is old and unmaintained"; -} - -static const TypeInfo connex_type = { - .name = MACHINE_TYPE_NAME("connex"), - .parent = TYPE_MACHINE, - .class_init = connex_class_init, -}; - -static void verdex_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Gumstix Verdex Pro XL6P COMs (PXA270)"; - mc->init = verdex_init; - mc->ignore_memory_transaction_failures = true; - mc->deprecation_reason = "machine is old and unmaintained"; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); -} - -static const TypeInfo verdex_type = { - .name = MACHINE_TYPE_NAME("verdex"), - .parent = TYPE_MACHINE, - .class_init = verdex_class_init, -}; - -static void gumstix_machine_init(void) -{ - type_register_static(&connex_type); - type_register_static(&verdex_type); -} - -type_init(gumstix_machine_init) 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 PXA2XX select USB_OHCI_SYSBUS select PCMCIA -config GUMSTIX - bool - default y - depends on TCG && ARM - select PFLASH_CFI01 - select SMC91C111 - select PXA2XX - config Z2 bool default y diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_XEN', if_true: files( system_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmu-common.c')) system_ss.add(when: 'CONFIG_COLLIE', if_true: files('collie.c')) system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4_boards.c')) -system_ss.add(when: 'CONFIG_GUMSTIX', if_true: files('gumstix.c')) system_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap2.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_peripherals.c')) -- 2.34.1 The 'mainstone' machine has been deprecated since 9.0, and so we can remove it for the 9.2 release. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-11-peter.maydell@linaro.org --- MAINTAINERS | 2 - docs/system/arm/mainstone.rst | 25 ---- docs/system/target-arm.rst | 1 - configs/devices/arm-softmmu/default.mak | 1 - hw/arm/mainstone.c | 175 ------------------------ hw/arm/Kconfig | 8 -- hw/arm/meson.build | 1 - 7 files changed, 213 deletions(-) delete mode 100644 docs/system/arm/mainstone.rst delete mode 100644 hw/arm/mainstone.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ PXA2XX M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes -F: hw/arm/mainstone.c F: hw/arm/z2.c F: hw/*/pxa2xx* F: hw/gpio/max7310.c @@ -XXX,XX +XXX,XX @@ F: hw/misc/mst_fpga.c F: hw/adc/max111x.c F: include/hw/adc/max111x.h F: include/hw/arm/pxa.h -F: docs/system/arm/mainstone.rst SABRELITE / i.MX6 M: Peter Maydell <peter.maydell@linaro.org> diff --git a/docs/system/arm/mainstone.rst b/docs/system/arm/mainstone.rst deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/system/arm/mainstone.rst +++ /dev/null @@ -XXX,XX +XXX,XX @@ -Intel Mainstone II board (``mainstone``) -======================================== - -The ``mainstone`` board emulates the Intel Mainstone II development -board, which uses a PXA270 CPU. - -Emulated devices: - -- Flash memory -- Keypad -- MMC controller -- 91C111 ethernet -- PIC -- Timer -- DMA -- GPIO -- FIR -- Serial -- LCD controller -- SSP -- USB controller -- RTC -- PCMCIA -- I2C -- I2S diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/cubieboard arm/emcraft-sf2 arm/musicpal - arm/mainstone arm/kzm arm/nseries arm/nrf diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ # CONFIG_VERSATILE=n # CONFIG_VEXPRESS=n # CONFIG_ZYNQ=n -# CONFIG_MAINSTONE=n # CONFIG_Z2=n # CONFIG_NPCM7XX=n # CONFIG_COLLIE=n diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/mainstone.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * PXA270-based Intel Mainstone platforms. - * - * Copyright (c) 2007 by Armin Kuster <akuster@kama-aina.net> or - * <akuster@mvista.com> - * - * Code based on spitz platform by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GNU GPL v2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ -#include "qemu/osdep.h" -#include "qemu/units.h" -#include "qemu/error-report.h" -#include "qapi/error.h" -#include "hw/arm/pxa.h" -#include "hw/arm/boot.h" -#include "net/net.h" -#include "hw/net/smc91c111.h" -#include "hw/boards.h" -#include "hw/block/flash.h" -#include "hw/sysbus.h" -#include "exec/address-spaces.h" - -/* Device addresses */ -#define MST_FPGA_PHYS 0x08000000 -#define MST_ETH_PHYS 0x10000300 -#define MST_FLASH_0 0x00000000 -#define MST_FLASH_1 0x04000000 - -/* IRQ definitions */ -#define MMC_IRQ 0 -#define USIM_IRQ 1 -#define USBC_IRQ 2 -#define ETHERNET_IRQ 3 -#define AC97_IRQ 4 -#define PEN_IRQ 5 -#define MSINS_IRQ 6 -#define EXBRD_IRQ 7 -#define S0_CD_IRQ 9 -#define S0_STSCHG_IRQ 10 -#define S0_IRQ 11 -#define S1_CD_IRQ 13 -#define S1_STSCHG_IRQ 14 -#define S1_IRQ 15 - -static const struct keymap map[0xE0] = { - [0 ... 0xDF] = { -1, -1 }, - [0x1e] = {0,0}, /* a */ - [0x30] = {0,1}, /* b */ - [0x2e] = {0,2}, /* c */ - [0x20] = {0,3}, /* d */ - [0x12] = {0,4}, /* e */ - [0x21] = {0,5}, /* f */ - [0x22] = {1,0}, /* g */ - [0x23] = {1,1}, /* h */ - [0x17] = {1,2}, /* i */ - [0x24] = {1,3}, /* j */ - [0x25] = {1,4}, /* k */ - [0x26] = {1,5}, /* l */ - [0x32] = {2,0}, /* m */ - [0x31] = {2,1}, /* n */ - [0x18] = {2,2}, /* o */ - [0x19] = {2,3}, /* p */ - [0x10] = {2,4}, /* q */ - [0x13] = {2,5}, /* r */ - [0x1f] = {3,0}, /* s */ - [0x14] = {3,1}, /* t */ - [0x16] = {3,2}, /* u */ - [0x2f] = {3,3}, /* v */ - [0x11] = {3,4}, /* w */ - [0x2d] = {3,5}, /* x */ - [0x34] = {4,0}, /* . */ - [0x15] = {4,2}, /* y */ - [0x2c] = {4,3}, /* z */ - [0x35] = {4,4}, /* / */ - [0xc7] = {5,0}, /* Home */ - [0x2a] = {5,1}, /* shift */ - /* - * There are two matrix positions which map to space, - * but QEMU can only use one of them for the reverse - * mapping, so simply use the second one. - */ - /* [0x39] = {5,2}, space */ - [0x39] = {5,3}, /* space */ - /* - * Matrix position {5,4} and other keys are missing here. - * TODO: Compare with Linux code and test real hardware. - */ - [0x1c] = {5,4}, /* enter */ - [0x0e] = {5,5}, /* backspace */ - [0xc8] = {6,0}, /* up */ - [0xd0] = {6,1}, /* down */ - [0xcb] = {6,2}, /* left */ - [0xcd] = {6,3}, /* right */ -}; - -enum mainstone_model_e { mainstone }; - -#define MAINSTONE_RAM_SIZE (64 * MiB) -#define MAINSTONE_ROM_SIZE (8 * MiB) -#define MAINSTONE_FLASH_SIZE (32 * MiB) - -static struct arm_boot_info mainstone_binfo = { - .loader_start = PXA2XX_SDRAM_BASE, - .ram_size = MAINSTONE_RAM_SIZE, -}; - -#define FLASH_SECTOR_SIZE (256 * KiB) - -static void mainstone_common_init(MachineState *machine, - enum mainstone_model_e model, int arm_id) -{ - hwaddr mainstone_flash_base[] = { MST_FLASH_0, MST_FLASH_1 }; - PXA2xxState *mpu; - DeviceState *mst_irq; - DriveInfo *dinfo; - int i; - MemoryRegion *rom = g_new(MemoryRegion, 1); - - /* Setup CPU & memory */ - mpu = pxa270_init(mainstone_binfo.ram_size, machine->cpu_type); - memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM_SIZE, - &error_fatal); - memory_region_add_subregion(get_system_memory(), 0x00000000, rom); - - /* There are two 32MiB flash devices on the board */ - for (i = 0; i < 2; i ++) { - dinfo = drive_get(IF_PFLASH, 0, i); - pflash_cfi01_register(mainstone_flash_base[i], - i ? "mainstone.flash1" : "mainstone.flash0", - MAINSTONE_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0); - } - - mst_irq = sysbus_create_simple("mainstone-fpga", MST_FPGA_PHYS, - qdev_get_gpio_in(mpu->gpio, 0)); - - /* setup keypad */ - pxa27x_register_keypad(mpu->kp, map, 0xe0); - - /* MMC/SD host */ - pxa2xx_mmci_handlers(mpu->mmc, NULL, qdev_get_gpio_in(mst_irq, MMC_IRQ)); - - pxa2xx_pcmcia_set_irq_cb(mpu->pcmcia[0], - qdev_get_gpio_in(mst_irq, S0_IRQ), - qdev_get_gpio_in(mst_irq, S0_CD_IRQ)); - pxa2xx_pcmcia_set_irq_cb(mpu->pcmcia[1], - qdev_get_gpio_in(mst_irq, S1_IRQ), - qdev_get_gpio_in(mst_irq, S1_CD_IRQ)); - - smc91c111_init(MST_ETH_PHYS, qdev_get_gpio_in(mst_irq, ETHERNET_IRQ)); - - mainstone_binfo.board_id = arm_id; - arm_load_kernel(mpu->cpu, machine, &mainstone_binfo); -} - -static void mainstone_init(MachineState *machine) -{ - mainstone_common_init(machine, mainstone, 0x196); -} - -static void mainstone2_machine_init(MachineClass *mc) -{ - mc->desc = "Mainstone II (PXA27x)"; - mc->init = mainstone_init; - mc->ignore_memory_transaction_failures = true; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c5"); - mc->deprecation_reason = "machine is old and unmaintained"; -} - -DEFINE_MACHINE("mainstone", mainstone2_machine_init) 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 INTEGRATOR select PL181 # display select SMC91C111 -config MAINSTONE - bool - default y - depends on TCG && ARM - select PXA2XX - select PFLASH_CFI01 - select SMC91C111 - config MPS3R bool default y diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_DIGIC', if_true: files('digic_boards.c')) arm_ss.add(when: 'CONFIG_EMCRAFT_SF2', if_true: files('msf2-som.c')) arm_ss.add(when: 'CONFIG_HIGHBANK', if_true: files('highbank.c')) arm_ss.add(when: 'CONFIG_INTEGRATOR', if_true: files('integratorcp.c')) -arm_ss.add(when: 'CONFIG_MAINSTONE', if_true: files('mainstone.c')) arm_ss.add(when: 'CONFIG_MICROBIT', if_true: files('microbit.c')) arm_ss.add(when: 'CONFIG_MPS3R', if_true: files('mps3r.c')) arm_ss.add(when: 'CONFIG_MUSICPAL', if_true: files('musicpal.c')) -- 2.34.1 The MAINSTONE_FPGA device was used only by the 'mainstone' machine type, so we can remove it now. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-12-peter.maydell@linaro.org --- MAINTAINERS | 1 - hw/misc/mst_fpga.c | 269 -------------------------------------------- hw/misc/meson.build | 1 - 3 files changed, 271 deletions(-) delete mode 100644 hw/misc/mst_fpga.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Odd Fixes F: hw/arm/z2.c F: hw/*/pxa2xx* F: hw/gpio/max7310.c -F: hw/misc/mst_fpga.c F: hw/adc/max111x.c F: include/hw/adc/max111x.h F: include/hw/arm/pxa.h diff --git a/hw/misc/mst_fpga.c b/hw/misc/mst_fpga.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/misc/mst_fpga.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * PXA270-based Intel Mainstone platforms. - * FPGA driver - * - * Copyright (c) 2007 by Armin Kuster <akuster@kama-aina.net> or - * <akuster@mvista.com> - * - * This code is licensed under the GNU GPL v2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "qemu/module.h" -#include "qom/object.h" - -/* Mainstone FPGA for extern irqs */ -#define FPGA_GPIO_PIN 0 -#define MST_NUM_IRQS 16 -#define MST_LEDDAT1 0x10 -#define MST_LEDDAT2 0x14 -#define MST_LEDCTRL 0x40 -#define MST_GPSWR 0x60 -#define MST_MSCWR1 0x80 -#define MST_MSCWR2 0x84 -#define MST_MSCWR3 0x88 -#define MST_MSCRD 0x90 -#define MST_INTMSKENA 0xc0 -#define MST_INTSETCLR 0xd0 -#define MST_PCMCIA0 0xe0 -#define MST_PCMCIA1 0xe4 - -#define MST_PCMCIAx_READY (1 << 10) -#define MST_PCMCIAx_nCD (1 << 5) - -#define MST_PCMCIA_CD0_IRQ 9 -#define MST_PCMCIA_CD1_IRQ 13 - -#define TYPE_MAINSTONE_FPGA "mainstone-fpga" -OBJECT_DECLARE_SIMPLE_TYPE(mst_irq_state, MAINSTONE_FPGA) - -struct mst_irq_state { - SysBusDevice parent_obj; - - MemoryRegion iomem; - - qemu_irq parent; - - uint32_t prev_level; - uint32_t leddat1; - uint32_t leddat2; - uint32_t ledctrl; - uint32_t gpswr; - uint32_t mscwr1; - uint32_t mscwr2; - uint32_t mscwr3; - uint32_t mscrd; - uint32_t intmskena; - uint32_t intsetclr; - uint32_t pcmcia0; - uint32_t pcmcia1; -}; - -static void -mst_fpga_set_irq(void *opaque, int irq, int level) -{ - mst_irq_state *s = (mst_irq_state *)opaque; - uint32_t oldint = s->intsetclr & s->intmskena; - - if (level) - s->prev_level |= 1u << irq; - else - s->prev_level &= ~(1u << irq); - - switch(irq) { - case MST_PCMCIA_CD0_IRQ: - if (level) - s->pcmcia0 &= ~MST_PCMCIAx_nCD; - else - s->pcmcia0 |= MST_PCMCIAx_nCD; - break; - case MST_PCMCIA_CD1_IRQ: - if (level) - s->pcmcia1 &= ~MST_PCMCIAx_nCD; - else - s->pcmcia1 |= MST_PCMCIAx_nCD; - break; - } - - if ((s->intmskena & (1u << irq)) && level) - s->intsetclr |= 1u << irq; - - if (oldint != (s->intsetclr & s->intmskena)) - qemu_set_irq(s->parent, s->intsetclr & s->intmskena); -} - - -static uint64_t -mst_fpga_readb(void *opaque, hwaddr addr, unsigned size) -{ - mst_irq_state *s = (mst_irq_state *) opaque; - - switch (addr) { - case MST_LEDDAT1: - return s->leddat1; - case MST_LEDDAT2: - return s->leddat2; - case MST_LEDCTRL: - return s->ledctrl; - case MST_GPSWR: - return s->gpswr; - case MST_MSCWR1: - return s->mscwr1; - case MST_MSCWR2: - return s->mscwr2; - case MST_MSCWR3: - return s->mscwr3; - case MST_MSCRD: - return s->mscrd; - case MST_INTMSKENA: - return s->intmskena; - case MST_INTSETCLR: - return s->intsetclr; - case MST_PCMCIA0: - return s->pcmcia0; - case MST_PCMCIA1: - return s->pcmcia1; - default: - printf("Mainstone - mst_fpga_readb: Bad register offset " - "0x" HWADDR_FMT_plx "\n", addr); - } - return 0; -} - -static void -mst_fpga_writeb(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - mst_irq_state *s = (mst_irq_state *) opaque; - value &= 0xffffffff; - - switch (addr) { - case MST_LEDDAT1: - s->leddat1 = value; - break; - case MST_LEDDAT2: - s->leddat2 = value; - break; - case MST_LEDCTRL: - s->ledctrl = value; - break; - case MST_GPSWR: - s->gpswr = value; - break; - case MST_MSCWR1: - s->mscwr1 = value; - break; - case MST_MSCWR2: - s->mscwr2 = value; - break; - case MST_MSCWR3: - s->mscwr3 = value; - break; - case MST_MSCRD: - s->mscrd = value; - break; - case MST_INTMSKENA: /* Mask interrupt */ - s->intmskena = (value & 0xFEEFF); - qemu_set_irq(s->parent, s->intsetclr & s->intmskena); - break; - case MST_INTSETCLR: /* clear or set interrupt */ - s->intsetclr = (value & 0xFEEFF); - qemu_set_irq(s->parent, s->intsetclr & s->intmskena); - break; - /* For PCMCIAx allow the to change only power and reset */ - case MST_PCMCIA0: - s->pcmcia0 = (value & 0x1f) | (s->pcmcia0 & ~0x1f); - break; - case MST_PCMCIA1: - s->pcmcia1 = (value & 0x1f) | (s->pcmcia1 & ~0x1f); - break; - default: - printf("Mainstone - mst_fpga_writeb: Bad register offset " - "0x" HWADDR_FMT_plx "\n", addr); - } -} - -static const MemoryRegionOps mst_fpga_ops = { - .read = mst_fpga_readb, - .write = mst_fpga_writeb, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static int mst_fpga_post_load(void *opaque, int version_id) -{ - mst_irq_state *s = (mst_irq_state *) opaque; - - qemu_set_irq(s->parent, s->intsetclr & s->intmskena); - return 0; -} - -static void mst_fpga_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - mst_irq_state *s = MAINSTONE_FPGA(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - s->pcmcia0 = MST_PCMCIAx_READY | MST_PCMCIAx_nCD; - s->pcmcia1 = MST_PCMCIAx_READY | MST_PCMCIAx_nCD; - - sysbus_init_irq(sbd, &s->parent); - - /* alloc the external 16 irqs */ - qdev_init_gpio_in(dev, mst_fpga_set_irq, MST_NUM_IRQS); - - memory_region_init_io(&s->iomem, obj, &mst_fpga_ops, s, - "fpga", 0x00100000); - sysbus_init_mmio(sbd, &s->iomem); -} - -static const VMStateDescription vmstate_mst_fpga_regs = { - .name = "mainstone_fpga", - .version_id = 0, - .minimum_version_id = 0, - .post_load = mst_fpga_post_load, - .fields = (const VMStateField[]) { - VMSTATE_UINT32(prev_level, mst_irq_state), - VMSTATE_UINT32(leddat1, mst_irq_state), - VMSTATE_UINT32(leddat2, mst_irq_state), - VMSTATE_UINT32(ledctrl, mst_irq_state), - VMSTATE_UINT32(gpswr, mst_irq_state), - VMSTATE_UINT32(mscwr1, mst_irq_state), - VMSTATE_UINT32(mscwr2, mst_irq_state), - VMSTATE_UINT32(mscwr3, mst_irq_state), - VMSTATE_UINT32(mscrd, mst_irq_state), - VMSTATE_UINT32(intmskena, mst_irq_state), - VMSTATE_UINT32(intsetclr, mst_irq_state), - VMSTATE_UINT32(pcmcia0, mst_irq_state), - VMSTATE_UINT32(pcmcia1, mst_irq_state), - VMSTATE_END_OF_LIST(), - }, -}; - -static void mst_fpga_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->desc = "Mainstone II FPGA"; - dc->vmsd = &vmstate_mst_fpga_regs; -} - -static const TypeInfo mst_fpga_info = { - .name = TYPE_MAINSTONE_FPGA, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(mst_irq_state), - .instance_init = mst_fpga_init, - .class_init = mst_fpga_class_init, -}; - -static void mst_fpga_register_types(void) -{ - type_register_static(&mst_fpga_info); -} - -type_init(mst_fpga_register_types) diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_IMX', if_true: files( 'imx_ccm.c', 'imx_rngc.c', )) -system_ss.add(when: 'CONFIG_MAINSTONE', if_true: files('mst_fpga.c')) system_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( 'npcm7xx_clk.c', 'npcm7xx_gcr.c', -- 2.34.1 The 'z2' machine was deprecated in 9.0, so we can remove it for 9.2. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-13-peter.maydell@linaro.org --- MAINTAINERS | 1 - configs/devices/arm-softmmu/default.mak | 1 - hw/arm/z2.c | 355 ------------------------ hw/arm/Kconfig | 9 - hw/arm/meson.build | 1 - 5 files changed, 367 deletions(-) delete mode 100644 hw/arm/z2.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ PXA2XX M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes -F: hw/arm/z2.c F: hw/*/pxa2xx* F: hw/gpio/max7310.c F: hw/adc/max111x.c diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ # CONFIG_VERSATILE=n # CONFIG_VEXPRESS=n # CONFIG_ZYNQ=n -# CONFIG_Z2=n # CONFIG_NPCM7XX=n # CONFIG_COLLIE=n # CONFIG_ASPEED_SOC=n diff --git a/hw/arm/z2.c b/hw/arm/z2.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/z2.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * PXA270-based Zipit Z2 device - * - * Copyright (c) 2011 by Vasily Khoruzhick <anarsoul@gmail.com> - * - * Code is based on mainstone platform. - * - * This code is licensed under the GNU GPL v2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "qemu/units.h" -#include "hw/arm/pxa.h" -#include "hw/arm/boot.h" -#include "hw/i2c/i2c.h" -#include "hw/irq.h" -#include "hw/ssi/ssi.h" -#include "migration/vmstate.h" -#include "hw/boards.h" -#include "hw/block/flash.h" -#include "ui/console.h" -#include "hw/audio/wm8750.h" -#include "audio/audio.h" -#include "exec/address-spaces.h" -#include "qom/object.h" -#include "qapi/error.h" -#include "trace.h" - -static const struct keymap map[0x100] = { - [0 ... 0xff] = { -1, -1 }, - [0x3b] = {0, 0}, /* Option = F1 */ - [0xc8] = {0, 1}, /* Up */ - [0xd0] = {0, 2}, /* Down */ - [0xcb] = {0, 3}, /* Left */ - [0xcd] = {0, 4}, /* Right */ - [0xcf] = {0, 5}, /* End */ - [0x0d] = {0, 6}, /* KPPLUS */ - [0xc7] = {1, 0}, /* Home */ - [0x10] = {1, 1}, /* Q */ - [0x17] = {1, 2}, /* I */ - [0x22] = {1, 3}, /* G */ - [0x2d] = {1, 4}, /* X */ - [0x1c] = {1, 5}, /* Enter */ - [0x0c] = {1, 6}, /* KPMINUS */ - [0xc9] = {2, 0}, /* PageUp */ - [0x11] = {2, 1}, /* W */ - [0x18] = {2, 2}, /* O */ - [0x23] = {2, 3}, /* H */ - [0x2e] = {2, 4}, /* C */ - [0x38] = {2, 5}, /* LeftAlt */ - [0xd1] = {3, 0}, /* PageDown */ - [0x12] = {3, 1}, /* E */ - [0x19] = {3, 2}, /* P */ - [0x24] = {3, 3}, /* J */ - [0x2f] = {3, 4}, /* V */ - [0x2a] = {3, 5}, /* LeftShift */ - [0x01] = {4, 0}, /* Esc */ - [0x13] = {4, 1}, /* R */ - [0x1e] = {4, 2}, /* A */ - [0x25] = {4, 3}, /* K */ - [0x30] = {4, 4}, /* B */ - [0x1d] = {4, 5}, /* LeftCtrl */ - [0x0f] = {5, 0}, /* Tab */ - [0x14] = {5, 1}, /* T */ - [0x1f] = {5, 2}, /* S */ - [0x26] = {5, 3}, /* L */ - [0x31] = {5, 4}, /* N */ - [0x39] = {5, 5}, /* Space */ - [0x3c] = {6, 0}, /* Stop = F2 */ - [0x15] = {6, 1}, /* Y */ - [0x20] = {6, 2}, /* D */ - [0x0e] = {6, 3}, /* Backspace */ - [0x32] = {6, 4}, /* M */ - [0x33] = {6, 5}, /* Comma */ - [0x3d] = {7, 0}, /* Play = F3 */ - [0x16] = {7, 1}, /* U */ - [0x21] = {7, 2}, /* F */ - [0x2c] = {7, 3}, /* Z */ - [0x27] = {7, 4}, /* Semicolon */ - [0x34] = {7, 5}, /* Dot */ -}; - -#define Z2_RAM_SIZE 0x02000000 -#define Z2_FLASH_BASE 0x00000000 -#define Z2_FLASH_SIZE 0x00800000 - -static struct arm_boot_info z2_binfo = { - .loader_start = PXA2XX_SDRAM_BASE, - .ram_size = Z2_RAM_SIZE, -}; - -#define Z2_GPIO_SD_DETECT 96 -#define Z2_GPIO_AC_IN 0 -#define Z2_GPIO_KEY_ON 1 -#define Z2_GPIO_LCD_CS 88 - -struct ZipitLCD { - SSIPeripheral ssidev; - int32_t selected; - int32_t enabled; - uint8_t buf[3]; - uint32_t cur_reg; - int pos; -}; - -#define TYPE_ZIPIT_LCD "zipit-lcd" -OBJECT_DECLARE_SIMPLE_TYPE(ZipitLCD, ZIPIT_LCD) - -static uint32_t zipit_lcd_transfer(SSIPeripheral *dev, uint32_t value) -{ - ZipitLCD *z = ZIPIT_LCD(dev); - uint16_t val; - - trace_z2_lcd_reg_update(z->cur_reg, z->buf[0], z->buf[1], z->buf[2], value); - if (z->selected) { - z->buf[z->pos] = value & 0xff; - z->pos++; - } - if (z->pos == 3) { - switch (z->buf[0]) { - case 0x74: - z->cur_reg = z->buf[2]; - break; - case 0x76: - val = z->buf[1] << 8 | z->buf[2]; - if (z->cur_reg == 0x22 && val == 0x0000) { - z->enabled = 1; - trace_z2_lcd_enable_disable_result("enabled"); - } else if (z->cur_reg == 0x10 && val == 0x0000) { - z->enabled = 0; - trace_z2_lcd_enable_disable_result("disabled"); - } - break; - default: - break; - } - z->pos = 0; - } - return 0; -} - -static void z2_lcd_cs(void *opaque, int line, int level) -{ - ZipitLCD *z2_lcd = opaque; - z2_lcd->selected = !level; -} - -static void zipit_lcd_realize(SSIPeripheral *dev, Error **errp) -{ - ZipitLCD *z = ZIPIT_LCD(dev); - z->selected = 0; - z->enabled = 0; - z->pos = 0; -} - -static const VMStateDescription vmstate_zipit_lcd_state = { - .name = "zipit-lcd", - .version_id = 2, - .minimum_version_id = 2, - .fields = (const VMStateField[]) { - VMSTATE_SSI_PERIPHERAL(ssidev, ZipitLCD), - VMSTATE_INT32(selected, ZipitLCD), - VMSTATE_INT32(enabled, ZipitLCD), - VMSTATE_BUFFER(buf, ZipitLCD), - VMSTATE_UINT32(cur_reg, ZipitLCD), - VMSTATE_INT32(pos, ZipitLCD), - VMSTATE_END_OF_LIST(), - } -}; - -static void zipit_lcd_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - SSIPeripheralClass *k = SSI_PERIPHERAL_CLASS(klass); - - k->realize = zipit_lcd_realize; - k->transfer = zipit_lcd_transfer; - dc->vmsd = &vmstate_zipit_lcd_state; -} - -static const TypeInfo zipit_lcd_info = { - .name = TYPE_ZIPIT_LCD, - .parent = TYPE_SSI_PERIPHERAL, - .instance_size = sizeof(ZipitLCD), - .class_init = zipit_lcd_class_init, -}; - -#define TYPE_AER915 "aer915" -OBJECT_DECLARE_SIMPLE_TYPE(AER915State, AER915) - -struct AER915State { - I2CSlave parent_obj; - - int len; - uint8_t buf[3]; -}; - -static int aer915_send(I2CSlave *i2c, uint8_t data) -{ - AER915State *s = AER915(i2c); - - s->buf[s->len] = data; - if (s->len++ > 2) { - trace_z2_aer915_send_too_long(s->len); - return 1; - } - - if (s->len == 2) { - trace_z2_aer915_send(s->buf[0], s->buf[1]); - } - - return 0; -} - -static int aer915_event(I2CSlave *i2c, enum i2c_event event) -{ - AER915State *s = AER915(i2c); - - trace_z2_aer915_event(s->len, event); - switch (event) { - case I2C_START_SEND: - s->len = 0; - break; - case I2C_START_RECV: - break; - case I2C_FINISH: - break; - default: - break; - } - - return 0; -} - -static uint8_t aer915_recv(I2CSlave *slave) -{ - AER915State *s = AER915(slave); - int retval = 0x00; - - switch (s->buf[0]) { - /* Return hardcoded battery voltage, - * 0xf0 means ~4.1V - */ - case 0x02: - retval = 0xf0; - break; - /* Return 0x00 for other regs, - * we don't know what they are for, - * anyway they return 0x00 on real hardware. - */ - default: - break; - } - - return retval; -} - -static const VMStateDescription vmstate_aer915_state = { - .name = "aer915", - .version_id = 1, - .minimum_version_id = 1, - .fields = (const VMStateField[]) { - VMSTATE_INT32(len, AER915State), - VMSTATE_BUFFER(buf, AER915State), - VMSTATE_END_OF_LIST(), - } -}; - -static void aer915_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); - - k->event = aer915_event; - k->recv = aer915_recv; - k->send = aer915_send; - dc->vmsd = &vmstate_aer915_state; -} - -static const TypeInfo aer915_info = { - .name = TYPE_AER915, - .parent = TYPE_I2C_SLAVE, - .instance_size = sizeof(AER915State), - .class_init = aer915_class_init, -}; - -#define FLASH_SECTOR_SIZE (64 * KiB) - -static void z2_init(MachineState *machine) -{ - PXA2xxState *mpu; - DriveInfo *dinfo; - void *z2_lcd; - I2CBus *bus; - DeviceState *wm; - I2CSlave *i2c_dev; - - /* Setup CPU & memory */ - mpu = pxa270_init(z2_binfo.ram_size, machine->cpu_type); - - dinfo = drive_get(IF_PFLASH, 0, 0); - pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0); - - /* setup keypad */ - pxa27x_register_keypad(mpu->kp, map, 0x100); - - /* MMC/SD host */ - pxa2xx_mmci_handlers(mpu->mmc, - NULL, - qdev_get_gpio_in(mpu->gpio, Z2_GPIO_SD_DETECT)); - - type_register_static(&zipit_lcd_info); - type_register_static(&aer915_info); - z2_lcd = ssi_create_peripheral(mpu->ssp[1], TYPE_ZIPIT_LCD); - bus = pxa2xx_i2c_bus(mpu->i2c[0]); - - i2c_slave_create_simple(bus, TYPE_AER915, 0x55); - - i2c_dev = i2c_slave_new(TYPE_WM8750, 0x1b); - wm = DEVICE(i2c_dev); - - if (machine->audiodev) { - qdev_prop_set_string(wm, "audiodev", machine->audiodev); - } - i2c_slave_realize_and_unref(i2c_dev, bus, &error_abort); - - mpu->i2s->opaque = wm; - mpu->i2s->codec_out = wm8750_dac_dat; - mpu->i2s->codec_in = wm8750_adc_dat; - wm8750_data_req_set(wm, mpu->i2s->data_req, mpu->i2s); - - qdev_connect_gpio_out(mpu->gpio, Z2_GPIO_LCD_CS, - qemu_allocate_irq(z2_lcd_cs, z2_lcd, 0)); - - z2_binfo.board_id = 0x6dd; - arm_load_kernel(mpu->cpu, machine, &z2_binfo); -} - -static void z2_machine_init(MachineClass *mc) -{ - mc->desc = "Zipit Z2 (PXA27x)"; - mc->init = z2_init; - mc->ignore_memory_transaction_failures = true; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c5"); - mc->deprecation_reason = "machine is old and unmaintained"; - - machine_add_audiodev_property(mc); -} - -DEFINE_MACHINE("z2", z2_machine_init) 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 PXA2XX select USB_OHCI_SYSBUS select PCMCIA -config Z2 - bool - default y - depends on TCG && ARM - select PFLASH_CFI01 - select WM8750 - select PL011 # UART - select PXA2XX - config REALVIEW bool default y diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_STRONGARM', if_true: files('strongarm.c')) system_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) system_ss.add(when: 'CONFIG_VERSATILE', if_true: files('versatilepb.c')) system_ss.add(when: 'CONFIG_VEXPRESS', if_true: files('vexpress.c')) -system_ss.add(when: 'CONFIG_Z2', if_true: files('z2.c')) hw_arch += {'arm': arm_ss} -- 2.34.1 Currently the STRONGARM KConfig symbol pulls in PXA2XX. Since we've now removed all the true uses of PXA2XX, we'd like to remove the PXA2XX symbol too. To permit that, make STRONGARM directly select the things it truly depends on: * pxa25x-timer * SSI Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-14-peter.maydell@linaro.org --- hw/arm/Kconfig | 4 +++- hw/timer/Kconfig | 3 +++ hw/timer/meson.build | 2 +- 3 files changed, 7 insertions(+), 2 deletions(-) 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 PXA2XX select SSI select USB_OHCI_SYSBUS select PCMCIA + select PXA2XX_TIMER config REALVIEW bool @@ -XXX,XX +XXX,XX @@ config STM32VLDISCOVERY config STRONGARM bool - select PXA2XX + select PXA2XX_TIMER + select SSI config COLLIE bool diff --git a/hw/timer/Kconfig b/hw/timer/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/Kconfig +++ b/hw/timer/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10_PIT bool select PTIMER +config PXA2XX_TIMER + bool + config SIFIVE_PWM bool diff --git a/hw/timer/meson.build b/hw/timer/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/meson.build +++ b/hw/timer/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_timer.c')) system_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_timer.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_gptimer.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_synctimer.c')) -system_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_timer.c')) +system_ss.add(when: 'CONFIG_PXA2XX_TIMER', if_true: files('pxa2xx_timer.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_systmr.c')) system_ss.add(when: 'CONFIG_SH_TIMER', if_true: files('sh_timer.c')) system_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_timer.c')) -- 2.34.1 pxa2xx_timer includes pxa.h, but it doesn't actually make use of any of the #defines, function prototypes or structs defined there. Remove the unnecessary include (we will shortly be removing the whole header file). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-15-peter.maydell@linaro.org --- hw/timer/pxa2xx_timer.c | 1 - 1 file changed, 1 deletion(-) diff --git a/hw/timer/pxa2xx_timer.c b/hw/timer/pxa2xx_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/pxa2xx_timer.c +++ b/hw/timer/pxa2xx_timer.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "qemu/timer.h" #include "sysemu/runstate.h" -#include "hw/arm/pxa.h" #include "hw/sysbus.h" #include "migration/vmstate.h" #include "qemu/log.h" -- 2.34.1 All the callers of pxa270_init() and pxa255_init() have now been removed, so we can remove pxa2xx.c. This also removes the only uses of a lot of pxa2xx specific devices, which will be removed in subsequent commits. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-16-peter.maydell@linaro.org --- include/hw/arm/pxa.h | 78 -- hw/arm/pxa2xx.c | 2393 ------------------------------------------ hw/arm/meson.build | 2 +- 3 files changed, 1 insertion(+), 2472 deletions(-) delete mode 100644 hw/arm/pxa2xx.c diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ PXA2xxKeyPadState *pxa27x_keypad_init(MemoryRegion *sysmem, void pxa27x_register_keypad(PXA2xxKeyPadState *kp, const struct keymap *map, int size); -/* pxa2xx.c */ -#define TYPE_PXA2XX_I2C "pxa2xx_i2c" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxI2CState, PXA2XX_I2C) - -PXA2xxI2CState *pxa2xx_i2c_init(hwaddr base, - qemu_irq irq, uint32_t page_size); -I2CBus *pxa2xx_i2c_bus(PXA2xxI2CState *s); - -typedef struct PXA2xxI2SState PXA2xxI2SState; - -#define TYPE_PXA2XX_FIR "pxa2xx-fir" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxFIrState, PXA2XX_FIR) - -typedef struct { - ARMCPU *cpu; - DeviceState *pic; - qemu_irq reset; - MemoryRegion sdram; - MemoryRegion internal; - MemoryRegion cm_iomem; - MemoryRegion mm_iomem; - MemoryRegion pm_iomem; - DeviceState *dma; - DeviceState *gpio; - PXA2xxLCDState *lcd; - SSIBus **ssp; - PXA2xxI2CState *i2c[2]; - PXA2xxMMCIState *mmc; - PXA2xxPCMCIAState *pcmcia[2]; - PXA2xxI2SState *i2s; - PXA2xxFIrState *fir; - PXA2xxKeyPadState *kp; - - /* Power management */ - hwaddr pm_base; - uint32_t pm_regs[0x40]; - - /* Clock management */ - hwaddr cm_base; - uint32_t cm_regs[4]; - uint32_t clkcfg; - - /* Memory management */ - hwaddr mm_base; - uint32_t mm_regs[0x1a]; - - /* Performance monitoring */ - uint32_t pmnc; -} PXA2xxState; - -struct PXA2xxI2SState { - MemoryRegion iomem; - qemu_irq irq; - qemu_irq rx_dma; - qemu_irq tx_dma; - void (*data_req)(void *, int, int); - - uint32_t control[2]; - uint32_t status; - uint32_t mask; - uint32_t clk; - - int enable; - int rx_len; - int tx_len; - void (*codec_out)(void *, uint32_t); - uint32_t (*codec_in)(void *); - void *opaque; - - int fifo_len; - uint32_t fifo[16]; -}; - -# define PA_FMT "0x%08lx" - -PXA2xxState *pxa270_init(unsigned int sdram_size, const char *revision); -PXA2xxState *pxa255_init(unsigned int sdram_size); - #endif /* PXA_H */ diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/pxa2xx.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel XScale PXA255/270 processor support. - * - * Copyright (c) 2006 Openedhand Ltd. - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GPL. - */ - -#include "qemu/osdep.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qapi/error.h" -#include "exec/address-spaces.h" -#include "cpu.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "hw/arm/pxa.h" -#include "sysemu/sysemu.h" -#include "hw/char/serial.h" -#include "hw/i2c/i2c.h" -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "hw/qdev-properties-system.h" -#include "hw/ssi/ssi.h" -#include "hw/sd/sd.h" -#include "chardev/char-fe.h" -#include "sysemu/blockdev.h" -#include "sysemu/qtest.h" -#include "sysemu/rtc.h" -#include "qemu/cutils.h" -#include "qemu/log.h" -#include "qom/object.h" -#include "target/arm/cpregs.h" - -static struct { - hwaddr io_base; - int irqn; -} pxa255_serial[] = { - { 0x40100000, PXA2XX_PIC_FFUART }, - { 0x40200000, PXA2XX_PIC_BTUART }, - { 0x40700000, PXA2XX_PIC_STUART }, - { 0x41600000, PXA25X_PIC_HWUART }, - { 0, 0 } -}, pxa270_serial[] = { - { 0x40100000, PXA2XX_PIC_FFUART }, - { 0x40200000, PXA2XX_PIC_BTUART }, - { 0x40700000, PXA2XX_PIC_STUART }, - { 0, 0 } -}; - -typedef struct PXASSPDef { - hwaddr io_base; - int irqn; -} PXASSPDef; - -#if 0 -static PXASSPDef pxa250_ssp[] = { - { 0x41000000, PXA2XX_PIC_SSP }, - { 0, 0 } -}; -#endif - -static PXASSPDef pxa255_ssp[] = { - { 0x41000000, PXA2XX_PIC_SSP }, - { 0x41400000, PXA25X_PIC_NSSP }, - { 0, 0 } -}; - -#if 0 -static PXASSPDef pxa26x_ssp[] = { - { 0x41000000, PXA2XX_PIC_SSP }, - { 0x41400000, PXA25X_PIC_NSSP }, - { 0x41500000, PXA26X_PIC_ASSP }, - { 0, 0 } -}; -#endif - -static PXASSPDef pxa27x_ssp[] = { - { 0x41000000, PXA2XX_PIC_SSP }, - { 0x41700000, PXA27X_PIC_SSP2 }, - { 0x41900000, PXA2XX_PIC_SSP3 }, - { 0, 0 } -}; - -#define PMCR 0x00 /* Power Manager Control register */ -#define PSSR 0x04 /* Power Manager Sleep Status register */ -#define PSPR 0x08 /* Power Manager Scratch-Pad register */ -#define PWER 0x0c /* Power Manager Wake-Up Enable register */ -#define PRER 0x10 /* Power Manager Rising-Edge Detect Enable register */ -#define PFER 0x14 /* Power Manager Falling-Edge Detect Enable register */ -#define PEDR 0x18 /* Power Manager Edge-Detect Status register */ -#define PCFR 0x1c /* Power Manager General Configuration register */ -#define PGSR0 0x20 /* Power Manager GPIO Sleep-State register 0 */ -#define PGSR1 0x24 /* Power Manager GPIO Sleep-State register 1 */ -#define PGSR2 0x28 /* Power Manager GPIO Sleep-State register 2 */ -#define PGSR3 0x2c /* Power Manager GPIO Sleep-State register 3 */ -#define RCSR 0x30 /* Reset Controller Status register */ -#define PSLR 0x34 /* Power Manager Sleep Configuration register */ -#define PTSR 0x38 /* Power Manager Standby Configuration register */ -#define PVCR 0x40 /* Power Manager Voltage Change Control register */ -#define PUCR 0x4c /* Power Manager USIM Card Control/Status register */ -#define PKWR 0x50 /* Power Manager Keyboard Wake-Up Enable register */ -#define PKSR 0x54 /* Power Manager Keyboard Level-Detect Status */ -#define PCMD0 0x80 /* Power Manager I2C Command register File 0 */ -#define PCMD31 0xfc /* Power Manager I2C Command register File 31 */ - -static uint64_t pxa2xx_pm_read(void *opaque, hwaddr addr, - unsigned size) -{ - PXA2xxState *s = (PXA2xxState *) opaque; - - switch (addr) { - case PMCR ... PCMD31: - if (addr & 3) - goto fail; - - return s->pm_regs[addr >> 2]; - default: - fail: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } - return 0; -} - -static void pxa2xx_pm_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - PXA2xxState *s = (PXA2xxState *) opaque; - - switch (addr) { - case PMCR: - /* Clear the write-one-to-clear bits... */ - s->pm_regs[addr >> 2] &= ~(value & 0x2a); - /* ...and set the plain r/w bits */ - s->pm_regs[addr >> 2] &= ~0x15; - s->pm_regs[addr >> 2] |= value & 0x15; - break; - - case PSSR: /* Read-clean registers */ - case RCSR: - case PKSR: - s->pm_regs[addr >> 2] &= ~value; - break; - - default: /* Read-write registers */ - if (!(addr & 3)) { - s->pm_regs[addr >> 2] = value; - break; - } - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } -} - -static const MemoryRegionOps pxa2xx_pm_ops = { - .read = pxa2xx_pm_read, - .write = pxa2xx_pm_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static const VMStateDescription vmstate_pxa2xx_pm = { - .name = "pxa2xx_pm", - .version_id = 0, - .minimum_version_id = 0, - .fields = (const VMStateField[]) { - VMSTATE_UINT32_ARRAY(pm_regs, PXA2xxState, 0x40), - VMSTATE_END_OF_LIST() - } -}; - -#define CCCR 0x00 /* Core Clock Configuration register */ -#define CKEN 0x04 /* Clock Enable register */ -#define OSCC 0x08 /* Oscillator Configuration register */ -#define CCSR 0x0c /* Core Clock Status register */ - -static uint64_t pxa2xx_cm_read(void *opaque, hwaddr addr, - unsigned size) -{ - PXA2xxState *s = (PXA2xxState *) opaque; - - switch (addr) { - case CCCR: - case CKEN: - case OSCC: - return s->cm_regs[addr >> 2]; - - case CCSR: - return s->cm_regs[CCCR >> 2] | (3 << 28); - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } - return 0; -} - -static void pxa2xx_cm_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - PXA2xxState *s = (PXA2xxState *) opaque; - - switch (addr) { - case CCCR: - case CKEN: - s->cm_regs[addr >> 2] = value; - break; - - case OSCC: - s->cm_regs[addr >> 2] &= ~0x6c; - s->cm_regs[addr >> 2] |= value & 0x6e; - if ((value >> 1) & 1) /* OON */ - s->cm_regs[addr >> 2] |= 1 << 0; /* Oscillator is now stable */ - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } -} - -static const MemoryRegionOps pxa2xx_cm_ops = { - .read = pxa2xx_cm_read, - .write = pxa2xx_cm_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static const VMStateDescription vmstate_pxa2xx_cm = { - .name = "pxa2xx_cm", - .version_id = 0, - .minimum_version_id = 0, - .fields = (const VMStateField[]) { - VMSTATE_UINT32_ARRAY(cm_regs, PXA2xxState, 4), - VMSTATE_UINT32(clkcfg, PXA2xxState), - VMSTATE_UINT32(pmnc, PXA2xxState), - VMSTATE_END_OF_LIST() - } -}; - -static uint64_t pxa2xx_clkcfg_read(CPUARMState *env, const ARMCPRegInfo *ri) -{ - PXA2xxState *s = (PXA2xxState *)ri->opaque; - return s->clkcfg; -} - -static void pxa2xx_clkcfg_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - PXA2xxState *s = (PXA2xxState *)ri->opaque; - s->clkcfg = value & 0xf; - if (value & 2) { - printf("%s: CPU frequency change attempt\n", __func__); - } -} - -static void pxa2xx_pwrmode_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - PXA2xxState *s = (PXA2xxState *)ri->opaque; - static const char *pwrmode[8] = { - "Normal", "Idle", "Deep-idle", "Standby", - "Sleep", "reserved (!)", "reserved (!)", "Deep-sleep", - }; - - if (value & 8) { - printf("%s: CPU voltage change attempt\n", __func__); - } - switch (value & 7) { - case 0: - /* Do nothing */ - break; - - case 1: - /* Idle */ - if (!(s->cm_regs[CCCR >> 2] & (1U << 31))) { /* CPDIS */ - cpu_interrupt(CPU(s->cpu), CPU_INTERRUPT_HALT); - break; - } - /* Fall through. */ - - case 2: - /* Deep-Idle */ - cpu_interrupt(CPU(s->cpu), CPU_INTERRUPT_HALT); - s->pm_regs[RCSR >> 2] |= 0x8; /* Set GPR */ - goto message; - - case 3: - s->cpu->env.uncached_cpsr = ARM_CPU_MODE_SVC; - s->cpu->env.daif = PSTATE_A | PSTATE_F | PSTATE_I; - s->cpu->env.cp15.sctlr_ns = 0; - s->cpu->env.cp15.cpacr_el1 = 0; - s->cpu->env.cp15.ttbr0_el[1] = 0; - s->cpu->env.cp15.dacr_ns = 0; - s->pm_regs[PSSR >> 2] |= 0x8; /* Set STS */ - s->pm_regs[RCSR >> 2] |= 0x8; /* Set GPR */ - - /* - * The scratch-pad register is almost universally used - * for storing the return address on suspend. For the - * lack of a resuming bootloader, perform a jump - * directly to that address. - */ - memset(s->cpu->env.regs, 0, 4 * 15); - s->cpu->env.regs[15] = s->pm_regs[PSPR >> 2]; - -#if 0 - buffer = 0xe59ff000; /* ldr pc, [pc, #0] */ - cpu_physical_memory_write(0, &buffer, 4); - buffer = s->pm_regs[PSPR >> 2]; - cpu_physical_memory_write(8, &buffer, 4); -#endif - - /* Suspend */ - cpu_interrupt(current_cpu, CPU_INTERRUPT_HALT); - - goto message; - - default: - message: - printf("%s: machine entered %s mode\n", __func__, - pwrmode[value & 7]); - } -} - -static uint64_t pxa2xx_cppmnc_read(CPUARMState *env, const ARMCPRegInfo *ri) -{ - PXA2xxState *s = (PXA2xxState *)ri->opaque; - return s->pmnc; -} - -static void pxa2xx_cppmnc_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - PXA2xxState *s = (PXA2xxState *)ri->opaque; - s->pmnc = value; -} - -static uint64_t pxa2xx_cpccnt_read(CPUARMState *env, const ARMCPRegInfo *ri) -{ - PXA2xxState *s = (PXA2xxState *)ri->opaque; - if (s->pmnc & 1) { - return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - } else { - return 0; - } -} - -static const ARMCPRegInfo pxa_cp_reginfo[] = { - /* cp14 crm==1: perf registers */ - { .name = "CPPMNC", .cp = 14, .crn = 0, .crm = 1, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_IO, - .readfn = pxa2xx_cppmnc_read, .writefn = pxa2xx_cppmnc_write }, - { .name = "CPCCNT", .cp = 14, .crn = 1, .crm = 1, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_IO, - .readfn = pxa2xx_cpccnt_read, .writefn = arm_cp_write_ignore }, - { .name = "CPINTEN", .cp = 14, .crn = 4, .crm = 1, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPFLAG", .cp = 14, .crn = 5, .crm = 1, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPEVTSEL", .cp = 14, .crn = 8, .crm = 1, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - /* cp14 crm==2: performance count registers */ - { .name = "CPPMN0", .cp = 14, .crn = 0, .crm = 2, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPPMN1", .cp = 14, .crn = 1, .crm = 2, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPPMN2", .cp = 14, .crn = 2, .crm = 2, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPPMN3", .cp = 14, .crn = 2, .crm = 3, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - /* cp14 crn==6: CLKCFG */ - { .name = "CLKCFG", .cp = 14, .crn = 6, .crm = 0, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_IO, - .readfn = pxa2xx_clkcfg_read, .writefn = pxa2xx_clkcfg_write }, - /* cp14 crn==7: PWRMODE */ - { .name = "PWRMODE", .cp = 14, .crn = 7, .crm = 0, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_IO, - .readfn = arm_cp_read_zero, .writefn = pxa2xx_pwrmode_write }, -}; - -static void pxa2xx_setup_cp14(PXA2xxState *s) -{ - define_arm_cp_regs_with_opaque(s->cpu, pxa_cp_reginfo, s); -} - -#define MDCNFG 0x00 /* SDRAM Configuration register */ -#define MDREFR 0x04 /* SDRAM Refresh Control register */ -#define MSC0 0x08 /* Static Memory Control register 0 */ -#define MSC1 0x0c /* Static Memory Control register 1 */ -#define MSC2 0x10 /* Static Memory Control register 2 */ -#define MECR 0x14 /* Expansion Memory Bus Config register */ -#define SXCNFG 0x1c /* Synchronous Static Memory Config register */ -#define MCMEM0 0x28 /* PC Card Memory Socket 0 Timing register */ -#define MCMEM1 0x2c /* PC Card Memory Socket 1 Timing register */ -#define MCATT0 0x30 /* PC Card Attribute Socket 0 register */ -#define MCATT1 0x34 /* PC Card Attribute Socket 1 register */ -#define MCIO0 0x38 /* PC Card I/O Socket 0 Timing register */ -#define MCIO1 0x3c /* PC Card I/O Socket 1 Timing register */ -#define MDMRS 0x40 /* SDRAM Mode Register Set Config register */ -#define BOOT_DEF 0x44 /* Boot-time Default Configuration register */ -#define ARB_CNTL 0x48 /* Arbiter Control register */ -#define BSCNTR0 0x4c /* Memory Buffer Strength Control register 0 */ -#define BSCNTR1 0x50 /* Memory Buffer Strength Control register 1 */ -#define LCDBSCNTR 0x54 /* LCD Buffer Strength Control register */ -#define MDMRSLP 0x58 /* Low Power SDRAM Mode Set Config register */ -#define BSCNTR2 0x5c /* Memory Buffer Strength Control register 2 */ -#define BSCNTR3 0x60 /* Memory Buffer Strength Control register 3 */ -#define SA1110 0x64 /* SA-1110 Memory Compatibility register */ - -static uint64_t pxa2xx_mm_read(void *opaque, hwaddr addr, - unsigned size) -{ - PXA2xxState *s = (PXA2xxState *) opaque; - - switch (addr) { - case MDCNFG ... SA1110: - if ((addr & 3) == 0) - return s->mm_regs[addr >> 2]; - /* fall through */ - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } - return 0; -} - -static void pxa2xx_mm_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - PXA2xxState *s = (PXA2xxState *) opaque; - - switch (addr) { - case MDCNFG ... SA1110: - if ((addr & 3) == 0) { - s->mm_regs[addr >> 2] = value; - break; - } - /* fallthrough */ - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } -} - -static const MemoryRegionOps pxa2xx_mm_ops = { - .read = pxa2xx_mm_read, - .write = pxa2xx_mm_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static const VMStateDescription vmstate_pxa2xx_mm = { - .name = "pxa2xx_mm", - .version_id = 0, - .minimum_version_id = 0, - .fields = (const VMStateField[]) { - VMSTATE_UINT32_ARRAY(mm_regs, PXA2xxState, 0x1a), - VMSTATE_END_OF_LIST() - } -}; - -#define TYPE_PXA2XX_SSP "pxa2xx-ssp" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxSSPState, PXA2XX_SSP) - -/* Synchronous Serial Ports */ -struct PXA2xxSSPState { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - MemoryRegion iomem; - qemu_irq irq; - uint32_t enable; - SSIBus *bus; - - uint32_t sscr[2]; - uint32_t sspsp; - uint32_t ssto; - uint32_t ssitr; - uint32_t sssr; - uint8_t sstsa; - uint8_t ssrsa; - uint8_t ssacd; - - uint32_t rx_fifo[16]; - uint32_t rx_level; - uint32_t rx_start; -}; - -static bool pxa2xx_ssp_vmstate_validate(void *opaque, int version_id) -{ - PXA2xxSSPState *s = opaque; - - return s->rx_start < sizeof(s->rx_fifo); -} - -static const VMStateDescription vmstate_pxa2xx_ssp = { - .name = "pxa2xx-ssp", - .version_id = 1, - .minimum_version_id = 1, - .fields = (const VMStateField[]) { - VMSTATE_UINT32(enable, PXA2xxSSPState), - VMSTATE_UINT32_ARRAY(sscr, PXA2xxSSPState, 2), - VMSTATE_UINT32(sspsp, PXA2xxSSPState), - VMSTATE_UINT32(ssto, PXA2xxSSPState), - VMSTATE_UINT32(ssitr, PXA2xxSSPState), - VMSTATE_UINT32(sssr, PXA2xxSSPState), - VMSTATE_UINT8(sstsa, PXA2xxSSPState), - VMSTATE_UINT8(ssrsa, PXA2xxSSPState), - VMSTATE_UINT8(ssacd, PXA2xxSSPState), - VMSTATE_UINT32(rx_level, PXA2xxSSPState), - VMSTATE_UINT32(rx_start, PXA2xxSSPState), - VMSTATE_VALIDATE("fifo is 16 bytes", pxa2xx_ssp_vmstate_validate), - VMSTATE_UINT32_ARRAY(rx_fifo, PXA2xxSSPState, 16), - VMSTATE_END_OF_LIST() - } -}; - -#define SSCR0 0x00 /* SSP Control register 0 */ -#define SSCR1 0x04 /* SSP Control register 1 */ -#define SSSR 0x08 /* SSP Status register */ -#define SSITR 0x0c /* SSP Interrupt Test register */ -#define SSDR 0x10 /* SSP Data register */ -#define SSTO 0x28 /* SSP Time-Out register */ -#define SSPSP 0x2c /* SSP Programmable Serial Protocol register */ -#define SSTSA 0x30 /* SSP TX Time Slot Active register */ -#define SSRSA 0x34 /* SSP RX Time Slot Active register */ -#define SSTSS 0x38 /* SSP Time Slot Status register */ -#define SSACD 0x3c /* SSP Audio Clock Divider register */ - -/* Bitfields for above registers */ -#define SSCR0_SPI(x) (((x) & 0x30) == 0x00) -#define SSCR0_SSP(x) (((x) & 0x30) == 0x10) -#define SSCR0_UWIRE(x) (((x) & 0x30) == 0x20) -#define SSCR0_PSP(x) (((x) & 0x30) == 0x30) -#define SSCR0_SSE (1 << 7) -#define SSCR0_RIM (1 << 22) -#define SSCR0_TIM (1 << 23) -#define SSCR0_MOD (1U << 31) -#define SSCR0_DSS(x) (((((x) >> 16) & 0x10) | ((x) & 0xf)) + 1) -#define SSCR1_RIE (1 << 0) -#define SSCR1_TIE (1 << 1) -#define SSCR1_LBM (1 << 2) -#define SSCR1_MWDS (1 << 5) -#define SSCR1_TFT(x) ((((x) >> 6) & 0xf) + 1) -#define SSCR1_RFT(x) ((((x) >> 10) & 0xf) + 1) -#define SSCR1_EFWR (1 << 14) -#define SSCR1_PINTE (1 << 18) -#define SSCR1_TINTE (1 << 19) -#define SSCR1_RSRE (1 << 20) -#define SSCR1_TSRE (1 << 21) -#define SSCR1_EBCEI (1 << 29) -#define SSITR_INT (7 << 5) -#define SSSR_TNF (1 << 2) -#define SSSR_RNE (1 << 3) -#define SSSR_TFS (1 << 5) -#define SSSR_RFS (1 << 6) -#define SSSR_ROR (1 << 7) -#define SSSR_PINT (1 << 18) -#define SSSR_TINT (1 << 19) -#define SSSR_EOC (1 << 20) -#define SSSR_TUR (1 << 21) -#define SSSR_BCE (1 << 23) -#define SSSR_RW 0x00bc0080 - -static void pxa2xx_ssp_int_update(PXA2xxSSPState *s) -{ - int level = 0; - - level |= s->ssitr & SSITR_INT; - level |= (s->sssr & SSSR_BCE) && (s->sscr[1] & SSCR1_EBCEI); - level |= (s->sssr & SSSR_TUR) && !(s->sscr[0] & SSCR0_TIM); - level |= (s->sssr & SSSR_EOC) && (s->sssr & (SSSR_TINT | SSSR_PINT)); - level |= (s->sssr & SSSR_TINT) && (s->sscr[1] & SSCR1_TINTE); - level |= (s->sssr & SSSR_PINT) && (s->sscr[1] & SSCR1_PINTE); - level |= (s->sssr & SSSR_ROR) && !(s->sscr[0] & SSCR0_RIM); - level |= (s->sssr & SSSR_RFS) && (s->sscr[1] & SSCR1_RIE); - level |= (s->sssr & SSSR_TFS) && (s->sscr[1] & SSCR1_TIE); - qemu_set_irq(s->irq, !!level); -} - -static void pxa2xx_ssp_fifo_update(PXA2xxSSPState *s) -{ - s->sssr &= ~(0xf << 12); /* Clear RFL */ - s->sssr &= ~(0xf << 8); /* Clear TFL */ - s->sssr &= ~SSSR_TFS; - s->sssr &= ~SSSR_TNF; - if (s->enable) { - s->sssr |= ((s->rx_level - 1) & 0xf) << 12; - if (s->rx_level >= SSCR1_RFT(s->sscr[1])) - s->sssr |= SSSR_RFS; - else - s->sssr &= ~SSSR_RFS; - if (s->rx_level) - s->sssr |= SSSR_RNE; - else - s->sssr &= ~SSSR_RNE; - /* TX FIFO is never filled, so it is always in underrun - condition if SSP is enabled */ - s->sssr |= SSSR_TFS; - s->sssr |= SSSR_TNF; - } - - pxa2xx_ssp_int_update(s); -} - -static uint64_t pxa2xx_ssp_read(void *opaque, hwaddr addr, - unsigned size) -{ - PXA2xxSSPState *s = (PXA2xxSSPState *) opaque; - uint32_t retval; - - switch (addr) { - case SSCR0: - return s->sscr[0]; - case SSCR1: - return s->sscr[1]; - case SSPSP: - return s->sspsp; - case SSTO: - return s->ssto; - case SSITR: - return s->ssitr; - case SSSR: - return s->sssr | s->ssitr; - case SSDR: - if (!s->enable) - return 0xffffffff; - if (s->rx_level < 1) { - printf("%s: SSP Rx Underrun\n", __func__); - return 0xffffffff; - } - s->rx_level --; - retval = s->rx_fifo[s->rx_start ++]; - s->rx_start &= 0xf; - pxa2xx_ssp_fifo_update(s); - return retval; - case SSTSA: - return s->sstsa; - case SSRSA: - return s->ssrsa; - case SSTSS: - return 0; - case SSACD: - return s->ssacd; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } - return 0; -} - -static void pxa2xx_ssp_write(void *opaque, hwaddr addr, - uint64_t value64, unsigned size) -{ - PXA2xxSSPState *s = (PXA2xxSSPState *) opaque; - uint32_t value = value64; - - switch (addr) { - case SSCR0: - s->sscr[0] = value & 0xc7ffffff; - s->enable = value & SSCR0_SSE; - if (value & SSCR0_MOD) - printf("%s: Attempt to use network mode\n", __func__); - if (s->enable && SSCR0_DSS(value) < 4) - printf("%s: Wrong data size: %u bits\n", __func__, - SSCR0_DSS(value)); - if (!(value & SSCR0_SSE)) { - s->sssr = 0; - s->ssitr = 0; - s->rx_level = 0; - } - pxa2xx_ssp_fifo_update(s); - break; - - case SSCR1: - s->sscr[1] = value; - if (value & (SSCR1_LBM | SSCR1_EFWR)) - printf("%s: Attempt to use SSP test mode\n", __func__); - pxa2xx_ssp_fifo_update(s); - break; - - case SSPSP: - s->sspsp = value; - break; - - case SSTO: - s->ssto = value; - break; - - case SSITR: - s->ssitr = value & SSITR_INT; - pxa2xx_ssp_int_update(s); - break; - - case SSSR: - s->sssr &= ~(value & SSSR_RW); - pxa2xx_ssp_int_update(s); - break; - - case SSDR: - if (SSCR0_UWIRE(s->sscr[0])) { - if (s->sscr[1] & SSCR1_MWDS) - value &= 0xffff; - else - value &= 0xff; - } else - /* Note how 32bits overflow does no harm here */ - value &= (1 << SSCR0_DSS(s->sscr[0])) - 1; - - /* Data goes from here to the Tx FIFO and is shifted out from - * there directly to the slave, no need to buffer it. - */ - if (s->enable) { - uint32_t readval; - readval = ssi_transfer(s->bus, value); - if (s->rx_level < 0x10) { - s->rx_fifo[(s->rx_start + s->rx_level ++) & 0xf] = readval; - } else { - s->sssr |= SSSR_ROR; - } - } - pxa2xx_ssp_fifo_update(s); - break; - - case SSTSA: - s->sstsa = value; - break; - - case SSRSA: - s->ssrsa = value; - break; - - case SSACD: - s->ssacd = value; - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } -} - -static const MemoryRegionOps pxa2xx_ssp_ops = { - .read = pxa2xx_ssp_read, - .write = pxa2xx_ssp_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void pxa2xx_ssp_reset(DeviceState *d) -{ - PXA2xxSSPState *s = PXA2XX_SSP(d); - - s->enable = 0; - s->sscr[0] = s->sscr[1] = 0; - s->sspsp = 0; - s->ssto = 0; - s->ssitr = 0; - s->sssr = 0; - s->sstsa = 0; - s->ssrsa = 0; - s->ssacd = 0; - s->rx_start = s->rx_level = 0; -} - -static void pxa2xx_ssp_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - PXA2xxSSPState *s = PXA2XX_SSP(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - sysbus_init_irq(sbd, &s->irq); - - memory_region_init_io(&s->iomem, obj, &pxa2xx_ssp_ops, s, - "pxa2xx-ssp", 0x1000); - sysbus_init_mmio(sbd, &s->iomem); - - s->bus = ssi_create_bus(dev, "ssi"); -} - -/* Real-Time Clock */ -#define RCNR 0x00 /* RTC Counter register */ -#define RTAR 0x04 /* RTC Alarm register */ -#define RTSR 0x08 /* RTC Status register */ -#define RTTR 0x0c /* RTC Timer Trim register */ -#define RDCR 0x10 /* RTC Day Counter register */ -#define RYCR 0x14 /* RTC Year Counter register */ -#define RDAR1 0x18 /* RTC Wristwatch Day Alarm register 1 */ -#define RYAR1 0x1c /* RTC Wristwatch Year Alarm register 1 */ -#define RDAR2 0x20 /* RTC Wristwatch Day Alarm register 2 */ -#define RYAR2 0x24 /* RTC Wristwatch Year Alarm register 2 */ -#define SWCR 0x28 /* RTC Stopwatch Counter register */ -#define SWAR1 0x2c /* RTC Stopwatch Alarm register 1 */ -#define SWAR2 0x30 /* RTC Stopwatch Alarm register 2 */ -#define RTCPICR 0x34 /* RTC Periodic Interrupt Counter register */ -#define PIAR 0x38 /* RTC Periodic Interrupt Alarm register */ - -#define TYPE_PXA2XX_RTC "pxa2xx_rtc" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxRTCState, PXA2XX_RTC) - -struct PXA2xxRTCState { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - MemoryRegion iomem; - uint32_t rttr; - uint32_t rtsr; - uint32_t rtar; - uint32_t rdar1; - uint32_t rdar2; - uint32_t ryar1; - uint32_t ryar2; - uint32_t swar1; - uint32_t swar2; - uint32_t piar; - uint32_t last_rcnr; - uint32_t last_rdcr; - uint32_t last_rycr; - uint32_t last_swcr; - uint32_t last_rtcpicr; - int64_t last_hz; - int64_t last_sw; - int64_t last_pi; - QEMUTimer *rtc_hz; - QEMUTimer *rtc_rdal1; - QEMUTimer *rtc_rdal2; - QEMUTimer *rtc_swal1; - QEMUTimer *rtc_swal2; - QEMUTimer *rtc_pi; - qemu_irq rtc_irq; -}; - -static inline void pxa2xx_rtc_int_update(PXA2xxRTCState *s) -{ - qemu_set_irq(s->rtc_irq, !!(s->rtsr & 0x2553)); -} - -static void pxa2xx_rtc_hzupdate(PXA2xxRTCState *s) -{ - int64_t rt = qemu_clock_get_ms(rtc_clock); - s->last_rcnr += ((rt - s->last_hz) << 15) / - (1000 * ((s->rttr & 0xffff) + 1)); - s->last_rdcr += ((rt - s->last_hz) << 15) / - (1000 * ((s->rttr & 0xffff) + 1)); - s->last_hz = rt; -} - -static void pxa2xx_rtc_swupdate(PXA2xxRTCState *s) -{ - int64_t rt = qemu_clock_get_ms(rtc_clock); - if (s->rtsr & (1 << 12)) - s->last_swcr += (rt - s->last_sw) / 10; - s->last_sw = rt; -} - -static void pxa2xx_rtc_piupdate(PXA2xxRTCState *s) -{ - int64_t rt = qemu_clock_get_ms(rtc_clock); - if (s->rtsr & (1 << 15)) - s->last_swcr += rt - s->last_pi; - s->last_pi = rt; -} - -static inline void pxa2xx_rtc_alarm_update(PXA2xxRTCState *s, - uint32_t rtsr) -{ - if ((rtsr & (1 << 2)) && !(rtsr & (1 << 0))) - timer_mod(s->rtc_hz, s->last_hz + - (((s->rtar - s->last_rcnr) * 1000 * - ((s->rttr & 0xffff) + 1)) >> 15)); - else - timer_del(s->rtc_hz); - - if ((rtsr & (1 << 5)) && !(rtsr & (1 << 4))) - timer_mod(s->rtc_rdal1, s->last_hz + - (((s->rdar1 - s->last_rdcr) * 1000 * - ((s->rttr & 0xffff) + 1)) >> 15)); /* TODO: fixup */ - else - timer_del(s->rtc_rdal1); - - if ((rtsr & (1 << 7)) && !(rtsr & (1 << 6))) - timer_mod(s->rtc_rdal2, s->last_hz + - (((s->rdar2 - s->last_rdcr) * 1000 * - ((s->rttr & 0xffff) + 1)) >> 15)); /* TODO: fixup */ - else - timer_del(s->rtc_rdal2); - - if ((rtsr & 0x1200) == 0x1200 && !(rtsr & (1 << 8))) - timer_mod(s->rtc_swal1, s->last_sw + - (s->swar1 - s->last_swcr) * 10); /* TODO: fixup */ - else - timer_del(s->rtc_swal1); - - if ((rtsr & 0x1800) == 0x1800 && !(rtsr & (1 << 10))) - timer_mod(s->rtc_swal2, s->last_sw + - (s->swar2 - s->last_swcr) * 10); /* TODO: fixup */ - else - timer_del(s->rtc_swal2); - - if ((rtsr & 0xc000) == 0xc000 && !(rtsr & (1 << 13))) - timer_mod(s->rtc_pi, s->last_pi + - (s->piar & 0xffff) - s->last_rtcpicr); - else - timer_del(s->rtc_pi); -} - -static inline void pxa2xx_rtc_hz_tick(void *opaque) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - s->rtsr |= (1 << 0); - pxa2xx_rtc_alarm_update(s, s->rtsr); - pxa2xx_rtc_int_update(s); -} - -static inline void pxa2xx_rtc_rdal1_tick(void *opaque) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - s->rtsr |= (1 << 4); - pxa2xx_rtc_alarm_update(s, s->rtsr); - pxa2xx_rtc_int_update(s); -} - -static inline void pxa2xx_rtc_rdal2_tick(void *opaque) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - s->rtsr |= (1 << 6); - pxa2xx_rtc_alarm_update(s, s->rtsr); - pxa2xx_rtc_int_update(s); -} - -static inline void pxa2xx_rtc_swal1_tick(void *opaque) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - s->rtsr |= (1 << 8); - pxa2xx_rtc_alarm_update(s, s->rtsr); - pxa2xx_rtc_int_update(s); -} - -static inline void pxa2xx_rtc_swal2_tick(void *opaque) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - s->rtsr |= (1 << 10); - pxa2xx_rtc_alarm_update(s, s->rtsr); - pxa2xx_rtc_int_update(s); -} - -static inline void pxa2xx_rtc_pi_tick(void *opaque) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - s->rtsr |= (1 << 13); - pxa2xx_rtc_piupdate(s); - s->last_rtcpicr = 0; - pxa2xx_rtc_alarm_update(s, s->rtsr); - pxa2xx_rtc_int_update(s); -} - -static uint64_t pxa2xx_rtc_read(void *opaque, hwaddr addr, - unsigned size) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - - switch (addr) { - case RTTR: - return s->rttr; - case RTSR: - return s->rtsr; - case RTAR: - return s->rtar; - case RDAR1: - return s->rdar1; - case RDAR2: - return s->rdar2; - case RYAR1: - return s->ryar1; - case RYAR2: - return s->ryar2; - case SWAR1: - return s->swar1; - case SWAR2: - return s->swar2; - case PIAR: - return s->piar; - case RCNR: - return s->last_rcnr + - ((qemu_clock_get_ms(rtc_clock) - s->last_hz) << 15) / - (1000 * ((s->rttr & 0xffff) + 1)); - case RDCR: - return s->last_rdcr + - ((qemu_clock_get_ms(rtc_clock) - s->last_hz) << 15) / - (1000 * ((s->rttr & 0xffff) + 1)); - case RYCR: - return s->last_rycr; - case SWCR: - if (s->rtsr & (1 << 12)) - return s->last_swcr + - (qemu_clock_get_ms(rtc_clock) - s->last_sw) / 10; - else - return s->last_swcr; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } - return 0; -} - -static void pxa2xx_rtc_write(void *opaque, hwaddr addr, - uint64_t value64, unsigned size) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - uint32_t value = value64; - - switch (addr) { - case RTTR: - if (!(s->rttr & (1U << 31))) { - pxa2xx_rtc_hzupdate(s); - s->rttr = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - } - break; - - case RTSR: - if ((s->rtsr ^ value) & (1 << 15)) - pxa2xx_rtc_piupdate(s); - - if ((s->rtsr ^ value) & (1 << 12)) - pxa2xx_rtc_swupdate(s); - - if (((s->rtsr ^ value) & 0x4aac) | (value & ~0xdaac)) - pxa2xx_rtc_alarm_update(s, value); - - s->rtsr = (value & 0xdaac) | (s->rtsr & ~(value & ~0xdaac)); - pxa2xx_rtc_int_update(s); - break; - - case RTAR: - s->rtar = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case RDAR1: - s->rdar1 = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case RDAR2: - s->rdar2 = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case RYAR1: - s->ryar1 = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case RYAR2: - s->ryar2 = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case SWAR1: - pxa2xx_rtc_swupdate(s); - s->swar1 = value; - s->last_swcr = 0; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case SWAR2: - s->swar2 = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case PIAR: - s->piar = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case RCNR: - pxa2xx_rtc_hzupdate(s); - s->last_rcnr = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case RDCR: - pxa2xx_rtc_hzupdate(s); - s->last_rdcr = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case RYCR: - s->last_rycr = value; - break; - - case SWCR: - pxa2xx_rtc_swupdate(s); - s->last_swcr = value; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - case RTCPICR: - pxa2xx_rtc_piupdate(s); - s->last_rtcpicr = value & 0xffff; - pxa2xx_rtc_alarm_update(s, s->rtsr); - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - } -} - -static const MemoryRegionOps pxa2xx_rtc_ops = { - .read = pxa2xx_rtc_read, - .write = pxa2xx_rtc_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void pxa2xx_rtc_init(Object *obj) -{ - PXA2xxRTCState *s = PXA2XX_RTC(obj); - SysBusDevice *dev = SYS_BUS_DEVICE(obj); - struct tm tm; - int wom; - - s->rttr = 0x7fff; - s->rtsr = 0; - - qemu_get_timedate(&tm, 0); - wom = ((tm.tm_mday - 1) / 7) + 1; - - s->last_rcnr = (uint32_t) mktimegm(&tm); - s->last_rdcr = (wom << 20) | ((tm.tm_wday + 1) << 17) | - (tm.tm_hour << 12) | (tm.tm_min << 6) | tm.tm_sec; - s->last_rycr = ((tm.tm_year + 1900) << 9) | - ((tm.tm_mon + 1) << 5) | tm.tm_mday; - s->last_swcr = (tm.tm_hour << 19) | - (tm.tm_min << 13) | (tm.tm_sec << 7); - s->last_rtcpicr = 0; - s->last_hz = s->last_sw = s->last_pi = qemu_clock_get_ms(rtc_clock); - - sysbus_init_irq(dev, &s->rtc_irq); - - memory_region_init_io(&s->iomem, obj, &pxa2xx_rtc_ops, s, - "pxa2xx-rtc", 0x10000); - sysbus_init_mmio(dev, &s->iomem); -} - -static void pxa2xx_rtc_realize(DeviceState *dev, Error **errp) -{ - PXA2xxRTCState *s = PXA2XX_RTC(dev); - s->rtc_hz = timer_new_ms(rtc_clock, pxa2xx_rtc_hz_tick, s); - s->rtc_rdal1 = timer_new_ms(rtc_clock, pxa2xx_rtc_rdal1_tick, s); - s->rtc_rdal2 = timer_new_ms(rtc_clock, pxa2xx_rtc_rdal2_tick, s); - s->rtc_swal1 = timer_new_ms(rtc_clock, pxa2xx_rtc_swal1_tick, s); - s->rtc_swal2 = timer_new_ms(rtc_clock, pxa2xx_rtc_swal2_tick, s); - s->rtc_pi = timer_new_ms(rtc_clock, pxa2xx_rtc_pi_tick, s); -} - -static int pxa2xx_rtc_pre_save(void *opaque) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - - pxa2xx_rtc_hzupdate(s); - pxa2xx_rtc_piupdate(s); - pxa2xx_rtc_swupdate(s); - - return 0; -} - -static int pxa2xx_rtc_post_load(void *opaque, int version_id) -{ - PXA2xxRTCState *s = (PXA2xxRTCState *) opaque; - - pxa2xx_rtc_alarm_update(s, s->rtsr); - - return 0; -} - -static const VMStateDescription vmstate_pxa2xx_rtc_regs = { - .name = "pxa2xx_rtc", - .version_id = 0, - .minimum_version_id = 0, - .pre_save = pxa2xx_rtc_pre_save, - .post_load = pxa2xx_rtc_post_load, - .fields = (const VMStateField[]) { - VMSTATE_UINT32(rttr, PXA2xxRTCState), - VMSTATE_UINT32(rtsr, PXA2xxRTCState), - VMSTATE_UINT32(rtar, PXA2xxRTCState), - VMSTATE_UINT32(rdar1, PXA2xxRTCState), - VMSTATE_UINT32(rdar2, PXA2xxRTCState), - VMSTATE_UINT32(ryar1, PXA2xxRTCState), - VMSTATE_UINT32(ryar2, PXA2xxRTCState), - VMSTATE_UINT32(swar1, PXA2xxRTCState), - VMSTATE_UINT32(swar2, PXA2xxRTCState), - VMSTATE_UINT32(piar, PXA2xxRTCState), - VMSTATE_UINT32(last_rcnr, PXA2xxRTCState), - VMSTATE_UINT32(last_rdcr, PXA2xxRTCState), - VMSTATE_UINT32(last_rycr, PXA2xxRTCState), - VMSTATE_UINT32(last_swcr, PXA2xxRTCState), - VMSTATE_UINT32(last_rtcpicr, PXA2xxRTCState), - VMSTATE_INT64(last_hz, PXA2xxRTCState), - VMSTATE_INT64(last_sw, PXA2xxRTCState), - VMSTATE_INT64(last_pi, PXA2xxRTCState), - VMSTATE_END_OF_LIST(), - }, -}; - -static void pxa2xx_rtc_sysbus_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->desc = "PXA2xx RTC Controller"; - dc->vmsd = &vmstate_pxa2xx_rtc_regs; - dc->realize = pxa2xx_rtc_realize; -} - -static const TypeInfo pxa2xx_rtc_sysbus_info = { - .name = TYPE_PXA2XX_RTC, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PXA2xxRTCState), - .instance_init = pxa2xx_rtc_init, - .class_init = pxa2xx_rtc_sysbus_class_init, -}; - -/* I2C Interface */ - -#define TYPE_PXA2XX_I2C_SLAVE "pxa2xx-i2c-slave" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxI2CSlaveState, PXA2XX_I2C_SLAVE) - -struct PXA2xxI2CSlaveState { - I2CSlave parent_obj; - - PXA2xxI2CState *host; -}; - -struct PXA2xxI2CState { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - MemoryRegion iomem; - PXA2xxI2CSlaveState *slave; - I2CBus *bus; - qemu_irq irq; - uint32_t offset; - uint32_t region_size; - - uint16_t control; - uint16_t status; - uint8_t ibmr; - uint8_t data; -}; - -#define IBMR 0x80 /* I2C Bus Monitor register */ -#define IDBR 0x88 /* I2C Data Buffer register */ -#define ICR 0x90 /* I2C Control register */ -#define ISR 0x98 /* I2C Status register */ -#define ISAR 0xa0 /* I2C Slave Address register */ - -static void pxa2xx_i2c_update(PXA2xxI2CState *s) -{ - uint16_t level = 0; - level |= s->status & s->control & (1 << 10); /* BED */ - level |= (s->status & (1 << 7)) && (s->control & (1 << 9)); /* IRF */ - level |= (s->status & (1 << 6)) && (s->control & (1 << 8)); /* ITE */ - level |= s->status & (1 << 9); /* SAD */ - qemu_set_irq(s->irq, !!level); -} - -/* These are only stubs now. */ -static int pxa2xx_i2c_event(I2CSlave *i2c, enum i2c_event event) -{ - PXA2xxI2CSlaveState *slave = PXA2XX_I2C_SLAVE(i2c); - PXA2xxI2CState *s = slave->host; - - switch (event) { - case I2C_START_SEND: - s->status |= (1 << 9); /* set SAD */ - s->status &= ~(1 << 0); /* clear RWM */ - break; - case I2C_START_RECV: - s->status |= (1 << 9); /* set SAD */ - s->status |= 1 << 0; /* set RWM */ - break; - case I2C_FINISH: - s->status |= (1 << 4); /* set SSD */ - break; - case I2C_NACK: - s->status |= 1 << 1; /* set ACKNAK */ - break; - default: - return -1; - } - pxa2xx_i2c_update(s); - - return 0; -} - -static uint8_t pxa2xx_i2c_rx(I2CSlave *i2c) -{ - PXA2xxI2CSlaveState *slave = PXA2XX_I2C_SLAVE(i2c); - PXA2xxI2CState *s = slave->host; - - if ((s->control & (1 << 14)) || !(s->control & (1 << 6))) { - return 0; - } - - if (s->status & (1 << 0)) { /* RWM */ - s->status |= 1 << 6; /* set ITE */ - } - pxa2xx_i2c_update(s); - - return s->data; -} - -static int pxa2xx_i2c_tx(I2CSlave *i2c, uint8_t data) -{ - PXA2xxI2CSlaveState *slave = PXA2XX_I2C_SLAVE(i2c); - PXA2xxI2CState *s = slave->host; - - if ((s->control & (1 << 14)) || !(s->control & (1 << 6))) { - return 1; - } - - if (!(s->status & (1 << 0))) { /* RWM */ - s->status |= 1 << 7; /* set IRF */ - s->data = data; - } - pxa2xx_i2c_update(s); - - return 1; -} - -static uint64_t pxa2xx_i2c_read(void *opaque, hwaddr addr, - unsigned size) -{ - PXA2xxI2CState *s = (PXA2xxI2CState *) opaque; - I2CSlave *slave; - - addr -= s->offset; - switch (addr) { - case ICR: - return s->control; - case ISR: - return s->status | (i2c_bus_busy(s->bus) << 2); - case ISAR: - slave = I2C_SLAVE(s->slave); - return slave->address; - case IDBR: - return s->data; - case IBMR: - if (s->status & (1 << 2)) - s->ibmr ^= 3; /* Fake SCL and SDA pin changes */ - else - s->ibmr = 0; - return s->ibmr; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } - return 0; -} - -static void pxa2xx_i2c_write(void *opaque, hwaddr addr, - uint64_t value64, unsigned size) -{ - PXA2xxI2CState *s = (PXA2xxI2CState *) opaque; - uint32_t value = value64; - int ack; - - addr -= s->offset; - switch (addr) { - case ICR: - s->control = value & 0xfff7; - if ((value & (1 << 3)) && (value & (1 << 6))) { /* TB and IUE */ - /* TODO: slave mode */ - if (value & (1 << 0)) { /* START condition */ - if (s->data & 1) - s->status |= 1 << 0; /* set RWM */ - else - s->status &= ~(1 << 0); /* clear RWM */ - ack = !i2c_start_transfer(s->bus, s->data >> 1, s->data & 1); - } else { - if (s->status & (1 << 0)) { /* RWM */ - s->data = i2c_recv(s->bus); - if (value & (1 << 2)) /* ACKNAK */ - i2c_nack(s->bus); - ack = 1; - } else - ack = !i2c_send(s->bus, s->data); - } - - if (value & (1 << 1)) /* STOP condition */ - i2c_end_transfer(s->bus); - - if (ack) { - if (value & (1 << 0)) /* START condition */ - s->status |= 1 << 6; /* set ITE */ - else - if (s->status & (1 << 0)) /* RWM */ - s->status |= 1 << 7; /* set IRF */ - else - s->status |= 1 << 6; /* set ITE */ - s->status &= ~(1 << 1); /* clear ACKNAK */ - } else { - s->status |= 1 << 6; /* set ITE */ - s->status |= 1 << 10; /* set BED */ - s->status |= 1 << 1; /* set ACKNAK */ - } - } - if (!(value & (1 << 3)) && (value & (1 << 6))) /* !TB and IUE */ - if (value & (1 << 4)) /* MA */ - i2c_end_transfer(s->bus); - pxa2xx_i2c_update(s); - break; - - case ISR: - s->status &= ~(value & 0x07f0); - pxa2xx_i2c_update(s); - break; - - case ISAR: - i2c_slave_set_address(I2C_SLAVE(s->slave), value & 0x7f); - break; - - case IDBR: - s->data = value & 0xff; - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - } -} - -static const MemoryRegionOps pxa2xx_i2c_ops = { - .read = pxa2xx_i2c_read, - .write = pxa2xx_i2c_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static const VMStateDescription vmstate_pxa2xx_i2c_slave = { - .name = "pxa2xx_i2c_slave", - .version_id = 1, - .minimum_version_id = 1, - .fields = (const VMStateField[]) { - VMSTATE_I2C_SLAVE(parent_obj, PXA2xxI2CSlaveState), - VMSTATE_END_OF_LIST() - } -}; - -static const VMStateDescription vmstate_pxa2xx_i2c = { - .name = "pxa2xx_i2c", - .version_id = 1, - .minimum_version_id = 1, - .fields = (const VMStateField[]) { - VMSTATE_UINT16(control, PXA2xxI2CState), - VMSTATE_UINT16(status, PXA2xxI2CState), - VMSTATE_UINT8(ibmr, PXA2xxI2CState), - VMSTATE_UINT8(data, PXA2xxI2CState), - VMSTATE_STRUCT_POINTER(slave, PXA2xxI2CState, - vmstate_pxa2xx_i2c_slave, PXA2xxI2CSlaveState), - VMSTATE_END_OF_LIST() - } -}; - -static void pxa2xx_i2c_slave_class_init(ObjectClass *klass, void *data) -{ - I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); - - k->event = pxa2xx_i2c_event; - k->recv = pxa2xx_i2c_rx; - k->send = pxa2xx_i2c_tx; -} - -static const TypeInfo pxa2xx_i2c_slave_info = { - .name = TYPE_PXA2XX_I2C_SLAVE, - .parent = TYPE_I2C_SLAVE, - .instance_size = sizeof(PXA2xxI2CSlaveState), - .class_init = pxa2xx_i2c_slave_class_init, -}; - -PXA2xxI2CState *pxa2xx_i2c_init(hwaddr base, - qemu_irq irq, uint32_t region_size) -{ - DeviceState *dev; - SysBusDevice *i2c_dev; - PXA2xxI2CState *s; - I2CBus *i2cbus; - - dev = qdev_new(TYPE_PXA2XX_I2C); - qdev_prop_set_uint32(dev, "size", region_size + 1); - qdev_prop_set_uint32(dev, "offset", base & region_size); - - /* FIXME: Should the slave device really be on a separate bus? */ - i2cbus = i2c_init_bus(dev, "dummy"); - - i2c_dev = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(i2c_dev, &error_fatal); - sysbus_mmio_map(i2c_dev, 0, base & ~region_size); - sysbus_connect_irq(i2c_dev, 0, irq); - - s = PXA2XX_I2C(i2c_dev); - s->slave = PXA2XX_I2C_SLAVE(i2c_slave_create_simple(i2cbus, - TYPE_PXA2XX_I2C_SLAVE, - 0)); - s->slave->host = s; - - return s; -} - -static void pxa2xx_i2c_initfn(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - PXA2xxI2CState *s = PXA2XX_I2C(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - s->bus = i2c_init_bus(dev, NULL); - - memory_region_init_io(&s->iomem, obj, &pxa2xx_i2c_ops, s, - "pxa2xx-i2c", s->region_size); - sysbus_init_mmio(sbd, &s->iomem); - sysbus_init_irq(sbd, &s->irq); -} - -I2CBus *pxa2xx_i2c_bus(PXA2xxI2CState *s) -{ - return s->bus; -} - -static Property pxa2xx_i2c_properties[] = { - DEFINE_PROP_UINT32("size", PXA2xxI2CState, region_size, 0x10000), - DEFINE_PROP_UINT32("offset", PXA2xxI2CState, offset, 0), - DEFINE_PROP_END_OF_LIST(), -}; - -static void pxa2xx_i2c_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->desc = "PXA2xx I2C Bus Controller"; - dc->vmsd = &vmstate_pxa2xx_i2c; - device_class_set_props(dc, pxa2xx_i2c_properties); -} - -static const TypeInfo pxa2xx_i2c_info = { - .name = TYPE_PXA2XX_I2C, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PXA2xxI2CState), - .instance_init = pxa2xx_i2c_initfn, - .class_init = pxa2xx_i2c_class_init, -}; - -/* PXA Inter-IC Sound Controller */ -static void pxa2xx_i2s_reset(PXA2xxI2SState *i2s) -{ - i2s->rx_len = 0; - i2s->tx_len = 0; - i2s->fifo_len = 0; - i2s->clk = 0x1a; - i2s->control[0] = 0x00; - i2s->control[1] = 0x00; - i2s->status = 0x00; - i2s->mask = 0x00; -} - -#define SACR_TFTH(val) ((val >> 8) & 0xf) -#define SACR_RFTH(val) ((val >> 12) & 0xf) -#define SACR_DREC(val) (val & (1 << 3)) -#define SACR_DPRL(val) (val & (1 << 4)) - -static inline void pxa2xx_i2s_update(PXA2xxI2SState *i2s) -{ - int rfs, tfs; - rfs = SACR_RFTH(i2s->control[0]) < i2s->rx_len && - !SACR_DREC(i2s->control[1]); - tfs = (i2s->tx_len || i2s->fifo_len < SACR_TFTH(i2s->control[0])) && - i2s->enable && !SACR_DPRL(i2s->control[1]); - - qemu_set_irq(i2s->rx_dma, rfs); - qemu_set_irq(i2s->tx_dma, tfs); - - i2s->status &= 0xe0; - if (i2s->fifo_len < 16 || !i2s->enable) - i2s->status |= 1 << 0; /* TNF */ - if (i2s->rx_len) - i2s->status |= 1 << 1; /* RNE */ - if (i2s->enable) - i2s->status |= 1 << 2; /* BSY */ - if (tfs) - i2s->status |= 1 << 3; /* TFS */ - if (rfs) - i2s->status |= 1 << 4; /* RFS */ - if (!(i2s->tx_len && i2s->enable)) - i2s->status |= i2s->fifo_len << 8; /* TFL */ - i2s->status |= MAX(i2s->rx_len, 0xf) << 12; /* RFL */ - - qemu_set_irq(i2s->irq, i2s->status & i2s->mask); -} - -#define SACR0 0x00 /* Serial Audio Global Control register */ -#define SACR1 0x04 /* Serial Audio I2S/MSB-Justified Control register */ -#define SASR0 0x0c /* Serial Audio Interface and FIFO Status register */ -#define SAIMR 0x14 /* Serial Audio Interrupt Mask register */ -#define SAICR 0x18 /* Serial Audio Interrupt Clear register */ -#define SADIV 0x60 /* Serial Audio Clock Divider register */ -#define SADR 0x80 /* Serial Audio Data register */ - -static uint64_t pxa2xx_i2s_read(void *opaque, hwaddr addr, - unsigned size) -{ - PXA2xxI2SState *s = (PXA2xxI2SState *) opaque; - - switch (addr) { - case SACR0: - return s->control[0]; - case SACR1: - return s->control[1]; - case SASR0: - return s->status; - case SAIMR: - return s->mask; - case SAICR: - return 0; - case SADIV: - return s->clk; - case SADR: - if (s->rx_len > 0) { - s->rx_len --; - pxa2xx_i2s_update(s); - return s->codec_in(s->opaque); - } - return 0; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } - return 0; -} - -static void pxa2xx_i2s_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - PXA2xxI2SState *s = (PXA2xxI2SState *) opaque; - uint32_t *sample; - - switch (addr) { - case SACR0: - if (value & (1 << 3)) /* RST */ - pxa2xx_i2s_reset(s); - s->control[0] = value & 0xff3d; - if (!s->enable && (value & 1) && s->tx_len) { /* ENB */ - for (sample = s->fifo; s->fifo_len > 0; s->fifo_len --, sample ++) - s->codec_out(s->opaque, *sample); - s->status &= ~(1 << 7); /* I2SOFF */ - } - if (value & (1 << 4)) /* EFWR */ - printf("%s: Attempt to use special function\n", __func__); - s->enable = (value & 9) == 1; /* ENB && !RST*/ - pxa2xx_i2s_update(s); - break; - case SACR1: - s->control[1] = value & 0x0039; - if (value & (1 << 5)) /* ENLBF */ - printf("%s: Attempt to use loopback function\n", __func__); - if (value & (1 << 4)) /* DPRL */ - s->fifo_len = 0; - pxa2xx_i2s_update(s); - break; - case SAIMR: - s->mask = value & 0x0078; - pxa2xx_i2s_update(s); - break; - case SAICR: - s->status &= ~(value & (3 << 5)); - pxa2xx_i2s_update(s); - break; - case SADIV: - s->clk = value & 0x007f; - break; - case SADR: - if (s->tx_len && s->enable) { - s->tx_len --; - pxa2xx_i2s_update(s); - s->codec_out(s->opaque, value); - } else if (s->fifo_len < 16) { - s->fifo[s->fifo_len ++] = value; - pxa2xx_i2s_update(s); - } - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - } -} - -static const MemoryRegionOps pxa2xx_i2s_ops = { - .read = pxa2xx_i2s_read, - .write = pxa2xx_i2s_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static const VMStateDescription vmstate_pxa2xx_i2s = { - .name = "pxa2xx_i2s", - .version_id = 0, - .minimum_version_id = 0, - .fields = (const VMStateField[]) { - VMSTATE_UINT32_ARRAY(control, PXA2xxI2SState, 2), - VMSTATE_UINT32(status, PXA2xxI2SState), - VMSTATE_UINT32(mask, PXA2xxI2SState), - VMSTATE_UINT32(clk, PXA2xxI2SState), - VMSTATE_INT32(enable, PXA2xxI2SState), - VMSTATE_INT32(rx_len, PXA2xxI2SState), - VMSTATE_INT32(tx_len, PXA2xxI2SState), - VMSTATE_INT32(fifo_len, PXA2xxI2SState), - VMSTATE_END_OF_LIST() - } -}; - -static void pxa2xx_i2s_data_req(void *opaque, int tx, int rx) -{ - PXA2xxI2SState *s = (PXA2xxI2SState *) opaque; - uint32_t *sample; - - /* Signal FIFO errors */ - if (s->enable && s->tx_len) - s->status |= 1 << 5; /* TUR */ - if (s->enable && s->rx_len) - s->status |= 1 << 6; /* ROR */ - - /* Should be tx - MIN(tx, s->fifo_len) but we don't really need to - * handle the cases where it makes a difference. */ - s->tx_len = tx - s->fifo_len; - s->rx_len = rx; - /* Note that is s->codec_out wasn't set, we wouldn't get called. */ - if (s->enable) - for (sample = s->fifo; s->fifo_len; s->fifo_len --, sample ++) - s->codec_out(s->opaque, *sample); - pxa2xx_i2s_update(s); -} - -static PXA2xxI2SState *pxa2xx_i2s_init(MemoryRegion *sysmem, - hwaddr base, - qemu_irq irq, qemu_irq rx_dma, qemu_irq tx_dma) -{ - PXA2xxI2SState *s = g_new0(PXA2xxI2SState, 1); - - s->irq = irq; - s->rx_dma = rx_dma; - s->tx_dma = tx_dma; - s->data_req = pxa2xx_i2s_data_req; - - pxa2xx_i2s_reset(s); - - memory_region_init_io(&s->iomem, NULL, &pxa2xx_i2s_ops, s, - "pxa2xx-i2s", 0x100000); - memory_region_add_subregion(sysmem, base, &s->iomem); - - vmstate_register(NULL, base, &vmstate_pxa2xx_i2s, s); - - return s; -} - -/* PXA Fast Infra-red Communications Port */ -struct PXA2xxFIrState { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - MemoryRegion iomem; - qemu_irq irq; - qemu_irq rx_dma; - qemu_irq tx_dma; - uint32_t enable; - CharBackend chr; - - uint8_t control[3]; - uint8_t status[2]; - - uint32_t rx_len; - uint32_t rx_start; - uint8_t rx_fifo[64]; -}; - -static void pxa2xx_fir_reset(DeviceState *d) -{ - PXA2xxFIrState *s = PXA2XX_FIR(d); - - s->control[0] = 0x00; - s->control[1] = 0x00; - s->control[2] = 0x00; - s->status[0] = 0x00; - s->status[1] = 0x00; - s->enable = 0; -} - -static inline void pxa2xx_fir_update(PXA2xxFIrState *s) -{ - static const int tresh[4] = { 8, 16, 32, 0 }; - int intr = 0; - if ((s->control[0] & (1 << 4)) && /* RXE */ - s->rx_len >= tresh[s->control[2] & 3]) /* TRIG */ - s->status[0] |= 1 << 4; /* RFS */ - else - s->status[0] &= ~(1 << 4); /* RFS */ - if (s->control[0] & (1 << 3)) /* TXE */ - s->status[0] |= 1 << 3; /* TFS */ - else - s->status[0] &= ~(1 << 3); /* TFS */ - if (s->rx_len) - s->status[1] |= 1 << 2; /* RNE */ - else - s->status[1] &= ~(1 << 2); /* RNE */ - if (s->control[0] & (1 << 4)) /* RXE */ - s->status[1] |= 1 << 0; /* RSY */ - else - s->status[1] &= ~(1 << 0); /* RSY */ - - intr |= (s->control[0] & (1 << 5)) && /* RIE */ - (s->status[0] & (1 << 4)); /* RFS */ - intr |= (s->control[0] & (1 << 6)) && /* TIE */ - (s->status[0] & (1 << 3)); /* TFS */ - intr |= (s->control[2] & (1 << 4)) && /* TRAIL */ - (s->status[0] & (1 << 6)); /* EOC */ - intr |= (s->control[0] & (1 << 2)) && /* TUS */ - (s->status[0] & (1 << 1)); /* TUR */ - intr |= s->status[0] & 0x25; /* FRE, RAB, EIF */ - - qemu_set_irq(s->rx_dma, (s->status[0] >> 4) & 1); - qemu_set_irq(s->tx_dma, (s->status[0] >> 3) & 1); - - qemu_set_irq(s->irq, intr && s->enable); -} - -#define ICCR0 0x00 /* FICP Control register 0 */ -#define ICCR1 0x04 /* FICP Control register 1 */ -#define ICCR2 0x08 /* FICP Control register 2 */ -#define ICDR 0x0c /* FICP Data register */ -#define ICSR0 0x14 /* FICP Status register 0 */ -#define ICSR1 0x18 /* FICP Status register 1 */ -#define ICFOR 0x1c /* FICP FIFO Occupancy Status register */ - -static uint64_t pxa2xx_fir_read(void *opaque, hwaddr addr, - unsigned size) -{ - PXA2xxFIrState *s = (PXA2xxFIrState *) opaque; - uint8_t ret; - - switch (addr) { - case ICCR0: - return s->control[0]; - case ICCR1: - return s->control[1]; - case ICCR2: - return s->control[2]; - case ICDR: - s->status[0] &= ~0x01; - s->status[1] &= ~0x72; - if (s->rx_len) { - s->rx_len --; - ret = s->rx_fifo[s->rx_start ++]; - s->rx_start &= 63; - pxa2xx_fir_update(s); - return ret; - } - printf("%s: Rx FIFO underrun.\n", __func__); - break; - case ICSR0: - return s->status[0]; - case ICSR1: - return s->status[1] | (1 << 3); /* TNF */ - case ICFOR: - return s->rx_len; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - break; - } - return 0; -} - -static void pxa2xx_fir_write(void *opaque, hwaddr addr, - uint64_t value64, unsigned size) -{ - PXA2xxFIrState *s = (PXA2xxFIrState *) opaque; - uint32_t value = value64; - uint8_t ch; - - switch (addr) { - case ICCR0: - s->control[0] = value; - if (!(value & (1 << 4))) /* RXE */ - s->rx_len = s->rx_start = 0; - if (!(value & (1 << 3))) { /* TXE */ - /* Nop */ - } - s->enable = value & 1; /* ITR */ - if (!s->enable) - s->status[0] = 0; - pxa2xx_fir_update(s); - break; - case ICCR1: - s->control[1] = value; - break; - case ICCR2: - s->control[2] = value & 0x3f; - pxa2xx_fir_update(s); - break; - case ICDR: - if (s->control[2] & (1 << 2)) { /* TXP */ - ch = value; - } else { - ch = ~value; - } - if (s->enable && (s->control[0] & (1 << 3))) { /* TXE */ - /* XXX this blocks entire thread. Rewrite to use - * qemu_chr_fe_write and background I/O callbacks */ - qemu_chr_fe_write_all(&s->chr, &ch, 1); - } - break; - case ICSR0: - s->status[0] &= ~(value & 0x66); - pxa2xx_fir_update(s); - break; - case ICFOR: - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, addr); - } -} - -static const MemoryRegionOps pxa2xx_fir_ops = { - .read = pxa2xx_fir_read, - .write = pxa2xx_fir_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static int pxa2xx_fir_is_empty(void *opaque) -{ - PXA2xxFIrState *s = (PXA2xxFIrState *) opaque; - return (s->rx_len < 64); -} - -static void pxa2xx_fir_rx(void *opaque, const uint8_t *buf, int size) -{ - PXA2xxFIrState *s = (PXA2xxFIrState *) opaque; - if (!(s->control[0] & (1 << 4))) /* RXE */ - return; - - while (size --) { - s->status[1] |= 1 << 4; /* EOF */ - if (s->rx_len >= 64) { - s->status[1] |= 1 << 6; /* ROR */ - break; - } - - if (s->control[2] & (1 << 3)) /* RXP */ - s->rx_fifo[(s->rx_start + s->rx_len ++) & 63] = *(buf ++); - else - s->rx_fifo[(s->rx_start + s->rx_len ++) & 63] = ~*(buf ++); - } - - pxa2xx_fir_update(s); -} - -static void pxa2xx_fir_event(void *opaque, QEMUChrEvent event) -{ -} - -static void pxa2xx_fir_instance_init(Object *obj) -{ - PXA2xxFIrState *s = PXA2XX_FIR(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - memory_region_init_io(&s->iomem, obj, &pxa2xx_fir_ops, s, - "pxa2xx-fir", 0x1000); - sysbus_init_mmio(sbd, &s->iomem); - sysbus_init_irq(sbd, &s->irq); - sysbus_init_irq(sbd, &s->rx_dma); - sysbus_init_irq(sbd, &s->tx_dma); -} - -static void pxa2xx_fir_realize(DeviceState *dev, Error **errp) -{ - PXA2xxFIrState *s = PXA2XX_FIR(dev); - - qemu_chr_fe_set_handlers(&s->chr, pxa2xx_fir_is_empty, - pxa2xx_fir_rx, pxa2xx_fir_event, NULL, s, NULL, - true); -} - -static bool pxa2xx_fir_vmstate_validate(void *opaque, int version_id) -{ - PXA2xxFIrState *s = opaque; - - return s->rx_start < ARRAY_SIZE(s->rx_fifo); -} - -static const VMStateDescription pxa2xx_fir_vmsd = { - .name = "pxa2xx-fir", - .version_id = 1, - .minimum_version_id = 1, - .fields = (const VMStateField[]) { - VMSTATE_UINT32(enable, PXA2xxFIrState), - VMSTATE_UINT8_ARRAY(control, PXA2xxFIrState, 3), - VMSTATE_UINT8_ARRAY(status, PXA2xxFIrState, 2), - VMSTATE_UINT32(rx_len, PXA2xxFIrState), - VMSTATE_UINT32(rx_start, PXA2xxFIrState), - VMSTATE_VALIDATE("fifo is 64 bytes", pxa2xx_fir_vmstate_validate), - VMSTATE_UINT8_ARRAY(rx_fifo, PXA2xxFIrState, 64), - VMSTATE_END_OF_LIST() - } -}; - -static Property pxa2xx_fir_properties[] = { - DEFINE_PROP_CHR("chardev", PXA2xxFIrState, chr), - DEFINE_PROP_END_OF_LIST(), -}; - -static void pxa2xx_fir_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = pxa2xx_fir_realize; - dc->vmsd = &pxa2xx_fir_vmsd; - device_class_set_props(dc, pxa2xx_fir_properties); - device_class_set_legacy_reset(dc, pxa2xx_fir_reset); -} - -static const TypeInfo pxa2xx_fir_info = { - .name = TYPE_PXA2XX_FIR, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PXA2xxFIrState), - .class_init = pxa2xx_fir_class_init, - .instance_init = pxa2xx_fir_instance_init, -}; - -static PXA2xxFIrState *pxa2xx_fir_init(MemoryRegion *sysmem, - hwaddr base, - qemu_irq irq, qemu_irq rx_dma, - qemu_irq tx_dma, - Chardev *chr) -{ - DeviceState *dev; - SysBusDevice *sbd; - - dev = qdev_new(TYPE_PXA2XX_FIR); - qdev_prop_set_chr(dev, "chardev", chr); - sbd = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(sbd, &error_fatal); - sysbus_mmio_map(sbd, 0, base); - sysbus_connect_irq(sbd, 0, irq); - sysbus_connect_irq(sbd, 1, rx_dma); - sysbus_connect_irq(sbd, 2, tx_dma); - return PXA2XX_FIR(dev); -} - -static void pxa2xx_reset(void *opaque, int line, int level) -{ - PXA2xxState *s = (PXA2xxState *) opaque; - - if (level && (s->pm_regs[PCFR >> 2] & 0x10)) { /* GPR_EN */ - cpu_reset(CPU(s->cpu)); - /* TODO: reset peripherals */ - } -} - -/* Initialise a PXA270 integrated chip (ARM based core). */ -PXA2xxState *pxa270_init(unsigned int sdram_size, const char *cpu_type) -{ - MemoryRegion *address_space = get_system_memory(); - PXA2xxState *s; - int i; - DriveInfo *dinfo; - s = g_new0(PXA2xxState, 1); - - if (strncmp(cpu_type, "pxa27", 5)) { - error_report("Machine requires a PXA27x processor"); - exit(1); - } - - s->cpu = ARM_CPU(cpu_create(cpu_type)); - s->reset = qemu_allocate_irq(pxa2xx_reset, s, 0); - - /* SDRAM & Internal Memory Storage */ - memory_region_init_ram(&s->sdram, NULL, "pxa270.sdram", sdram_size, - &error_fatal); - memory_region_add_subregion(address_space, PXA2XX_SDRAM_BASE, &s->sdram); - memory_region_init_ram(&s->internal, NULL, "pxa270.internal", 0x40000, - &error_fatal); - memory_region_add_subregion(address_space, PXA2XX_INTERNAL_BASE, - &s->internal); - - s->pic = pxa2xx_pic_init(0x40d00000, s->cpu); - - s->dma = pxa27x_dma_init(0x40000000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_DMA)); - - sysbus_create_varargs("pxa27x-timer", 0x40a00000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_OST_0 + 0), - qdev_get_gpio_in(s->pic, PXA2XX_PIC_OST_0 + 1), - qdev_get_gpio_in(s->pic, PXA2XX_PIC_OST_0 + 2), - qdev_get_gpio_in(s->pic, PXA2XX_PIC_OST_0 + 3), - qdev_get_gpio_in(s->pic, PXA27X_PIC_OST_4_11), - NULL); - - s->gpio = pxa2xx_gpio_init(0x40e00000, s->cpu, s->pic, 121); - - s->mmc = pxa2xx_mmci_init(address_space, 0x41100000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_MMC), - qdev_get_gpio_in(s->dma, PXA2XX_RX_RQ_MMCI), - qdev_get_gpio_in(s->dma, PXA2XX_TX_RQ_MMCI)); - dinfo = drive_get(IF_SD, 0, 0); - if (dinfo) { - DeviceState *carddev; - - /* Create and plug in the sd card */ - carddev = qdev_new(TYPE_SD_CARD); - qdev_prop_set_drive_err(carddev, "drive", - blk_by_legacy_dinfo(dinfo), &error_fatal); - qdev_realize_and_unref(carddev, qdev_get_child_bus(DEVICE(s->mmc), - "sd-bus"), - &error_fatal); - } else if (!qtest_enabled()) { - warn_report("missing SecureDigital device"); - } - - for (i = 0; pxa270_serial[i].io_base; i++) { - if (serial_hd(i)) { - serial_mm_init(address_space, pxa270_serial[i].io_base, 2, - qdev_get_gpio_in(s->pic, pxa270_serial[i].irqn), - 14857000 / 16, serial_hd(i), - DEVICE_NATIVE_ENDIAN); - } else { - break; - } - } - if (serial_hd(i)) - s->fir = pxa2xx_fir_init(address_space, 0x40800000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_ICP), - qdev_get_gpio_in(s->dma, PXA2XX_RX_RQ_ICP), - qdev_get_gpio_in(s->dma, PXA2XX_TX_RQ_ICP), - serial_hd(i)); - - s->lcd = pxa2xx_lcdc_init(address_space, 0x44000000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_LCD)); - - s->cm_base = 0x41300000; - s->cm_regs[CCCR >> 2] = 0x02000210; /* 416.0 MHz */ - s->clkcfg = 0x00000009; /* Turbo mode active */ - memory_region_init_io(&s->cm_iomem, NULL, &pxa2xx_cm_ops, s, "pxa2xx-cm", 0x1000); - memory_region_add_subregion(address_space, s->cm_base, &s->cm_iomem); - vmstate_register(NULL, 0, &vmstate_pxa2xx_cm, s); - - pxa2xx_setup_cp14(s); - - s->mm_base = 0x48000000; - s->mm_regs[MDMRS >> 2] = 0x00020002; - s->mm_regs[MDREFR >> 2] = 0x03ca4000; - s->mm_regs[MECR >> 2] = 0x00000001; /* Two PC Card sockets */ - memory_region_init_io(&s->mm_iomem, NULL, &pxa2xx_mm_ops, s, "pxa2xx-mm", 0x1000); - memory_region_add_subregion(address_space, s->mm_base, &s->mm_iomem); - vmstate_register(NULL, 0, &vmstate_pxa2xx_mm, s); - - s->pm_base = 0x40f00000; - memory_region_init_io(&s->pm_iomem, NULL, &pxa2xx_pm_ops, s, "pxa2xx-pm", 0x100); - memory_region_add_subregion(address_space, s->pm_base, &s->pm_iomem); - vmstate_register(NULL, 0, &vmstate_pxa2xx_pm, s); - - for (i = 0; pxa27x_ssp[i].io_base; i ++); - s->ssp = g_new0(SSIBus *, i); - for (i = 0; pxa27x_ssp[i].io_base; i ++) { - DeviceState *dev; - dev = sysbus_create_simple(TYPE_PXA2XX_SSP, pxa27x_ssp[i].io_base, - qdev_get_gpio_in(s->pic, pxa27x_ssp[i].irqn)); - s->ssp[i] = (SSIBus *)qdev_get_child_bus(dev, "ssi"); - } - - sysbus_create_simple("sysbus-ohci", 0x4c000000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_USBH1)); - - s->pcmcia[0] = PXA2XX_PCMCIA(sysbus_create_simple(TYPE_PXA2XX_PCMCIA, - 0x20000000, NULL)); - s->pcmcia[1] = PXA2XX_PCMCIA(sysbus_create_simple(TYPE_PXA2XX_PCMCIA, - 0x30000000, NULL)); - - sysbus_create_simple(TYPE_PXA2XX_RTC, 0x40900000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_RTCALARM)); - - s->i2c[0] = pxa2xx_i2c_init(0x40301600, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_I2C), 0xffff); - s->i2c[1] = pxa2xx_i2c_init(0x40f00100, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_PWRI2C), 0xff); - - s->i2s = pxa2xx_i2s_init(address_space, 0x40400000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_I2S), - qdev_get_gpio_in(s->dma, PXA2XX_RX_RQ_I2S), - qdev_get_gpio_in(s->dma, PXA2XX_TX_RQ_I2S)); - - s->kp = pxa27x_keypad_init(address_space, 0x41500000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_KEYPAD)); - - /* GPIO1 resets the processor */ - /* The handler can be overridden by board-specific code */ - qdev_connect_gpio_out(s->gpio, 1, s->reset); - return s; -} - -/* Initialise a PXA255 integrated chip (ARM based core). */ -PXA2xxState *pxa255_init(unsigned int sdram_size) -{ - MemoryRegion *address_space = get_system_memory(); - PXA2xxState *s; - int i; - DriveInfo *dinfo; - - s = g_new0(PXA2xxState, 1); - - s->cpu = ARM_CPU(cpu_create(ARM_CPU_TYPE_NAME("pxa255"))); - s->reset = qemu_allocate_irq(pxa2xx_reset, s, 0); - - /* SDRAM & Internal Memory Storage */ - memory_region_init_ram(&s->sdram, NULL, "pxa255.sdram", sdram_size, - &error_fatal); - memory_region_add_subregion(address_space, PXA2XX_SDRAM_BASE, &s->sdram); - memory_region_init_ram(&s->internal, NULL, "pxa255.internal", - PXA2XX_INTERNAL_SIZE, &error_fatal); - memory_region_add_subregion(address_space, PXA2XX_INTERNAL_BASE, - &s->internal); - - s->pic = pxa2xx_pic_init(0x40d00000, s->cpu); - - s->dma = pxa255_dma_init(0x40000000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_DMA)); - - sysbus_create_varargs("pxa25x-timer", 0x40a00000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_OST_0 + 0), - qdev_get_gpio_in(s->pic, PXA2XX_PIC_OST_0 + 1), - qdev_get_gpio_in(s->pic, PXA2XX_PIC_OST_0 + 2), - qdev_get_gpio_in(s->pic, PXA2XX_PIC_OST_0 + 3), - NULL); - - s->gpio = pxa2xx_gpio_init(0x40e00000, s->cpu, s->pic, 85); - - s->mmc = pxa2xx_mmci_init(address_space, 0x41100000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_MMC), - qdev_get_gpio_in(s->dma, PXA2XX_RX_RQ_MMCI), - qdev_get_gpio_in(s->dma, PXA2XX_TX_RQ_MMCI)); - dinfo = drive_get(IF_SD, 0, 0); - if (dinfo) { - DeviceState *carddev; - - /* Create and plug in the sd card */ - carddev = qdev_new(TYPE_SD_CARD); - qdev_prop_set_drive_err(carddev, "drive", - blk_by_legacy_dinfo(dinfo), &error_fatal); - qdev_realize_and_unref(carddev, qdev_get_child_bus(DEVICE(s->mmc), - "sd-bus"), - &error_fatal); - } else if (!qtest_enabled()) { - warn_report("missing SecureDigital device"); - } - - for (i = 0; pxa255_serial[i].io_base; i++) { - if (serial_hd(i)) { - serial_mm_init(address_space, pxa255_serial[i].io_base, 2, - qdev_get_gpio_in(s->pic, pxa255_serial[i].irqn), - 14745600 / 16, serial_hd(i), - DEVICE_NATIVE_ENDIAN); - } else { - break; - } - } - if (serial_hd(i)) - s->fir = pxa2xx_fir_init(address_space, 0x40800000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_ICP), - qdev_get_gpio_in(s->dma, PXA2XX_RX_RQ_ICP), - qdev_get_gpio_in(s->dma, PXA2XX_TX_RQ_ICP), - serial_hd(i)); - - s->lcd = pxa2xx_lcdc_init(address_space, 0x44000000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_LCD)); - - s->cm_base = 0x41300000; - s->cm_regs[CCCR >> 2] = 0x00000121; /* from datasheet */ - s->cm_regs[CKEN >> 2] = 0x00017def; /* from datasheet */ - - s->clkcfg = 0x00000009; /* Turbo mode active */ - memory_region_init_io(&s->cm_iomem, NULL, &pxa2xx_cm_ops, s, "pxa2xx-cm", 0x1000); - memory_region_add_subregion(address_space, s->cm_base, &s->cm_iomem); - vmstate_register(NULL, 0, &vmstate_pxa2xx_cm, s); - - pxa2xx_setup_cp14(s); - - s->mm_base = 0x48000000; - s->mm_regs[MDMRS >> 2] = 0x00020002; - s->mm_regs[MDREFR >> 2] = 0x03ca4000; - s->mm_regs[MECR >> 2] = 0x00000001; /* Two PC Card sockets */ - memory_region_init_io(&s->mm_iomem, NULL, &pxa2xx_mm_ops, s, "pxa2xx-mm", 0x1000); - memory_region_add_subregion(address_space, s->mm_base, &s->mm_iomem); - vmstate_register(NULL, 0, &vmstate_pxa2xx_mm, s); - - s->pm_base = 0x40f00000; - memory_region_init_io(&s->pm_iomem, NULL, &pxa2xx_pm_ops, s, "pxa2xx-pm", 0x100); - memory_region_add_subregion(address_space, s->pm_base, &s->pm_iomem); - vmstate_register(NULL, 0, &vmstate_pxa2xx_pm, s); - - for (i = 0; pxa255_ssp[i].io_base; i ++); - s->ssp = g_new0(SSIBus *, i); - for (i = 0; pxa255_ssp[i].io_base; i ++) { - DeviceState *dev; - dev = sysbus_create_simple(TYPE_PXA2XX_SSP, pxa255_ssp[i].io_base, - qdev_get_gpio_in(s->pic, pxa255_ssp[i].irqn)); - s->ssp[i] = (SSIBus *)qdev_get_child_bus(dev, "ssi"); - } - - s->pcmcia[0] = PXA2XX_PCMCIA(sysbus_create_simple(TYPE_PXA2XX_PCMCIA, - 0x20000000, NULL)); - s->pcmcia[1] = PXA2XX_PCMCIA(sysbus_create_simple(TYPE_PXA2XX_PCMCIA, - 0x30000000, NULL)); - - sysbus_create_simple(TYPE_PXA2XX_RTC, 0x40900000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_RTCALARM)); - - s->i2c[0] = pxa2xx_i2c_init(0x40301600, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_I2C), 0xffff); - s->i2c[1] = pxa2xx_i2c_init(0x40f00100, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_PWRI2C), 0xff); - - s->i2s = pxa2xx_i2s_init(address_space, 0x40400000, - qdev_get_gpio_in(s->pic, PXA2XX_PIC_I2S), - qdev_get_gpio_in(s->dma, PXA2XX_RX_RQ_I2S), - qdev_get_gpio_in(s->dma, PXA2XX_TX_RQ_I2S)); - - /* GPIO1 resets the processor */ - /* The handler can be overridden by board-specific code */ - qdev_connect_gpio_out(s->gpio, 1, s->reset); - return s; -} - -static void pxa2xx_ssp_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - device_class_set_legacy_reset(dc, pxa2xx_ssp_reset); - dc->vmsd = &vmstate_pxa2xx_ssp; -} - -static const TypeInfo pxa2xx_ssp_info = { - .name = TYPE_PXA2XX_SSP, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PXA2xxSSPState), - .instance_init = pxa2xx_ssp_init, - .class_init = pxa2xx_ssp_class_init, -}; - -static void pxa2xx_register_types(void) -{ - type_register_static(&pxa2xx_i2c_slave_info); - type_register_static(&pxa2xx_ssp_info); - type_register_static(&pxa2xx_i2c_info); - type_register_static(&pxa2xx_rtc_sysbus_info); - type_register_static(&pxa2xx_fir_info); -} - -type_init(pxa2xx_register_types) diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_SABRELITE', if_true: files('sabrelite.c')) arm_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m.c')) arm_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210.c')) -arm_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx.c', 'pxa2xx_gpio.c', 'pxa2xx_pic.c')) +arm_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_gpio.c', 'pxa2xx_pic.c')) arm_ss.add(when: 'CONFIG_DIGIC', if_true: files('digic.c')) arm_ss.add(when: 'CONFIG_OMAP', if_true: files('omap1.c')) arm_ss.add(when: 'CONFIG_ALLWINNER_A10', if_true: files('allwinner-a10.c', 'cubieboard.c')) -- 2.34.1 Remove the pxa2xx-specific pxa2xx_mmci device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-17-peter.maydell@linaro.org --- include/hw/arm/pxa.h | 10 - hw/sd/pxa2xx_mmci.c | 594 ------------------------------------------- hw/sd/meson.build | 1 - hw/sd/trace-events | 4 - 4 files changed, 609 deletions(-) delete mode 100644 hw/sd/pxa2xx_mmci.c diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ PXA2xxLCDState *pxa2xx_lcdc_init(MemoryRegion *sysmem, hwaddr base, qemu_irq irq); void pxa2xx_lcd_vsync_notifier(PXA2xxLCDState *s, qemu_irq handler); -/* pxa2xx_mmci.c */ -#define TYPE_PXA2XX_MMCI "pxa2xx-mmci" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxMMCIState, PXA2XX_MMCI) - -PXA2xxMMCIState *pxa2xx_mmci_init(MemoryRegion *sysmem, - hwaddr base, - qemu_irq irq, qemu_irq rx_dma, qemu_irq tx_dma); -void pxa2xx_mmci_handlers(PXA2xxMMCIState *s, qemu_irq readonly, - qemu_irq coverswitch); - /* pxa2xx_pcmcia.c */ #define TYPE_PXA2XX_PCMCIA "pxa2xx-pcmcia" OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxPCMCIAState, PXA2XX_PCMCIA) diff --git a/hw/sd/pxa2xx_mmci.c b/hw/sd/pxa2xx_mmci.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/sd/pxa2xx_mmci.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel XScale PXA255/270 MultiMediaCard/SD/SDIO Controller emulation. - * - * Copyright (c) 2006 Openedhand Ltd. - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GPLv2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "hw/arm/pxa.h" -#include "hw/sd/sd.h" -#include "hw/qdev-properties.h" -#include "qemu/log.h" -#include "qemu/module.h" -#include "trace.h" -#include "qom/object.h" - -#define TYPE_PXA2XX_MMCI_BUS "pxa2xx-mmci-bus" -/* This is reusing the SDBus typedef from SD_BUS */ -DECLARE_INSTANCE_CHECKER(SDBus, PXA2XX_MMCI_BUS, - TYPE_PXA2XX_MMCI_BUS) - -struct PXA2xxMMCIState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - qemu_irq irq; - qemu_irq rx_dma; - qemu_irq tx_dma; - qemu_irq inserted; - qemu_irq readonly; - - BlockBackend *blk; - SDBus sdbus; - - uint32_t status; - uint32_t clkrt; - uint32_t spi; - uint32_t cmdat; - uint32_t resp_tout; - uint32_t read_tout; - int32_t blklen; - int32_t numblk; - uint32_t intmask; - uint32_t intreq; - int32_t cmd; - uint32_t arg; - - int32_t active; - int32_t bytesleft; - uint8_t tx_fifo[64]; - uint32_t tx_start; - uint32_t tx_len; - uint8_t rx_fifo[32]; - uint32_t rx_start; - uint32_t rx_len; - uint16_t resp_fifo[9]; - uint32_t resp_len; - - int32_t cmdreq; -}; - -static bool pxa2xx_mmci_vmstate_validate(void *opaque, int version_id) -{ - PXA2xxMMCIState *s = opaque; - - return s->tx_start < ARRAY_SIZE(s->tx_fifo) - && s->rx_start < ARRAY_SIZE(s->rx_fifo) - && s->tx_len <= ARRAY_SIZE(s->tx_fifo) - && s->rx_len <= ARRAY_SIZE(s->rx_fifo) - && s->resp_len <= ARRAY_SIZE(s->resp_fifo); -} - - -static const VMStateDescription vmstate_pxa2xx_mmci = { - .name = "pxa2xx-mmci", - .version_id = 2, - .minimum_version_id = 2, - .fields = (const VMStateField[]) { - VMSTATE_UINT32(status, PXA2xxMMCIState), - VMSTATE_UINT32(clkrt, PXA2xxMMCIState), - VMSTATE_UINT32(spi, PXA2xxMMCIState), - VMSTATE_UINT32(cmdat, PXA2xxMMCIState), - VMSTATE_UINT32(resp_tout, PXA2xxMMCIState), - VMSTATE_UINT32(read_tout, PXA2xxMMCIState), - VMSTATE_INT32(blklen, PXA2xxMMCIState), - VMSTATE_INT32(numblk, PXA2xxMMCIState), - VMSTATE_UINT32(intmask, PXA2xxMMCIState), - VMSTATE_UINT32(intreq, PXA2xxMMCIState), - VMSTATE_INT32(cmd, PXA2xxMMCIState), - VMSTATE_UINT32(arg, PXA2xxMMCIState), - VMSTATE_INT32(cmdreq, PXA2xxMMCIState), - VMSTATE_INT32(active, PXA2xxMMCIState), - VMSTATE_INT32(bytesleft, PXA2xxMMCIState), - VMSTATE_UINT32(tx_start, PXA2xxMMCIState), - VMSTATE_UINT32(tx_len, PXA2xxMMCIState), - VMSTATE_UINT32(rx_start, PXA2xxMMCIState), - VMSTATE_UINT32(rx_len, PXA2xxMMCIState), - VMSTATE_UINT32(resp_len, PXA2xxMMCIState), - VMSTATE_VALIDATE("fifo size incorrect", pxa2xx_mmci_vmstate_validate), - VMSTATE_UINT8_ARRAY(tx_fifo, PXA2xxMMCIState, 64), - VMSTATE_UINT8_ARRAY(rx_fifo, PXA2xxMMCIState, 32), - VMSTATE_UINT16_ARRAY(resp_fifo, PXA2xxMMCIState, 9), - VMSTATE_END_OF_LIST() - } -}; - -#define MMC_STRPCL 0x00 /* MMC Clock Start/Stop register */ -#define MMC_STAT 0x04 /* MMC Status register */ -#define MMC_CLKRT 0x08 /* MMC Clock Rate register */ -#define MMC_SPI 0x0c /* MMC SPI Mode register */ -#define MMC_CMDAT 0x10 /* MMC Command/Data register */ -#define MMC_RESTO 0x14 /* MMC Response Time-Out register */ -#define MMC_RDTO 0x18 /* MMC Read Time-Out register */ -#define MMC_BLKLEN 0x1c /* MMC Block Length register */ -#define MMC_NUMBLK 0x20 /* MMC Number of Blocks register */ -#define MMC_PRTBUF 0x24 /* MMC Buffer Partly Full register */ -#define MMC_I_MASK 0x28 /* MMC Interrupt Mask register */ -#define MMC_I_REG 0x2c /* MMC Interrupt Request register */ -#define MMC_CMD 0x30 /* MMC Command register */ -#define MMC_ARGH 0x34 /* MMC Argument High register */ -#define MMC_ARGL 0x38 /* MMC Argument Low register */ -#define MMC_RES 0x3c /* MMC Response FIFO */ -#define MMC_RXFIFO 0x40 /* MMC Receive FIFO */ -#define MMC_TXFIFO 0x44 /* MMC Transmit FIFO */ -#define MMC_RDWAIT 0x48 /* MMC RD_WAIT register */ -#define MMC_BLKS_REM 0x4c /* MMC Blocks Remaining register */ - -/* Bitfield masks */ -#define STRPCL_STOP_CLK (1 << 0) -#define STRPCL_STRT_CLK (1 << 1) -#define STAT_TOUT_RES (1 << 1) -#define STAT_CLK_EN (1 << 8) -#define STAT_DATA_DONE (1 << 11) -#define STAT_PRG_DONE (1 << 12) -#define STAT_END_CMDRES (1 << 13) -#define SPI_SPI_MODE (1 << 0) -#define CMDAT_RES_TYPE (3 << 0) -#define CMDAT_DATA_EN (1 << 2) -#define CMDAT_WR_RD (1 << 3) -#define CMDAT_DMA_EN (1 << 7) -#define CMDAT_STOP_TRAN (1 << 10) -#define INT_DATA_DONE (1 << 0) -#define INT_PRG_DONE (1 << 1) -#define INT_END_CMD (1 << 2) -#define INT_STOP_CMD (1 << 3) -#define INT_CLK_OFF (1 << 4) -#define INT_RXFIFO_REQ (1 << 5) -#define INT_TXFIFO_REQ (1 << 6) -#define INT_TINT (1 << 7) -#define INT_DAT_ERR (1 << 8) -#define INT_RES_ERR (1 << 9) -#define INT_RD_STALLED (1 << 10) -#define INT_SDIO_INT (1 << 11) -#define INT_SDIO_SACK (1 << 12) -#define PRTBUF_PRT_BUF (1 << 0) - -/* Route internal interrupt lines to the global IC and DMA */ -static void pxa2xx_mmci_int_update(PXA2xxMMCIState *s) -{ - uint32_t mask = s->intmask; - if (s->cmdat & CMDAT_DMA_EN) { - mask |= INT_RXFIFO_REQ | INT_TXFIFO_REQ; - - qemu_set_irq(s->rx_dma, !!(s->intreq & INT_RXFIFO_REQ)); - qemu_set_irq(s->tx_dma, !!(s->intreq & INT_TXFIFO_REQ)); - } - - qemu_set_irq(s->irq, !!(s->intreq & ~mask)); -} - -static void pxa2xx_mmci_fifo_update(PXA2xxMMCIState *s) -{ - if (!s->active) - return; - - if (s->cmdat & CMDAT_WR_RD) { - while (s->bytesleft && s->tx_len) { - sdbus_write_byte(&s->sdbus, s->tx_fifo[s->tx_start++]); - s->tx_start &= 0x1f; - s->tx_len --; - s->bytesleft --; - } - if (s->bytesleft) - s->intreq |= INT_TXFIFO_REQ; - } else - while (s->bytesleft && s->rx_len < 32) { - s->rx_fifo[(s->rx_start + (s->rx_len ++)) & 0x1f] = - sdbus_read_byte(&s->sdbus); - s->bytesleft --; - s->intreq |= INT_RXFIFO_REQ; - } - - if (!s->bytesleft) { - s->active = 0; - s->intreq |= INT_DATA_DONE; - s->status |= STAT_DATA_DONE; - - if (s->cmdat & CMDAT_WR_RD) { - s->intreq |= INT_PRG_DONE; - s->status |= STAT_PRG_DONE; - } - } - - pxa2xx_mmci_int_update(s); -} - -static void pxa2xx_mmci_wakequeues(PXA2xxMMCIState *s) -{ - int rsplen, i; - SDRequest request; - uint8_t response[16]; - - s->active = 1; - s->rx_len = 0; - s->tx_len = 0; - s->cmdreq = 0; - - request.cmd = s->cmd; - request.arg = s->arg; - request.crc = 0; /* FIXME */ - - rsplen = sdbus_do_command(&s->sdbus, &request, response); - s->intreq |= INT_END_CMD; - - memset(s->resp_fifo, 0, sizeof(s->resp_fifo)); - switch (s->cmdat & CMDAT_RES_TYPE) { -#define PXAMMCI_RESP(wd, value0, value1) \ - s->resp_fifo[(wd) + 0] |= (value0); \ - s->resp_fifo[(wd) + 1] |= (value1) << 8; - case 0: /* No response */ - goto complete; - - case 1: /* R1, R4, R5 or R6 */ - if (rsplen < 4) - goto timeout; - goto complete; - - case 2: /* R2 */ - if (rsplen < 16) - goto timeout; - goto complete; - - case 3: /* R3 */ - if (rsplen < 4) - goto timeout; - goto complete; - - complete: - for (i = 0; rsplen > 0; i ++, rsplen -= 2) { - PXAMMCI_RESP(i, response[i * 2], response[i * 2 + 1]); - } - s->status |= STAT_END_CMDRES; - - if (!(s->cmdat & CMDAT_DATA_EN)) - s->active = 0; - else - s->bytesleft = s->numblk * s->blklen; - - s->resp_len = 0; - break; - - timeout: - s->active = 0; - s->status |= STAT_TOUT_RES; - break; - } - - pxa2xx_mmci_fifo_update(s); -} - -static uint64_t pxa2xx_mmci_read(void *opaque, hwaddr offset, unsigned size) -{ - PXA2xxMMCIState *s = (PXA2xxMMCIState *) opaque; - uint32_t ret = 0; - - switch (offset) { - case MMC_STRPCL: - break; - case MMC_STAT: - ret = s->status; - break; - case MMC_CLKRT: - ret = s->clkrt; - break; - case MMC_SPI: - ret = s->spi; - break; - case MMC_CMDAT: - ret = s->cmdat; - break; - case MMC_RESTO: - ret = s->resp_tout; - break; - case MMC_RDTO: - ret = s->read_tout; - break; - case MMC_BLKLEN: - ret = s->blklen; - break; - case MMC_NUMBLK: - ret = s->numblk; - break; - case MMC_PRTBUF: - break; - case MMC_I_MASK: - ret = s->intmask; - break; - case MMC_I_REG: - ret = s->intreq; - break; - case MMC_CMD: - ret = s->cmd | 0x40; - break; - case MMC_ARGH: - ret = s->arg >> 16; - break; - case MMC_ARGL: - ret = s->arg & 0xffff; - break; - case MMC_RES: - ret = (s->resp_len < 9) ? s->resp_fifo[s->resp_len++] : 0; - break; - case MMC_RXFIFO: - while (size-- && s->rx_len) { - ret |= s->rx_fifo[s->rx_start++] << (size << 3); - s->rx_start &= 0x1f; - s->rx_len --; - } - s->intreq &= ~INT_RXFIFO_REQ; - pxa2xx_mmci_fifo_update(s); - break; - case MMC_RDWAIT: - break; - case MMC_BLKS_REM: - ret = s->numblk; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: incorrect register 0x%02" HWADDR_PRIx "\n", - __func__, offset); - } - trace_pxa2xx_mmci_read(size, offset, ret); - - return ret; -} - -static void pxa2xx_mmci_write(void *opaque, - hwaddr offset, uint64_t value, unsigned size) -{ - PXA2xxMMCIState *s = (PXA2xxMMCIState *) opaque; - - trace_pxa2xx_mmci_write(size, offset, value); - switch (offset) { - case MMC_STRPCL: - if (value & STRPCL_STRT_CLK) { - s->status |= STAT_CLK_EN; - s->intreq &= ~INT_CLK_OFF; - - if (s->cmdreq && !(s->cmdat & CMDAT_STOP_TRAN)) { - s->status &= STAT_CLK_EN; - pxa2xx_mmci_wakequeues(s); - } - } - - if (value & STRPCL_STOP_CLK) { - s->status &= ~STAT_CLK_EN; - s->intreq |= INT_CLK_OFF; - s->active = 0; - } - - pxa2xx_mmci_int_update(s); - break; - - case MMC_CLKRT: - s->clkrt = value & 7; - break; - - case MMC_SPI: - s->spi = value & 0xf; - if (value & SPI_SPI_MODE) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: attempted to use card in SPI mode\n", __func__); - } - break; - - case MMC_CMDAT: - s->cmdat = value & 0x3dff; - s->active = 0; - s->cmdreq = 1; - if (!(value & CMDAT_STOP_TRAN)) { - s->status &= STAT_CLK_EN; - - if (s->status & STAT_CLK_EN) - pxa2xx_mmci_wakequeues(s); - } - - pxa2xx_mmci_int_update(s); - break; - - case MMC_RESTO: - s->resp_tout = value & 0x7f; - break; - - case MMC_RDTO: - s->read_tout = value & 0xffff; - break; - - case MMC_BLKLEN: - s->blklen = value & 0xfff; - break; - - case MMC_NUMBLK: - s->numblk = value & 0xffff; - break; - - case MMC_PRTBUF: - if (value & PRTBUF_PRT_BUF) { - s->tx_start ^= 32; - s->tx_len = 0; - } - pxa2xx_mmci_fifo_update(s); - break; - - case MMC_I_MASK: - s->intmask = value & 0x1fff; - pxa2xx_mmci_int_update(s); - break; - - case MMC_CMD: - s->cmd = value & 0x3f; - break; - - case MMC_ARGH: - s->arg &= 0x0000ffff; - s->arg |= value << 16; - break; - - case MMC_ARGL: - s->arg &= 0xffff0000; - s->arg |= value & 0x0000ffff; - break; - - case MMC_TXFIFO: - while (size-- && s->tx_len < 0x20) - s->tx_fifo[(s->tx_start + (s->tx_len ++)) & 0x1f] = - (value >> (size << 3)) & 0xff; - s->intreq &= ~INT_TXFIFO_REQ; - pxa2xx_mmci_fifo_update(s); - break; - - case MMC_RDWAIT: - case MMC_BLKS_REM: - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: incorrect reg 0x%02" HWADDR_PRIx " " - "(value 0x%08" PRIx64 ")\n", __func__, offset, value); - } -} - -static const MemoryRegionOps pxa2xx_mmci_ops = { - .read = pxa2xx_mmci_read, - .write = pxa2xx_mmci_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -PXA2xxMMCIState *pxa2xx_mmci_init(MemoryRegion *sysmem, - hwaddr base, - qemu_irq irq, qemu_irq rx_dma, qemu_irq tx_dma) -{ - DeviceState *dev; - - dev = sysbus_create_simple(TYPE_PXA2XX_MMCI, base, irq); - qdev_connect_gpio_out_named(dev, "rx-dma", 0, rx_dma); - qdev_connect_gpio_out_named(dev, "tx-dma", 0, tx_dma); - - return PXA2XX_MMCI(dev); -} - -static void pxa2xx_mmci_set_inserted(DeviceState *dev, bool inserted) -{ - PXA2xxMMCIState *s = PXA2XX_MMCI(dev); - - qemu_set_irq(s->inserted, inserted); -} - -static void pxa2xx_mmci_set_readonly(DeviceState *dev, bool readonly) -{ - PXA2xxMMCIState *s = PXA2XX_MMCI(dev); - - qemu_set_irq(s->readonly, readonly); -} - -void pxa2xx_mmci_handlers(PXA2xxMMCIState *s, qemu_irq readonly, - qemu_irq coverswitch) -{ - DeviceState *dev = DEVICE(s); - - s->readonly = readonly; - s->inserted = coverswitch; - - pxa2xx_mmci_set_inserted(dev, sdbus_get_inserted(&s->sdbus)); - pxa2xx_mmci_set_readonly(dev, sdbus_get_readonly(&s->sdbus)); -} - -static void pxa2xx_mmci_reset(DeviceState *d) -{ - PXA2xxMMCIState *s = PXA2XX_MMCI(d); - - s->status = 0; - s->clkrt = 0; - s->spi = 0; - s->cmdat = 0; - s->resp_tout = 0; - s->read_tout = 0; - s->blklen = 0; - s->numblk = 0; - s->intmask = 0; - s->intreq = 0; - s->cmd = 0; - s->arg = 0; - s->active = 0; - s->bytesleft = 0; - s->tx_start = 0; - s->tx_len = 0; - s->rx_start = 0; - s->rx_len = 0; - s->resp_len = 0; - s->cmdreq = 0; - memset(s->tx_fifo, 0, sizeof(s->tx_fifo)); - memset(s->rx_fifo, 0, sizeof(s->rx_fifo)); - memset(s->resp_fifo, 0, sizeof(s->resp_fifo)); -} - -static void pxa2xx_mmci_instance_init(Object *obj) -{ - PXA2xxMMCIState *s = PXA2XX_MMCI(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - DeviceState *dev = DEVICE(obj); - - memory_region_init_io(&s->iomem, obj, &pxa2xx_mmci_ops, s, - "pxa2xx-mmci", 0x00100000); - sysbus_init_mmio(sbd, &s->iomem); - sysbus_init_irq(sbd, &s->irq); - qdev_init_gpio_out_named(dev, &s->rx_dma, "rx-dma", 1); - qdev_init_gpio_out_named(dev, &s->tx_dma, "tx-dma", 1); - - qbus_init(&s->sdbus, sizeof(s->sdbus), - TYPE_PXA2XX_MMCI_BUS, DEVICE(obj), "sd-bus"); -} - -static void pxa2xx_mmci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->vmsd = &vmstate_pxa2xx_mmci; - device_class_set_legacy_reset(dc, pxa2xx_mmci_reset); -} - -static void pxa2xx_mmci_bus_class_init(ObjectClass *klass, void *data) -{ - SDBusClass *sbc = SD_BUS_CLASS(klass); - - sbc->set_inserted = pxa2xx_mmci_set_inserted; - sbc->set_readonly = pxa2xx_mmci_set_readonly; -} - -static const TypeInfo pxa2xx_mmci_types[] = { - { - .name = TYPE_PXA2XX_MMCI, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PXA2xxMMCIState), - .instance_init = pxa2xx_mmci_instance_init, - .class_init = pxa2xx_mmci_class_init, - }, - { - .name = TYPE_PXA2XX_MMCI_BUS, - .parent = TYPE_SD_BUS, - .instance_size = sizeof(SDBus), - .class_init = pxa2xx_mmci_bus_class_init, - }, -}; - -DEFINE_TYPES(pxa2xx_mmci_types) diff --git a/hw/sd/meson.build b/hw/sd/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/meson.build +++ b/hw/sd/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_SDHCI_PCI', if_true: files('sdhci-pci.c')) system_ss.add(when: 'CONFIG_SSI_SD', if_true: files('ssi-sd.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_mmc.c')) -system_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_mmci.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_sdhost.c')) system_ss.add(when: 'CONFIG_ASPEED_SOC', if_true: files('aspeed_sdhci.c')) system_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-sdhost.c')) diff --git a/hw/sd/trace-events b/hw/sd/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/trace-events +++ b/hw/sd/trace-events @@ -XXX,XX +XXX,XX @@ sdcard_set_voltage(uint16_t millivolts) "%u mV" sdcard_ext_csd_update(unsigned index, uint8_t oval, uint8_t nval) "index %u: 0x%02x -> 0x%02x" sdcard_switch(unsigned access, unsigned index, unsigned value, unsigned set) "SWITCH acc:%u idx:%u val:%u set:%u" -# pxa2xx_mmci.c -pxa2xx_mmci_read(uint8_t size, uint32_t addr, uint32_t value) "size %d addr 0x%02x value 0x%08x" -pxa2xx_mmci_write(uint8_t size, uint32_t addr, uint32_t value) "size %d addr 0x%02x value 0x%08x" - # pl181.c pl181_command_send(uint8_t cmd, uint32_t arg) "sending CMD%02d arg 0x%08" PRIx32 pl181_command_sent(void) "command sent" -- 2.34.1 Remove the pxa2xx-specific pxa2xx_keypad device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-18-peter.maydell@linaro.org --- include/hw/arm/pxa.h | 12 -- hw/input/pxa2xx_keypad.c | 331 --------------------------------------- hw/input/meson.build | 1 - 3 files changed, 344 deletions(-) delete mode 100644 hw/input/pxa2xx_keypad.c diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ int pxa2xx_pcmcia_attach(void *opaque, PCMCIACardState *card); int pxa2xx_pcmcia_detach(void *opaque); void pxa2xx_pcmcia_set_irq_cb(void *opaque, qemu_irq irq, qemu_irq cd_irq); -/* pxa2xx_keypad.c */ -struct keymap { - int8_t column; - int8_t row; -}; -typedef struct PXA2xxKeyPadState PXA2xxKeyPadState; -PXA2xxKeyPadState *pxa27x_keypad_init(MemoryRegion *sysmem, - hwaddr base, - qemu_irq irq); -void pxa27x_register_keypad(PXA2xxKeyPadState *kp, - const struct keymap *map, int size); - #endif /* PXA_H */ diff --git a/hw/input/pxa2xx_keypad.c b/hw/input/pxa2xx_keypad.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/input/pxa2xx_keypad.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel PXA27X Keypad Controller emulation. - * - * Copyright (c) 2007 MontaVista Software, Inc - * Written by Armin Kuster <akuster@kama-aina.net> - * or <Akuster@mvista.com> - * - * This code is licensed under the GPLv2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "qemu/log.h" -#include "hw/irq.h" -#include "migration/vmstate.h" -#include "hw/arm/pxa.h" -#include "ui/console.h" - -/* - * Keypad - */ -#define KPC 0x00 /* Keypad Interface Control register */ -#define KPDK 0x08 /* Keypad Interface Direct Key register */ -#define KPREC 0x10 /* Keypad Interface Rotary Encoder register */ -#define KPMK 0x18 /* Keypad Interface Matrix Key register */ -#define KPAS 0x20 /* Keypad Interface Automatic Scan register */ -#define KPASMKP0 0x28 /* Keypad Interface Automatic Scan Multiple - Key Presser register 0 */ -#define KPASMKP1 0x30 /* Keypad Interface Automatic Scan Multiple - Key Presser register 1 */ -#define KPASMKP2 0x38 /* Keypad Interface Automatic Scan Multiple - Key Presser register 2 */ -#define KPASMKP3 0x40 /* Keypad Interface Automatic Scan Multiple - Key Presser register 3 */ -#define KPKDI 0x48 /* Keypad Interface Key Debounce Interval - register */ - -/* Keypad defines */ -#define KPC_AS (0x1 << 30) /* Automatic Scan bit */ -#define KPC_ASACT (0x1 << 29) /* Automatic Scan on Activity */ -#define KPC_MI (0x1 << 22) /* Matrix interrupt bit */ -#define KPC_IMKP (0x1 << 21) /* Ignore Multiple Key Press */ -#define KPC_MS7 (0x1 << 20) /* Matrix scan line 7 */ -#define KPC_MS6 (0x1 << 19) /* Matrix scan line 6 */ -#define KPC_MS5 (0x1 << 18) /* Matrix scan line 5 */ -#define KPC_MS4 (0x1 << 17) /* Matrix scan line 4 */ -#define KPC_MS3 (0x1 << 16) /* Matrix scan line 3 */ -#define KPC_MS2 (0x1 << 15) /* Matrix scan line 2 */ -#define KPC_MS1 (0x1 << 14) /* Matrix scan line 1 */ -#define KPC_MS0 (0x1 << 13) /* Matrix scan line 0 */ -#define KPC_ME (0x1 << 12) /* Matrix Keypad Enable */ -#define KPC_MIE (0x1 << 11) /* Matrix Interrupt Enable */ -#define KPC_DK_DEB_SEL (0x1 << 9) /* Direct Keypad Debounce Select */ -#define KPC_DI (0x1 << 5) /* Direct key interrupt bit */ -#define KPC_RE_ZERO_DEB (0x1 << 4) /* Rotary Encoder Zero Debounce */ -#define KPC_REE1 (0x1 << 3) /* Rotary Encoder1 Enable */ -#define KPC_REE0 (0x1 << 2) /* Rotary Encoder0 Enable */ -#define KPC_DE (0x1 << 1) /* Direct Keypad Enable */ -#define KPC_DIE (0x1 << 0) /* Direct Keypad interrupt Enable */ - -#define KPDK_DKP (0x1 << 31) -#define KPDK_DK7 (0x1 << 7) -#define KPDK_DK6 (0x1 << 6) -#define KPDK_DK5 (0x1 << 5) -#define KPDK_DK4 (0x1 << 4) -#define KPDK_DK3 (0x1 << 3) -#define KPDK_DK2 (0x1 << 2) -#define KPDK_DK1 (0x1 << 1) -#define KPDK_DK0 (0x1 << 0) - -#define KPREC_OF1 (0x1 << 31) -#define KPREC_UF1 (0x1 << 30) -#define KPREC_OF0 (0x1 << 15) -#define KPREC_UF0 (0x1 << 14) - -#define KPMK_MKP (0x1 << 31) -#define KPAS_SO (0x1 << 31) -#define KPASMKPx_SO (0x1 << 31) - - -#define KPASMKPx_MKC(row, col) (1 << (row + 16 * (col % 2))) - -#define PXAKBD_MAXROW 8 -#define PXAKBD_MAXCOL 8 - -struct PXA2xxKeyPadState { - MemoryRegion iomem; - qemu_irq irq; - const struct keymap *map; - int pressed_cnt; - int alt_code; - - uint32_t kpc; - uint32_t kpdk; - uint32_t kprec; - uint32_t kpmk; - uint32_t kpas; - uint32_t kpasmkp[4]; - uint32_t kpkdi; -}; - -static void pxa27x_keypad_find_pressed_key(PXA2xxKeyPadState *kp, int *row, int *col) -{ - int i; - for (i = 0; i < 4; i++) - { - *col = i * 2; - for (*row = 0; *row < 8; (*row)++) { - if (kp->kpasmkp[i] & (1 << *row)) - return; - } - *col = i * 2 + 1; - for (*row = 0; *row < 8; (*row)++) { - if (kp->kpasmkp[i] & (1 << (*row + 16))) - return; - } - } -} - -static void pxa27x_keyboard_event (PXA2xxKeyPadState *kp, int keycode) -{ - int row, col, rel, assert_irq = 0; - uint32_t val; - - if (keycode == 0xe0) { - kp->alt_code = 1; - return; - } - - if(!(kp->kpc & KPC_ME)) /* skip if not enabled */ - return; - - rel = (keycode & 0x80) ? 1 : 0; /* key release from qemu */ - keycode &= ~0x80; /* strip qemu key release bit */ - if (kp->alt_code) { - keycode |= 0x80; - kp->alt_code = 0; - } - - row = kp->map[keycode].row; - col = kp->map[keycode].column; - if (row == -1 || col == -1) { - return; - } - - val = KPASMKPx_MKC(row, col); - if (rel) { - if (kp->kpasmkp[col / 2] & val) { - kp->kpasmkp[col / 2] &= ~val; - kp->pressed_cnt--; - assert_irq = 1; - } - } else { - if (!(kp->kpasmkp[col / 2] & val)) { - kp->kpasmkp[col / 2] |= val; - kp->pressed_cnt++; - assert_irq = 1; - } - } - kp->kpas = ((kp->pressed_cnt & 0x1f) << 26) | (0xf << 4) | 0xf; - if (kp->pressed_cnt == 1) { - kp->kpas &= ~((0xf << 4) | 0xf); - if (rel) { - pxa27x_keypad_find_pressed_key(kp, &row, &col); - } - kp->kpas |= ((row & 0xf) << 4) | (col & 0xf); - } - - if (!(kp->kpc & (KPC_AS | KPC_ASACT))) - assert_irq = 0; - - if (assert_irq && (kp->kpc & KPC_MIE)) { - kp->kpc |= KPC_MI; - qemu_irq_raise(kp->irq); - } -} - -static uint64_t pxa2xx_keypad_read(void *opaque, hwaddr offset, - unsigned size) -{ - PXA2xxKeyPadState *s = (PXA2xxKeyPadState *) opaque; - uint32_t tmp; - - switch (offset) { - case KPC: - tmp = s->kpc; - if(tmp & KPC_MI) - s->kpc &= ~(KPC_MI); - if(tmp & KPC_DI) - s->kpc &= ~(KPC_DI); - qemu_irq_lower(s->irq); - return tmp; - case KPDK: - return s->kpdk; - case KPREC: - tmp = s->kprec; - if(tmp & KPREC_OF1) - s->kprec &= ~(KPREC_OF1); - if(tmp & KPREC_UF1) - s->kprec &= ~(KPREC_UF1); - if(tmp & KPREC_OF0) - s->kprec &= ~(KPREC_OF0); - if(tmp & KPREC_UF0) - s->kprec &= ~(KPREC_UF0); - return tmp; - case KPMK: - tmp = s->kpmk; - if(tmp & KPMK_MKP) - s->kpmk &= ~(KPMK_MKP); - return tmp; - case KPAS: - return s->kpas; - case KPASMKP0: - return s->kpasmkp[0]; - case KPASMKP1: - return s->kpasmkp[1]; - case KPASMKP2: - return s->kpasmkp[2]; - case KPASMKP3: - return s->kpasmkp[3]; - case KPKDI: - return s->kpkdi; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } - - return 0; -} - -static void pxa2xx_keypad_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PXA2xxKeyPadState *s = (PXA2xxKeyPadState *) opaque; - - switch (offset) { - case KPC: - s->kpc = value; - if (s->kpc & KPC_AS) { - s->kpc &= ~(KPC_AS); - } - break; - case KPDK: - s->kpdk = value; - break; - case KPREC: - s->kprec = value; - break; - case KPMK: - s->kpmk = value; - break; - case KPAS: - s->kpas = value; - break; - case KPASMKP0: - s->kpasmkp[0] = value; - break; - case KPASMKP1: - s->kpasmkp[1] = value; - break; - case KPASMKP2: - s->kpasmkp[2] = value; - break; - case KPASMKP3: - s->kpasmkp[3] = value; - break; - case KPKDI: - s->kpkdi = value; - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } -} - -static const MemoryRegionOps pxa2xx_keypad_ops = { - .read = pxa2xx_keypad_read, - .write = pxa2xx_keypad_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static const VMStateDescription vmstate_pxa2xx_keypad = { - .name = "pxa2xx_keypad", - .version_id = 0, - .minimum_version_id = 0, - .fields = (const VMStateField[]) { - VMSTATE_UINT32(kpc, PXA2xxKeyPadState), - VMSTATE_UINT32(kpdk, PXA2xxKeyPadState), - VMSTATE_UINT32(kprec, PXA2xxKeyPadState), - VMSTATE_UINT32(kpmk, PXA2xxKeyPadState), - VMSTATE_UINT32(kpas, PXA2xxKeyPadState), - VMSTATE_UINT32_ARRAY(kpasmkp, PXA2xxKeyPadState, 4), - VMSTATE_UINT32(kpkdi, PXA2xxKeyPadState), - VMSTATE_END_OF_LIST() - } -}; - -PXA2xxKeyPadState *pxa27x_keypad_init(MemoryRegion *sysmem, - hwaddr base, - qemu_irq irq) -{ - PXA2xxKeyPadState *s; - - s = g_new0(PXA2xxKeyPadState, 1); - s->irq = irq; - - memory_region_init_io(&s->iomem, NULL, &pxa2xx_keypad_ops, s, - "pxa2xx-keypad", 0x00100000); - memory_region_add_subregion(sysmem, base, &s->iomem); - - vmstate_register(NULL, 0, &vmstate_pxa2xx_keypad, s); - - return s; -} - -void pxa27x_register_keypad(PXA2xxKeyPadState *kp, - const struct keymap *map, int size) -{ - if(!map || size < 0x80) { - fprintf(stderr, "%s - No PXA keypad map defined\n", __func__); - exit(-1); - } - - kp->map = map; - qemu_add_kbd_event_handler((QEMUPutKBDEvent *) pxa27x_keyboard_event, kp); -} diff --git a/hw/input/meson.build b/hw/input/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/input/meson.build +++ b/hw/input/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_VIRTIO_INPUT', if_true: files('virtio-input.c')) system_ss.add(when: 'CONFIG_VIRTIO_INPUT', if_true: files('virtio-input-hid.c')) system_ss.add(when: 'CONFIG_VIRTIO_INPUT_HOST', if_true: files('virtio-input-host.c')) -system_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_keypad.c')) system_ss.add(when: 'CONFIG_TSC210X', if_true: files('tsc210x.c')) system_ss.add(when: 'CONFIG_LASIPS2', if_true: files('lasips2.c')) -- 2.34.1 Remove the pxa2xx-specific pxa2xx_lcd device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-19-peter.maydell@linaro.org --- include/hw/arm/pxa.h | 6 - hw/display/pxa2xx_lcd.c | 1451 --------------------------------------- hw/display/meson.build | 1 - 3 files changed, 1458 deletions(-) delete mode 100644 hw/display/pxa2xx_lcd.c diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ void pxa2xx_gpio_read_notifier(DeviceState *dev, qemu_irq handler); DeviceState *pxa255_dma_init(hwaddr base, qemu_irq irq); DeviceState *pxa27x_dma_init(hwaddr base, qemu_irq irq); -/* pxa2xx_lcd.c */ -typedef struct PXA2xxLCDState PXA2xxLCDState; -PXA2xxLCDState *pxa2xx_lcdc_init(MemoryRegion *sysmem, - hwaddr base, qemu_irq irq); -void pxa2xx_lcd_vsync_notifier(PXA2xxLCDState *s, qemu_irq handler); - /* pxa2xx_pcmcia.c */ #define TYPE_PXA2XX_PCMCIA "pxa2xx-pcmcia" OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxPCMCIAState, PXA2XX_PCMCIA) diff --git a/hw/display/pxa2xx_lcd.c b/hw/display/pxa2xx_lcd.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/display/pxa2xx_lcd.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel XScale PXA255/270 LCDC emulation. - * - * Copyright (c) 2006 Openedhand Ltd. - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GPLv2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "qemu/log.h" -#include "hw/irq.h" -#include "migration/vmstate.h" -#include "ui/console.h" -#include "hw/arm/pxa.h" -#include "ui/pixel_ops.h" -#include "hw/boards.h" -/* FIXME: For graphic_rotate. Should probably be done in common code. */ -#include "sysemu/sysemu.h" -#include "framebuffer.h" - -struct DMAChannel { - uint32_t branch; - uint8_t up; - uint8_t palette[1024]; - uint8_t pbuffer[1024]; - void (*redraw)(PXA2xxLCDState *s, hwaddr addr, - int *miny, int *maxy); - - uint32_t descriptor; - uint32_t source; - uint32_t id; - uint32_t command; -}; - -struct PXA2xxLCDState { - MemoryRegion *sysmem; - MemoryRegion iomem; - MemoryRegionSection fbsection; - qemu_irq irq; - int irqlevel; - - int invalidated; - QemuConsole *con; - int dest_width; - int xres, yres; - int pal_for; - int transp; - enum { - pxa_lcdc_2bpp = 1, - pxa_lcdc_4bpp = 2, - pxa_lcdc_8bpp = 3, - pxa_lcdc_16bpp = 4, - pxa_lcdc_18bpp = 5, - pxa_lcdc_18pbpp = 6, - pxa_lcdc_19bpp = 7, - pxa_lcdc_19pbpp = 8, - pxa_lcdc_24bpp = 9, - pxa_lcdc_25bpp = 10, - } bpp; - - uint32_t control[6]; - uint32_t status[2]; - uint32_t ovl1c[2]; - uint32_t ovl2c[2]; - uint32_t ccr; - uint32_t cmdcr; - uint32_t trgbr; - uint32_t tcr; - uint32_t liidr; - uint8_t bscntr; - - struct DMAChannel dma_ch[7]; - - qemu_irq vsync_cb; - int orientation; -}; - -typedef struct QEMU_PACKED { - uint32_t fdaddr; - uint32_t fsaddr; - uint32_t fidr; - uint32_t ldcmd; -} PXAFrameDescriptor; - -#define LCCR0 0x000 /* LCD Controller Control register 0 */ -#define LCCR1 0x004 /* LCD Controller Control register 1 */ -#define LCCR2 0x008 /* LCD Controller Control register 2 */ -#define LCCR3 0x00c /* LCD Controller Control register 3 */ -#define LCCR4 0x010 /* LCD Controller Control register 4 */ -#define LCCR5 0x014 /* LCD Controller Control register 5 */ - -#define FBR0 0x020 /* DMA Channel 0 Frame Branch register */ -#define FBR1 0x024 /* DMA Channel 1 Frame Branch register */ -#define FBR2 0x028 /* DMA Channel 2 Frame Branch register */ -#define FBR3 0x02c /* DMA Channel 3 Frame Branch register */ -#define FBR4 0x030 /* DMA Channel 4 Frame Branch register */ -#define FBR5 0x110 /* DMA Channel 5 Frame Branch register */ -#define FBR6 0x114 /* DMA Channel 6 Frame Branch register */ - -#define LCSR1 0x034 /* LCD Controller Status register 1 */ -#define LCSR0 0x038 /* LCD Controller Status register 0 */ -#define LIIDR 0x03c /* LCD Controller Interrupt ID register */ - -#define TRGBR 0x040 /* TMED RGB Seed register */ -#define TCR 0x044 /* TMED Control register */ - -#define OVL1C1 0x050 /* Overlay 1 Control register 1 */ -#define OVL1C2 0x060 /* Overlay 1 Control register 2 */ -#define OVL2C1 0x070 /* Overlay 2 Control register 1 */ -#define OVL2C2 0x080 /* Overlay 2 Control register 2 */ -#define CCR 0x090 /* Cursor Control register */ - -#define CMDCR 0x100 /* Command Control register */ -#define PRSR 0x104 /* Panel Read Status register */ - -#define PXA_LCDDMA_CHANS 7 -#define DMA_FDADR 0x00 /* Frame Descriptor Address register */ -#define DMA_FSADR 0x04 /* Frame Source Address register */ -#define DMA_FIDR 0x08 /* Frame ID register */ -#define DMA_LDCMD 0x0c /* Command register */ - -/* LCD Buffer Strength Control register */ -#define BSCNTR 0x04000054 - -/* Bitfield masks */ -#define LCCR0_ENB (1 << 0) -#define LCCR0_CMS (1 << 1) -#define LCCR0_SDS (1 << 2) -#define LCCR0_LDM (1 << 3) -#define LCCR0_SOFM0 (1 << 4) -#define LCCR0_IUM (1 << 5) -#define LCCR0_EOFM0 (1 << 6) -#define LCCR0_PAS (1 << 7) -#define LCCR0_DPD (1 << 9) -#define LCCR0_DIS (1 << 10) -#define LCCR0_QDM (1 << 11) -#define LCCR0_PDD (0xff << 12) -#define LCCR0_BSM0 (1 << 20) -#define LCCR0_OUM (1 << 21) -#define LCCR0_LCDT (1 << 22) -#define LCCR0_RDSTM (1 << 23) -#define LCCR0_CMDIM (1 << 24) -#define LCCR0_OUC (1 << 25) -#define LCCR0_LDDALT (1 << 26) -#define LCCR1_PPL(x) ((x) & 0x3ff) -#define LCCR2_LPP(x) ((x) & 0x3ff) -#define LCCR3_API (15 << 16) -#define LCCR3_BPP(x) ((((x) >> 24) & 7) | (((x) >> 26) & 8)) -#define LCCR3_PDFOR(x) (((x) >> 30) & 3) -#define LCCR4_K1(x) (((x) >> 0) & 7) -#define LCCR4_K2(x) (((x) >> 3) & 7) -#define LCCR4_K3(x) (((x) >> 6) & 7) -#define LCCR4_PALFOR(x) (((x) >> 15) & 3) -#define LCCR5_SOFM(ch) (1 << (ch - 1)) -#define LCCR5_EOFM(ch) (1 << (ch + 7)) -#define LCCR5_BSM(ch) (1 << (ch + 15)) -#define LCCR5_IUM(ch) (1 << (ch + 23)) -#define OVLC1_EN (1 << 31) -#define CCR_CEN (1 << 31) -#define FBR_BRA (1 << 0) -#define FBR_BINT (1 << 1) -#define FBR_SRCADDR (0xfffffff << 4) -#define LCSR0_LDD (1 << 0) -#define LCSR0_SOF0 (1 << 1) -#define LCSR0_BER (1 << 2) -#define LCSR0_ABC (1 << 3) -#define LCSR0_IU0 (1 << 4) -#define LCSR0_IU1 (1 << 5) -#define LCSR0_OU (1 << 6) -#define LCSR0_QD (1 << 7) -#define LCSR0_EOF0 (1 << 8) -#define LCSR0_BS0 (1 << 9) -#define LCSR0_SINT (1 << 10) -#define LCSR0_RDST (1 << 11) -#define LCSR0_CMDINT (1 << 12) -#define LCSR0_BERCH(x) (((x) & 7) << 28) -#define LCSR1_SOF(ch) (1 << (ch - 1)) -#define LCSR1_EOF(ch) (1 << (ch + 7)) -#define LCSR1_BS(ch) (1 << (ch + 15)) -#define LCSR1_IU(ch) (1 << (ch + 23)) -#define LDCMD_LENGTH(x) ((x) & 0x001ffffc) -#define LDCMD_EOFINT (1 << 21) -#define LDCMD_SOFINT (1 << 22) -#define LDCMD_PAL (1 << 26) - -/* Size of a pixel in the QEMU UI output surface, in bytes */ -#define DEST_PIXEL_WIDTH 4 - -/* Line drawing code to handle the various possible guest pixel formats */ - -# define SKIP_PIXEL(to) do { to += deststep; } while (0) -# define COPY_PIXEL(to, from) \ - do { \ - *(uint32_t *) to = from; \ - SKIP_PIXEL(to); \ - } while (0) - -#if HOST_BIG_ENDIAN -# define SWAP_WORDS 1 -#endif - -#define FN_2(x) FN(x + 1) FN(x) -#define FN_4(x) FN_2(x + 2) FN_2(x) - -static void pxa2xx_draw_line2(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t *palette = opaque; - uint32_t data; - while (width > 0) { - data = *(uint32_t *) src; -#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 2)) & 3]); -#ifdef SWAP_WORDS - FN_4(12) - FN_4(8) - FN_4(4) - FN_4(0) -#else - FN_4(0) - FN_4(4) - FN_4(8) - FN_4(12) -#endif -#undef FN - width -= 16; - src += 4; - } -} - -static void pxa2xx_draw_line4(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t *palette = opaque; - uint32_t data; - while (width > 0) { - data = *(uint32_t *) src; -#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 4)) & 0xf]); -#ifdef SWAP_WORDS - FN_2(6) - FN_2(4) - FN_2(2) - FN_2(0) -#else - FN_2(0) - FN_2(2) - FN_2(4) - FN_2(6) -#endif -#undef FN - width -= 8; - src += 4; - } -} - -static void pxa2xx_draw_line8(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t *palette = opaque; - uint32_t data; - while (width > 0) { - data = *(uint32_t *) src; -#define FN(x) COPY_PIXEL(dest, palette[(data >> (x)) & 0xff]); -#ifdef SWAP_WORDS - FN(24) - FN(16) - FN(8) - FN(0) -#else - FN(0) - FN(8) - FN(16) - FN(24) -#endif -#undef FN - width -= 4; - src += 4; - } -} - -static void pxa2xx_draw_line16(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x1f) << 3; - data >>= 5; - g = (data & 0x3f) << 2; - data >>= 6; - r = (data & 0x1f) << 3; - data >>= 5; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - b = (data & 0x1f) << 3; - data >>= 5; - g = (data & 0x3f) << 2; - data >>= 6; - r = (data & 0x1f) << 3; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - width -= 2; - src += 4; - } -} - -static void pxa2xx_draw_line16t(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x1f) << 3; - data >>= 5; - g = (data & 0x1f) << 3; - data >>= 5; - r = (data & 0x1f) << 3; - data >>= 5; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - data >>= 1; - b = (data & 0x1f) << 3; - data >>= 5; - g = (data & 0x1f) << 3; - data >>= 5; - r = (data & 0x1f) << 3; - data >>= 5; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 2; - src += 4; - } -} - -static void pxa2xx_draw_line18(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x3f) << 2; - data >>= 6; - g = (data & 0x3f) << 2; - data >>= 6; - r = (data & 0x3f) << 2; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - width -= 1; - src += 4; - } -} - -/* The wicked packed format */ -static void pxa2xx_draw_line18p(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data[3]; - unsigned int r, g, b; - while (width > 0) { - data[0] = *(uint32_t *) src; - src += 4; - data[1] = *(uint32_t *) src; - src += 4; - data[2] = *(uint32_t *) src; - src += 4; -#ifdef SWAP_WORDS - data[0] = bswap32(data[0]); - data[1] = bswap32(data[1]); - data[2] = bswap32(data[2]); -#endif - b = (data[0] & 0x3f) << 2; - data[0] >>= 6; - g = (data[0] & 0x3f) << 2; - data[0] >>= 6; - r = (data[0] & 0x3f) << 2; - data[0] >>= 12; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - b = (data[0] & 0x3f) << 2; - data[0] >>= 6; - g = ((data[1] & 0xf) << 4) | (data[0] << 2); - data[1] >>= 4; - r = (data[1] & 0x3f) << 2; - data[1] >>= 12; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - b = (data[1] & 0x3f) << 2; - data[1] >>= 6; - g = (data[1] & 0x3f) << 2; - data[1] >>= 6; - r = ((data[2] & 0x3) << 6) | (data[1] << 2); - data[2] >>= 8; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - b = (data[2] & 0x3f) << 2; - data[2] >>= 6; - g = (data[2] & 0x3f) << 2; - data[2] >>= 6; - r = data[2] << 2; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - width -= 4; - } -} - -static void pxa2xx_draw_line19(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x3f) << 2; - data >>= 6; - g = (data & 0x3f) << 2; - data >>= 6; - r = (data & 0x3f) << 2; - data >>= 6; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 1; - src += 4; - } -} - -/* The wicked packed format */ -static void pxa2xx_draw_line19p(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data[3]; - unsigned int r, g, b; - while (width > 0) { - data[0] = *(uint32_t *) src; - src += 4; - data[1] = *(uint32_t *) src; - src += 4; - data[2] = *(uint32_t *) src; - src += 4; -# ifdef SWAP_WORDS - data[0] = bswap32(data[0]); - data[1] = bswap32(data[1]); - data[2] = bswap32(data[2]); -# endif - b = (data[0] & 0x3f) << 2; - data[0] >>= 6; - g = (data[0] & 0x3f) << 2; - data[0] >>= 6; - r = (data[0] & 0x3f) << 2; - data[0] >>= 6; - if (data[0] & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - data[0] >>= 6; - b = (data[0] & 0x3f) << 2; - data[0] >>= 6; - g = ((data[1] & 0xf) << 4) | (data[0] << 2); - data[1] >>= 4; - r = (data[1] & 0x3f) << 2; - data[1] >>= 6; - if (data[1] & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - data[1] >>= 6; - b = (data[1] & 0x3f) << 2; - data[1] >>= 6; - g = (data[1] & 0x3f) << 2; - data[1] >>= 6; - r = ((data[2] & 0x3) << 6) | (data[1] << 2); - data[2] >>= 2; - if (data[2] & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - data[2] >>= 6; - b = (data[2] & 0x3f) << 2; - data[2] >>= 6; - g = (data[2] & 0x3f) << 2; - data[2] >>= 6; - r = data[2] << 2; - data[2] >>= 6; - if (data[2] & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 4; - } -} - -static void pxa2xx_draw_line24(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = data & 0xff; - data >>= 8; - g = data & 0xff; - data >>= 8; - r = data & 0xff; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - width -= 1; - src += 4; - } -} - -static void pxa2xx_draw_line24t(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x7f) << 1; - data >>= 7; - g = data & 0xff; - data >>= 8; - r = data & 0xff; - data >>= 8; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 1; - src += 4; - } -} - -static void pxa2xx_draw_line25(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = data & 0xff; - data >>= 8; - g = data & 0xff; - data >>= 8; - r = data & 0xff; - data >>= 8; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 1; - src += 4; - } -} - -/* Overlay planes disabled, no transparency */ -static drawfn pxa2xx_draw_fn_32[16] = { - [0 ... 0xf] = NULL, - [pxa_lcdc_2bpp] = pxa2xx_draw_line2, - [pxa_lcdc_4bpp] = pxa2xx_draw_line4, - [pxa_lcdc_8bpp] = pxa2xx_draw_line8, - [pxa_lcdc_16bpp] = pxa2xx_draw_line16, - [pxa_lcdc_18bpp] = pxa2xx_draw_line18, - [pxa_lcdc_18pbpp] = pxa2xx_draw_line18p, - [pxa_lcdc_24bpp] = pxa2xx_draw_line24, -}; - -/* Overlay planes enabled, transparency used */ -static drawfn pxa2xx_draw_fn_32t[16] = { - [0 ... 0xf] = NULL, - [pxa_lcdc_4bpp] = pxa2xx_draw_line4, - [pxa_lcdc_8bpp] = pxa2xx_draw_line8, - [pxa_lcdc_16bpp] = pxa2xx_draw_line16t, - [pxa_lcdc_19bpp] = pxa2xx_draw_line19, - [pxa_lcdc_19pbpp] = pxa2xx_draw_line19p, - [pxa_lcdc_24bpp] = pxa2xx_draw_line24t, - [pxa_lcdc_25bpp] = pxa2xx_draw_line25, -}; - -#undef COPY_PIXEL -#undef SKIP_PIXEL - -#ifdef SWAP_WORDS -# undef SWAP_WORDS -#endif - -/* Route internal interrupt lines to the global IC */ -static void pxa2xx_lcdc_int_update(PXA2xxLCDState *s) -{ - int level = 0; - level |= (s->status[0] & LCSR0_LDD) && !(s->control[0] & LCCR0_LDM); - level |= (s->status[0] & LCSR0_SOF0) && !(s->control[0] & LCCR0_SOFM0); - level |= (s->status[0] & LCSR0_IU0) && !(s->control[0] & LCCR0_IUM); - level |= (s->status[0] & LCSR0_IU1) && !(s->control[5] & LCCR5_IUM(1)); - level |= (s->status[0] & LCSR0_OU) && !(s->control[0] & LCCR0_OUM); - level |= (s->status[0] & LCSR0_QD) && !(s->control[0] & LCCR0_QDM); - level |= (s->status[0] & LCSR0_EOF0) && !(s->control[0] & LCCR0_EOFM0); - level |= (s->status[0] & LCSR0_BS0) && !(s->control[0] & LCCR0_BSM0); - level |= (s->status[0] & LCSR0_RDST) && !(s->control[0] & LCCR0_RDSTM); - level |= (s->status[0] & LCSR0_CMDINT) && !(s->control[0] & LCCR0_CMDIM); - level |= (s->status[1] & ~s->control[5]); - - qemu_set_irq(s->irq, !!level); - s->irqlevel = level; -} - -/* Set Branch Status interrupt high and poke associated registers */ -static inline void pxa2xx_dma_bs_set(PXA2xxLCDState *s, int ch) -{ - int unmasked; - if (ch == 0) { - s->status[0] |= LCSR0_BS0; - unmasked = !(s->control[0] & LCCR0_BSM0); - } else { - s->status[1] |= LCSR1_BS(ch); - unmasked = !(s->control[5] & LCCR5_BSM(ch)); - } - - if (unmasked) { - if (s->irqlevel) - s->status[0] |= LCSR0_SINT; - else - s->liidr = s->dma_ch[ch].id; - } -} - -/* Set Start Of Frame Status interrupt high and poke associated registers */ -static inline void pxa2xx_dma_sof_set(PXA2xxLCDState *s, int ch) -{ - int unmasked; - if (!(s->dma_ch[ch].command & LDCMD_SOFINT)) - return; - - if (ch == 0) { - s->status[0] |= LCSR0_SOF0; - unmasked = !(s->control[0] & LCCR0_SOFM0); - } else { - s->status[1] |= LCSR1_SOF(ch); - unmasked = !(s->control[5] & LCCR5_SOFM(ch)); - } - - if (unmasked) { - if (s->irqlevel) - s->status[0] |= LCSR0_SINT; - else - s->liidr = s->dma_ch[ch].id; - } -} - -/* Set End Of Frame Status interrupt high and poke associated registers */ -static inline void pxa2xx_dma_eof_set(PXA2xxLCDState *s, int ch) -{ - int unmasked; - if (!(s->dma_ch[ch].command & LDCMD_EOFINT)) - return; - - if (ch == 0) { - s->status[0] |= LCSR0_EOF0; - unmasked = !(s->control[0] & LCCR0_EOFM0); - } else { - s->status[1] |= LCSR1_EOF(ch); - unmasked = !(s->control[5] & LCCR5_EOFM(ch)); - } - - if (unmasked) { - if (s->irqlevel) - s->status[0] |= LCSR0_SINT; - else - s->liidr = s->dma_ch[ch].id; - } -} - -/* Set Bus Error Status interrupt high and poke associated registers */ -static inline void pxa2xx_dma_ber_set(PXA2xxLCDState *s, int ch) -{ - s->status[0] |= LCSR0_BERCH(ch) | LCSR0_BER; - if (s->irqlevel) - s->status[0] |= LCSR0_SINT; - else - s->liidr = s->dma_ch[ch].id; -} - -/* Load new Frame Descriptors from DMA */ -static void pxa2xx_descriptor_load(PXA2xxLCDState *s) -{ - PXAFrameDescriptor desc; - hwaddr descptr; - int i; - - for (i = 0; i < PXA_LCDDMA_CHANS; i ++) { - s->dma_ch[i].source = 0; - - if (!s->dma_ch[i].up) - continue; - - if (s->dma_ch[i].branch & FBR_BRA) { - descptr = s->dma_ch[i].branch & FBR_SRCADDR; - if (s->dma_ch[i].branch & FBR_BINT) - pxa2xx_dma_bs_set(s, i); - s->dma_ch[i].branch &= ~FBR_BRA; - } else - descptr = s->dma_ch[i].descriptor; - - if (!((descptr >= PXA2XX_SDRAM_BASE && descptr + - sizeof(desc) <= PXA2XX_SDRAM_BASE + current_machine->ram_size) || - (descptr >= PXA2XX_INTERNAL_BASE && descptr + sizeof(desc) <= - PXA2XX_INTERNAL_BASE + PXA2XX_INTERNAL_SIZE))) { - continue; - } - - cpu_physical_memory_read(descptr, &desc, sizeof(desc)); - s->dma_ch[i].descriptor = le32_to_cpu(desc.fdaddr); - s->dma_ch[i].source = le32_to_cpu(desc.fsaddr); - s->dma_ch[i].id = le32_to_cpu(desc.fidr); - s->dma_ch[i].command = le32_to_cpu(desc.ldcmd); - } -} - -static uint64_t pxa2xx_lcdc_read(void *opaque, hwaddr offset, - unsigned size) -{ - PXA2xxLCDState *s = (PXA2xxLCDState *) opaque; - int ch; - - switch (offset) { - case LCCR0: - return s->control[0]; - case LCCR1: - return s->control[1]; - case LCCR2: - return s->control[2]; - case LCCR3: - return s->control[3]; - case LCCR4: - return s->control[4]; - case LCCR5: - return s->control[5]; - - case OVL1C1: - return s->ovl1c[0]; - case OVL1C2: - return s->ovl1c[1]; - case OVL2C1: - return s->ovl2c[0]; - case OVL2C2: - return s->ovl2c[1]; - - case CCR: - return s->ccr; - - case CMDCR: - return s->cmdcr; - - case TRGBR: - return s->trgbr; - case TCR: - return s->tcr; - - case 0x200 ... 0x1000: /* DMA per-channel registers */ - ch = (offset - 0x200) >> 4; - if (!(ch >= 0 && ch < PXA_LCDDMA_CHANS)) - goto fail; - - switch (offset & 0xf) { - case DMA_FDADR: - return s->dma_ch[ch].descriptor; - case DMA_FSADR: - return s->dma_ch[ch].source; - case DMA_FIDR: - return s->dma_ch[ch].id; - case DMA_LDCMD: - return s->dma_ch[ch].command; - default: - goto fail; - } - - case FBR0: - return s->dma_ch[0].branch; - case FBR1: - return s->dma_ch[1].branch; - case FBR2: - return s->dma_ch[2].branch; - case FBR3: - return s->dma_ch[3].branch; - case FBR4: - return s->dma_ch[4].branch; - case FBR5: - return s->dma_ch[5].branch; - case FBR6: - return s->dma_ch[6].branch; - - case BSCNTR: - return s->bscntr; - - case PRSR: - return 0; - - case LCSR0: - return s->status[0]; - case LCSR1: - return s->status[1]; - case LIIDR: - return s->liidr; - - default: - fail: - qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIX "\n", - __func__, offset); - } - - return 0; -} - -static void pxa2xx_lcdc_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PXA2xxLCDState *s = (PXA2xxLCDState *) opaque; - int ch; - - switch (offset) { - case LCCR0: - /* ACK Quick Disable done */ - if ((s->control[0] & LCCR0_ENB) && !(value & LCCR0_ENB)) - s->status[0] |= LCSR0_QD; - - if (!(s->control[0] & LCCR0_LCDT) && (value & LCCR0_LCDT)) { - qemu_log_mask(LOG_UNIMP, - "%s: internal frame buffer unsupported\n", __func__); - } - if ((s->control[3] & LCCR3_API) && - (value & LCCR0_ENB) && !(value & LCCR0_LCDT)) - s->status[0] |= LCSR0_ABC; - - s->control[0] = value & 0x07ffffff; - pxa2xx_lcdc_int_update(s); - - s->dma_ch[0].up = !!(value & LCCR0_ENB); - s->dma_ch[1].up = (s->ovl1c[0] & OVLC1_EN) || (value & LCCR0_SDS); - break; - - case LCCR1: - s->control[1] = value; - break; - - case LCCR2: - s->control[2] = value; - break; - - case LCCR3: - s->control[3] = value & 0xefffffff; - s->bpp = LCCR3_BPP(value); - break; - - case LCCR4: - s->control[4] = value & 0x83ff81ff; - break; - - case LCCR5: - s->control[5] = value & 0x3f3f3f3f; - break; - - case OVL1C1: - if (!(s->ovl1c[0] & OVLC1_EN) && (value & OVLC1_EN)) { - qemu_log_mask(LOG_UNIMP, "%s: Overlay 1 not supported\n", __func__); - } - s->ovl1c[0] = value & 0x80ffffff; - s->dma_ch[1].up = (value & OVLC1_EN) || (s->control[0] & LCCR0_SDS); - break; - - case OVL1C2: - s->ovl1c[1] = value & 0x000fffff; - break; - - case OVL2C1: - if (!(s->ovl2c[0] & OVLC1_EN) && (value & OVLC1_EN)) { - qemu_log_mask(LOG_UNIMP, "%s: Overlay 2 not supported\n", __func__); - } - s->ovl2c[0] = value & 0x80ffffff; - s->dma_ch[2].up = !!(value & OVLC1_EN); - s->dma_ch[3].up = !!(value & OVLC1_EN); - s->dma_ch[4].up = !!(value & OVLC1_EN); - break; - - case OVL2C2: - s->ovl2c[1] = value & 0x007fffff; - break; - - case CCR: - if (!(s->ccr & CCR_CEN) && (value & CCR_CEN)) { - qemu_log_mask(LOG_UNIMP, - "%s: Hardware cursor unimplemented\n", __func__); - } - s->ccr = value & 0x81ffffe7; - s->dma_ch[5].up = !!(value & CCR_CEN); - break; - - case CMDCR: - s->cmdcr = value & 0xff; - break; - - case TRGBR: - s->trgbr = value & 0x00ffffff; - break; - - case TCR: - s->tcr = value & 0x7fff; - break; - - case 0x200 ... 0x1000: /* DMA per-channel registers */ - ch = (offset - 0x200) >> 4; - if (!(ch >= 0 && ch < PXA_LCDDMA_CHANS)) - goto fail; - - switch (offset & 0xf) { - case DMA_FDADR: - s->dma_ch[ch].descriptor = value & 0xfffffff0; - break; - - default: - goto fail; - } - break; - - case FBR0: - s->dma_ch[0].branch = value & 0xfffffff3; - break; - case FBR1: - s->dma_ch[1].branch = value & 0xfffffff3; - break; - case FBR2: - s->dma_ch[2].branch = value & 0xfffffff3; - break; - case FBR3: - s->dma_ch[3].branch = value & 0xfffffff3; - break; - case FBR4: - s->dma_ch[4].branch = value & 0xfffffff3; - break; - case FBR5: - s->dma_ch[5].branch = value & 0xfffffff3; - break; - case FBR6: - s->dma_ch[6].branch = value & 0xfffffff3; - break; - - case BSCNTR: - s->bscntr = value & 0xf; - break; - - case PRSR: - break; - - case LCSR0: - s->status[0] &= ~(value & 0xfff); - if (value & LCSR0_BER) - s->status[0] &= ~LCSR0_BERCH(7); - break; - - case LCSR1: - s->status[1] &= ~(value & 0x3e3f3f); - break; - - default: - fail: - qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIX "\n", - __func__, offset); - } -} - -static const MemoryRegionOps pxa2xx_lcdc_ops = { - .read = pxa2xx_lcdc_read, - .write = pxa2xx_lcdc_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -/* Load new palette for a given DMA channel, convert to internal format */ -static void pxa2xx_palette_parse(PXA2xxLCDState *s, int ch, int bpp) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - int i, n, format, r, g, b, alpha; - uint32_t *dest; - uint8_t *src; - s->pal_for = LCCR4_PALFOR(s->control[4]); - format = s->pal_for; - - switch (bpp) { - case pxa_lcdc_2bpp: - n = 4; - break; - case pxa_lcdc_4bpp: - n = 16; - break; - case pxa_lcdc_8bpp: - n = 256; - break; - default: - return; - } - - src = (uint8_t *) s->dma_ch[ch].pbuffer; - dest = (uint32_t *) s->dma_ch[ch].palette; - alpha = r = g = b = 0; - - for (i = 0; i < n; i ++) { - switch (format) { - case 0: /* 16 bpp, no transparency */ - alpha = 0; - if (s->control[0] & LCCR0_CMS) { - r = g = b = *(uint16_t *) src & 0xff; - } - else { - r = (*(uint16_t *) src & 0xf800) >> 8; - g = (*(uint16_t *) src & 0x07e0) >> 3; - b = (*(uint16_t *) src & 0x001f) << 3; - } - src += 2; - break; - case 1: /* 16 bpp plus transparency */ - alpha = *(uint32_t *) src & (1 << 24); - if (s->control[0] & LCCR0_CMS) - r = g = b = *(uint32_t *) src & 0xff; - else { - r = (*(uint32_t *) src & 0xf80000) >> 16; - g = (*(uint32_t *) src & 0x00fc00) >> 8; - b = (*(uint32_t *) src & 0x0000f8); - } - src += 4; - break; - case 2: /* 18 bpp plus transparency */ - alpha = *(uint32_t *) src & (1 << 24); - if (s->control[0] & LCCR0_CMS) - r = g = b = *(uint32_t *) src & 0xff; - else { - r = (*(uint32_t *) src & 0xfc0000) >> 16; - g = (*(uint32_t *) src & 0x00fc00) >> 8; - b = (*(uint32_t *) src & 0x0000fc); - } - src += 4; - break; - case 3: /* 24 bpp plus transparency */ - alpha = *(uint32_t *) src & (1 << 24); - if (s->control[0] & LCCR0_CMS) - r = g = b = *(uint32_t *) src & 0xff; - else { - r = (*(uint32_t *) src & 0xff0000) >> 16; - g = (*(uint32_t *) src & 0x00ff00) >> 8; - b = (*(uint32_t *) src & 0x0000ff); - } - src += 4; - break; - } - switch (surface_bits_per_pixel(surface)) { - case 8: - *dest = rgb_to_pixel8(r, g, b) | alpha; - break; - case 15: - *dest = rgb_to_pixel15(r, g, b) | alpha; - break; - case 16: - *dest = rgb_to_pixel16(r, g, b) | alpha; - break; - case 24: - *dest = rgb_to_pixel24(r, g, b) | alpha; - break; - case 32: - *dest = rgb_to_pixel32(r, g, b) | alpha; - break; - } - dest ++; - } -} - -static inline drawfn pxa2xx_drawfn(PXA2xxLCDState *s) -{ - if (s->transp) { - return pxa2xx_draw_fn_32t[s->bpp]; - } else { - return pxa2xx_draw_fn_32[s->bpp]; - } -} - -static void pxa2xx_lcdc_dma0_redraw_rot0(PXA2xxLCDState *s, - hwaddr addr, int *miny, int *maxy) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - int src_width, dest_width; - drawfn fn = pxa2xx_drawfn(s); - if (!fn) - return; - - src_width = (s->xres + 3) & ~3; /* Pad to a 4 pixels multiple */ - if (s->bpp == pxa_lcdc_19pbpp || s->bpp == pxa_lcdc_18pbpp) - src_width *= 3; - else if (s->bpp > pxa_lcdc_16bpp) - src_width *= 4; - else if (s->bpp > pxa_lcdc_8bpp) - src_width *= 2; - - dest_width = s->xres * DEST_PIXEL_WIDTH; - *miny = 0; - if (s->invalidated) { - framebuffer_update_memory_section(&s->fbsection, s->sysmem, - addr, s->yres, src_width); - } - framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres, - src_width, dest_width, DEST_PIXEL_WIDTH, - s->invalidated, - fn, s->dma_ch[0].palette, miny, maxy); -} - -static void pxa2xx_lcdc_dma0_redraw_rot90(PXA2xxLCDState *s, - hwaddr addr, int *miny, int *maxy) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - int src_width, dest_width; - drawfn fn = pxa2xx_drawfn(s); - if (!fn) - return; - - src_width = (s->xres + 3) & ~3; /* Pad to a 4 pixels multiple */ - if (s->bpp == pxa_lcdc_19pbpp || s->bpp == pxa_lcdc_18pbpp) - src_width *= 3; - else if (s->bpp > pxa_lcdc_16bpp) - src_width *= 4; - else if (s->bpp > pxa_lcdc_8bpp) - src_width *= 2; - - dest_width = s->yres * DEST_PIXEL_WIDTH; - *miny = 0; - if (s->invalidated) { - framebuffer_update_memory_section(&s->fbsection, s->sysmem, - addr, s->yres, src_width); - } - framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres, - src_width, DEST_PIXEL_WIDTH, -dest_width, - s->invalidated, - fn, s->dma_ch[0].palette, - miny, maxy); -} - -static void pxa2xx_lcdc_dma0_redraw_rot180(PXA2xxLCDState *s, - hwaddr addr, int *miny, int *maxy) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - int src_width, dest_width; - drawfn fn = pxa2xx_drawfn(s); - if (!fn) { - return; - } - - src_width = (s->xres + 3) & ~3; /* Pad to a 4 pixels multiple */ - if (s->bpp == pxa_lcdc_19pbpp || s->bpp == pxa_lcdc_18pbpp) { - src_width *= 3; - } else if (s->bpp > pxa_lcdc_16bpp) { - src_width *= 4; - } else if (s->bpp > pxa_lcdc_8bpp) { - src_width *= 2; - } - - dest_width = s->xres * DEST_PIXEL_WIDTH; - *miny = 0; - if (s->invalidated) { - framebuffer_update_memory_section(&s->fbsection, s->sysmem, - addr, s->yres, src_width); - } - framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres, - src_width, -dest_width, -DEST_PIXEL_WIDTH, - s->invalidated, - fn, s->dma_ch[0].palette, miny, maxy); -} - -static void pxa2xx_lcdc_dma0_redraw_rot270(PXA2xxLCDState *s, - hwaddr addr, int *miny, int *maxy) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - int src_width, dest_width; - drawfn fn = pxa2xx_drawfn(s); - if (!fn) { - return; - } - - src_width = (s->xres + 3) & ~3; /* Pad to a 4 pixels multiple */ - if (s->bpp == pxa_lcdc_19pbpp || s->bpp == pxa_lcdc_18pbpp) { - src_width *= 3; - } else if (s->bpp > pxa_lcdc_16bpp) { - src_width *= 4; - } else if (s->bpp > pxa_lcdc_8bpp) { - src_width *= 2; - } - - dest_width = s->yres * DEST_PIXEL_WIDTH; - *miny = 0; - if (s->invalidated) { - framebuffer_update_memory_section(&s->fbsection, s->sysmem, - addr, s->yres, src_width); - } - framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres, - src_width, -DEST_PIXEL_WIDTH, dest_width, - s->invalidated, - fn, s->dma_ch[0].palette, - miny, maxy); -} - -static void pxa2xx_lcdc_resize(PXA2xxLCDState *s) -{ - int width, height; - if (!(s->control[0] & LCCR0_ENB)) - return; - - width = LCCR1_PPL(s->control[1]) + 1; - height = LCCR2_LPP(s->control[2]) + 1; - - if (width != s->xres || height != s->yres) { - if (s->orientation == 90 || s->orientation == 270) { - qemu_console_resize(s->con, height, width); - } else { - qemu_console_resize(s->con, width, height); - } - s->invalidated = 1; - s->xres = width; - s->yres = height; - } -} - -static void pxa2xx_update_display(void *opaque) -{ - PXA2xxLCDState *s = (PXA2xxLCDState *) opaque; - hwaddr fbptr; - int miny, maxy; - int ch; - if (!(s->control[0] & LCCR0_ENB)) - return; - - pxa2xx_descriptor_load(s); - - pxa2xx_lcdc_resize(s); - miny = s->yres; - maxy = 0; - s->transp = s->dma_ch[2].up || s->dma_ch[3].up; - /* Note: With overlay planes the order depends on LCCR0 bit 25. */ - for (ch = 0; ch < PXA_LCDDMA_CHANS; ch ++) - if (s->dma_ch[ch].up) { - if (!s->dma_ch[ch].source) { - pxa2xx_dma_ber_set(s, ch); - continue; - } - fbptr = s->dma_ch[ch].source; - if (!((fbptr >= PXA2XX_SDRAM_BASE && - fbptr <= PXA2XX_SDRAM_BASE + current_machine->ram_size) || - (fbptr >= PXA2XX_INTERNAL_BASE && - fbptr <= PXA2XX_INTERNAL_BASE + PXA2XX_INTERNAL_SIZE))) { - pxa2xx_dma_ber_set(s, ch); - continue; - } - - if (s->dma_ch[ch].command & LDCMD_PAL) { - cpu_physical_memory_read(fbptr, s->dma_ch[ch].pbuffer, - MAX(LDCMD_LENGTH(s->dma_ch[ch].command), - sizeof(s->dma_ch[ch].pbuffer))); - pxa2xx_palette_parse(s, ch, s->bpp); - } else { - /* Do we need to reparse palette */ - if (LCCR4_PALFOR(s->control[4]) != s->pal_for) - pxa2xx_palette_parse(s, ch, s->bpp); - - /* ACK frame start */ - pxa2xx_dma_sof_set(s, ch); - - s->dma_ch[ch].redraw(s, fbptr, &miny, &maxy); - s->invalidated = 0; - - /* ACK frame completed */ - pxa2xx_dma_eof_set(s, ch); - } - } - - if (s->control[0] & LCCR0_DIS) { - /* ACK last frame completed */ - s->control[0] &= ~LCCR0_ENB; - s->status[0] |= LCSR0_LDD; - } - - if (miny >= 0) { - switch (s->orientation) { - case 0: - dpy_gfx_update(s->con, 0, miny, s->xres, maxy - miny + 1); - break; - case 90: - dpy_gfx_update(s->con, miny, 0, maxy - miny + 1, s->xres); - break; - case 180: - maxy = s->yres - maxy - 1; - miny = s->yres - miny - 1; - dpy_gfx_update(s->con, 0, maxy, s->xres, miny - maxy + 1); - break; - case 270: - maxy = s->yres - maxy - 1; - miny = s->yres - miny - 1; - dpy_gfx_update(s->con, maxy, 0, miny - maxy + 1, s->xres); - break; - } - } - pxa2xx_lcdc_int_update(s); - - qemu_irq_raise(s->vsync_cb); -} - -static void pxa2xx_invalidate_display(void *opaque) -{ - PXA2xxLCDState *s = (PXA2xxLCDState *) opaque; - s->invalidated = 1; -} - -static void pxa2xx_lcdc_orientation(void *opaque, int angle) -{ - PXA2xxLCDState *s = (PXA2xxLCDState *) opaque; - - switch (angle) { - case 0: - s->dma_ch[0].redraw = pxa2xx_lcdc_dma0_redraw_rot0; - break; - case 90: - s->dma_ch[0].redraw = pxa2xx_lcdc_dma0_redraw_rot90; - break; - case 180: - s->dma_ch[0].redraw = pxa2xx_lcdc_dma0_redraw_rot180; - break; - case 270: - s->dma_ch[0].redraw = pxa2xx_lcdc_dma0_redraw_rot270; - break; - } - - s->orientation = angle; - s->xres = s->yres = -1; - pxa2xx_lcdc_resize(s); -} - -static const VMStateDescription vmstate_dma_channel = { - .name = "dma_channel", - .version_id = 0, - .minimum_version_id = 0, - .fields = (const VMStateField[]) { - VMSTATE_UINT32(branch, struct DMAChannel), - VMSTATE_UINT8(up, struct DMAChannel), - VMSTATE_BUFFER(pbuffer, struct DMAChannel), - VMSTATE_UINT32(descriptor, struct DMAChannel), - VMSTATE_UINT32(source, struct DMAChannel), - VMSTATE_UINT32(id, struct DMAChannel), - VMSTATE_UINT32(command, struct DMAChannel), - VMSTATE_END_OF_LIST() - } -}; - -static int pxa2xx_lcdc_post_load(void *opaque, int version_id) -{ - PXA2xxLCDState *s = opaque; - - s->bpp = LCCR3_BPP(s->control[3]); - s->xres = s->yres = s->pal_for = -1; - - return 0; -} - -static const VMStateDescription vmstate_pxa2xx_lcdc = { - .name = "pxa2xx_lcdc", - .version_id = 0, - .minimum_version_id = 0, - .post_load = pxa2xx_lcdc_post_load, - .fields = (const VMStateField[]) { - VMSTATE_INT32(irqlevel, PXA2xxLCDState), - VMSTATE_INT32(transp, PXA2xxLCDState), - VMSTATE_UINT32_ARRAY(control, PXA2xxLCDState, 6), - VMSTATE_UINT32_ARRAY(status, PXA2xxLCDState, 2), - VMSTATE_UINT32_ARRAY(ovl1c, PXA2xxLCDState, 2), - VMSTATE_UINT32_ARRAY(ovl2c, PXA2xxLCDState, 2), - VMSTATE_UINT32(ccr, PXA2xxLCDState), - VMSTATE_UINT32(cmdcr, PXA2xxLCDState), - VMSTATE_UINT32(trgbr, PXA2xxLCDState), - VMSTATE_UINT32(tcr, PXA2xxLCDState), - VMSTATE_UINT32(liidr, PXA2xxLCDState), - VMSTATE_UINT8(bscntr, PXA2xxLCDState), - VMSTATE_STRUCT_ARRAY(dma_ch, PXA2xxLCDState, 7, 0, - vmstate_dma_channel, struct DMAChannel), - VMSTATE_END_OF_LIST() - } -}; - -static const GraphicHwOps pxa2xx_ops = { - .invalidate = pxa2xx_invalidate_display, - .gfx_update = pxa2xx_update_display, -}; - -PXA2xxLCDState *pxa2xx_lcdc_init(MemoryRegion *sysmem, - hwaddr base, qemu_irq irq) -{ - PXA2xxLCDState *s; - - s = g_new0(PXA2xxLCDState, 1); - s->invalidated = 1; - s->irq = irq; - s->sysmem = sysmem; - - pxa2xx_lcdc_orientation(s, graphic_rotate); - - memory_region_init_io(&s->iomem, NULL, &pxa2xx_lcdc_ops, s, - "pxa2xx-lcd-controller", 0x00100000); - memory_region_add_subregion(sysmem, base, &s->iomem); - - s->con = graphic_console_init(NULL, 0, &pxa2xx_ops, s); - - vmstate_register(NULL, 0, &vmstate_pxa2xx_lcdc, s); - - return s; -} - -void pxa2xx_lcd_vsync_notifier(PXA2xxLCDState *s, qemu_irq handler) -{ - s->vsync_cb = handler; -} diff --git a/hw/display/meson.build b/hw/display/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210_fimd.c')) system_ss.add(when: 'CONFIG_FRAMEBUFFER', if_true: files('framebuffer.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_dss.c')) -system_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_lcd.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_fb.c')) system_ss.add(when: 'CONFIG_SM501', if_true: files('sm501.c')) system_ss.add(when: 'CONFIG_TCX', if_true: files('tcx.c')) -- 2.34.1 Remove the pxa2xx-specific pxa2xx_dma device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-20-peter.maydell@linaro.org --- include/hw/arm/pxa.h | 4 - hw/dma/pxa2xx_dma.c | 591 ------------------------------------------- hw/dma/meson.build | 1 - 3 files changed, 596 deletions(-) delete mode 100644 hw/dma/pxa2xx_dma.c diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ DeviceState *pxa2xx_gpio_init(hwaddr base, ARMCPU *cpu, DeviceState *pic, int lines); void pxa2xx_gpio_read_notifier(DeviceState *dev, qemu_irq handler); -/* pxa2xx_dma.c */ -DeviceState *pxa255_dma_init(hwaddr base, qemu_irq irq); -DeviceState *pxa27x_dma_init(hwaddr base, qemu_irq irq); - /* pxa2xx_pcmcia.c */ #define TYPE_PXA2XX_PCMCIA "pxa2xx-pcmcia" OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxPCMCIAState, PXA2XX_PCMCIA) diff --git a/hw/dma/pxa2xx_dma.c b/hw/dma/pxa2xx_dma.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/dma/pxa2xx_dma.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel XScale PXA255/270 DMA controller. - * - * Copyright (c) 2006 Openedhand Ltd. - * Copyright (c) 2006 Thorsten Zitterell - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GPL. - */ - -#include "qemu/osdep.h" -#include "qemu/log.h" -#include "hw/hw.h" -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "hw/arm/pxa.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "qapi/error.h" -#include "qemu/module.h" -#include "qom/object.h" - -#define PXA255_DMA_NUM_CHANNELS 16 -#define PXA27X_DMA_NUM_CHANNELS 32 - -#define PXA2XX_DMA_NUM_REQUESTS 75 - -typedef struct { - uint32_t descr; - uint32_t src; - uint32_t dest; - uint32_t cmd; - uint32_t state; - int request; -} PXA2xxDMAChannel; - -#define TYPE_PXA2XX_DMA "pxa2xx-dma" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxDMAState, PXA2XX_DMA) - -struct PXA2xxDMAState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - qemu_irq irq; - - uint32_t stopintr; - uint32_t eorintr; - uint32_t rasintr; - uint32_t startintr; - uint32_t endintr; - - uint32_t align; - uint32_t pio; - - int channels; - PXA2xxDMAChannel *chan; - - uint8_t req[PXA2XX_DMA_NUM_REQUESTS]; - - /* Flag to avoid recursive DMA invocations. */ - int running; -}; - -#define DCSR0 0x0000 /* DMA Control / Status register for Channel 0 */ -#define DCSR31 0x007c /* DMA Control / Status register for Channel 31 */ -#define DALGN 0x00a0 /* DMA Alignment register */ -#define DPCSR 0x00a4 /* DMA Programmed I/O Control Status register */ -#define DRQSR0 0x00e0 /* DMA DREQ<0> Status register */ -#define DRQSR1 0x00e4 /* DMA DREQ<1> Status register */ -#define DRQSR2 0x00e8 /* DMA DREQ<2> Status register */ -#define DINT 0x00f0 /* DMA Interrupt register */ -#define DRCMR0 0x0100 /* Request to Channel Map register 0 */ -#define DRCMR63 0x01fc /* Request to Channel Map register 63 */ -#define D_CH0 0x0200 /* Channel 0 Descriptor start */ -#define DRCMR64 0x1100 /* Request to Channel Map register 64 */ -#define DRCMR74 0x1128 /* Request to Channel Map register 74 */ - -/* Per-channel register */ -#define DDADR 0x00 -#define DSADR 0x01 -#define DTADR 0x02 -#define DCMD 0x03 - -/* Bit-field masks */ -#define DRCMR_CHLNUM 0x1f -#define DRCMR_MAPVLD (1 << 7) -#define DDADR_STOP (1 << 0) -#define DDADR_BREN (1 << 1) -#define DCMD_LEN 0x1fff -#define DCMD_WIDTH(x) (1 << ((((x) >> 14) & 3) - 1)) -#define DCMD_SIZE(x) (4 << (((x) >> 16) & 3)) -#define DCMD_FLYBYT (1 << 19) -#define DCMD_FLYBYS (1 << 20) -#define DCMD_ENDIRQEN (1 << 21) -#define DCMD_STARTIRQEN (1 << 22) -#define DCMD_CMPEN (1 << 25) -#define DCMD_FLOWTRG (1 << 28) -#define DCMD_FLOWSRC (1 << 29) -#define DCMD_INCTRGADDR (1 << 30) -#define DCMD_INCSRCADDR (1 << 31) -#define DCSR_BUSERRINTR (1 << 0) -#define DCSR_STARTINTR (1 << 1) -#define DCSR_ENDINTR (1 << 2) -#define DCSR_STOPINTR (1 << 3) -#define DCSR_RASINTR (1 << 4) -#define DCSR_REQPEND (1 << 8) -#define DCSR_EORINT (1 << 9) -#define DCSR_CMPST (1 << 10) -#define DCSR_MASKRUN (1 << 22) -#define DCSR_RASIRQEN (1 << 23) -#define DCSR_CLRCMPST (1 << 24) -#define DCSR_SETCMPST (1 << 25) -#define DCSR_EORSTOPEN (1 << 26) -#define DCSR_EORJMPEN (1 << 27) -#define DCSR_EORIRQEN (1 << 28) -#define DCSR_STOPIRQEN (1 << 29) -#define DCSR_NODESCFETCH (1 << 30) -#define DCSR_RUN (1 << 31) - -static inline void pxa2xx_dma_update(PXA2xxDMAState *s, int ch) -{ - if (ch >= 0) { - if ((s->chan[ch].state & DCSR_STOPIRQEN) && - (s->chan[ch].state & DCSR_STOPINTR)) - s->stopintr |= 1 << ch; - else - s->stopintr &= ~(1 << ch); - - if ((s->chan[ch].state & DCSR_EORIRQEN) && - (s->chan[ch].state & DCSR_EORINT)) - s->eorintr |= 1 << ch; - else - s->eorintr &= ~(1 << ch); - - if ((s->chan[ch].state & DCSR_RASIRQEN) && - (s->chan[ch].state & DCSR_RASINTR)) - s->rasintr |= 1 << ch; - else - s->rasintr &= ~(1 << ch); - - if (s->chan[ch].state & DCSR_STARTINTR) - s->startintr |= 1 << ch; - else - s->startintr &= ~(1 << ch); - - if (s->chan[ch].state & DCSR_ENDINTR) - s->endintr |= 1 << ch; - else - s->endintr &= ~(1 << ch); - } - - if (s->stopintr | s->eorintr | s->rasintr | s->startintr | s->endintr) - qemu_irq_raise(s->irq); - else - qemu_irq_lower(s->irq); -} - -static inline void pxa2xx_dma_descriptor_fetch( - PXA2xxDMAState *s, int ch) -{ - uint32_t desc[4]; - hwaddr daddr = s->chan[ch].descr & ~0xf; - if ((s->chan[ch].descr & DDADR_BREN) && (s->chan[ch].state & DCSR_CMPST)) - daddr += 32; - - cpu_physical_memory_read(daddr, desc, 16); - s->chan[ch].descr = desc[DDADR]; - s->chan[ch].src = desc[DSADR]; - s->chan[ch].dest = desc[DTADR]; - s->chan[ch].cmd = desc[DCMD]; - - if (s->chan[ch].cmd & DCMD_FLOWSRC) - s->chan[ch].src &= ~3; - if (s->chan[ch].cmd & DCMD_FLOWTRG) - s->chan[ch].dest &= ~3; - - if (s->chan[ch].cmd & (DCMD_CMPEN | DCMD_FLYBYS | DCMD_FLYBYT)) - printf("%s: unsupported mode in channel %i\n", __func__, ch); - - if (s->chan[ch].cmd & DCMD_STARTIRQEN) - s->chan[ch].state |= DCSR_STARTINTR; -} - -static void pxa2xx_dma_run(PXA2xxDMAState *s) -{ - int c, srcinc, destinc; - uint32_t n, size; - uint32_t width; - uint32_t length; - uint8_t buffer[32]; - PXA2xxDMAChannel *ch; - - if (s->running ++) - return; - - while (s->running) { - s->running = 1; - for (c = 0; c < s->channels; c ++) { - ch = &s->chan[c]; - - while ((ch->state & DCSR_RUN) && !(ch->state & DCSR_STOPINTR)) { - /* Test for pending requests */ - if ((ch->cmd & (DCMD_FLOWSRC | DCMD_FLOWTRG)) && !ch->request) - break; - - length = ch->cmd & DCMD_LEN; - size = DCMD_SIZE(ch->cmd); - width = DCMD_WIDTH(ch->cmd); - - srcinc = (ch->cmd & DCMD_INCSRCADDR) ? width : 0; - destinc = (ch->cmd & DCMD_INCTRGADDR) ? width : 0; - - while (length) { - size = MIN(length, size); - - for (n = 0; n < size; n += width) { - cpu_physical_memory_read(ch->src, buffer + n, width); - ch->src += srcinc; - } - - for (n = 0; n < size; n += width) { - cpu_physical_memory_write(ch->dest, buffer + n, width); - ch->dest += destinc; - } - - length -= size; - - if ((ch->cmd & (DCMD_FLOWSRC | DCMD_FLOWTRG)) && - !ch->request) { - ch->state |= DCSR_EORINT; - if (ch->state & DCSR_EORSTOPEN) - ch->state |= DCSR_STOPINTR; - if ((ch->state & DCSR_EORJMPEN) && - !(ch->state & DCSR_NODESCFETCH)) - pxa2xx_dma_descriptor_fetch(s, c); - break; - } - } - - ch->cmd = (ch->cmd & ~DCMD_LEN) | length; - - /* Is the transfer complete now? */ - if (!length) { - if (ch->cmd & DCMD_ENDIRQEN) - ch->state |= DCSR_ENDINTR; - - if ((ch->state & DCSR_NODESCFETCH) || - (ch->descr & DDADR_STOP) || - (ch->state & DCSR_EORSTOPEN)) { - ch->state |= DCSR_STOPINTR; - ch->state &= ~DCSR_RUN; - - break; - } - - ch->state |= DCSR_STOPINTR; - break; - } - } - } - - s->running --; - } -} - -static uint64_t pxa2xx_dma_read(void *opaque, hwaddr offset, - unsigned size) -{ - PXA2xxDMAState *s = (PXA2xxDMAState *) opaque; - unsigned int channel; - - if (size != 4) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad access width %u\n", - __func__, size); - return 5; - } - - switch (offset) { - case DRCMR64 ... DRCMR74: - offset -= DRCMR64 - DRCMR0 - (64 << 2); - /* Fall through */ - case DRCMR0 ... DRCMR63: - channel = (offset - DRCMR0) >> 2; - return s->req[channel]; - - case DRQSR0: - case DRQSR1: - case DRQSR2: - return 0; - - case DCSR0 ... DCSR31: - channel = offset >> 2; - if (s->chan[channel].request) - return s->chan[channel].state | DCSR_REQPEND; - return s->chan[channel].state; - - case DINT: - return s->stopintr | s->eorintr | s->rasintr | - s->startintr | s->endintr; - - case DALGN: - return s->align; - - case DPCSR: - return s->pio; - } - - if (offset >= D_CH0 && offset < D_CH0 + (s->channels << 4)) { - channel = (offset - D_CH0) >> 4; - switch ((offset & 0x0f) >> 2) { - case DDADR: - return s->chan[channel].descr; - case DSADR: - return s->chan[channel].src; - case DTADR: - return s->chan[channel].dest; - case DCMD: - return s->chan[channel].cmd; - } - } - qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIX "\n", - __func__, offset); - return 7; -} - -static void pxa2xx_dma_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PXA2xxDMAState *s = (PXA2xxDMAState *) opaque; - unsigned int channel; - - if (size != 4) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad access width %u\n", - __func__, size); - return; - } - - switch (offset) { - case DRCMR64 ... DRCMR74: - offset -= DRCMR64 - DRCMR0 - (64 << 2); - /* Fall through */ - case DRCMR0 ... DRCMR63: - channel = (offset - DRCMR0) >> 2; - - if (value & DRCMR_MAPVLD) - if ((value & DRCMR_CHLNUM) > s->channels) - hw_error("%s: Bad DMA channel %i\n", - __func__, (unsigned)value & DRCMR_CHLNUM); - - s->req[channel] = value; - break; - - case DRQSR0: - case DRQSR1: - case DRQSR2: - /* Nothing to do */ - break; - - case DCSR0 ... DCSR31: - channel = offset >> 2; - s->chan[channel].state &= 0x0000071f & ~(value & - (DCSR_EORINT | DCSR_ENDINTR | - DCSR_STARTINTR | DCSR_BUSERRINTR)); - s->chan[channel].state |= value & 0xfc800000; - - if (s->chan[channel].state & DCSR_STOPIRQEN) - s->chan[channel].state &= ~DCSR_STOPINTR; - - if (value & DCSR_NODESCFETCH) { - /* No-descriptor-fetch mode */ - if (value & DCSR_RUN) { - s->chan[channel].state &= ~DCSR_STOPINTR; - pxa2xx_dma_run(s); - } - } else { - /* Descriptor-fetch mode */ - if (value & DCSR_RUN) { - s->chan[channel].state &= ~DCSR_STOPINTR; - pxa2xx_dma_descriptor_fetch(s, channel); - pxa2xx_dma_run(s); - } - } - - /* Shouldn't matter as our DMA is synchronous. */ - if (!(value & (DCSR_RUN | DCSR_MASKRUN))) - s->chan[channel].state |= DCSR_STOPINTR; - - if (value & DCSR_CLRCMPST) - s->chan[channel].state &= ~DCSR_CMPST; - if (value & DCSR_SETCMPST) - s->chan[channel].state |= DCSR_CMPST; - - pxa2xx_dma_update(s, channel); - break; - - case DALGN: - s->align = value; - break; - - case DPCSR: - s->pio = value & 0x80000001; - break; - - default: - if (offset >= D_CH0 && offset < D_CH0 + (s->channels << 4)) { - channel = (offset - D_CH0) >> 4; - switch ((offset & 0x0f) >> 2) { - case DDADR: - s->chan[channel].descr = value; - break; - case DSADR: - s->chan[channel].src = value; - break; - case DTADR: - s->chan[channel].dest = value; - break; - case DCMD: - s->chan[channel].cmd = value; - break; - default: - goto fail; - } - - break; - } - fail: - qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIX "\n", - __func__, offset); - } -} - -static const MemoryRegionOps pxa2xx_dma_ops = { - .read = pxa2xx_dma_read, - .write = pxa2xx_dma_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void pxa2xx_dma_request(void *opaque, int req_num, int on) -{ - PXA2xxDMAState *s = opaque; - int ch; - if (req_num < 0 || req_num >= PXA2XX_DMA_NUM_REQUESTS) - hw_error("%s: Bad DMA request %i\n", __func__, req_num); - - if (!(s->req[req_num] & DRCMR_MAPVLD)) - return; - ch = s->req[req_num] & DRCMR_CHLNUM; - - if (!s->chan[ch].request && on) - s->chan[ch].state |= DCSR_RASINTR; - else - s->chan[ch].state &= ~DCSR_RASINTR; - if (s->chan[ch].request && !on) - s->chan[ch].state |= DCSR_EORINT; - - s->chan[ch].request = on; - if (on) { - pxa2xx_dma_run(s); - pxa2xx_dma_update(s, ch); - } -} - -static void pxa2xx_dma_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - PXA2xxDMAState *s = PXA2XX_DMA(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - memset(s->req, 0, sizeof(uint8_t) * PXA2XX_DMA_NUM_REQUESTS); - - qdev_init_gpio_in(dev, pxa2xx_dma_request, PXA2XX_DMA_NUM_REQUESTS); - - memory_region_init_io(&s->iomem, obj, &pxa2xx_dma_ops, s, - "pxa2xx.dma", 0x00010000); - sysbus_init_mmio(sbd, &s->iomem); - sysbus_init_irq(sbd, &s->irq); -} - -static void pxa2xx_dma_realize(DeviceState *dev, Error **errp) -{ - PXA2xxDMAState *s = PXA2XX_DMA(dev); - int i; - - if (s->channels <= 0) { - error_setg(errp, "channels value invalid"); - return; - } - - s->chan = g_new0(PXA2xxDMAChannel, s->channels); - - for (i = 0; i < s->channels; i ++) - s->chan[i].state = DCSR_STOPINTR; -} - -DeviceState *pxa27x_dma_init(hwaddr base, qemu_irq irq) -{ - DeviceState *dev; - - dev = qdev_new("pxa2xx-dma"); - qdev_prop_set_int32(dev, "channels", PXA27X_DMA_NUM_CHANNELS); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq); - - return dev; -} - -DeviceState *pxa255_dma_init(hwaddr base, qemu_irq irq) -{ - DeviceState *dev; - - dev = qdev_new("pxa2xx-dma"); - qdev_prop_set_int32(dev, "channels", PXA27X_DMA_NUM_CHANNELS); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq); - - return dev; -} - -static bool is_version_0(void *opaque, int version_id) -{ - return version_id == 0; -} - -static const VMStateDescription vmstate_pxa2xx_dma_chan = { - .name = "pxa2xx_dma_chan", - .version_id = 1, - .minimum_version_id = 1, - .fields = (const VMStateField[]) { - VMSTATE_UINT32(descr, PXA2xxDMAChannel), - VMSTATE_UINT32(src, PXA2xxDMAChannel), - VMSTATE_UINT32(dest, PXA2xxDMAChannel), - VMSTATE_UINT32(cmd, PXA2xxDMAChannel), - VMSTATE_UINT32(state, PXA2xxDMAChannel), - VMSTATE_INT32(request, PXA2xxDMAChannel), - VMSTATE_END_OF_LIST(), - }, -}; - -static const VMStateDescription vmstate_pxa2xx_dma = { - .name = "pxa2xx_dma", - .version_id = 1, - .minimum_version_id = 0, - .fields = (const VMStateField[]) { - VMSTATE_UNUSED_TEST(is_version_0, 4), - VMSTATE_UINT32(stopintr, PXA2xxDMAState), - VMSTATE_UINT32(eorintr, PXA2xxDMAState), - VMSTATE_UINT32(rasintr, PXA2xxDMAState), - VMSTATE_UINT32(startintr, PXA2xxDMAState), - VMSTATE_UINT32(endintr, PXA2xxDMAState), - VMSTATE_UINT32(align, PXA2xxDMAState), - VMSTATE_UINT32(pio, PXA2xxDMAState), - VMSTATE_BUFFER(req, PXA2xxDMAState), - VMSTATE_STRUCT_VARRAY_POINTER_INT32(chan, PXA2xxDMAState, channels, - vmstate_pxa2xx_dma_chan, PXA2xxDMAChannel), - VMSTATE_END_OF_LIST(), - }, -}; - -static Property pxa2xx_dma_properties[] = { - DEFINE_PROP_INT32("channels", PXA2xxDMAState, channels, -1), - DEFINE_PROP_END_OF_LIST(), -}; - -static void pxa2xx_dma_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->desc = "PXA2xx DMA controller"; - dc->vmsd = &vmstate_pxa2xx_dma; - device_class_set_props(dc, pxa2xx_dma_properties); - dc->realize = pxa2xx_dma_realize; -} - -static const TypeInfo pxa2xx_dma_info = { - .name = TYPE_PXA2XX_DMA, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PXA2xxDMAState), - .instance_init = pxa2xx_dma_init, - .class_init = pxa2xx_dma_class_init, -}; - -static void pxa2xx_dma_register_types(void) -{ - type_register_static(&pxa2xx_dma_info); -} - -type_init(pxa2xx_dma_register_types) diff --git a/hw/dma/meson.build b/hw/dma/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/meson.build +++ b/hw/dma/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_STP2000', if_true: files('sparc32_dma.c')) system_ss.add(when: 'CONFIG_XLNX_ZYNQMP_ARM', if_true: files('xlnx_dpdma.c')) system_ss.add(when: 'CONFIG_XLNX_ZDMA', if_true: files('xlnx-zdma.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_dma.c', 'soc_dma.c')) -system_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_dma.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_dma.c')) system_ss.add(when: 'CONFIG_SIFIVE_PDMA', if_true: files('sifive_pdma.c')) system_ss.add(when: 'CONFIG_XLNX_CSU_DMA', if_true: files('xlnx_csu_dma.c')) -- 2.34.1 Remove the pxa2xx specific pcmcia device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-21-peter.maydell@linaro.org --- include/hw/arm/pxa.h | 8 -- hw/pcmcia/pxa2xx.c | 248 ------------------------------------------ hw/pcmcia/meson.build | 1 - 3 files changed, 257 deletions(-) delete mode 100644 hw/pcmcia/pxa2xx.c diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ DeviceState *pxa2xx_gpio_init(hwaddr base, ARMCPU *cpu, DeviceState *pic, int lines); void pxa2xx_gpio_read_notifier(DeviceState *dev, qemu_irq handler); -/* pxa2xx_pcmcia.c */ -#define TYPE_PXA2XX_PCMCIA "pxa2xx-pcmcia" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxPCMCIAState, PXA2XX_PCMCIA) - -int pxa2xx_pcmcia_attach(void *opaque, PCMCIACardState *card); -int pxa2xx_pcmcia_detach(void *opaque); -void pxa2xx_pcmcia_set_irq_cb(void *opaque, qemu_irq irq, qemu_irq cd_irq); - #endif /* PXA_H */ diff --git a/hw/pcmcia/pxa2xx.c b/hw/pcmcia/pxa2xx.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/pcmcia/pxa2xx.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel XScale PXA255/270 PC Card and CompactFlash Interface. - * - * Copyright (c) 2006 Openedhand Ltd. - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GPLv2. - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "qapi/error.h" -#include "qemu/module.h" -#include "hw/pcmcia.h" -#include "hw/arm/pxa.h" - -struct PXA2xxPCMCIAState { - SysBusDevice parent_obj; - - PCMCIASocket slot; - MemoryRegion container_mem; - MemoryRegion common_iomem; - MemoryRegion attr_iomem; - MemoryRegion iomem; - - qemu_irq irq; - qemu_irq cd_irq; - - PCMCIACardState *card; -}; - -static uint64_t pxa2xx_pcmcia_common_read(void *opaque, - hwaddr offset, unsigned size) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - PCMCIACardClass *pcc; - - if (s->slot.attached) { - pcc = PCMCIA_CARD_GET_CLASS(s->card); - return pcc->common_read(s->card, offset); - } - - return 0; -} - -static void pxa2xx_pcmcia_common_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - PCMCIACardClass *pcc; - - if (s->slot.attached) { - pcc = PCMCIA_CARD_GET_CLASS(s->card); - pcc->common_write(s->card, offset, value); - } -} - -static uint64_t pxa2xx_pcmcia_attr_read(void *opaque, - hwaddr offset, unsigned size) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - PCMCIACardClass *pcc; - - if (s->slot.attached) { - pcc = PCMCIA_CARD_GET_CLASS(s->card); - return pcc->attr_read(s->card, offset); - } - - return 0; -} - -static void pxa2xx_pcmcia_attr_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - PCMCIACardClass *pcc; - - if (s->slot.attached) { - pcc = PCMCIA_CARD_GET_CLASS(s->card); - pcc->attr_write(s->card, offset, value); - } -} - -static uint64_t pxa2xx_pcmcia_io_read(void *opaque, - hwaddr offset, unsigned size) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - PCMCIACardClass *pcc; - - if (s->slot.attached) { - pcc = PCMCIA_CARD_GET_CLASS(s->card); - return pcc->io_read(s->card, offset); - } - - return 0; -} - -static void pxa2xx_pcmcia_io_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - PCMCIACardClass *pcc; - - if (s->slot.attached) { - pcc = PCMCIA_CARD_GET_CLASS(s->card); - pcc->io_write(s->card, offset, value); - } -} - -static const MemoryRegionOps pxa2xx_pcmcia_common_ops = { - .read = pxa2xx_pcmcia_common_read, - .write = pxa2xx_pcmcia_common_write, - .endianness = DEVICE_NATIVE_ENDIAN -}; - -static const MemoryRegionOps pxa2xx_pcmcia_attr_ops = { - .read = pxa2xx_pcmcia_attr_read, - .write = pxa2xx_pcmcia_attr_write, - .endianness = DEVICE_NATIVE_ENDIAN -}; - -static const MemoryRegionOps pxa2xx_pcmcia_io_ops = { - .read = pxa2xx_pcmcia_io_read, - .write = pxa2xx_pcmcia_io_write, - .endianness = DEVICE_NATIVE_ENDIAN -}; - -static void pxa2xx_pcmcia_set_irq(void *opaque, int line, int level) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - if (!s->irq) - return; - - qemu_set_irq(s->irq, level); -} - -static void pxa2xx_pcmcia_initfn(Object *obj) -{ - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - PXA2xxPCMCIAState *s = PXA2XX_PCMCIA(obj); - - memory_region_init(&s->container_mem, obj, "container", 0x10000000); - sysbus_init_mmio(sbd, &s->container_mem); - - /* Socket I/O Memory Space */ - memory_region_init_io(&s->iomem, obj, &pxa2xx_pcmcia_io_ops, s, - "pxa2xx-pcmcia-io", 0x04000000); - memory_region_add_subregion(&s->container_mem, 0x00000000, - &s->iomem); - - /* Then next 64 MB is reserved */ - - /* Socket Attribute Memory Space */ - memory_region_init_io(&s->attr_iomem, obj, &pxa2xx_pcmcia_attr_ops, s, - "pxa2xx-pcmcia-attribute", 0x04000000); - memory_region_add_subregion(&s->container_mem, 0x08000000, - &s->attr_iomem); - - /* Socket Common Memory Space */ - memory_region_init_io(&s->common_iomem, obj, &pxa2xx_pcmcia_common_ops, s, - "pxa2xx-pcmcia-common", 0x04000000); - memory_region_add_subregion(&s->container_mem, 0x0c000000, - &s->common_iomem); - - s->slot.irq = qemu_allocate_irq(pxa2xx_pcmcia_set_irq, s, 0); - - object_property_add_link(obj, "card", TYPE_PCMCIA_CARD, - (Object **)&s->card, - NULL, /* read-only property */ - 0); -} - -/* Insert a new card into a slot */ -int pxa2xx_pcmcia_attach(void *opaque, PCMCIACardState *card) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - PCMCIACardClass *pcc; - - if (s->slot.attached) { - return -EEXIST; - } - - if (s->cd_irq) { - qemu_irq_raise(s->cd_irq); - } - - s->card = card; - pcc = PCMCIA_CARD_GET_CLASS(s->card); - - s->slot.attached = true; - s->card->slot = &s->slot; - pcc->attach(s->card); - - return 0; -} - -/* Eject card from the slot */ -int pxa2xx_pcmcia_detach(void *opaque) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - PCMCIACardClass *pcc; - - if (!s->slot.attached) { - return -ENOENT; - } - - pcc = PCMCIA_CARD_GET_CLASS(s->card); - pcc->detach(s->card); - s->card->slot = NULL; - s->card = NULL; - - s->slot.attached = false; - - if (s->irq) { - qemu_irq_lower(s->irq); - } - if (s->cd_irq) { - qemu_irq_lower(s->cd_irq); - } - - return 0; -} - -/* Who to notify on card events */ -void pxa2xx_pcmcia_set_irq_cb(void *opaque, qemu_irq irq, qemu_irq cd_irq) -{ - PXA2xxPCMCIAState *s = (PXA2xxPCMCIAState *) opaque; - s->irq = irq; - s->cd_irq = cd_irq; -} - -static const TypeInfo pxa2xx_pcmcia_type_info = { - .name = TYPE_PXA2XX_PCMCIA, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PXA2xxPCMCIAState), - .instance_init = pxa2xx_pcmcia_initfn, -}; - -static void pxa2xx_pcmcia_register_types(void) -{ - type_register_static(&pxa2xx_pcmcia_type_info); -} - -type_init(pxa2xx_pcmcia_register_types) diff --git a/hw/pcmcia/meson.build b/hw/pcmcia/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/pcmcia/meson.build +++ b/hw/pcmcia/meson.build @@ -1,2 +1 @@ system_ss.add(when: 'CONFIG_PCMCIA', if_true: files('pcmcia.c')) -system_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx.c')) -- 2.34.1 Remove the pxa2xx-specific GPIO device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-22-peter.maydell@linaro.org --- include/hw/arm/pxa.h | 5 - hw/arm/pxa2xx_gpio.c | 365 ------------------------------------------- hw/arm/meson.build | 2 +- 3 files changed, 1 insertion(+), 371 deletions(-) delete mode 100644 hw/arm/pxa2xx_gpio.c diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ /* pxa2xx_pic.c */ DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu); -/* pxa2xx_gpio.c */ -DeviceState *pxa2xx_gpio_init(hwaddr base, - ARMCPU *cpu, DeviceState *pic, int lines); -void pxa2xx_gpio_read_notifier(DeviceState *dev, qemu_irq handler); - #endif /* PXA_H */ diff --git a/hw/arm/pxa2xx_gpio.c b/hw/arm/pxa2xx_gpio.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/pxa2xx_gpio.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel XScale PXA255/270 GPIO controller emulation. - * - * Copyright (c) 2006 Openedhand Ltd. - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GPL. - */ - -#include "qemu/osdep.h" -#include "cpu.h" -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "hw/arm/pxa.h" -#include "qapi/error.h" -#include "qemu/log.h" -#include "qemu/module.h" -#include "qom/object.h" - -#define PXA2XX_GPIO_BANKS 4 - -#define TYPE_PXA2XX_GPIO "pxa2xx-gpio" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxGPIOInfo, PXA2XX_GPIO) - -struct PXA2xxGPIOInfo { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - MemoryRegion iomem; - qemu_irq irq0, irq1, irqX; - int lines; - ARMCPU *cpu; - - /* XXX: GNU C vectors are more suitable */ - uint32_t ilevel[PXA2XX_GPIO_BANKS]; - uint32_t olevel[PXA2XX_GPIO_BANKS]; - uint32_t dir[PXA2XX_GPIO_BANKS]; - uint32_t rising[PXA2XX_GPIO_BANKS]; - uint32_t falling[PXA2XX_GPIO_BANKS]; - uint32_t status[PXA2XX_GPIO_BANKS]; - uint32_t gafr[PXA2XX_GPIO_BANKS * 2]; - - uint32_t prev_level[PXA2XX_GPIO_BANKS]; - qemu_irq handler[PXA2XX_GPIO_BANKS * 32]; - qemu_irq read_notify; -}; - -static struct { - enum { - GPIO_NONE, - GPLR, - GPSR, - GPCR, - GPDR, - GRER, - GFER, - GEDR, - GAFR_L, - GAFR_U, - } reg; - int bank; -} pxa2xx_gpio_regs[0x200] = { - [0 ... 0x1ff] = { GPIO_NONE, 0 }, -#define PXA2XX_REG(reg, a0, a1, a2, a3) \ - [a0] = { reg, 0 }, [a1] = { reg, 1 }, [a2] = { reg, 2 }, [a3] = { reg, 3 }, - - PXA2XX_REG(GPLR, 0x000, 0x004, 0x008, 0x100) - PXA2XX_REG(GPSR, 0x018, 0x01c, 0x020, 0x118) - PXA2XX_REG(GPCR, 0x024, 0x028, 0x02c, 0x124) - PXA2XX_REG(GPDR, 0x00c, 0x010, 0x014, 0x10c) - PXA2XX_REG(GRER, 0x030, 0x034, 0x038, 0x130) - PXA2XX_REG(GFER, 0x03c, 0x040, 0x044, 0x13c) - PXA2XX_REG(GEDR, 0x048, 0x04c, 0x050, 0x148) - PXA2XX_REG(GAFR_L, 0x054, 0x05c, 0x064, 0x06c) - PXA2XX_REG(GAFR_U, 0x058, 0x060, 0x068, 0x070) -}; - -static void pxa2xx_gpio_irq_update(PXA2xxGPIOInfo *s) -{ - if (s->status[0] & (1 << 0)) - qemu_irq_raise(s->irq0); - else - qemu_irq_lower(s->irq0); - - if (s->status[0] & (1 << 1)) - qemu_irq_raise(s->irq1); - else - qemu_irq_lower(s->irq1); - - if ((s->status[0] & ~3) | s->status[1] | s->status[2] | s->status[3]) - qemu_irq_raise(s->irqX); - else - qemu_irq_lower(s->irqX); -} - -/* Bitmap of pins used as standby and sleep wake-up sources. */ -static const int pxa2xx_gpio_wake[PXA2XX_GPIO_BANKS] = { - 0x8003fe1b, 0x002001fc, 0xec080000, 0x0012007f, -}; - -static void pxa2xx_gpio_set(void *opaque, int line, int level) -{ - PXA2xxGPIOInfo *s = (PXA2xxGPIOInfo *) opaque; - CPUState *cpu = CPU(s->cpu); - int bank; - uint32_t mask; - - if (line >= s->lines) { - printf("%s: No GPIO pin %i\n", __func__, line); - return; - } - - bank = line >> 5; - mask = 1U << (line & 31); - - if (level) { - s->status[bank] |= s->rising[bank] & mask & - ~s->ilevel[bank] & ~s->dir[bank]; - s->ilevel[bank] |= mask; - } else { - s->status[bank] |= s->falling[bank] & mask & - s->ilevel[bank] & ~s->dir[bank]; - s->ilevel[bank] &= ~mask; - } - - if (s->status[bank] & mask) - pxa2xx_gpio_irq_update(s); - - /* Wake-up GPIOs */ - if (cpu->halted && (mask & ~s->dir[bank] & pxa2xx_gpio_wake[bank])) { - cpu_interrupt(cpu, CPU_INTERRUPT_EXITTB); - } -} - -static void pxa2xx_gpio_handler_update(PXA2xxGPIOInfo *s) { - uint32_t level, diff; - int i, bit, line; - for (i = 0; i < PXA2XX_GPIO_BANKS; i ++) { - level = s->olevel[i] & s->dir[i]; - - for (diff = s->prev_level[i] ^ level; diff; diff ^= 1 << bit) { - bit = ctz32(diff); - line = bit + 32 * i; - qemu_set_irq(s->handler[line], (level >> bit) & 1); - } - - s->prev_level[i] = level; - } -} - -static uint64_t pxa2xx_gpio_read(void *opaque, hwaddr offset, - unsigned size) -{ - PXA2xxGPIOInfo *s = (PXA2xxGPIOInfo *) opaque; - uint32_t ret; - int bank; - if (offset >= 0x200) - return 0; - - bank = pxa2xx_gpio_regs[offset].bank; - switch (pxa2xx_gpio_regs[offset].reg) { - case GPDR: /* GPIO Pin-Direction registers */ - return s->dir[bank]; - - case GPSR: /* GPIO Pin-Output Set registers */ - qemu_log_mask(LOG_GUEST_ERROR, - "pxa2xx GPIO: read from write only register GPSR\n"); - return 0; - - case GPCR: /* GPIO Pin-Output Clear registers */ - qemu_log_mask(LOG_GUEST_ERROR, - "pxa2xx GPIO: read from write only register GPCR\n"); - return 0; - - case GRER: /* GPIO Rising-Edge Detect Enable registers */ - return s->rising[bank]; - - case GFER: /* GPIO Falling-Edge Detect Enable registers */ - return s->falling[bank]; - - case GAFR_L: /* GPIO Alternate Function registers */ - return s->gafr[bank * 2]; - - case GAFR_U: /* GPIO Alternate Function registers */ - return s->gafr[bank * 2 + 1]; - - case GPLR: /* GPIO Pin-Level registers */ - ret = (s->olevel[bank] & s->dir[bank]) | - (s->ilevel[bank] & ~s->dir[bank]); - qemu_irq_raise(s->read_notify); - return ret; - - case GEDR: /* GPIO Edge Detect Status registers */ - return s->status[bank]; - - default: - qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIX "\n", - __func__, offset); - } - - return 0; -} - -static void pxa2xx_gpio_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PXA2xxGPIOInfo *s = (PXA2xxGPIOInfo *) opaque; - int bank; - if (offset >= 0x200) - return; - - bank = pxa2xx_gpio_regs[offset].bank; - switch (pxa2xx_gpio_regs[offset].reg) { - case GPDR: /* GPIO Pin-Direction registers */ - s->dir[bank] = value; - pxa2xx_gpio_handler_update(s); - break; - - case GPSR: /* GPIO Pin-Output Set registers */ - s->olevel[bank] |= value; - pxa2xx_gpio_handler_update(s); - break; - - case GPCR: /* GPIO Pin-Output Clear registers */ - s->olevel[bank] &= ~value; - pxa2xx_gpio_handler_update(s); - break; - - case GRER: /* GPIO Rising-Edge Detect Enable registers */ - s->rising[bank] = value; - break; - - case GFER: /* GPIO Falling-Edge Detect Enable registers */ - s->falling[bank] = value; - break; - - case GAFR_L: /* GPIO Alternate Function registers */ - s->gafr[bank * 2] = value; - break; - - case GAFR_U: /* GPIO Alternate Function registers */ - s->gafr[bank * 2 + 1] = value; - break; - - case GEDR: /* GPIO Edge Detect Status registers */ - s->status[bank] &= ~value; - pxa2xx_gpio_irq_update(s); - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIX "\n", - __func__, offset); - } -} - -static const MemoryRegionOps pxa_gpio_ops = { - .read = pxa2xx_gpio_read, - .write = pxa2xx_gpio_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -DeviceState *pxa2xx_gpio_init(hwaddr base, - ARMCPU *cpu, DeviceState *pic, int lines) -{ - DeviceState *dev; - - dev = qdev_new(TYPE_PXA2XX_GPIO); - qdev_prop_set_int32(dev, "lines", lines); - object_property_set_link(OBJECT(dev), "cpu", OBJECT(cpu), &error_abort); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, - qdev_get_gpio_in(pic, PXA2XX_PIC_GPIO_0)); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 1, - qdev_get_gpio_in(pic, PXA2XX_PIC_GPIO_1)); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 2, - qdev_get_gpio_in(pic, PXA2XX_PIC_GPIO_X)); - - return dev; -} - -static void pxa2xx_gpio_initfn(Object *obj) -{ - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - DeviceState *dev = DEVICE(sbd); - PXA2xxGPIOInfo *s = PXA2XX_GPIO(dev); - - memory_region_init_io(&s->iomem, obj, &pxa_gpio_ops, - s, "pxa2xx-gpio", 0x1000); - sysbus_init_mmio(sbd, &s->iomem); - sysbus_init_irq(sbd, &s->irq0); - sysbus_init_irq(sbd, &s->irq1); - sysbus_init_irq(sbd, &s->irqX); -} - -static void pxa2xx_gpio_realize(DeviceState *dev, Error **errp) -{ - PXA2xxGPIOInfo *s = PXA2XX_GPIO(dev); - - qdev_init_gpio_in(dev, pxa2xx_gpio_set, s->lines); - qdev_init_gpio_out(dev, s->handler, s->lines); -} - -/* - * Registers a callback to notify on GPLR reads. This normally - * shouldn't be needed but it is used for the hack on Spitz machines. - */ -void pxa2xx_gpio_read_notifier(DeviceState *dev, qemu_irq handler) -{ - PXA2xxGPIOInfo *s = PXA2XX_GPIO(dev); - - s->read_notify = handler; -} - -static const VMStateDescription vmstate_pxa2xx_gpio_regs = { - .name = "pxa2xx-gpio", - .version_id = 1, - .minimum_version_id = 1, - .fields = (const VMStateField[]) { - VMSTATE_UINT32_ARRAY(ilevel, PXA2xxGPIOInfo, PXA2XX_GPIO_BANKS), - VMSTATE_UINT32_ARRAY(olevel, PXA2xxGPIOInfo, PXA2XX_GPIO_BANKS), - VMSTATE_UINT32_ARRAY(dir, PXA2xxGPIOInfo, PXA2XX_GPIO_BANKS), - VMSTATE_UINT32_ARRAY(rising, PXA2xxGPIOInfo, PXA2XX_GPIO_BANKS), - VMSTATE_UINT32_ARRAY(falling, PXA2xxGPIOInfo, PXA2XX_GPIO_BANKS), - VMSTATE_UINT32_ARRAY(status, PXA2xxGPIOInfo, PXA2XX_GPIO_BANKS), - VMSTATE_UINT32_ARRAY(gafr, PXA2xxGPIOInfo, PXA2XX_GPIO_BANKS * 2), - VMSTATE_UINT32_ARRAY(prev_level, PXA2xxGPIOInfo, PXA2XX_GPIO_BANKS), - VMSTATE_END_OF_LIST(), - }, -}; - -static Property pxa2xx_gpio_properties[] = { - DEFINE_PROP_INT32("lines", PXA2xxGPIOInfo, lines, 0), - DEFINE_PROP_LINK("cpu", PXA2xxGPIOInfo, cpu, TYPE_ARM_CPU, ARMCPU *), - DEFINE_PROP_END_OF_LIST(), -}; - -static void pxa2xx_gpio_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->desc = "PXA2xx GPIO controller"; - device_class_set_props(dc, pxa2xx_gpio_properties); - dc->vmsd = &vmstate_pxa2xx_gpio_regs; - dc->realize = pxa2xx_gpio_realize; -} - -static const TypeInfo pxa2xx_gpio_info = { - .name = TYPE_PXA2XX_GPIO, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PXA2xxGPIOInfo), - .instance_init = pxa2xx_gpio_initfn, - .class_init = pxa2xx_gpio_class_init, -}; - -static void pxa2xx_gpio_register_types(void) -{ - type_register_static(&pxa2xx_gpio_info); -} - -type_init(pxa2xx_gpio_register_types) diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_SABRELITE', if_true: files('sabrelite.c')) arm_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m.c')) arm_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210.c')) -arm_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_gpio.c', 'pxa2xx_pic.c')) +arm_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_pic.c')) arm_ss.add(when: 'CONFIG_DIGIC', if_true: files('digic.c')) arm_ss.add(when: 'CONFIG_OMAP', if_true: files('omap1.c')) arm_ss.add(when: 'CONFIG_ALLWINNER_A10', if_true: files('allwinner-a10.c', 'cubieboard.c')) -- 2.34.1 Remove the pxa2xx-specific interrupt controller device. As this is the last user of the pxa.h header file and the CONFIG_PXA2XX define we can remove those too. This completes the removal of the pxa2xx specific code. We leave: * pxa2xx_timer -- still used by the Collie board (strongarm) * the definitions of the CPUs themselves in target/arm (still usable by linux-user mode) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-23-peter.maydell@linaro.org --- MAINTAINERS | 10 -- include/hw/arm/pxa.h | 74 --------- hw/arm/pxa2xx_pic.c | 359 ------------------------------------------- hw/arm/Kconfig | 11 -- hw/arm/meson.build | 1 - 5 files changed, 455 deletions(-) delete mode 100644 include/hw/arm/pxa.h delete mode 100644 hw/arm/pxa2xx_pic.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/intc/realview_gic.c F: include/hw/intc/realview_gic.h F: docs/system/arm/realview.rst -PXA2XX -M: Peter Maydell <peter.maydell@linaro.org> -L: qemu-arm@nongnu.org -S: Odd Fixes -F: hw/*/pxa2xx* -F: hw/gpio/max7310.c -F: hw/adc/max111x.c -F: include/hw/adc/max111x.h -F: include/hw/arm/pxa.h - SABRELITE / i.MX6 M: Peter Maydell <peter.maydell@linaro.org> R: Jean-Christophe Dubois <jcd@tribudubois.net> diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/hw/arm/pxa.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel XScale PXA255/270 processor support. - * - * Copyright (c) 2006 Openedhand Ltd. - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GNU GPL v2. - */ - -#ifndef PXA_H -#define PXA_H - -#include "exec/memory.h" -#include "target/arm/cpu-qom.h" -#include "hw/pcmcia.h" -#include "qom/object.h" - -/* Interrupt numbers */ -# define PXA2XX_PIC_SSP3 0 -# define PXA2XX_PIC_USBH2 2 -# define PXA2XX_PIC_USBH1 3 -# define PXA2XX_PIC_KEYPAD 4 -# define PXA2XX_PIC_PWRI2C 6 -# define PXA25X_PIC_HWUART 7 -# define PXA27X_PIC_OST_4_11 7 -# define PXA2XX_PIC_GPIO_0 8 -# define PXA2XX_PIC_GPIO_1 9 -# define PXA2XX_PIC_GPIO_X 10 -# define PXA2XX_PIC_I2S 13 -# define PXA26X_PIC_ASSP 15 -# define PXA25X_PIC_NSSP 16 -# define PXA27X_PIC_SSP2 16 -# define PXA2XX_PIC_LCD 17 -# define PXA2XX_PIC_I2C 18 -# define PXA2XX_PIC_ICP 19 -# define PXA2XX_PIC_STUART 20 -# define PXA2XX_PIC_BTUART 21 -# define PXA2XX_PIC_FFUART 22 -# define PXA2XX_PIC_MMC 23 -# define PXA2XX_PIC_SSP 24 -# define PXA2XX_PIC_DMA 25 -# define PXA2XX_PIC_OST_0 26 -# define PXA2XX_PIC_RTC1HZ 30 -# define PXA2XX_PIC_RTCALARM 31 - -/* DMA requests */ -# define PXA2XX_RX_RQ_I2S 2 -# define PXA2XX_TX_RQ_I2S 3 -# define PXA2XX_RX_RQ_BTUART 4 -# define PXA2XX_TX_RQ_BTUART 5 -# define PXA2XX_RX_RQ_FFUART 6 -# define PXA2XX_TX_RQ_FFUART 7 -# define PXA2XX_RX_RQ_SSP1 13 -# define PXA2XX_TX_RQ_SSP1 14 -# define PXA2XX_RX_RQ_SSP2 15 -# define PXA2XX_TX_RQ_SSP2 16 -# define PXA2XX_RX_RQ_ICP 17 -# define PXA2XX_TX_RQ_ICP 18 -# define PXA2XX_RX_RQ_STUART 19 -# define PXA2XX_TX_RQ_STUART 20 -# define PXA2XX_RX_RQ_MMCI 21 -# define PXA2XX_TX_RQ_MMCI 22 -# define PXA2XX_USB_RQ(x) ((x) + 24) -# define PXA2XX_RX_RQ_SSP3 66 -# define PXA2XX_TX_RQ_SSP3 67 - -# define PXA2XX_SDRAM_BASE 0xa0000000 -# define PXA2XX_INTERNAL_BASE 0x5c000000 -# define PXA2XX_INTERNAL_SIZE 0x40000 - -/* pxa2xx_pic.c */ -DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu); - -#endif /* PXA_H */ diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/pxa2xx_pic.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel XScale PXA Programmable Interrupt Controller. - * - * Copyright (c) 2006 Openedhand Ltd. - * Copyright (c) 2006 Thorsten Zitterell - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GPL. - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "qemu/module.h" -#include "qemu/log.h" -#include "cpu.h" -#include "hw/arm/pxa.h" -#include "hw/sysbus.h" -#include "hw/qdev-properties.h" -#include "migration/vmstate.h" -#include "qom/object.h" -#include "target/arm/cpregs.h" - -#define ICIP 0x00 /* Interrupt Controller IRQ Pending register */ -#define ICMR 0x04 /* Interrupt Controller Mask register */ -#define ICLR 0x08 /* Interrupt Controller Level register */ -#define ICFP 0x0c /* Interrupt Controller FIQ Pending register */ -#define ICPR 0x10 /* Interrupt Controller Pending register */ -#define ICCR 0x14 /* Interrupt Controller Control register */ -#define ICHP 0x18 /* Interrupt Controller Highest Priority register */ -#define IPR0 0x1c /* Interrupt Controller Priority register 0 */ -#define IPR31 0x98 /* Interrupt Controller Priority register 31 */ -#define ICIP2 0x9c /* Interrupt Controller IRQ Pending register 2 */ -#define ICMR2 0xa0 /* Interrupt Controller Mask register 2 */ -#define ICLR2 0xa4 /* Interrupt Controller Level register 2 */ -#define ICFP2 0xa8 /* Interrupt Controller FIQ Pending register 2 */ -#define ICPR2 0xac /* Interrupt Controller Pending register 2 */ -#define IPR32 0xb0 /* Interrupt Controller Priority register 32 */ -#define IPR39 0xcc /* Interrupt Controller Priority register 39 */ - -#define PXA2XX_PIC_SRCS 40 - -#define TYPE_PXA2XX_PIC "pxa2xx_pic" -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxPICState, PXA2XX_PIC) - -struct PXA2xxPICState { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - MemoryRegion iomem; - ARMCPU *cpu; - uint32_t int_enabled[2]; - uint32_t int_pending[2]; - uint32_t is_fiq[2]; - uint32_t int_idle; - uint32_t priority[PXA2XX_PIC_SRCS]; -}; - -static void pxa2xx_pic_update(void *opaque) -{ - uint32_t mask[2]; - PXA2xxPICState *s = (PXA2xxPICState *) opaque; - CPUState *cpu = CPU(s->cpu); - - if (cpu->halted) { - mask[0] = s->int_pending[0] & (s->int_enabled[0] | s->int_idle); - mask[1] = s->int_pending[1] & (s->int_enabled[1] | s->int_idle); - if (mask[0] || mask[1]) { - cpu_interrupt(cpu, CPU_INTERRUPT_EXITTB); - } - } - - mask[0] = s->int_pending[0] & s->int_enabled[0]; - mask[1] = s->int_pending[1] & s->int_enabled[1]; - - if ((mask[0] & s->is_fiq[0]) || (mask[1] & s->is_fiq[1])) { - cpu_interrupt(cpu, CPU_INTERRUPT_FIQ); - } else { - cpu_reset_interrupt(cpu, CPU_INTERRUPT_FIQ); - } - - if ((mask[0] & ~s->is_fiq[0]) || (mask[1] & ~s->is_fiq[1])) { - cpu_interrupt(cpu, CPU_INTERRUPT_HARD); - } else { - cpu_reset_interrupt(cpu, CPU_INTERRUPT_HARD); - } -} - -/* Note: Here level means state of the signal on a pin, not - * IRQ/FIQ distinction as in PXA Developer Manual. */ -static void pxa2xx_pic_set_irq(void *opaque, int irq, int level) -{ - PXA2xxPICState *s = (PXA2xxPICState *) opaque; - int int_set = (irq >= 32); - irq &= 31; - - if (level) - s->int_pending[int_set] |= 1 << irq; - else - s->int_pending[int_set] &= ~(1 << irq); - - pxa2xx_pic_update(opaque); -} - -static inline uint32_t pxa2xx_pic_highest(PXA2xxPICState *s) { - int i, int_set, irq; - uint32_t bit, mask[2]; - uint32_t ichp = 0x003f003f; /* Both IDs invalid */ - - mask[0] = s->int_pending[0] & s->int_enabled[0]; - mask[1] = s->int_pending[1] & s->int_enabled[1]; - - for (i = PXA2XX_PIC_SRCS - 1; i >= 0; i --) { - irq = s->priority[i] & 0x3f; - if ((s->priority[i] & (1U << 31)) && irq < PXA2XX_PIC_SRCS) { - /* Source peripheral ID is valid. */ - bit = 1 << (irq & 31); - int_set = (irq >= 32); - - if (mask[int_set] & bit & s->is_fiq[int_set]) { - /* FIQ asserted */ - ichp &= 0xffff0000; - ichp |= (1 << 15) | irq; - } - - if (mask[int_set] & bit & ~s->is_fiq[int_set]) { - /* IRQ asserted */ - ichp &= 0x0000ffff; - ichp |= (1U << 31) | (irq << 16); - } - } - } - - return ichp; -} - -static uint64_t pxa2xx_pic_mem_read(void *opaque, hwaddr offset, - unsigned size) -{ - PXA2xxPICState *s = (PXA2xxPICState *) opaque; - - switch (offset) { - case ICIP: /* IRQ Pending register */ - return s->int_pending[0] & ~s->is_fiq[0] & s->int_enabled[0]; - case ICIP2: /* IRQ Pending register 2 */ - return s->int_pending[1] & ~s->is_fiq[1] & s->int_enabled[1]; - case ICMR: /* Mask register */ - return s->int_enabled[0]; - case ICMR2: /* Mask register 2 */ - return s->int_enabled[1]; - case ICLR: /* Level register */ - return s->is_fiq[0]; - case ICLR2: /* Level register 2 */ - return s->is_fiq[1]; - case ICCR: /* Idle mask */ - return (s->int_idle == 0); - case ICFP: /* FIQ Pending register */ - return s->int_pending[0] & s->is_fiq[0] & s->int_enabled[0]; - case ICFP2: /* FIQ Pending register 2 */ - return s->int_pending[1] & s->is_fiq[1] & s->int_enabled[1]; - case ICPR: /* Pending register */ - return s->int_pending[0]; - case ICPR2: /* Pending register 2 */ - return s->int_pending[1]; - case IPR0 ... IPR31: - return s->priority[0 + ((offset - IPR0 ) >> 2)]; - case IPR32 ... IPR39: - return s->priority[32 + ((offset - IPR32) >> 2)]; - case ICHP: /* Highest Priority register */ - return pxa2xx_pic_highest(s); - default: - qemu_log_mask(LOG_GUEST_ERROR, - "pxa2xx_pic_mem_read: bad register offset 0x%" HWADDR_PRIx - "\n", offset); - return 0; - } -} - -static void pxa2xx_pic_mem_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PXA2xxPICState *s = (PXA2xxPICState *) opaque; - - switch (offset) { - case ICMR: /* Mask register */ - s->int_enabled[0] = value; - break; - case ICMR2: /* Mask register 2 */ - s->int_enabled[1] = value; - break; - case ICLR: /* Level register */ - s->is_fiq[0] = value; - break; - case ICLR2: /* Level register 2 */ - s->is_fiq[1] = value; - break; - case ICCR: /* Idle mask */ - s->int_idle = (value & 1) ? 0 : ~0; - break; - case IPR0 ... IPR31: - s->priority[0 + ((offset - IPR0 ) >> 2)] = value & 0x8000003f; - break; - case IPR32 ... IPR39: - s->priority[32 + ((offset - IPR32) >> 2)] = value & 0x8000003f; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "pxa2xx_pic_mem_write: bad register offset 0x%" - HWADDR_PRIx "\n", offset); - return; - } - pxa2xx_pic_update(opaque); -} - -/* Interrupt Controller Coprocessor Space Register Mapping */ -static const int pxa2xx_cp_reg_map[0x10] = { - [0x0 ... 0xf] = -1, - [0x0] = ICIP, - [0x1] = ICMR, - [0x2] = ICLR, - [0x3] = ICFP, - [0x4] = ICPR, - [0x5] = ICHP, - [0x6] = ICIP2, - [0x7] = ICMR2, - [0x8] = ICLR2, - [0x9] = ICFP2, - [0xa] = ICPR2, -}; - -static uint64_t pxa2xx_pic_cp_read(CPUARMState *env, const ARMCPRegInfo *ri) -{ - int offset = pxa2xx_cp_reg_map[ri->crn]; - return pxa2xx_pic_mem_read(ri->opaque, offset, 4); -} - -static void pxa2xx_pic_cp_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - int offset = pxa2xx_cp_reg_map[ri->crn]; - pxa2xx_pic_mem_write(ri->opaque, offset, value, 4); -} - -#define REGINFO_FOR_PIC_CP(NAME, CRN) \ - { .name = NAME, .cp = 6, .crn = CRN, .crm = 0, .opc1 = 0, .opc2 = 0, \ - .access = PL1_RW, .type = ARM_CP_IO, \ - .readfn = pxa2xx_pic_cp_read, .writefn = pxa2xx_pic_cp_write } - -static const ARMCPRegInfo pxa_pic_cp_reginfo[] = { - REGINFO_FOR_PIC_CP("ICIP", 0), - REGINFO_FOR_PIC_CP("ICMR", 1), - REGINFO_FOR_PIC_CP("ICLR", 2), - REGINFO_FOR_PIC_CP("ICFP", 3), - REGINFO_FOR_PIC_CP("ICPR", 4), - REGINFO_FOR_PIC_CP("ICHP", 5), - REGINFO_FOR_PIC_CP("ICIP2", 6), - REGINFO_FOR_PIC_CP("ICMR2", 7), - REGINFO_FOR_PIC_CP("ICLR2", 8), - REGINFO_FOR_PIC_CP("ICFP2", 9), - REGINFO_FOR_PIC_CP("ICPR2", 0xa), -}; - -static const MemoryRegionOps pxa2xx_pic_ops = { - .read = pxa2xx_pic_mem_read, - .write = pxa2xx_pic_mem_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static int pxa2xx_pic_post_load(void *opaque, int version_id) -{ - pxa2xx_pic_update(opaque); - return 0; -} - -static void pxa2xx_pic_reset_hold(Object *obj, ResetType type) -{ - PXA2xxPICState *s = PXA2XX_PIC(obj); - - s->int_pending[0] = 0; - s->int_pending[1] = 0; - s->int_enabled[0] = 0; - s->int_enabled[1] = 0; - s->is_fiq[0] = 0; - s->is_fiq[1] = 0; -} - -DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) -{ - DeviceState *dev = qdev_new(TYPE_PXA2XX_PIC); - - object_property_set_link(OBJECT(dev), "arm-cpu", - OBJECT(cpu), &error_abort); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - - return dev; -} - -static void pxa2xx_pic_realize(DeviceState *dev, Error **errp) -{ - PXA2xxPICState *s = PXA2XX_PIC(dev); - - qdev_init_gpio_in(dev, pxa2xx_pic_set_irq, PXA2XX_PIC_SRCS); - - /* Enable IC memory-mapped registers access. */ - memory_region_init_io(&s->iomem, OBJECT(s), &pxa2xx_pic_ops, s, - "pxa2xx-pic", 0x00100000); - sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); - - /* Enable IC coprocessor access. */ - define_arm_cp_regs_with_opaque(s->cpu, pxa_pic_cp_reginfo, s); -} - -static const VMStateDescription vmstate_pxa2xx_pic_regs = { - .name = "pxa2xx_pic", - .version_id = 0, - .minimum_version_id = 0, - .post_load = pxa2xx_pic_post_load, - .fields = (const VMStateField[]) { - VMSTATE_UINT32_ARRAY(int_enabled, PXA2xxPICState, 2), - VMSTATE_UINT32_ARRAY(int_pending, PXA2xxPICState, 2), - VMSTATE_UINT32_ARRAY(is_fiq, PXA2xxPICState, 2), - VMSTATE_UINT32(int_idle, PXA2xxPICState), - VMSTATE_UINT32_ARRAY(priority, PXA2xxPICState, PXA2XX_PIC_SRCS), - VMSTATE_END_OF_LIST(), - }, -}; - -static Property pxa2xx_pic_properties[] = { - DEFINE_PROP_LINK("arm-cpu", PXA2xxPICState, cpu, - TYPE_ARM_CPU, ARMCPU *), - DEFINE_PROP_END_OF_LIST(), -}; - -static void pxa2xx_pic_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - ResettableClass *rc = RESETTABLE_CLASS(klass); - - device_class_set_props(dc, pxa2xx_pic_properties); - dc->realize = pxa2xx_pic_realize; - dc->desc = "PXA2xx PIC"; - dc->vmsd = &vmstate_pxa2xx_pic_regs; - rc->phases.hold = pxa2xx_pic_reset_hold; -} - -static const TypeInfo pxa2xx_pic_info = { - .name = TYPE_PXA2XX_PIC, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PXA2xxPICState), - .class_init = pxa2xx_pic_class_init, -}; - -static void pxa2xx_pic_register_types(void) -{ - type_register_static(&pxa2xx_pic_info); -} - -type_init(pxa2xx_pic_register_types) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config OMAP select SD select SERIAL -config PXA2XX - bool - select FRAMEBUFFER - select I2C - select SERIAL - select SD - select SSI - select USB_OHCI_SYSBUS - select PCMCIA - select PXA2XX_TIMER - config REALVIEW bool default y diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_SABRELITE', if_true: files('sabrelite.c')) arm_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m.c')) arm_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210.c')) -arm_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_pic.c')) arm_ss.add(when: 'CONFIG_DIGIC', if_true: files('digic.c')) arm_ss.add(when: 'CONFIG_OMAP', if_true: files('omap1.c')) arm_ss.add(when: 'CONFIG_ALLWINNER_A10', if_true: files('allwinner-a10.c', 'cubieboard.c')) -- 2.34.1 The pxa27x-timer can be removed now we have removed the PXA2xx SoC models. The pxa25x-timer device must remain as it is still used by strongarm. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-24-peter.maydell@linaro.org --- hw/timer/pxa2xx_timer.c | 24 ------------------------ 1 file changed, 24 deletions(-) diff --git a/hw/timer/pxa2xx_timer.c b/hw/timer/pxa2xx_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/pxa2xx_timer.c +++ b/hw/timer/pxa2xx_timer.c @@ -XXX,XX +XXX,XX @@ #define OSNR 0x20 #define PXA25X_FREQ 3686400 /* 3.6864 MHz */ -#define PXA27X_FREQ 3250000 /* 3.25 MHz */ static int pxa2xx_timer4_freq[8] = { [0] = 0, @@ -XXX,XX +XXX,XX @@ static const TypeInfo pxa25x_timer_dev_info = { .class_init = pxa25x_timer_dev_class_init, }; -static Property pxa27x_timer_dev_properties[] = { - DEFINE_PROP_UINT32("freq", PXA2xxTimerInfo, freq, PXA27X_FREQ), - DEFINE_PROP_BIT("tm4", PXA2xxTimerInfo, flags, - PXA2XX_TIMER_HAVE_TM4, true), - DEFINE_PROP_END_OF_LIST(), -}; - -static void pxa27x_timer_dev_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->desc = "PXA27x timer"; - device_class_set_props(dc, pxa27x_timer_dev_properties); -} - -static const TypeInfo pxa27x_timer_dev_info = { - .name = "pxa27x-timer", - .parent = TYPE_PXA2XX_TIMER, - .instance_size = sizeof(PXA2xxTimerInfo), - .class_init = pxa27x_timer_dev_class_init, -}; - static void pxa2xx_timer_class_init(ObjectClass *oc, void *data) { DeviceClass *dc = DEVICE_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static void pxa2xx_timer_register_types(void) { type_register_static(&pxa2xx_timer_type_info); type_register_static(&pxa25x_timer_dev_info); - type_register_static(&pxa27x_timer_dev_info); } type_init(pxa2xx_timer_register_types) -- 2.34.1 Remove the 'n800' and 'n810' machine types, which modelled Nokia internet tablets. These were deprecated in 9.0 and so we can remove them for 9.2. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-26-peter.maydell@linaro.org [PMM: added removal of arm-n800-machine.c post-review] --- MAINTAINERS | 3 - docs/system/arm/nseries.rst | 33 - docs/system/target-arm.rst | 1 - configs/devices/arm-softmmu/default.mak | 1 - hw/arm/nseries.c | 1473 ----------------------- tests/qtest/libqos/arm-n800-machine.c | 92 -- hw/arm/meson.build | 1 - tests/avocado/machine_arm_n8x0.py | 49 - tests/qtest/libqos/meson.build | 1 - 9 files changed, 1654 deletions(-) delete mode 100644 docs/system/arm/nseries.rst delete mode 100644 hw/arm/nseries.c delete mode 100644 tests/qtest/libqos/arm-n800-machine.c delete mode 100755 tests/avocado/machine_arm_n8x0.py diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ nSeries M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes -F: hw/arm/nseries.c F: hw/display/blizzard.c F: hw/input/lm832x.c F: hw/input/tsc2005.c @@ -XXX,XX +XXX,XX @@ F: include/hw/display/blizzard.h F: include/hw/input/lm832x.h F: include/hw/input/tsc2xxx.h F: include/hw/misc/cbus.h -F: tests/avocado/machine_arm_n8x0.py -F: docs/system/arm/nseries.rst Raspberry Pi M: Peter Maydell <peter.maydell@linaro.org> diff --git a/docs/system/arm/nseries.rst b/docs/system/arm/nseries.rst deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/system/arm/nseries.rst +++ /dev/null @@ -XXX,XX +XXX,XX @@ -Nokia N800 and N810 tablets (``n800``, ``n810``) -================================================ - -Nokia N800 and N810 internet tablets (known also as RX-34 and RX-44 / -48) emulation supports the following elements: - -- Texas Instruments OMAP2420 System-on-chip (ARM1136 core) - -- RAM and non-volatile OneNAND Flash memories - -- Display connected to EPSON remote framebuffer chip and OMAP on-chip - display controller and a LS041y3 MIPI DBI-C controller - -- TI TSC2301 (in N800) and TI TSC2005 (in N810) touchscreen - controllers driven through SPI bus - -- National Semiconductor LM8323-controlled qwerty keyboard driven - through |I2C| bus - -- Secure Digital card connected to OMAP MMC/SD host - -- Three OMAP on-chip UARTs and on-chip STI debugging console - -- Mentor Graphics \"Inventra\" dual-role USB controller embedded in a - TI TUSB6010 chip - only USB host mode is supported - -- TI TMP105 temperature sensor driven through |I2C| bus - -- TI TWL92230C power management companion with an RTC on - |I2C| bus - -- Nokia RETU and TAHVO multi-purpose chips with an RTC, connected - through CBUS diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/emcraft-sf2 arm/musicpal arm/kzm - arm/nseries arm/nrf arm/nuvoton arm/imx25-pdk diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ # CONFIG_MPS3R=n # CONFIG_MUSCA=n # CONFIG_SX1=n -# CONFIG_NSERIES=n # CONFIG_STELLARIS=n # CONFIG_STM32VLDISCOVERY=n # CONFIG_B_L475E_IOT01A=n diff --git a/hw/arm/nseries.c b/hw/arm/nseries.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/nseries.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Nokia N-series internet tablets. - * - * Copyright (C) 2007 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "cpu.h" -#include "chardev/char.h" -#include "qemu/cutils.h" -#include "qemu/bswap.h" -#include "qemu/hw-version.h" -#include "sysemu/reset.h" -#include "sysemu/runstate.h" -#include "sysemu/sysemu.h" -#include "hw/arm/omap.h" -#include "hw/arm/boot.h" -#include "hw/irq.h" -#include "ui/console.h" -#include "hw/boards.h" -#include "hw/i2c/i2c.h" -#include "hw/display/blizzard.h" -#include "hw/input/lm832x.h" -#include "hw/input/tsc2xxx.h" -#include "hw/misc/cbus.h" -#include "hw/sensor/tmp105.h" -#include "hw/qdev-properties.h" -#include "hw/block/flash.h" -#include "hw/hw.h" -#include "hw/loader.h" -#include "hw/sysbus.h" -#include "qemu/log.h" -#include "qemu/error-report.h" - - -/* Nokia N8x0 support */ -struct n800_s { - struct omap_mpu_state_s *mpu; - - struct rfbi_chip_s blizzard; - struct { - void *opaque; - uint32_t (*txrx)(void *opaque, uint32_t value, int len); - uWireSlave *chip; - } ts; - - int keymap[0x80]; - DeviceState *kbd; - - DeviceState *usb; - void *retu; - void *tahvo; - DeviceState *nand; -}; - -/* GPIO pins */ -#define N8X0_TUSB_ENABLE_GPIO 0 -#define N800_MMC2_WP_GPIO 8 -#define N800_UNKNOWN_GPIO0 9 /* out */ -#define N810_MMC2_VIOSD_GPIO 9 -#define N810_HEADSET_AMP_GPIO 10 -#define N800_CAM_TURN_GPIO 12 -#define N810_GPS_RESET_GPIO 12 -#define N800_BLIZZARD_POWERDOWN_GPIO 15 -#define N800_MMC1_WP_GPIO 23 -#define N810_MMC2_VSD_GPIO 23 -#define N8X0_ONENAND_GPIO 26 -#define N810_BLIZZARD_RESET_GPIO 30 -#define N800_UNKNOWN_GPIO2 53 /* out */ -#define N8X0_TUSB_INT_GPIO 58 -#define N8X0_BT_WKUP_GPIO 61 -#define N8X0_STI_GPIO 62 -#define N8X0_CBUS_SEL_GPIO 64 -#define N8X0_CBUS_DAT_GPIO 65 -#define N8X0_CBUS_CLK_GPIO 66 -#define N8X0_WLAN_IRQ_GPIO 87 -#define N8X0_BT_RESET_GPIO 92 -#define N8X0_TEA5761_CS_GPIO 93 -#define N800_UNKNOWN_GPIO 94 -#define N810_TSC_RESET_GPIO 94 -#define N800_CAM_ACT_GPIO 95 -#define N810_GPS_WAKEUP_GPIO 95 -#define N8X0_MMC_CS_GPIO 96 -#define N8X0_WLAN_PWR_GPIO 97 -#define N8X0_BT_HOST_WKUP_GPIO 98 -#define N810_SPEAKER_AMP_GPIO 101 -#define N810_KB_LOCK_GPIO 102 -#define N800_TSC_TS_GPIO 103 -#define N810_TSC_TS_GPIO 106 -#define N8X0_HEADPHONE_GPIO 107 -#define N8X0_RETU_GPIO 108 -#define N800_TSC_KP_IRQ_GPIO 109 -#define N810_KEYBOARD_GPIO 109 -#define N800_BAT_COVER_GPIO 110 -#define N810_SLIDE_GPIO 110 -#define N8X0_TAHVO_GPIO 111 -#define N800_UNKNOWN_GPIO4 112 /* out */ -#define N810_SLEEPX_LED_GPIO 112 -#define N800_TSC_RESET_GPIO 118 /* ? */ -#define N810_AIC33_RESET_GPIO 118 -#define N800_TSC_UNKNOWN_GPIO 119 /* out */ -#define N8X0_TMP105_GPIO 125 - -/* Config */ -#define BT_UART 0 -#define XLDR_LL_UART 1 - -/* Addresses on the I2C bus 0 */ -#define N810_TLV320AIC33_ADDR 0x18 /* Audio CODEC */ -#define N8X0_TCM825x_ADDR 0x29 /* Camera */ -#define N810_LP5521_ADDR 0x32 /* LEDs */ -#define N810_TSL2563_ADDR 0x3d /* Light sensor */ -#define N810_LM8323_ADDR 0x45 /* Keyboard */ -/* Addresses on the I2C bus 1 */ -#define N8X0_TMP105_ADDR 0x48 /* Temperature sensor */ -#define N8X0_MENELAUS_ADDR 0x72 /* Power management */ - -/* Chipselects on GPMC NOR interface */ -#define N8X0_ONENAND_CS 0 -#define N8X0_USB_ASYNC_CS 1 -#define N8X0_USB_SYNC_CS 4 - -#define N8X0_BD_ADDR 0x00, 0x1a, 0x89, 0x9e, 0x3e, 0x81 - -static void n800_mmc_cs_cb(void *opaque, int line, int level) -{ - /* TODO: this seems to actually be connected to the menelaus, to - * which also both MMC slots connect. */ - omap_mmc_enable((struct omap_mmc_s *) opaque, !level); -} - -static void n8x0_gpio_setup(struct n800_s *s) -{ - qdev_connect_gpio_out(s->mpu->gpio, N8X0_MMC_CS_GPIO, - qemu_allocate_irq(n800_mmc_cs_cb, s->mpu->mmc, 0)); - qemu_irq_lower(qdev_get_gpio_in(s->mpu->gpio, N800_BAT_COVER_GPIO)); -} - -#define MAEMO_CAL_HEADER(...) \ - 'C', 'o', 'n', 'F', 0x02, 0x00, 0x04, 0x00, \ - __VA_ARGS__, \ - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - -static const uint8_t n8x0_cal_wlan_mac[] = { - MAEMO_CAL_HEADER('w', 'l', 'a', 'n', '-', 'm', 'a', 'c') - 0x1c, 0x00, 0x00, 0x00, 0x47, 0xd6, 0x69, 0xb3, - 0x30, 0x08, 0xa0, 0x83, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, 0x1a, 0x00, 0x00, 0x00, - 0x89, 0x00, 0x00, 0x00, 0x9e, 0x00, 0x00, 0x00, - 0x5d, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, -}; - -static const uint8_t n8x0_cal_bt_id[] = { - MAEMO_CAL_HEADER('b', 't', '-', 'i', 'd', 0, 0, 0) - 0x0a, 0x00, 0x00, 0x00, 0xa3, 0x4b, 0xf6, 0x96, - 0xa8, 0xeb, 0xb2, 0x41, 0x00, 0x00, 0x00, 0x00, - N8X0_BD_ADDR, -}; - -static void n8x0_nand_setup(struct n800_s *s) -{ - char *otp_region; - DriveInfo *dinfo; - - s->nand = qdev_new("onenand"); - qdev_prop_set_uint16(s->nand, "manufacturer_id", NAND_MFR_SAMSUNG); - /* Either 0x40 or 0x48 are OK for the device ID */ - qdev_prop_set_uint16(s->nand, "device_id", 0x48); - qdev_prop_set_uint16(s->nand, "version_id", 0); - qdev_prop_set_int32(s->nand, "shift", 1); - dinfo = drive_get(IF_MTD, 0, 0); - if (dinfo) { - qdev_prop_set_drive_err(s->nand, "drive", blk_by_legacy_dinfo(dinfo), - &error_fatal); - } - sysbus_realize_and_unref(SYS_BUS_DEVICE(s->nand), &error_fatal); - sysbus_connect_irq(SYS_BUS_DEVICE(s->nand), 0, - qdev_get_gpio_in(s->mpu->gpio, N8X0_ONENAND_GPIO)); - omap_gpmc_attach(s->mpu->gpmc, N8X0_ONENAND_CS, - sysbus_mmio_get_region(SYS_BUS_DEVICE(s->nand), 0)); - otp_region = onenand_raw_otp(s->nand); - - memcpy(otp_region + 0x000, n8x0_cal_wlan_mac, sizeof(n8x0_cal_wlan_mac)); - memcpy(otp_region + 0x800, n8x0_cal_bt_id, sizeof(n8x0_cal_bt_id)); - /* XXX: in theory should also update the OOB for both pages */ -} - -static qemu_irq n8x0_system_powerdown; - -static void n8x0_powerdown_req(Notifier *n, void *opaque) -{ - qemu_irq_raise(n8x0_system_powerdown); -} - -static Notifier n8x0_system_powerdown_notifier = { - .notify = n8x0_powerdown_req -}; - -static void n8x0_i2c_setup(struct n800_s *s) -{ - DeviceState *dev; - qemu_irq tmp_irq = qdev_get_gpio_in(s->mpu->gpio, N8X0_TMP105_GPIO); - I2CBus *i2c = omap_i2c_bus(s->mpu->i2c[0]); - - /* Attach a menelaus PM chip */ - dev = DEVICE(i2c_slave_create_simple(i2c, "twl92230", N8X0_MENELAUS_ADDR)); - qdev_connect_gpio_out(dev, 3, - qdev_get_gpio_in(s->mpu->ih[0], - OMAP_INT_24XX_SYS_NIRQ)); - - n8x0_system_powerdown = qdev_get_gpio_in(dev, 3); - qemu_register_powerdown_notifier(&n8x0_system_powerdown_notifier); - - /* Attach a TMP105 PM chip (A0 wired to ground) */ - dev = DEVICE(i2c_slave_create_simple(i2c, TYPE_TMP105, N8X0_TMP105_ADDR)); - qdev_connect_gpio_out(dev, 0, tmp_irq); -} - -/* Touchscreen and keypad controller */ -static const MouseTransformInfo n800_pointercal = { - .x = 800, - .y = 480, - .a = { 14560, -68, -3455208, -39, -9621, 35152972, 65536 }, -}; - -static const MouseTransformInfo n810_pointercal = { - .x = 800, - .y = 480, - .a = { 15041, 148, -4731056, 171, -10238, 35933380, 65536 }, -}; - -#define RETU_KEYCODE 61 /* F3 */ - -static void n800_key_event(void *opaque, int keycode) -{ - struct n800_s *s = (struct n800_s *) opaque; - int code = s->keymap[keycode & 0x7f]; - - if (code == -1) { - if ((keycode & 0x7f) == RETU_KEYCODE) { - retu_key_event(s->retu, !(keycode & 0x80)); - } - return; - } - - tsc210x_key_event(s->ts.chip, code, !(keycode & 0x80)); -} - -static const int n800_keys[16] = { - -1, - 72, /* Up */ - 63, /* Home (F5) */ - -1, - 75, /* Left */ - 28, /* Enter */ - 77, /* Right */ - -1, - 1, /* Cycle (ESC) */ - 80, /* Down */ - 62, /* Menu (F4) */ - -1, - 66, /* Zoom- (F8) */ - 64, /* FullScreen (F6) */ - 65, /* Zoom+ (F7) */ - -1, -}; - -static void n800_tsc_kbd_setup(struct n800_s *s) -{ - int i; - - /* XXX: are the three pins inverted inside the chip between the - * tsc and the cpu (N4111)? */ - qemu_irq penirq = NULL; /* NC */ - qemu_irq kbirq = qdev_get_gpio_in(s->mpu->gpio, N800_TSC_KP_IRQ_GPIO); - qemu_irq dav = qdev_get_gpio_in(s->mpu->gpio, N800_TSC_TS_GPIO); - - s->ts.chip = tsc2301_init(penirq, kbirq, dav); - s->ts.opaque = s->ts.chip->opaque; - s->ts.txrx = tsc210x_txrx; - - for (i = 0; i < 0x80; i++) { - s->keymap[i] = -1; - } - for (i = 0; i < 0x10; i++) { - if (n800_keys[i] >= 0) { - s->keymap[n800_keys[i]] = i; - } - } - - qemu_add_kbd_event_handler(n800_key_event, s); - - tsc210x_set_transform(s->ts.chip, &n800_pointercal); -} - -static void n810_tsc_setup(struct n800_s *s) -{ - qemu_irq pintdav = qdev_get_gpio_in(s->mpu->gpio, N810_TSC_TS_GPIO); - - s->ts.opaque = tsc2005_init(pintdav); - s->ts.txrx = tsc2005_txrx; - - tsc2005_set_transform(s->ts.opaque, &n810_pointercal); -} - -/* N810 Keyboard controller */ -static void n810_key_event(void *opaque, int keycode) -{ - struct n800_s *s = (struct n800_s *) opaque; - int code = s->keymap[keycode & 0x7f]; - - if (code == -1) { - if ((keycode & 0x7f) == RETU_KEYCODE) { - retu_key_event(s->retu, !(keycode & 0x80)); - } - return; - } - - lm832x_key_event(s->kbd, code, !(keycode & 0x80)); -} - -#define M 0 - -static const int n810_keys[0x80] = { - [0x01] = 16, /* Q */ - [0x02] = 37, /* K */ - [0x03] = 24, /* O */ - [0x04] = 25, /* P */ - [0x05] = 14, /* Backspace */ - [0x06] = 30, /* A */ - [0x07] = 31, /* S */ - [0x08] = 32, /* D */ - [0x09] = 33, /* F */ - [0x0a] = 34, /* G */ - [0x0b] = 35, /* H */ - [0x0c] = 36, /* J */ - - [0x11] = 17, /* W */ - [0x12] = 62, /* Menu (F4) */ - [0x13] = 38, /* L */ - [0x14] = 40, /* ' (Apostrophe) */ - [0x16] = 44, /* Z */ - [0x17] = 45, /* X */ - [0x18] = 46, /* C */ - [0x19] = 47, /* V */ - [0x1a] = 48, /* B */ - [0x1b] = 49, /* N */ - [0x1c] = 42, /* Shift (Left shift) */ - [0x1f] = 65, /* Zoom+ (F7) */ - - [0x21] = 18, /* E */ - [0x22] = 39, /* ; (Semicolon) */ - [0x23] = 12, /* - (Minus) */ - [0x24] = 13, /* = (Equal) */ - [0x2b] = 56, /* Fn (Left Alt) */ - [0x2c] = 50, /* M */ - [0x2f] = 66, /* Zoom- (F8) */ - - [0x31] = 19, /* R */ - [0x32] = 29 | M, /* Right Ctrl */ - [0x34] = 57, /* Space */ - [0x35] = 51, /* , (Comma) */ - [0x37] = 72 | M, /* Up */ - [0x3c] = 82 | M, /* Compose (Insert) */ - [0x3f] = 64, /* FullScreen (F6) */ - - [0x41] = 20, /* T */ - [0x44] = 52, /* . (Dot) */ - [0x46] = 77 | M, /* Right */ - [0x4f] = 63, /* Home (F5) */ - [0x51] = 21, /* Y */ - [0x53] = 80 | M, /* Down */ - [0x55] = 28, /* Enter */ - [0x5f] = 1, /* Cycle (ESC) */ - - [0x61] = 22, /* U */ - [0x64] = 75 | M, /* Left */ - - [0x71] = 23, /* I */ -#if 0 - [0x75] = 28 | M, /* KP Enter (KP Enter) */ -#else - [0x75] = 15, /* KP Enter (Tab) */ -#endif -}; - -#undef M - -static void n810_kbd_setup(struct n800_s *s) -{ - qemu_irq kbd_irq = qdev_get_gpio_in(s->mpu->gpio, N810_KEYBOARD_GPIO); - int i; - - for (i = 0; i < 0x80; i++) { - s->keymap[i] = -1; - } - for (i = 0; i < 0x80; i++) { - if (n810_keys[i] > 0) { - s->keymap[n810_keys[i]] = i; - } - } - - qemu_add_kbd_event_handler(n810_key_event, s); - - /* Attach the LM8322 keyboard to the I2C bus, - * should happen in n8x0_i2c_setup and s->kbd be initialised here. */ - s->kbd = DEVICE(i2c_slave_create_simple(omap_i2c_bus(s->mpu->i2c[0]), - TYPE_LM8323, N810_LM8323_ADDR)); - qdev_connect_gpio_out(s->kbd, 0, kbd_irq); -} - -/* LCD MIPI DBI-C controller (URAL) */ -struct mipid_s { - int resp[4]; - int param[4]; - int p; - int pm; - int cmd; - - int sleep; - int booster; - int te; - int selfcheck; - int partial; - int normal; - int vscr; - int invert; - int onoff; - int gamma; - uint32_t id; -}; - -static void mipid_reset(struct mipid_s *s) -{ - s->pm = 0; - s->cmd = 0; - - s->sleep = 1; - s->booster = 0; - s->selfcheck = - (1 << 7) | /* Register loading OK. */ - (1 << 5) | /* The chip is attached. */ - (1 << 4); /* Display glass still in one piece. */ - s->te = 0; - s->partial = 0; - s->normal = 1; - s->vscr = 0; - s->invert = 0; - s->onoff = 1; - s->gamma = 0; -} - -static uint32_t mipid_txrx(void *opaque, uint32_t cmd, int len) -{ - struct mipid_s *s = (struct mipid_s *) opaque; - uint8_t ret; - - if (len > 9) { - hw_error("%s: FIXME: bad SPI word width %i\n", __func__, len); - } - - if (s->p >= ARRAY_SIZE(s->resp)) { - ret = 0; - } else { - ret = s->resp[s->p++]; - } - if (s->pm-- > 0) { - s->param[s->pm] = cmd; - } else { - s->cmd = cmd; - } - - switch (s->cmd) { - case 0x00: /* NOP */ - break; - - case 0x01: /* SWRESET */ - mipid_reset(s); - break; - - case 0x02: /* BSTROFF */ - s->booster = 0; - break; - case 0x03: /* BSTRON */ - s->booster = 1; - break; - - case 0x04: /* RDDID */ - s->p = 0; - s->resp[0] = (s->id >> 16) & 0xff; - s->resp[1] = (s->id >> 8) & 0xff; - s->resp[2] = (s->id >> 0) & 0xff; - break; - - case 0x06: /* RD_RED */ - case 0x07: /* RD_GREEN */ - /* XXX the bootloader sometimes issues RD_BLUE meaning RDDID so - * for the bootloader one needs to change this. */ - case 0x08: /* RD_BLUE */ - s->p = 0; - /* TODO: return first pixel components */ - s->resp[0] = 0x01; - break; - - case 0x09: /* RDDST */ - s->p = 0; - s->resp[0] = s->booster << 7; - s->resp[1] = (5 << 4) | (s->partial << 2) | - (s->sleep << 1) | s->normal; - s->resp[2] = (s->vscr << 7) | (s->invert << 5) | - (s->onoff << 2) | (s->te << 1) | (s->gamma >> 2); - s->resp[3] = s->gamma << 6; - break; - - case 0x0a: /* RDDPM */ - s->p = 0; - s->resp[0] = (s->onoff << 2) | (s->normal << 3) | (s->sleep << 4) | - (s->partial << 5) | (s->sleep << 6) | (s->booster << 7); - break; - case 0x0b: /* RDDMADCTR */ - s->p = 0; - s->resp[0] = 0; - break; - case 0x0c: /* RDDCOLMOD */ - s->p = 0; - s->resp[0] = 5; /* 65K colours */ - break; - case 0x0d: /* RDDIM */ - s->p = 0; - s->resp[0] = (s->invert << 5) | (s->vscr << 7) | s->gamma; - break; - case 0x0e: /* RDDSM */ - s->p = 0; - s->resp[0] = s->te << 7; - break; - case 0x0f: /* RDDSDR */ - s->p = 0; - s->resp[0] = s->selfcheck; - break; - - case 0x10: /* SLPIN */ - s->sleep = 1; - break; - case 0x11: /* SLPOUT */ - s->sleep = 0; - s->selfcheck ^= 1 << 6; /* POFF self-diagnosis Ok */ - break; - - case 0x12: /* PTLON */ - s->partial = 1; - s->normal = 0; - s->vscr = 0; - break; - case 0x13: /* NORON */ - s->partial = 0; - s->normal = 1; - s->vscr = 0; - break; - - case 0x20: /* INVOFF */ - s->invert = 0; - break; - case 0x21: /* INVON */ - s->invert = 1; - break; - - case 0x22: /* APOFF */ - case 0x23: /* APON */ - goto bad_cmd; - - case 0x25: /* WRCNTR */ - if (s->pm < 0) { - s->pm = 1; - } - goto bad_cmd; - - case 0x26: /* GAMSET */ - if (!s->pm) { - s->gamma = ctz32(s->param[0] & 0xf); - if (s->gamma == 32) { - s->gamma = -1; /* XXX: should this be 0? */ - } - } else if (s->pm < 0) { - s->pm = 1; - } - break; - - case 0x28: /* DISPOFF */ - s->onoff = 0; - break; - case 0x29: /* DISPON */ - s->onoff = 1; - break; - - case 0x2a: /* CASET */ - case 0x2b: /* RASET */ - case 0x2c: /* RAMWR */ - case 0x2d: /* RGBSET */ - case 0x2e: /* RAMRD */ - case 0x30: /* PTLAR */ - case 0x33: /* SCRLAR */ - goto bad_cmd; - - case 0x34: /* TEOFF */ - s->te = 0; - break; - case 0x35: /* TEON */ - if (!s->pm) { - s->te = 1; - } else if (s->pm < 0) { - s->pm = 1; - } - break; - - case 0x36: /* MADCTR */ - goto bad_cmd; - - case 0x37: /* VSCSAD */ - s->partial = 0; - s->normal = 0; - s->vscr = 1; - break; - - case 0x38: /* IDMOFF */ - case 0x39: /* IDMON */ - case 0x3a: /* COLMOD */ - goto bad_cmd; - - case 0xb0: /* CLKINT / DISCTL */ - case 0xb1: /* CLKEXT */ - if (s->pm < 0) { - s->pm = 2; - } - break; - - case 0xb4: /* FRMSEL */ - break; - - case 0xb5: /* FRM8SEL */ - case 0xb6: /* TMPRNG / INIESC */ - case 0xb7: /* TMPHIS / NOP2 */ - case 0xb8: /* TMPREAD / MADCTL */ - case 0xba: /* DISTCTR */ - case 0xbb: /* EPVOL */ - goto bad_cmd; - - case 0xbd: /* Unknown */ - s->p = 0; - s->resp[0] = 0; - s->resp[1] = 1; - break; - - case 0xc2: /* IFMOD */ - if (s->pm < 0) { - s->pm = 2; - } - break; - - case 0xc6: /* PWRCTL */ - case 0xc7: /* PPWRCTL */ - case 0xd0: /* EPWROUT */ - case 0xd1: /* EPWRIN */ - case 0xd4: /* RDEV */ - case 0xd5: /* RDRR */ - goto bad_cmd; - - case 0xda: /* RDID1 */ - s->p = 0; - s->resp[0] = (s->id >> 16) & 0xff; - break; - case 0xdb: /* RDID2 */ - s->p = 0; - s->resp[0] = (s->id >> 8) & 0xff; - break; - case 0xdc: /* RDID3 */ - s->p = 0; - s->resp[0] = (s->id >> 0) & 0xff; - break; - - default: - bad_cmd: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: unknown command 0x%02x\n", __func__, s->cmd); - break; - } - - return ret; -} - -static void *mipid_init(void) -{ - struct mipid_s *s = g_malloc0(sizeof(*s)); - - s->id = 0x838f03; - mipid_reset(s); - - return s; -} - -static void n8x0_spi_setup(struct n800_s *s) -{ - void *tsc = s->ts.opaque; - void *mipid = mipid_init(); - - omap_mcspi_attach(s->mpu->mcspi[0], s->ts.txrx, tsc, 0); - omap_mcspi_attach(s->mpu->mcspi[0], mipid_txrx, mipid, 1); -} - -/* This task is normally performed by the bootloader. If we're loading - * a kernel directly, we need to enable the Blizzard ourselves. */ -static void n800_dss_init(struct rfbi_chip_s *chip) -{ - uint8_t *fb_blank; - - chip->write(chip->opaque, 0, 0x2a); /* LCD Width register */ - chip->write(chip->opaque, 1, 0x64); - chip->write(chip->opaque, 0, 0x2c); /* LCD HNDP register */ - chip->write(chip->opaque, 1, 0x1e); - chip->write(chip->opaque, 0, 0x2e); /* LCD Height 0 register */ - chip->write(chip->opaque, 1, 0xe0); - chip->write(chip->opaque, 0, 0x30); /* LCD Height 1 register */ - chip->write(chip->opaque, 1, 0x01); - chip->write(chip->opaque, 0, 0x32); /* LCD VNDP register */ - chip->write(chip->opaque, 1, 0x06); - chip->write(chip->opaque, 0, 0x68); /* Display Mode register */ - chip->write(chip->opaque, 1, 1); /* Enable bit */ - - chip->write(chip->opaque, 0, 0x6c); - chip->write(chip->opaque, 1, 0x00); /* Input X Start Position */ - chip->write(chip->opaque, 1, 0x00); /* Input X Start Position */ - chip->write(chip->opaque, 1, 0x00); /* Input Y Start Position */ - chip->write(chip->opaque, 1, 0x00); /* Input Y Start Position */ - chip->write(chip->opaque, 1, 0x1f); /* Input X End Position */ - chip->write(chip->opaque, 1, 0x03); /* Input X End Position */ - chip->write(chip->opaque, 1, 0xdf); /* Input Y End Position */ - chip->write(chip->opaque, 1, 0x01); /* Input Y End Position */ - chip->write(chip->opaque, 1, 0x00); /* Output X Start Position */ - chip->write(chip->opaque, 1, 0x00); /* Output X Start Position */ - chip->write(chip->opaque, 1, 0x00); /* Output Y Start Position */ - chip->write(chip->opaque, 1, 0x00); /* Output Y Start Position */ - chip->write(chip->opaque, 1, 0x1f); /* Output X End Position */ - chip->write(chip->opaque, 1, 0x03); /* Output X End Position */ - chip->write(chip->opaque, 1, 0xdf); /* Output Y End Position */ - chip->write(chip->opaque, 1, 0x01); /* Output Y End Position */ - chip->write(chip->opaque, 1, 0x01); /* Input Data Format */ - chip->write(chip->opaque, 1, 0x01); /* Data Source Select */ - - fb_blank = memset(g_malloc(800 * 480 * 2), 0xff, 800 * 480 * 2); - /* Display Memory Data Port */ - chip->block(chip->opaque, 1, fb_blank, 800 * 480 * 2, 800); - g_free(fb_blank); -} - -static void n8x0_dss_setup(struct n800_s *s) -{ - s->blizzard.opaque = s1d13745_init(NULL); - s->blizzard.block = s1d13745_write_block; - s->blizzard.write = s1d13745_write; - s->blizzard.read = s1d13745_read; - - omap_rfbi_attach(s->mpu->dss, 0, &s->blizzard); -} - -static void n8x0_cbus_setup(struct n800_s *s) -{ - qemu_irq dat_out = qdev_get_gpio_in(s->mpu->gpio, N8X0_CBUS_DAT_GPIO); - qemu_irq retu_irq = qdev_get_gpio_in(s->mpu->gpio, N8X0_RETU_GPIO); - qemu_irq tahvo_irq = qdev_get_gpio_in(s->mpu->gpio, N8X0_TAHVO_GPIO); - - CBus *cbus = cbus_init(dat_out); - - qdev_connect_gpio_out(s->mpu->gpio, N8X0_CBUS_CLK_GPIO, cbus->clk); - qdev_connect_gpio_out(s->mpu->gpio, N8X0_CBUS_DAT_GPIO, cbus->dat); - qdev_connect_gpio_out(s->mpu->gpio, N8X0_CBUS_SEL_GPIO, cbus->sel); - - cbus_attach(cbus, s->retu = retu_init(retu_irq, 1)); - cbus_attach(cbus, s->tahvo = tahvo_init(tahvo_irq, 1)); -} - -static void n8x0_usb_setup(struct n800_s *s) -{ - SysBusDevice *dev; - s->usb = qdev_new("tusb6010"); - dev = SYS_BUS_DEVICE(s->usb); - sysbus_realize_and_unref(dev, &error_fatal); - sysbus_connect_irq(dev, 0, - qdev_get_gpio_in(s->mpu->gpio, N8X0_TUSB_INT_GPIO)); - /* Using the NOR interface */ - omap_gpmc_attach(s->mpu->gpmc, N8X0_USB_ASYNC_CS, - sysbus_mmio_get_region(dev, 0)); - omap_gpmc_attach(s->mpu->gpmc, N8X0_USB_SYNC_CS, - sysbus_mmio_get_region(dev, 1)); - qdev_connect_gpio_out(s->mpu->gpio, N8X0_TUSB_ENABLE_GPIO, - qdev_get_gpio_in(s->usb, 0)); /* tusb_pwr */ -} - -/* Setup done before the main bootloader starts by some early setup code - * - used when we want to run the main bootloader in emulation. This - * isn't documented. */ -static const uint32_t n800_pinout[104] = { - 0x080f00d8, 0x00d40808, 0x03080808, 0x080800d0, - 0x00dc0808, 0x0b0f0f00, 0x080800b4, 0x00c00808, - 0x08080808, 0x180800c4, 0x00b80000, 0x08080808, - 0x080800bc, 0x00cc0808, 0x08081818, 0x18180128, - 0x01241800, 0x18181818, 0x000000f0, 0x01300000, - 0x00001b0b, 0x1b0f0138, 0x00e0181b, 0x1b031b0b, - 0x180f0078, 0x00740018, 0x0f0f0f1a, 0x00000080, - 0x007c0000, 0x00000000, 0x00000088, 0x00840000, - 0x00000000, 0x00000094, 0x00980300, 0x0f180003, - 0x0000008c, 0x00900f0f, 0x0f0f1b00, 0x0f00009c, - 0x01140000, 0x1b1b0f18, 0x0818013c, 0x01400008, - 0x00001818, 0x000b0110, 0x010c1800, 0x0b030b0f, - 0x181800f4, 0x00f81818, 0x00000018, 0x000000fc, - 0x00401808, 0x00000000, 0x0f1b0030, 0x003c0008, - 0x00000000, 0x00000038, 0x00340000, 0x00000000, - 0x1a080070, 0x00641a1a, 0x08080808, 0x08080060, - 0x005c0808, 0x08080808, 0x08080058, 0x00540808, - 0x08080808, 0x0808006c, 0x00680808, 0x08080808, - 0x000000a8, 0x00b00000, 0x08080808, 0x000000a0, - 0x00a40000, 0x00000000, 0x08ff0050, 0x004c0808, - 0xffffffff, 0xffff0048, 0x0044ffff, 0xffffffff, - 0x000000ac, 0x01040800, 0x08080b0f, 0x18180100, - 0x01081818, 0x0b0b1808, 0x1a0300e4, 0x012c0b1a, - 0x02020018, 0x0b000134, 0x011c0800, 0x0b1b1b00, - 0x0f0000c8, 0x00ec181b, 0x000f0f02, 0x00180118, - 0x01200000, 0x0f0b1b1b, 0x0f0200e8, 0x0000020b, -}; - -static void n800_setup_nolo_tags(void *sram_base) -{ - int i; - uint32_t *p = sram_base + 0x8000; - uint32_t *v = sram_base + 0xa000; - - memset(p, 0, 0x3000); - - strcpy((void *) (p + 0), "QEMU N800"); - - strcpy((void *) (p + 8), "F5"); - - stl_p(p + 10, 0x04f70000); - strcpy((void *) (p + 9), "RX-34"); - - /* RAM size in MB? */ - stl_p(p + 12, 0x80); - - /* Pointer to the list of tags */ - stl_p(p + 13, OMAP2_SRAM_BASE + 0x9000); - - /* The NOLO tags start here */ - p = sram_base + 0x9000; -#define ADD_TAG(tag, len) \ - stw_p((uint16_t *) p + 0, tag); \ - stw_p((uint16_t *) p + 1, len); p++; \ - stl_p(p++, OMAP2_SRAM_BASE | (((void *) v - sram_base) & 0xffff)); - - /* OMAP STI console? Pin out settings? */ - ADD_TAG(0x6e01, 414); - for (i = 0; i < ARRAY_SIZE(n800_pinout); i++) { - stl_p(v++, n800_pinout[i]); - } - - /* Kernel memsize? */ - ADD_TAG(0x6e05, 1); - stl_p(v++, 2); - - /* NOLO serial console */ - ADD_TAG(0x6e02, 4); - stl_p(v++, XLDR_LL_UART); /* UART number (1 - 3) */ - -#if 0 - /* CBUS settings (Retu/AVilma) */ - ADD_TAG(0x6e03, 6); - stw_p((uint16_t *) v + 0, 65); /* CBUS GPIO0 */ - stw_p((uint16_t *) v + 1, 66); /* CBUS GPIO1 */ - stw_p((uint16_t *) v + 2, 64); /* CBUS GPIO2 */ - v += 2; -#endif - - /* Nokia ASIC BB5 (Retu/Tahvo) */ - ADD_TAG(0x6e0a, 4); - stw_p((uint16_t *) v + 0, 111); /* "Retu" interrupt GPIO */ - stw_p((uint16_t *) v + 1, 108); /* "Tahvo" interrupt GPIO */ - v++; - - /* LCD console? */ - ADD_TAG(0x6e04, 4); - stw_p((uint16_t *) v + 0, 30); /* ??? */ - stw_p((uint16_t *) v + 1, 24); /* ??? */ - v++; - -#if 0 - /* LCD settings */ - ADD_TAG(0x6e06, 2); - stw_p((uint16_t *) (v++), 15); /* ??? */ -#endif - - /* I^2C (Menelaus) */ - ADD_TAG(0x6e07, 4); - stl_p(v++, 0x00720000); /* ??? */ - - /* Unknown */ - ADD_TAG(0x6e0b, 6); - stw_p((uint16_t *) v + 0, 94); /* ??? */ - stw_p((uint16_t *) v + 1, 23); /* ??? */ - stw_p((uint16_t *) v + 2, 0); /* ??? */ - v += 2; - - /* OMAP gpio switch info */ - ADD_TAG(0x6e0c, 80); - strcpy((void *) v, "bat_cover"); v += 3; - stw_p((uint16_t *) v + 0, 110); /* GPIO num ??? */ - stw_p((uint16_t *) v + 1, 1); /* GPIO num ??? */ - v += 2; - strcpy((void *) v, "cam_act"); v += 3; - stw_p((uint16_t *) v + 0, 95); /* GPIO num ??? */ - stw_p((uint16_t *) v + 1, 32); /* GPIO num ??? */ - v += 2; - strcpy((void *) v, "cam_turn"); v += 3; - stw_p((uint16_t *) v + 0, 12); /* GPIO num ??? */ - stw_p((uint16_t *) v + 1, 33); /* GPIO num ??? */ - v += 2; - strcpy((void *) v, "headphone"); v += 3; - stw_p((uint16_t *) v + 0, 107); /* GPIO num ??? */ - stw_p((uint16_t *) v + 1, 17); /* GPIO num ??? */ - v += 2; - - /* Bluetooth */ - ADD_TAG(0x6e0e, 12); - stl_p(v++, 0x5c623d01); /* ??? */ - stl_p(v++, 0x00000201); /* ??? */ - stl_p(v++, 0x00000000); /* ??? */ - - /* CX3110x WLAN settings */ - ADD_TAG(0x6e0f, 8); - stl_p(v++, 0x00610025); /* ??? */ - stl_p(v++, 0xffff0057); /* ??? */ - - /* MMC host settings */ - ADD_TAG(0x6e10, 12); - stl_p(v++, 0xffff000f); /* ??? */ - stl_p(v++, 0xffffffff); /* ??? */ - stl_p(v++, 0x00000060); /* ??? */ - - /* OneNAND chip select */ - ADD_TAG(0x6e11, 10); - stl_p(v++, 0x00000401); /* ??? */ - stl_p(v++, 0x0002003a); /* ??? */ - stl_p(v++, 0x00000002); /* ??? */ - - /* TEA5761 sensor settings */ - ADD_TAG(0x6e12, 2); - stl_p(v++, 93); /* GPIO num ??? */ - -#if 0 - /* Unknown tag */ - ADD_TAG(6e09, 0); - - /* Kernel UART / console */ - ADD_TAG(6e12, 0); -#endif - - /* End of the list */ - stl_p(p++, 0x00000000); - stl_p(p++, 0x00000000); -} - -/* This task is normally performed by the bootloader. If we're loading - * a kernel directly, we need to set up GPMC mappings ourselves. */ -static void n800_gpmc_init(struct n800_s *s) -{ - uint32_t config7 = - (0xf << 8) | /* MASKADDRESS */ - (1 << 6) | /* CSVALID */ - (4 << 0); /* BASEADDRESS */ - - cpu_physical_memory_write(0x6800a078, /* GPMC_CONFIG7_0 */ - &config7, sizeof(config7)); -} - -/* Setup sequence done by the bootloader */ -static void n8x0_boot_init(void *opaque) -{ - struct n800_s *s = (struct n800_s *) opaque; - uint32_t buf; - - /* PRCM setup */ -#define omap_writel(addr, val) \ - buf = (val); \ - cpu_physical_memory_write(addr, &buf, sizeof(buf)) - - omap_writel(0x48008060, 0x41); /* PRCM_CLKSRC_CTRL */ - omap_writel(0x48008070, 1); /* PRCM_CLKOUT_CTRL */ - omap_writel(0x48008078, 0); /* PRCM_CLKEMUL_CTRL */ - omap_writel(0x48008090, 0); /* PRCM_VOLTSETUP */ - omap_writel(0x48008094, 0); /* PRCM_CLKSSETUP */ - omap_writel(0x48008098, 0); /* PRCM_POLCTRL */ - omap_writel(0x48008140, 2); /* CM_CLKSEL_MPU */ - omap_writel(0x48008148, 0); /* CM_CLKSTCTRL_MPU */ - omap_writel(0x48008158, 1); /* RM_RSTST_MPU */ - omap_writel(0x480081c8, 0x15); /* PM_WKDEP_MPU */ - omap_writel(0x480081d4, 0x1d4); /* PM_EVGENCTRL_MPU */ - omap_writel(0x480081d8, 0); /* PM_EVEGENONTIM_MPU */ - omap_writel(0x480081dc, 0); /* PM_EVEGENOFFTIM_MPU */ - omap_writel(0x480081e0, 0xc); /* PM_PWSTCTRL_MPU */ - omap_writel(0x48008200, 0x047e7ff7); /* CM_FCLKEN1_CORE */ - omap_writel(0x48008204, 0x00000004); /* CM_FCLKEN2_CORE */ - omap_writel(0x48008210, 0x047e7ff1); /* CM_ICLKEN1_CORE */ - omap_writel(0x48008214, 0x00000004); /* CM_ICLKEN2_CORE */ - omap_writel(0x4800821c, 0x00000000); /* CM_ICLKEN4_CORE */ - omap_writel(0x48008230, 0); /* CM_AUTOIDLE1_CORE */ - omap_writel(0x48008234, 0); /* CM_AUTOIDLE2_CORE */ - omap_writel(0x48008238, 7); /* CM_AUTOIDLE3_CORE */ - omap_writel(0x4800823c, 0); /* CM_AUTOIDLE4_CORE */ - omap_writel(0x48008240, 0x04360626); /* CM_CLKSEL1_CORE */ - omap_writel(0x48008244, 0x00000014); /* CM_CLKSEL2_CORE */ - omap_writel(0x48008248, 0); /* CM_CLKSTCTRL_CORE */ - omap_writel(0x48008300, 0x00000000); /* CM_FCLKEN_GFX */ - omap_writel(0x48008310, 0x00000000); /* CM_ICLKEN_GFX */ - omap_writel(0x48008340, 0x00000001); /* CM_CLKSEL_GFX */ - omap_writel(0x48008400, 0x00000004); /* CM_FCLKEN_WKUP */ - omap_writel(0x48008410, 0x00000004); /* CM_ICLKEN_WKUP */ - omap_writel(0x48008440, 0x00000000); /* CM_CLKSEL_WKUP */ - omap_writel(0x48008500, 0x000000cf); /* CM_CLKEN_PLL */ - omap_writel(0x48008530, 0x0000000c); /* CM_AUTOIDLE_PLL */ - omap_writel(0x48008540, /* CM_CLKSEL1_PLL */ - (0x78 << 12) | (6 << 8)); - omap_writel(0x48008544, 2); /* CM_CLKSEL2_PLL */ - - /* GPMC setup */ - n800_gpmc_init(s); - - /* Video setup */ - n800_dss_init(&s->blizzard); - - /* CPU setup */ - s->mpu->cpu->env.GE = 0x5; - - /* If the machine has a slided keyboard, open it */ - if (s->kbd) { - qemu_irq_raise(qdev_get_gpio_in(s->mpu->gpio, N810_SLIDE_GPIO)); - } -} - -#define OMAP_TAG_NOKIA_BT 0x4e01 -#define OMAP_TAG_WLAN_CX3110X 0x4e02 -#define OMAP_TAG_CBUS 0x4e03 -#define OMAP_TAG_EM_ASIC_BB5 0x4e04 - -static const struct omap_gpiosw_info_s { - const char *name; - int line; - int type; -} n800_gpiosw_info[] = { - { - "bat_cover", N800_BAT_COVER_GPIO, - OMAP_GPIOSW_TYPE_COVER | OMAP_GPIOSW_INVERTED, - }, { - "cam_act", N800_CAM_ACT_GPIO, - OMAP_GPIOSW_TYPE_ACTIVITY, - }, { - "cam_turn", N800_CAM_TURN_GPIO, - OMAP_GPIOSW_TYPE_ACTIVITY | OMAP_GPIOSW_INVERTED, - }, { - "headphone", N8X0_HEADPHONE_GPIO, - OMAP_GPIOSW_TYPE_CONNECTION | OMAP_GPIOSW_INVERTED, - }, - { /* end of list */ } -}, n810_gpiosw_info[] = { - { - "gps_reset", N810_GPS_RESET_GPIO, - OMAP_GPIOSW_TYPE_ACTIVITY | OMAP_GPIOSW_OUTPUT, - }, { - "gps_wakeup", N810_GPS_WAKEUP_GPIO, - OMAP_GPIOSW_TYPE_ACTIVITY | OMAP_GPIOSW_OUTPUT, - }, { - "headphone", N8X0_HEADPHONE_GPIO, - OMAP_GPIOSW_TYPE_CONNECTION | OMAP_GPIOSW_INVERTED, - }, { - "kb_lock", N810_KB_LOCK_GPIO, - OMAP_GPIOSW_TYPE_COVER | OMAP_GPIOSW_INVERTED, - }, { - "sleepx_led", N810_SLEEPX_LED_GPIO, - OMAP_GPIOSW_TYPE_ACTIVITY | OMAP_GPIOSW_INVERTED | OMAP_GPIOSW_OUTPUT, - }, { - "slide", N810_SLIDE_GPIO, - OMAP_GPIOSW_TYPE_COVER | OMAP_GPIOSW_INVERTED, - }, - { /* end of list */ } -}; - -static const struct omap_partition_info_s { - uint32_t offset; - uint32_t size; - int mask; - const char *name; -} n800_part_info[] = { - { 0x00000000, 0x00020000, 0x3, "bootloader" }, - { 0x00020000, 0x00060000, 0x0, "config" }, - { 0x00080000, 0x00200000, 0x0, "kernel" }, - { 0x00280000, 0x00200000, 0x3, "initfs" }, - { 0x00480000, 0x0fb80000, 0x3, "rootfs" }, - { /* end of list */ } -}, n810_part_info[] = { - { 0x00000000, 0x00020000, 0x3, "bootloader" }, - { 0x00020000, 0x00060000, 0x0, "config" }, - { 0x00080000, 0x00220000, 0x0, "kernel" }, - { 0x002a0000, 0x00400000, 0x0, "initfs" }, - { 0x006a0000, 0x0f960000, 0x0, "rootfs" }, - { /* end of list */ } -}; - -static const uint8_t n8x0_bd_addr[6] = { N8X0_BD_ADDR }; - -static int n8x0_atag_setup(void *p, int model) -{ - uint8_t *b; - uint16_t *w; - uint32_t *l; - const struct omap_gpiosw_info_s *gpiosw; - const struct omap_partition_info_s *partition; - const char *tag; - - w = p; - - stw_p(w++, OMAP_TAG_UART); /* u16 tag */ - stw_p(w++, 4); /* u16 len */ - stw_p(w++, (1 << 2) | (1 << 1) | (1 << 0)); /* uint enabled_uarts */ - w++; - -#if 0 - stw_p(w++, OMAP_TAG_SERIAL_CONSOLE); /* u16 tag */ - stw_p(w++, 4); /* u16 len */ - stw_p(w++, XLDR_LL_UART + 1); /* u8 console_uart */ - stw_p(w++, 115200); /* u32 console_speed */ -#endif - - stw_p(w++, OMAP_TAG_LCD); /* u16 tag */ - stw_p(w++, 36); /* u16 len */ - strcpy((void *) w, "QEMU LCD panel"); /* char panel_name[16] */ - w += 8; - strcpy((void *) w, "blizzard"); /* char ctrl_name[16] */ - w += 8; - stw_p(w++, N810_BLIZZARD_RESET_GPIO); /* TODO: n800 s16 nreset_gpio */ - stw_p(w++, 24); /* u8 data_lines */ - - stw_p(w++, OMAP_TAG_CBUS); /* u16 tag */ - stw_p(w++, 8); /* u16 len */ - stw_p(w++, N8X0_CBUS_CLK_GPIO); /* s16 clk_gpio */ - stw_p(w++, N8X0_CBUS_DAT_GPIO); /* s16 dat_gpio */ - stw_p(w++, N8X0_CBUS_SEL_GPIO); /* s16 sel_gpio */ - w++; - - stw_p(w++, OMAP_TAG_EM_ASIC_BB5); /* u16 tag */ - stw_p(w++, 4); /* u16 len */ - stw_p(w++, N8X0_RETU_GPIO); /* s16 retu_irq_gpio */ - stw_p(w++, N8X0_TAHVO_GPIO); /* s16 tahvo_irq_gpio */ - - gpiosw = (model == 810) ? n810_gpiosw_info : n800_gpiosw_info; - for (; gpiosw->name; gpiosw++) { - stw_p(w++, OMAP_TAG_GPIO_SWITCH); /* u16 tag */ - stw_p(w++, 20); /* u16 len */ - strcpy((void *) w, gpiosw->name); /* char name[12] */ - w += 6; - stw_p(w++, gpiosw->line); /* u16 gpio */ - stw_p(w++, gpiosw->type); - stw_p(w++, 0); - stw_p(w++, 0); - } - - stw_p(w++, OMAP_TAG_NOKIA_BT); /* u16 tag */ - stw_p(w++, 12); /* u16 len */ - b = (void *) w; - stb_p(b++, 0x01); /* u8 chip_type (CSR) */ - stb_p(b++, N8X0_BT_WKUP_GPIO); /* u8 bt_wakeup_gpio */ - stb_p(b++, N8X0_BT_HOST_WKUP_GPIO); /* u8 host_wakeup_gpio */ - stb_p(b++, N8X0_BT_RESET_GPIO); /* u8 reset_gpio */ - stb_p(b++, BT_UART + 1); /* u8 bt_uart */ - memcpy(b, &n8x0_bd_addr, 6); /* u8 bd_addr[6] */ - b += 6; - stb_p(b++, 0x02); /* u8 bt_sysclk (38.4) */ - w = (void *) b; - - stw_p(w++, OMAP_TAG_WLAN_CX3110X); /* u16 tag */ - stw_p(w++, 8); /* u16 len */ - stw_p(w++, 0x25); /* u8 chip_type */ - stw_p(w++, N8X0_WLAN_PWR_GPIO); /* s16 power_gpio */ - stw_p(w++, N8X0_WLAN_IRQ_GPIO); /* s16 irq_gpio */ - stw_p(w++, -1); /* s16 spi_cs_gpio */ - - stw_p(w++, OMAP_TAG_MMC); /* u16 tag */ - stw_p(w++, 16); /* u16 len */ - if (model == 810) { - stw_p(w++, 0x23f); /* unsigned flags */ - stw_p(w++, -1); /* s16 power_pin */ - stw_p(w++, -1); /* s16 switch_pin */ - stw_p(w++, -1); /* s16 wp_pin */ - stw_p(w++, 0x240); /* unsigned flags */ - stw_p(w++, 0xc000); /* s16 power_pin */ - stw_p(w++, 0x0248); /* s16 switch_pin */ - stw_p(w++, 0xc000); /* s16 wp_pin */ - } else { - stw_p(w++, 0xf); /* unsigned flags */ - stw_p(w++, -1); /* s16 power_pin */ - stw_p(w++, -1); /* s16 switch_pin */ - stw_p(w++, -1); /* s16 wp_pin */ - stw_p(w++, 0); /* unsigned flags */ - stw_p(w++, 0); /* s16 power_pin */ - stw_p(w++, 0); /* s16 switch_pin */ - stw_p(w++, 0); /* s16 wp_pin */ - } - - stw_p(w++, OMAP_TAG_TEA5761); /* u16 tag */ - stw_p(w++, 4); /* u16 len */ - stw_p(w++, N8X0_TEA5761_CS_GPIO); /* u16 enable_gpio */ - w++; - - partition = (model == 810) ? n810_part_info : n800_part_info; - for (; partition->name; partition++) { - stw_p(w++, OMAP_TAG_PARTITION); /* u16 tag */ - stw_p(w++, 28); /* u16 len */ - strcpy((void *) w, partition->name); /* char name[16] */ - l = (void *) (w + 8); - stl_p(l++, partition->size); /* unsigned int size */ - stl_p(l++, partition->offset); /* unsigned int offset */ - stl_p(l++, partition->mask); /* unsigned int mask_flags */ - w = (void *) l; - } - - stw_p(w++, OMAP_TAG_BOOT_REASON); /* u16 tag */ - stw_p(w++, 12); /* u16 len */ -#if 0 - strcpy((void *) w, "por"); /* char reason_str[12] */ - strcpy((void *) w, "charger"); /* char reason_str[12] */ - strcpy((void *) w, "32wd_to"); /* char reason_str[12] */ - strcpy((void *) w, "sw_rst"); /* char reason_str[12] */ - strcpy((void *) w, "mbus"); /* char reason_str[12] */ - strcpy((void *) w, "unknown"); /* char reason_str[12] */ - strcpy((void *) w, "swdg_to"); /* char reason_str[12] */ - strcpy((void *) w, "sec_vio"); /* char reason_str[12] */ - strcpy((void *) w, "pwr_key"); /* char reason_str[12] */ - strcpy((void *) w, "rtc_alarm"); /* char reason_str[12] */ -#else - strcpy((void *) w, "pwr_key"); /* char reason_str[12] */ -#endif - w += 6; - - tag = (model == 810) ? "RX-44" : "RX-34"; - stw_p(w++, OMAP_TAG_VERSION_STR); /* u16 tag */ - stw_p(w++, 24); /* u16 len */ - strcpy((void *) w, "product"); /* char component[12] */ - w += 6; - strcpy((void *) w, tag); /* char version[12] */ - w += 6; - - stw_p(w++, OMAP_TAG_VERSION_STR); /* u16 tag */ - stw_p(w++, 24); /* u16 len */ - strcpy((void *) w, "hw-build"); /* char component[12] */ - w += 6; - strcpy((void *) w, "QEMU "); - pstrcat((void *) w, 12, qemu_hw_version()); /* char version[12] */ - w += 6; - - tag = (model == 810) ? "1.1.10-qemu" : "1.1.6-qemu"; - stw_p(w++, OMAP_TAG_VERSION_STR); /* u16 tag */ - stw_p(w++, 24); /* u16 len */ - strcpy((void *) w, "nolo"); /* char component[12] */ - w += 6; - strcpy((void *) w, tag); /* char version[12] */ - w += 6; - - return (void *) w - p; -} - -static int n800_atag_setup(const struct arm_boot_info *info, void *p) -{ - return n8x0_atag_setup(p, 800); -} - -static int n810_atag_setup(const struct arm_boot_info *info, void *p) -{ - return n8x0_atag_setup(p, 810); -} - -static void n8x0_init(MachineState *machine, - struct arm_boot_info *binfo, int model) -{ - struct n800_s *s = g_malloc0(sizeof(*s)); - MachineClass *mc = MACHINE_GET_CLASS(machine); - - if (machine->ram_size != mc->default_ram_size) { - char *sz = size_to_str(mc->default_ram_size); - error_report("Invalid RAM size, should be %s", sz); - g_free(sz); - exit(EXIT_FAILURE); - } - binfo->ram_size = machine->ram_size; - - memory_region_add_subregion(get_system_memory(), OMAP2_Q2_BASE, - machine->ram); - - s->mpu = omap2420_mpu_init(machine->ram, machine->cpu_type); - - /* Setup peripherals - * - * Believed external peripherals layout in the N810: - * (spi bus 1) - * tsc2005 - * lcd_mipid - * (spi bus 2) - * Conexant cx3110x (WLAN) - * optional: pc2400m (WiMAX) - * (i2c bus 0) - * TLV320AIC33 (audio codec) - * TCM825x (camera by Toshiba) - * lp5521 (clever LEDs) - * tsl2563 (light sensor, hwmon, model 7, rev. 0) - * lm8323 (keypad, manf 00, rev 04) - * (i2c bus 1) - * tmp105 (temperature sensor, hwmon) - * menelaus (pm) - * (somewhere on i2c - maybe N800-only) - * tea5761 (FM tuner) - * (serial 0) - * GPS - * (some serial port) - * csr41814 (Bluetooth) - */ - n8x0_gpio_setup(s); - n8x0_nand_setup(s); - n8x0_i2c_setup(s); - if (model == 800) { - n800_tsc_kbd_setup(s); - } else if (model == 810) { - n810_tsc_setup(s); - n810_kbd_setup(s); - } - n8x0_spi_setup(s); - n8x0_dss_setup(s); - n8x0_cbus_setup(s); - n8x0_usb_setup(s); - - if (machine->kernel_filename) { - /* Or at the linux loader. */ - arm_load_kernel(s->mpu->cpu, machine, binfo); - - qemu_register_reset(n8x0_boot_init, s); - } - - if (option_rom[0].name && - (machine->boot_config.order[0] == 'n' || !machine->kernel_filename)) { - uint8_t *nolo_tags = g_new(uint8_t, 0x10000); - /* No, wait, better start at the ROM. */ - s->mpu->cpu->env.regs[15] = OMAP2_Q2_BASE + 0x400000; - - /* - * This is intended for loading the `secondary.bin' program from - * Nokia images (the NOLO bootloader). The entry point seems - * to be at OMAP2_Q2_BASE + 0x400000. - * - * The `2nd.bin' files contain some kind of earlier boot code and - * for them the entry point needs to be set to OMAP2_SRAM_BASE. - * - * The code above is for loading the `zImage' file from Nokia - * images. - */ - if (load_image_targphys(option_rom[0].name, - OMAP2_Q2_BASE + 0x400000, - machine->ram_size - 0x400000) < 0) { - error_report("Failed to load secondary bootloader %s", - option_rom[0].name); - exit(EXIT_FAILURE); - } - - n800_setup_nolo_tags(nolo_tags); - cpu_physical_memory_write(OMAP2_SRAM_BASE, nolo_tags, 0x10000); - g_free(nolo_tags); - } -} - -static struct arm_boot_info n800_binfo = { - .loader_start = OMAP2_Q2_BASE, - .board_id = 0x4f7, - .atag_board = n800_atag_setup, -}; - -static struct arm_boot_info n810_binfo = { - .loader_start = OMAP2_Q2_BASE, - /* 0x60c and 0x6bf (WiMAX Edition) have been assigned but are not - * used by some older versions of the bootloader and 5555 is used - * instead (including versions that shipped with many devices). */ - .board_id = 0x60c, - .atag_board = n810_atag_setup, -}; - -static void n800_init(MachineState *machine) -{ - n8x0_init(machine, &n800_binfo, 800); -} - -static void n810_init(MachineState *machine) -{ - n8x0_init(machine, &n810_binfo, 810); -} - -static void n800_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Nokia N800 tablet aka. RX-34 (OMAP2420)"; - mc->init = n800_init; - mc->default_boot_order = ""; - mc->ignore_memory_transaction_failures = true; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("arm1136-r2"); - /* Actually two chips of 0x4000000 bytes each */ - mc->default_ram_size = 0x08000000; - mc->default_ram_id = "omap2.dram"; - mc->deprecation_reason = "machine is old and unmaintained"; - - machine_add_audiodev_property(mc); -} - -static const TypeInfo n800_type = { - .name = MACHINE_TYPE_NAME("n800"), - .parent = TYPE_MACHINE, - .class_init = n800_class_init, -}; - -static void n810_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Nokia N810 tablet aka. RX-44 (OMAP2420)"; - mc->init = n810_init; - mc->default_boot_order = ""; - mc->ignore_memory_transaction_failures = true; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("arm1136-r2"); - /* Actually two chips of 0x4000000 bytes each */ - mc->default_ram_size = 0x08000000; - mc->default_ram_id = "omap2.dram"; - mc->deprecation_reason = "machine is old and unmaintained"; - - machine_add_audiodev_property(mc); -} - -static const TypeInfo n810_type = { - .name = MACHINE_TYPE_NAME("n810"), - .parent = TYPE_MACHINE, - .class_init = n810_class_init, -}; - -static void nseries_machine_init(void) -{ - type_register_static(&n800_type); - type_register_static(&n810_type); -} - -type_init(nseries_machine_init) diff --git a/tests/qtest/libqos/arm-n800-machine.c b/tests/qtest/libqos/arm-n800-machine.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/tests/qtest/libqos/arm-n800-machine.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * libqos driver framework - * - * Copyright (c) 2019 Red Hat, Inc. - * - * Author: Paolo Bonzini <pbonzini@redhat.com> - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License version 2.1 as published by the Free Software Foundation. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/> - */ - -#include "qemu/osdep.h" -#include "../libqtest.h" -#include "libqos-malloc.h" -#include "qgraph.h" -#include "i2c.h" - -#define ARM_PAGE_SIZE 4096 -#define N800_RAM_START 0x80000000 -#define N800_RAM_END 0x88000000 - -typedef struct QN800Machine QN800Machine; - -struct QN800Machine { - QOSGraphObject obj; - QGuestAllocator alloc; - OMAPI2C i2c_1; -}; - -static void *n800_get_driver(void *object, const char *interface) -{ - QN800Machine *machine = object; - if (!g_strcmp0(interface, "memory")) { - return &machine->alloc; - } - - fprintf(stderr, "%s not present in arm/n800\n", interface); - g_assert_not_reached(); -} - -static QOSGraphObject *n800_get_device(void *obj, const char *device) -{ - QN800Machine *machine = obj; - if (!g_strcmp0(device, "omap_i2c")) { - return &machine->i2c_1.obj; - } - - fprintf(stderr, "%s not present in arm/n800\n", device); - g_assert_not_reached(); -} - -static void n800_destructor(QOSGraphObject *obj) -{ - QN800Machine *machine = (QN800Machine *) obj; - alloc_destroy(&machine->alloc); -} - -static void *qos_create_machine_arm_n800(QTestState *qts) -{ - QN800Machine *machine = g_new0(QN800Machine, 1); - - alloc_init(&machine->alloc, 0, - N800_RAM_START, - N800_RAM_END, - ARM_PAGE_SIZE); - machine->obj.get_device = n800_get_device; - machine->obj.get_driver = n800_get_driver; - machine->obj.destructor = n800_destructor; - - omap_i2c_init(&machine->i2c_1, qts, 0x48070000); - return &machine->obj; -} - -static void n800_register_nodes(void) -{ - QOSGraphEdgeOptions edge = { - .extra_device_opts = "bus=i2c-bus.0" - }; - qos_node_create_machine("arm/n800", qos_create_machine_arm_n800); - qos_node_contains("arm/n800", "omap_i2c", &edge, NULL); -} - -libqos_init(n800_register_nodes); diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_MUSICPAL', if_true: files('musicpal.c')) arm_ss.add(when: 'CONFIG_NETDUINOPLUS2', if_true: files('netduinoplus2.c')) arm_ss.add(when: 'CONFIG_OLIMEX_STM32_H405', if_true: files('olimex-stm32-h405.c')) arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c', 'npcm7xx_boards.c')) -arm_ss.add(when: 'CONFIG_NSERIES', if_true: files('nseries.c')) arm_ss.add(when: 'CONFIG_REALVIEW', if_true: files('realview.c')) arm_ss.add(when: 'CONFIG_SBSA_REF', if_true: files('sbsa-ref.c')) arm_ss.add(when: 'CONFIG_STELLARIS', if_true: files('stellaris.c')) diff --git a/tests/avocado/machine_arm_n8x0.py b/tests/avocado/machine_arm_n8x0.py deleted file mode 100755 index XXXXXXX..XXXXXXX --- a/tests/avocado/machine_arm_n8x0.py +++ /dev/null @@ -XXX,XX +XXX,XX @@ -# Functional test that boots a Linux kernel and checks the console -# -# Copyright (c) 2020 Red Hat, Inc. -# -# Author: -# Thomas Huth <thuth@redhat.com> -# -# This work is licensed under the terms of the GNU GPL, version 2 or -# later. See the COPYING file in the top-level directory. - -import os - -from avocado import skipUnless -from avocado_qemu import QemuSystemTest -from avocado_qemu import wait_for_console_pattern - -class N8x0Machine(QemuSystemTest): - """Boots the Linux kernel and checks that the console is operational""" - - timeout = 90 - - def __do_test_n8x0(self): - kernel_url = ('http://stskeeps.subnetmask.net/meego-n8x0/' - 'meego-arm-n8x0-1.0.80.20100712.1431-' - 'vmlinuz-2.6.35~rc4-129.1-n8x0') - kernel_hash = 'e9d5ab8d7548923a0061b6fbf601465e479ed269' - kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) - - self.vm.set_console(console_index=1) - self.vm.add_args('-kernel', kernel_path, - '-append', 'printk.time=0 console=ttyS1') - self.vm.launch() - wait_for_console_pattern(self, 'TSC2005 driver initializing') - - @skipUnless(os.getenv('AVOCADO_ALLOW_UNTRUSTED_CODE'), 'untrusted code') - def test_n800(self): - """ - :avocado: tags=arch:arm - :avocado: tags=machine:n800 - """ - self.__do_test_n8x0() - - @skipUnless(os.getenv('AVOCADO_ALLOW_UNTRUSTED_CODE'), 'untrusted code') - def test_n810(self): - """ - :avocado: tags=arch:arm - :avocado: tags=machine:n810 - """ - self.__do_test_n8x0() diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqos/meson.build +++ b/tests/qtest/libqos/meson.build @@ -XXX,XX +XXX,XX @@ libqos_srcs = files( # qgraph machines: 'aarch64-xlnx-zcu102-machine.c', 'arm-imx25-pdk-machine.c', - 'arm-n800-machine.c', 'arm-raspi2-machine.c', 'arm-sabrelite-machine.c', 'arm-smdkc210-machine.c', -- 2.34.1 The devices in hw/misc/cbus.c were used only by the now-removed nseries machine types, so they can be removed. As this is the last use of the CONFIG_NSERIES define we can remove that from KConfig now. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-27-peter.maydell@linaro.org --- MAINTAINERS | 2 - include/hw/misc/cbus.h | 31 --- hw/misc/cbus.c | 619 ----------------------------------------- hw/arm/Kconfig | 14 - hw/misc/meson.build | 1 - 5 files changed, 667 deletions(-) delete mode 100644 include/hw/misc/cbus.h delete mode 100644 hw/misc/cbus.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/display/blizzard.c F: hw/input/lm832x.c F: hw/input/tsc2005.c F: hw/input/tsc210x.c -F: hw/misc/cbus.c F: hw/rtc/twl92230.c F: include/hw/display/blizzard.h F: include/hw/input/lm832x.h F: include/hw/input/tsc2xxx.h -F: include/hw/misc/cbus.h Raspberry Pi M: Peter Maydell <peter.maydell@linaro.org> diff --git a/include/hw/misc/cbus.h b/include/hw/misc/cbus.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/hw/misc/cbus.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * CBUS three-pin bus and the Retu / Betty / Tahvo / Vilma / Avilma / - * Hinku / Vinku / Ahne / Pihi chips used in various Nokia platforms. - * Based on reverse-engineering of a linux driver. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - */ - -#ifndef HW_MISC_CBUS_H -#define HW_MISC_CBUS_H - - -typedef struct { - qemu_irq clk; - qemu_irq dat; - qemu_irq sel; -} CBus; - -CBus *cbus_init(qemu_irq dat_out); -void cbus_attach(CBus *bus, void *slave_opaque); - -void *retu_init(qemu_irq irq, int vilma); -void *tahvo_init(qemu_irq irq, int betty); - -void retu_key_event(void *retu, int state); - -#endif diff --git a/hw/misc/cbus.c b/hw/misc/cbus.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/misc/cbus.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * CBUS three-pin bus and the Retu / Betty / Tahvo / Vilma / Avilma / - * Hinku / Vinku / Ahne / Pihi chips used in various Nokia platforms. - * Based on reverse-engineering of a linux driver. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "hw/hw.h" -#include "hw/irq.h" -#include "hw/misc/cbus.h" -#include "sysemu/runstate.h" - -//#define DEBUG - -typedef struct { - void *opaque; - void (*io)(void *opaque, int rw, int reg, uint16_t *val); - int addr; -} CBusSlave; - -typedef struct { - CBus cbus; - - int sel; - int dat; - int clk; - int bit; - int dir; - uint16_t val; - qemu_irq dat_out; - - int addr; - int reg; - int rw; - enum { - cbus_address, - cbus_value, - } cycle; - - CBusSlave *slave[8]; -} CBusPriv; - -static void cbus_io(CBusPriv *s) -{ - if (s->slave[s->addr]) - s->slave[s->addr]->io(s->slave[s->addr]->opaque, - s->rw, s->reg, &s->val); - else - hw_error("%s: bad slave address %i\n", __func__, s->addr); -} - -static void cbus_cycle(CBusPriv *s) -{ - switch (s->cycle) { - case cbus_address: - s->addr = (s->val >> 6) & 7; - s->rw = (s->val >> 5) & 1; - s->reg = (s->val >> 0) & 0x1f; - - s->cycle = cbus_value; - s->bit = 15; - s->dir = !s->rw; - s->val = 0; - - if (s->rw) - cbus_io(s); - break; - - case cbus_value: - if (!s->rw) - cbus_io(s); - - s->cycle = cbus_address; - s->bit = 8; - s->dir = 1; - s->val = 0; - break; - } -} - -static void cbus_clk(void *opaque, int line, int level) -{ - CBusPriv *s = (CBusPriv *) opaque; - - if (!s->sel && level && !s->clk) { - if (s->dir) - s->val |= s->dat << (s->bit --); - else - qemu_set_irq(s->dat_out, (s->val >> (s->bit --)) & 1); - - if (s->bit < 0) - cbus_cycle(s); - } - - s->clk = level; -} - -static void cbus_dat(void *opaque, int line, int level) -{ - CBusPriv *s = (CBusPriv *) opaque; - - s->dat = level; -} - -static void cbus_sel(void *opaque, int line, int level) -{ - CBusPriv *s = (CBusPriv *) opaque; - - if (!level) { - s->dir = 1; - s->bit = 8; - s->val = 0; - } - - s->sel = level; -} - -CBus *cbus_init(qemu_irq dat) -{ - CBusPriv *s = g_malloc0(sizeof(*s)); - - s->dat_out = dat; - s->cbus.clk = qemu_allocate_irq(cbus_clk, s, 0); - s->cbus.dat = qemu_allocate_irq(cbus_dat, s, 0); - s->cbus.sel = qemu_allocate_irq(cbus_sel, s, 0); - - s->sel = 1; - s->clk = 0; - s->dat = 0; - - return &s->cbus; -} - -void cbus_attach(CBus *bus, void *slave_opaque) -{ - CBusSlave *slave = (CBusSlave *) slave_opaque; - CBusPriv *s = (CBusPriv *) bus; - - s->slave[slave->addr] = slave; -} - -/* Retu/Vilma */ -typedef struct { - uint16_t irqst; - uint16_t irqen; - uint16_t cc[2]; - int channel; - uint16_t result[16]; - uint16_t sample; - uint16_t status; - - struct { - uint16_t cal; - } rtc; - - int is_vilma; - qemu_irq irq; - CBusSlave cbus; -} CBusRetu; - -static void retu_interrupt_update(CBusRetu *s) -{ - qemu_set_irq(s->irq, s->irqst & ~s->irqen); -} - -#define RETU_REG_ASICR 0x00 /* (RO) ASIC ID & revision */ -#define RETU_REG_IDR 0x01 /* (T) Interrupt ID */ -#define RETU_REG_IMR 0x02 /* (RW) Interrupt mask */ -#define RETU_REG_RTCDSR 0x03 /* (RW) RTC seconds register */ -#define RETU_REG_RTCHMR 0x04 /* (RO) RTC hours and minutes reg */ -#define RETU_REG_RTCHMAR 0x05 /* (RW) RTC hours and minutes set reg */ -#define RETU_REG_RTCCALR 0x06 /* (RW) RTC calibration register */ -#define RETU_REG_ADCR 0x08 /* (RW) ADC result register */ -#define RETU_REG_ADCSCR 0x09 /* (RW) ADC sample control register */ -#define RETU_REG_AFCR 0x0a /* (RW) AFC register */ -#define RETU_REG_ANTIFR 0x0b /* (RW) AntiF register */ -#define RETU_REG_CALIBR 0x0c /* (RW) CalibR register*/ -#define RETU_REG_CCR1 0x0d /* (RW) Common control register 1 */ -#define RETU_REG_CCR2 0x0e /* (RW) Common control register 2 */ -#define RETU_REG_RCTRL_CLR 0x0f /* (T) Regulator clear register */ -#define RETU_REG_RCTRL_SET 0x10 /* (T) Regulator set register */ -#define RETU_REG_TXCR 0x11 /* (RW) TxC register */ -#define RETU_REG_STATUS 0x16 /* (RO) Status register */ -#define RETU_REG_WATCHDOG 0x17 /* (RW) Watchdog register */ -#define RETU_REG_AUDTXR 0x18 /* (RW) Audio Codec Tx register */ -#define RETU_REG_AUDPAR 0x19 /* (RW) AudioPA register */ -#define RETU_REG_AUDRXR1 0x1a /* (RW) Audio receive register 1 */ -#define RETU_REG_AUDRXR2 0x1b /* (RW) Audio receive register 2 */ -#define RETU_REG_SGR1 0x1c /* (RW) */ -#define RETU_REG_SCR1 0x1d /* (RW) */ -#define RETU_REG_SGR2 0x1e /* (RW) */ -#define RETU_REG_SCR2 0x1f /* (RW) */ - -/* Retu Interrupt sources */ -enum { - retu_int_pwr = 0, /* Power button */ - retu_int_char = 1, /* Charger */ - retu_int_rtcs = 2, /* Seconds */ - retu_int_rtcm = 3, /* Minutes */ - retu_int_rtcd = 4, /* Days */ - retu_int_rtca = 5, /* Alarm */ - retu_int_hook = 6, /* Hook */ - retu_int_head = 7, /* Headset */ - retu_int_adcs = 8, /* ADC sample */ -}; - -/* Retu ADC channel wiring */ -enum { - retu_adc_bsi = 1, /* BSI */ - retu_adc_batt_temp = 2, /* Battery temperature */ - retu_adc_chg_volt = 3, /* Charger voltage */ - retu_adc_head_det = 4, /* Headset detection */ - retu_adc_hook_det = 5, /* Hook detection */ - retu_adc_rf_gp = 6, /* RF GP */ - retu_adc_tx_det = 7, /* Wideband Tx detection */ - retu_adc_batt_volt = 8, /* Battery voltage */ - retu_adc_sens = 10, /* Light sensor */ - retu_adc_sens_temp = 11, /* Light sensor temperature */ - retu_adc_bbatt_volt = 12, /* Backup battery voltage */ - retu_adc_self_temp = 13, /* RETU temperature */ -}; - -static inline uint16_t retu_read(CBusRetu *s, int reg) -{ -#ifdef DEBUG - printf("RETU read at %02x\n", reg); -#endif - - switch (reg) { - case RETU_REG_ASICR: - return 0x0215 | (s->is_vilma << 7); - - case RETU_REG_IDR: /* TODO: Or is this ffs(s->irqst)? */ - return s->irqst; - - case RETU_REG_IMR: - return s->irqen; - - case RETU_REG_RTCDSR: - case RETU_REG_RTCHMR: - case RETU_REG_RTCHMAR: - /* TODO */ - return 0x0000; - - case RETU_REG_RTCCALR: - return s->rtc.cal; - - case RETU_REG_ADCR: - return (s->channel << 10) | s->result[s->channel]; - case RETU_REG_ADCSCR: - return s->sample; - - case RETU_REG_AFCR: - case RETU_REG_ANTIFR: - case RETU_REG_CALIBR: - /* TODO */ - return 0x0000; - - case RETU_REG_CCR1: - return s->cc[0]; - case RETU_REG_CCR2: - return s->cc[1]; - - case RETU_REG_RCTRL_CLR: - case RETU_REG_RCTRL_SET: - case RETU_REG_TXCR: - /* TODO */ - return 0x0000; - - case RETU_REG_STATUS: - return s->status; - - case RETU_REG_WATCHDOG: - case RETU_REG_AUDTXR: - case RETU_REG_AUDPAR: - case RETU_REG_AUDRXR1: - case RETU_REG_AUDRXR2: - case RETU_REG_SGR1: - case RETU_REG_SCR1: - case RETU_REG_SGR2: - case RETU_REG_SCR2: - /* TODO */ - return 0x0000; - - default: - hw_error("%s: bad register %02x\n", __func__, reg); - } -} - -static inline void retu_write(CBusRetu *s, int reg, uint16_t val) -{ -#ifdef DEBUG - printf("RETU write of %04x at %02x\n", val, reg); -#endif - - switch (reg) { - case RETU_REG_IDR: - s->irqst ^= val; - retu_interrupt_update(s); - break; - - case RETU_REG_IMR: - s->irqen = val; - retu_interrupt_update(s); - break; - - case RETU_REG_RTCDSR: - case RETU_REG_RTCHMAR: - /* TODO */ - break; - - case RETU_REG_RTCCALR: - s->rtc.cal = val; - break; - - case RETU_REG_ADCR: - s->channel = (val >> 10) & 0xf; - s->irqst |= 1 << retu_int_adcs; - retu_interrupt_update(s); - break; - case RETU_REG_ADCSCR: - s->sample &= ~val; - break; - - case RETU_REG_AFCR: - case RETU_REG_ANTIFR: - case RETU_REG_CALIBR: - - case RETU_REG_CCR1: - s->cc[0] = val; - break; - case RETU_REG_CCR2: - s->cc[1] = val; - break; - - case RETU_REG_RCTRL_CLR: - case RETU_REG_RCTRL_SET: - /* TODO */ - break; - - case RETU_REG_WATCHDOG: - if (val == 0 && (s->cc[0] & 2)) - qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); - break; - - case RETU_REG_TXCR: - case RETU_REG_AUDTXR: - case RETU_REG_AUDPAR: - case RETU_REG_AUDRXR1: - case RETU_REG_AUDRXR2: - case RETU_REG_SGR1: - case RETU_REG_SCR1: - case RETU_REG_SGR2: - case RETU_REG_SCR2: - /* TODO */ - break; - - default: - hw_error("%s: bad register %02x\n", __func__, reg); - } -} - -static void retu_io(void *opaque, int rw, int reg, uint16_t *val) -{ - CBusRetu *s = (CBusRetu *) opaque; - - if (rw) - *val = retu_read(s, reg); - else - retu_write(s, reg, *val); -} - -void *retu_init(qemu_irq irq, int vilma) -{ - CBusRetu *s = g_malloc0(sizeof(*s)); - - s->irq = irq; - s->irqen = 0xffff; - s->irqst = 0x0000; - s->status = 0x0020; - s->is_vilma = !!vilma; - s->rtc.cal = 0x01; - s->result[retu_adc_bsi] = 0x3c2; - s->result[retu_adc_batt_temp] = 0x0fc; - s->result[retu_adc_chg_volt] = 0x165; - s->result[retu_adc_head_det] = 123; - s->result[retu_adc_hook_det] = 1023; - s->result[retu_adc_rf_gp] = 0x11; - s->result[retu_adc_tx_det] = 0x11; - s->result[retu_adc_batt_volt] = 0x250; - s->result[retu_adc_sens] = 2; - s->result[retu_adc_sens_temp] = 0x11; - s->result[retu_adc_bbatt_volt] = 0x3d0; - s->result[retu_adc_self_temp] = 0x330; - - s->cbus.opaque = s; - s->cbus.io = retu_io; - s->cbus.addr = 1; - - return &s->cbus; -} - -void retu_key_event(void *retu, int state) -{ - CBusSlave *slave = (CBusSlave *) retu; - CBusRetu *s = (CBusRetu *) slave->opaque; - - s->irqst |= 1 << retu_int_pwr; - retu_interrupt_update(s); - - if (state) - s->status &= ~(1 << 5); - else - s->status |= 1 << 5; -} - -#if 0 -static void retu_head_event(void *retu, int state) -{ - CBusSlave *slave = (CBusSlave *) retu; - CBusRetu *s = (CBusRetu *) slave->opaque; - - if ((s->cc[0] & 0x500) == 0x500) { /* TODO: Which bits? */ - /* TODO: reissue the interrupt every 100ms or so. */ - s->irqst |= 1 << retu_int_head; - retu_interrupt_update(s); - } - - if (state) - s->result[retu_adc_head_det] = 50; - else - s->result[retu_adc_head_det] = 123; -} - -static void retu_hook_event(void *retu, int state) -{ - CBusSlave *slave = (CBusSlave *) retu; - CBusRetu *s = (CBusRetu *) slave->opaque; - - if ((s->cc[0] & 0x500) == 0x500) { - /* TODO: reissue the interrupt every 100ms or so. */ - s->irqst |= 1 << retu_int_hook; - retu_interrupt_update(s); - } - - if (state) - s->result[retu_adc_hook_det] = 50; - else - s->result[retu_adc_hook_det] = 123; -} -#endif - -/* Tahvo/Betty */ -typedef struct { - uint16_t irqst; - uint16_t irqen; - uint8_t charger; - uint8_t backlight; - uint16_t usbr; - uint16_t power; - - int is_betty; - qemu_irq irq; - CBusSlave cbus; -} CBusTahvo; - -static void tahvo_interrupt_update(CBusTahvo *s) -{ - qemu_set_irq(s->irq, s->irqst & ~s->irqen); -} - -#define TAHVO_REG_ASICR 0x00 /* (RO) ASIC ID & revision */ -#define TAHVO_REG_IDR 0x01 /* (T) Interrupt ID */ -#define TAHVO_REG_IDSR 0x02 /* (RO) Interrupt status */ -#define TAHVO_REG_IMR 0x03 /* (RW) Interrupt mask */ -#define TAHVO_REG_CHAPWMR 0x04 /* (RW) Charger PWM */ -#define TAHVO_REG_LEDPWMR 0x05 /* (RW) LED PWM */ -#define TAHVO_REG_USBR 0x06 /* (RW) USB control */ -#define TAHVO_REG_RCR 0x07 /* (RW) Some kind of power management */ -#define TAHVO_REG_CCR1 0x08 /* (RW) Common control register 1 */ -#define TAHVO_REG_CCR2 0x09 /* (RW) Common control register 2 */ -#define TAHVO_REG_TESTR1 0x0a /* (RW) Test register 1 */ -#define TAHVO_REG_TESTR2 0x0b /* (RW) Test register 2 */ -#define TAHVO_REG_NOPR 0x0c /* (RW) Number of periods */ -#define TAHVO_REG_FRR 0x0d /* (RO) FR */ - -static inline uint16_t tahvo_read(CBusTahvo *s, int reg) -{ -#ifdef DEBUG - printf("TAHVO read at %02x\n", reg); -#endif - - switch (reg) { - case TAHVO_REG_ASICR: - return 0x0021 | (s->is_betty ? 0x0b00 : 0x0300); /* 22 in N810 */ - - case TAHVO_REG_IDR: - case TAHVO_REG_IDSR: /* XXX: what does this do? */ - return s->irqst; - - case TAHVO_REG_IMR: - return s->irqen; - - case TAHVO_REG_CHAPWMR: - return s->charger; - - case TAHVO_REG_LEDPWMR: - return s->backlight; - - case TAHVO_REG_USBR: - return s->usbr; - - case TAHVO_REG_RCR: - return s->power; - - case TAHVO_REG_CCR1: - case TAHVO_REG_CCR2: - case TAHVO_REG_TESTR1: - case TAHVO_REG_TESTR2: - case TAHVO_REG_NOPR: - case TAHVO_REG_FRR: - return 0x0000; - - default: - hw_error("%s: bad register %02x\n", __func__, reg); - } -} - -static inline void tahvo_write(CBusTahvo *s, int reg, uint16_t val) -{ -#ifdef DEBUG - printf("TAHVO write of %04x at %02x\n", val, reg); -#endif - - switch (reg) { - case TAHVO_REG_IDR: - s->irqst ^= val; - tahvo_interrupt_update(s); - break; - - case TAHVO_REG_IMR: - s->irqen = val; - tahvo_interrupt_update(s); - break; - - case TAHVO_REG_CHAPWMR: - s->charger = val; - break; - - case TAHVO_REG_LEDPWMR: - if (s->backlight != (val & 0x7f)) { - s->backlight = val & 0x7f; - printf("%s: LCD backlight now at %i / 127\n", - __func__, s->backlight); - } - break; - - case TAHVO_REG_USBR: - s->usbr = val; - break; - - case TAHVO_REG_RCR: - s->power = val; - break; - - case TAHVO_REG_CCR1: - case TAHVO_REG_CCR2: - case TAHVO_REG_TESTR1: - case TAHVO_REG_TESTR2: - case TAHVO_REG_NOPR: - case TAHVO_REG_FRR: - break; - - default: - hw_error("%s: bad register %02x\n", __func__, reg); - } -} - -static void tahvo_io(void *opaque, int rw, int reg, uint16_t *val) -{ - CBusTahvo *s = (CBusTahvo *) opaque; - - if (rw) - *val = tahvo_read(s, reg); - else - tahvo_write(s, reg, *val); -} - -void *tahvo_init(qemu_irq irq, int betty) -{ - CBusTahvo *s = g_malloc0(sizeof(*s)); - - s->irq = irq; - s->irqen = 0xffff; - s->irqst = 0x0000; - s->is_betty = !!betty; - - s->cbus.opaque = s; - s->cbus.io = tahvo_io; - s->cbus.addr = 2; - - return &s->cbus; -} 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 OLIMEX_STM32_H405 depends on TCG && ARM select STM32F405_SOC -config NSERIES - bool - default y - depends on TCG && ARM - select OMAP - select TMP105 # temperature sensor - select BLIZZARD # LCD/TV controller - select ONENAND - select TSC210X # touchscreen/sensors/audio - select TSC2005 # touchscreen/sensors/keypad - select LM832X # GPIO keyboard chip - select TWL92230 # energy-management - select TUSB6010 - config OMAP bool select FRAMEBUFFER diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_ALLWINNER_R40', if_true: files('allwinner-r40-ccu.c' system_ss.add(when: 'CONFIG_ALLWINNER_R40', if_true: files('allwinner-r40-dramc.c')) system_ss.add(when: 'CONFIG_AXP2XX_PMU', if_true: files('axp2xx.c')) system_ss.add(when: 'CONFIG_REALVIEW', if_true: files('arm_sysctl.c')) -system_ss.add(when: 'CONFIG_NSERIES', if_true: files('cbus.c')) system_ss.add(when: 'CONFIG_ECCMEMCTL', if_true: files('eccmemctl.c')) system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210_pmu.c', 'exynos4210_clk.c', 'exynos4210_rng.c')) system_ss.add(when: 'CONFIG_IMX', if_true: files( -- 2.34.1 Remove the blizzard display device, which was only used with the n800 and n810 machines. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20240903160751.4100218-28-peter.maydell@linaro.org --- MAINTAINERS | 2 - include/hw/display/blizzard.h | 21 - hw/display/blizzard.c | 1026 --------------------------------- hw/display/Kconfig | 3 - hw/display/meson.build | 1 - 5 files changed, 1053 deletions(-) delete mode 100644 include/hw/display/blizzard.h delete mode 100644 hw/display/blizzard.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ nSeries M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes -F: hw/display/blizzard.c F: hw/input/lm832x.c F: hw/input/tsc2005.c F: hw/input/tsc210x.c F: hw/rtc/twl92230.c -F: include/hw/display/blizzard.h F: include/hw/input/lm832x.h F: include/hw/input/tsc2xxx.h diff --git a/include/hw/display/blizzard.h b/include/hw/display/blizzard.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/hw/display/blizzard.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Epson S1D13744/S1D13745 (Blizzard/Hailstorm/Tornado) LCD/TV controller. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - */ - -#ifndef HW_DISPLAY_BLIZZARD_H -#define HW_DISPLAY_BLIZZARD_H - - -void *s1d13745_init(qemu_irq gpio_int); -void s1d13745_write(void *opaque, int dc, uint16_t value); -void s1d13745_write_block(void *opaque, int dc, - void *buf, size_t len, int pitch); -uint16_t s1d13745_read(void *opaque, int dc); - -#endif diff --git a/hw/display/blizzard.c b/hw/display/blizzard.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/display/blizzard.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Epson S1D13744/S1D13745 (Blizzard/Hailstorm/Tornado) LCD/TV controller. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "qemu/bitops.h" -#include "ui/console.h" -#include "hw/display/blizzard.h" -#include "ui/pixel_ops.h" - -typedef void (*blizzard_fn_t)(uint8_t *, const uint8_t *, unsigned int); - -typedef struct { - uint8_t reg; - uint32_t addr; - int swallow; - - int pll; - int pll_range; - int pll_ctrl; - uint8_t pll_mode; - uint8_t clksel; - int memenable; - int memrefresh; - uint8_t timing[3]; - int priority; - - uint8_t lcd_config; - int x; - int y; - int skipx; - int skipy; - uint8_t hndp; - uint8_t vndp; - uint8_t hsync; - uint8_t vsync; - uint8_t pclk; - uint8_t u; - uint8_t v; - uint8_t yrc[2]; - int ix[2]; - int iy[2]; - int ox[2]; - int oy[2]; - - int enable; - int blank; - int bpp; - int invalidate; - int mx[2]; - int my[2]; - uint8_t mode; - uint8_t effect; - uint8_t iformat; - uint8_t source; - QemuConsole *con; - blizzard_fn_t *line_fn_tab[2]; - void *fb; - - uint8_t hssi_config[3]; - uint8_t tv_config; - uint8_t tv_timing[4]; - uint8_t vbi; - uint8_t tv_x; - uint8_t tv_y; - uint8_t tv_test; - uint8_t tv_filter_config; - uint8_t tv_filter_idx; - uint8_t tv_filter_coeff[0x20]; - uint8_t border_r; - uint8_t border_g; - uint8_t border_b; - uint8_t gamma_config; - uint8_t gamma_idx; - uint8_t gamma_lut[0x100]; - uint8_t matrix_ena; - uint8_t matrix_coeff[0x12]; - uint8_t matrix_r; - uint8_t matrix_g; - uint8_t matrix_b; - uint8_t pm; - uint8_t status; - uint8_t rgbgpio_dir; - uint8_t rgbgpio; - uint8_t gpio_dir; - uint8_t gpio; - uint8_t gpio_edge[2]; - uint8_t gpio_irq; - uint8_t gpio_pdown; - - struct { - int x; - int y; - int dx; - int dy; - int len; - int buflen; - void *buf; - void *data; - uint16_t *ptr; - int angle; - int pitch; - blizzard_fn_t line_fn; - } data; -} BlizzardState; - -/* Bytes(!) per pixel */ -static const int blizzard_iformat_bpp[0x10] = { - 0, - 2, /* RGB 5:6:5*/ - 3, /* RGB 6:6:6 mode 1 */ - 3, /* RGB 8:8:8 mode 1 */ - 0, 0, - 4, /* RGB 6:6:6 mode 2 */ - 4, /* RGB 8:8:8 mode 2 */ - 0, /* YUV 4:2:2 */ - 0, /* YUV 4:2:0 */ - 0, 0, 0, 0, 0, 0, -}; - -static void blizzard_window(BlizzardState *s) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - uint8_t *src, *dst; - int bypp[2]; - int bypl[3]; - int y; - blizzard_fn_t fn = s->data.line_fn; - - if (!fn) - return; - if (s->mx[0] > s->data.x) - s->mx[0] = s->data.x; - if (s->my[0] > s->data.y) - s->my[0] = s->data.y; - if (s->mx[1] < s->data.x + s->data.dx) - s->mx[1] = s->data.x + s->data.dx; - if (s->my[1] < s->data.y + s->data.dy) - s->my[1] = s->data.y + s->data.dy; - - bypp[0] = s->bpp; - bypp[1] = surface_bytes_per_pixel(surface); - bypl[0] = bypp[0] * s->data.pitch; - bypl[1] = bypp[1] * s->x; - bypl[2] = bypp[0] * s->data.dx; - - src = s->data.data; - dst = s->fb + bypl[1] * s->data.y + bypp[1] * s->data.x; - for (y = s->data.dy; y > 0; y --, src += bypl[0], dst += bypl[1]) - fn(dst, src, bypl[2]); -} - -static int blizzard_transfer_setup(BlizzardState *s) -{ - if (s->source > 3 || !s->bpp || - s->ix[1] < s->ix[0] || s->iy[1] < s->iy[0]) - return 0; - - s->data.angle = s->effect & 3; - s->data.line_fn = s->line_fn_tab[!!s->data.angle][s->iformat]; - s->data.x = s->ix[0]; - s->data.y = s->iy[0]; - s->data.dx = s->ix[1] - s->ix[0] + 1; - s->data.dy = s->iy[1] - s->iy[0] + 1; - s->data.len = s->bpp * s->data.dx * s->data.dy; - s->data.pitch = s->data.dx; - if (s->data.len > s->data.buflen) { - s->data.buf = g_realloc(s->data.buf, s->data.len); - s->data.buflen = s->data.len; - } - s->data.ptr = s->data.buf; - s->data.data = s->data.buf; - s->data.len /= 2; - return 1; -} - -static void blizzard_reset(BlizzardState *s) -{ - s->reg = 0; - s->swallow = 0; - - s->pll = 9; - s->pll_range = 1; - s->pll_ctrl = 0x14; - s->pll_mode = 0x32; - s->clksel = 0x00; - s->memenable = 0; - s->memrefresh = 0x25c; - s->timing[0] = 0x3f; - s->timing[1] = 0x13; - s->timing[2] = 0x21; - s->priority = 0; - - s->lcd_config = 0x74; - s->x = 8; - s->y = 1; - s->skipx = 0; - s->skipy = 0; - s->hndp = 3; - s->vndp = 2; - s->hsync = 1; - s->vsync = 1; - s->pclk = 0x80; - - s->ix[0] = 0; - s->ix[1] = 0; - s->iy[0] = 0; - s->iy[1] = 0; - s->ox[0] = 0; - s->ox[1] = 0; - s->oy[0] = 0; - s->oy[1] = 0; - - s->yrc[0] = 0x00; - s->yrc[1] = 0x30; - s->u = 0; - s->v = 0; - - s->iformat = 3; - s->source = 0; - s->bpp = blizzard_iformat_bpp[s->iformat]; - - s->hssi_config[0] = 0x00; - s->hssi_config[1] = 0x00; - s->hssi_config[2] = 0x01; - s->tv_config = 0x00; - s->tv_timing[0] = 0x00; - s->tv_timing[1] = 0x00; - s->tv_timing[2] = 0x00; - s->tv_timing[3] = 0x00; - s->vbi = 0x10; - s->tv_x = 0x14; - s->tv_y = 0x03; - s->tv_test = 0x00; - s->tv_filter_config = 0x80; - s->tv_filter_idx = 0x00; - s->border_r = 0x10; - s->border_g = 0x80; - s->border_b = 0x80; - s->gamma_config = 0x00; - s->gamma_idx = 0x00; - s->matrix_ena = 0x00; - memset(&s->matrix_coeff, 0, sizeof(s->matrix_coeff)); - s->matrix_r = 0x00; - s->matrix_g = 0x00; - s->matrix_b = 0x00; - s->pm = 0x02; - s->status = 0x00; - s->rgbgpio_dir = 0x00; - s->gpio_dir = 0x00; - s->gpio_edge[0] = 0x00; - s->gpio_edge[1] = 0x00; - s->gpio_irq = 0x00; - s->gpio_pdown = 0xff; -} - -static inline void blizzard_invalidate_display(void *opaque) { - BlizzardState *s = (BlizzardState *) opaque; - - s->invalidate = 1; -} - -static uint16_t blizzard_reg_read(void *opaque, uint8_t reg) -{ - BlizzardState *s = (BlizzardState *) opaque; - - switch (reg) { - case 0x00: /* Revision Code */ - return 0xa5; - - case 0x02: /* Configuration Readback */ - return 0x83; /* Macrovision OK, CNF[2:0] = 3 */ - - case 0x04: /* PLL M-Divider */ - return (s->pll - 1) | (1 << 7); - case 0x06: /* PLL Lock Range Control */ - return s->pll_range; - case 0x08: /* PLL Lock Synthesis Control 0 */ - return s->pll_ctrl & 0xff; - case 0x0a: /* PLL Lock Synthesis Control 1 */ - return s->pll_ctrl >> 8; - case 0x0c: /* PLL Mode Control 0 */ - return s->pll_mode; - - case 0x0e: /* Clock-Source Select */ - return s->clksel; - - case 0x10: /* Memory Controller Activate */ - case 0x14: /* Memory Controller Bank 0 Status Flag */ - return s->memenable; - - case 0x18: /* Auto-Refresh Interval Setting 0 */ - return s->memrefresh & 0xff; - case 0x1a: /* Auto-Refresh Interval Setting 1 */ - return s->memrefresh >> 8; - - case 0x1c: /* Power-On Sequence Timing Control */ - return s->timing[0]; - case 0x1e: /* Timing Control 0 */ - return s->timing[1]; - case 0x20: /* Timing Control 1 */ - return s->timing[2]; - - case 0x24: /* Arbitration Priority Control */ - return s->priority; - - case 0x28: /* LCD Panel Configuration */ - return s->lcd_config; - - case 0x2a: /* LCD Horizontal Display Width */ - return s->x >> 3; - case 0x2c: /* LCD Horizontal Non-display Period */ - return s->hndp; - case 0x2e: /* LCD Vertical Display Height 0 */ - return s->y & 0xff; - case 0x30: /* LCD Vertical Display Height 1 */ - return s->y >> 8; - case 0x32: /* LCD Vertical Non-display Period */ - return s->vndp; - case 0x34: /* LCD HS Pulse-width */ - return s->hsync; - case 0x36: /* LCd HS Pulse Start Position */ - return s->skipx >> 3; - case 0x38: /* LCD VS Pulse-width */ - return s->vsync; - case 0x3a: /* LCD VS Pulse Start Position */ - return s->skipy; - - case 0x3c: /* PCLK Polarity */ - return s->pclk; - - case 0x3e: /* High-speed Serial Interface Tx Configuration Port 0 */ - return s->hssi_config[0]; - case 0x40: /* High-speed Serial Interface Tx Configuration Port 1 */ - return s->hssi_config[1]; - case 0x42: /* High-speed Serial Interface Tx Mode */ - return s->hssi_config[2]; - case 0x44: /* TV Display Configuration */ - return s->tv_config; - case 0x46 ... 0x4c: /* TV Vertical Blanking Interval Data bits */ - return s->tv_timing[(reg - 0x46) >> 1]; - case 0x4e: /* VBI: Closed Caption / XDS Control / Status */ - return s->vbi; - case 0x50: /* TV Horizontal Start Position */ - return s->tv_x; - case 0x52: /* TV Vertical Start Position */ - return s->tv_y; - case 0x54: /* TV Test Pattern Setting */ - return s->tv_test; - case 0x56: /* TV Filter Setting */ - return s->tv_filter_config; - case 0x58: /* TV Filter Coefficient Index */ - return s->tv_filter_idx; - case 0x5a: /* TV Filter Coefficient Data */ - if (s->tv_filter_idx < 0x20) - return s->tv_filter_coeff[s->tv_filter_idx ++]; - return 0; - - case 0x60: /* Input YUV/RGB Translate Mode 0 */ - return s->yrc[0]; - case 0x62: /* Input YUV/RGB Translate Mode 1 */ - return s->yrc[1]; - case 0x64: /* U Data Fix */ - return s->u; - case 0x66: /* V Data Fix */ - return s->v; - - case 0x68: /* Display Mode */ - return s->mode; - - case 0x6a: /* Special Effects */ - return s->effect; - - case 0x6c: /* Input Window X Start Position 0 */ - return s->ix[0] & 0xff; - case 0x6e: /* Input Window X Start Position 1 */ - return s->ix[0] >> 3; - case 0x70: /* Input Window Y Start Position 0 */ - return s->ix[0] & 0xff; - case 0x72: /* Input Window Y Start Position 1 */ - return s->ix[0] >> 3; - case 0x74: /* Input Window X End Position 0 */ - return s->ix[1] & 0xff; - case 0x76: /* Input Window X End Position 1 */ - return s->ix[1] >> 3; - case 0x78: /* Input Window Y End Position 0 */ - return s->ix[1] & 0xff; - case 0x7a: /* Input Window Y End Position 1 */ - return s->ix[1] >> 3; - case 0x7c: /* Output Window X Start Position 0 */ - return s->ox[0] & 0xff; - case 0x7e: /* Output Window X Start Position 1 */ - return s->ox[0] >> 3; - case 0x80: /* Output Window Y Start Position 0 */ - return s->oy[0] & 0xff; - case 0x82: /* Output Window Y Start Position 1 */ - return s->oy[0] >> 3; - case 0x84: /* Output Window X End Position 0 */ - return s->ox[1] & 0xff; - case 0x86: /* Output Window X End Position 1 */ - return s->ox[1] >> 3; - case 0x88: /* Output Window Y End Position 0 */ - return s->oy[1] & 0xff; - case 0x8a: /* Output Window Y End Position 1 */ - return s->oy[1] >> 3; - - case 0x8c: /* Input Data Format */ - return s->iformat; - case 0x8e: /* Data Source Select */ - return s->source; - case 0x90: /* Display Memory Data Port */ - return 0; - - case 0xa8: /* Border Color 0 */ - return s->border_r; - case 0xaa: /* Border Color 1 */ - return s->border_g; - case 0xac: /* Border Color 2 */ - return s->border_b; - - case 0xb4: /* Gamma Correction Enable */ - return s->gamma_config; - case 0xb6: /* Gamma Correction Table Index */ - return s->gamma_idx; - case 0xb8: /* Gamma Correction Table Data */ - return s->gamma_lut[s->gamma_idx ++]; - - case 0xba: /* 3x3 Matrix Enable */ - return s->matrix_ena; - case 0xbc ... 0xde: /* Coefficient Registers */ - return s->matrix_coeff[(reg - 0xbc) >> 1]; - case 0xe0: /* 3x3 Matrix Red Offset */ - return s->matrix_r; - case 0xe2: /* 3x3 Matrix Green Offset */ - return s->matrix_g; - case 0xe4: /* 3x3 Matrix Blue Offset */ - return s->matrix_b; - - case 0xe6: /* Power-save */ - return s->pm; - case 0xe8: /* Non-display Period Control / Status */ - return s->status | (1 << 5); - case 0xea: /* RGB Interface Control */ - return s->rgbgpio_dir; - case 0xec: /* RGB Interface Status */ - return s->rgbgpio; - case 0xee: /* General-purpose IO Pins Configuration */ - return s->gpio_dir; - case 0xf0: /* General-purpose IO Pins Status / Control */ - return s->gpio; - case 0xf2: /* GPIO Positive Edge Interrupt Trigger */ - return s->gpio_edge[0]; - case 0xf4: /* GPIO Negative Edge Interrupt Trigger */ - return s->gpio_edge[1]; - case 0xf6: /* GPIO Interrupt Status */ - return s->gpio_irq; - case 0xf8: /* GPIO Pull-down Control */ - return s->gpio_pdown; - - default: - fprintf(stderr, "%s: unknown register %02x\n", __func__, reg); - return 0; - } -} - -static void blizzard_reg_write(void *opaque, uint8_t reg, uint16_t value) -{ - BlizzardState *s = (BlizzardState *) opaque; - - switch (reg) { - case 0x04: /* PLL M-Divider */ - s->pll = (value & 0x3f) + 1; - break; - case 0x06: /* PLL Lock Range Control */ - s->pll_range = value & 3; - break; - case 0x08: /* PLL Lock Synthesis Control 0 */ - s->pll_ctrl &= 0xf00; - s->pll_ctrl |= (value << 0) & 0x0ff; - break; - case 0x0a: /* PLL Lock Synthesis Control 1 */ - s->pll_ctrl &= 0x0ff; - s->pll_ctrl |= (value << 8) & 0xf00; - break; - case 0x0c: /* PLL Mode Control 0 */ - s->pll_mode = value & 0x77; - if ((value & 3) == 0 || (value & 3) == 3) - fprintf(stderr, "%s: wrong PLL Control bits (%i)\n", - __func__, value & 3); - break; - - case 0x0e: /* Clock-Source Select */ - s->clksel = value & 0xff; - break; - - case 0x10: /* Memory Controller Activate */ - s->memenable = value & 1; - break; - case 0x14: /* Memory Controller Bank 0 Status Flag */ - break; - - case 0x18: /* Auto-Refresh Interval Setting 0 */ - s->memrefresh &= 0xf00; - s->memrefresh |= (value << 0) & 0x0ff; - break; - case 0x1a: /* Auto-Refresh Interval Setting 1 */ - s->memrefresh &= 0x0ff; - s->memrefresh |= (value << 8) & 0xf00; - break; - - case 0x1c: /* Power-On Sequence Timing Control */ - s->timing[0] = value & 0x7f; - break; - case 0x1e: /* Timing Control 0 */ - s->timing[1] = value & 0x17; - break; - case 0x20: /* Timing Control 1 */ - s->timing[2] = value & 0x35; - break; - - case 0x24: /* Arbitration Priority Control */ - s->priority = value & 1; - break; - - case 0x28: /* LCD Panel Configuration */ - s->lcd_config = value & 0xff; - if (value & (1 << 7)) - fprintf(stderr, "%s: data swap not supported!\n", __func__); - break; - - case 0x2a: /* LCD Horizontal Display Width */ - s->x = value << 3; - break; - case 0x2c: /* LCD Horizontal Non-display Period */ - s->hndp = value & 0xff; - break; - case 0x2e: /* LCD Vertical Display Height 0 */ - s->y &= 0x300; - s->y |= (value << 0) & 0x0ff; - break; - case 0x30: /* LCD Vertical Display Height 1 */ - s->y &= 0x0ff; - s->y |= (value << 8) & 0x300; - break; - case 0x32: /* LCD Vertical Non-display Period */ - s->vndp = value & 0xff; - break; - case 0x34: /* LCD HS Pulse-width */ - s->hsync = value & 0xff; - break; - case 0x36: /* LCD HS Pulse Start Position */ - s->skipx = value & 0xff; - break; - case 0x38: /* LCD VS Pulse-width */ - s->vsync = value & 0xbf; - break; - case 0x3a: /* LCD VS Pulse Start Position */ - s->skipy = value & 0xff; - break; - - case 0x3c: /* PCLK Polarity */ - s->pclk = value & 0x82; - /* Affects calculation of s->hndp, s->hsync and s->skipx. */ - break; - - case 0x3e: /* High-speed Serial Interface Tx Configuration Port 0 */ - s->hssi_config[0] = value; - break; - case 0x40: /* High-speed Serial Interface Tx Configuration Port 1 */ - s->hssi_config[1] = value; - if (((value >> 4) & 3) == 3) - fprintf(stderr, "%s: Illegal active-data-links value\n", - __func__); - break; - case 0x42: /* High-speed Serial Interface Tx Mode */ - s->hssi_config[2] = value & 0xbd; - break; - - case 0x44: /* TV Display Configuration */ - s->tv_config = value & 0xfe; - break; - case 0x46 ... 0x4c: /* TV Vertical Blanking Interval Data bits 0 */ - s->tv_timing[(reg - 0x46) >> 1] = value; - break; - case 0x4e: /* VBI: Closed Caption / XDS Control / Status */ - s->vbi = value; - break; - case 0x50: /* TV Horizontal Start Position */ - s->tv_x = value; - break; - case 0x52: /* TV Vertical Start Position */ - s->tv_y = value & 0x7f; - break; - case 0x54: /* TV Test Pattern Setting */ - s->tv_test = value; - break; - case 0x56: /* TV Filter Setting */ - s->tv_filter_config = value & 0xbf; - break; - case 0x58: /* TV Filter Coefficient Index */ - s->tv_filter_idx = value & 0x1f; - break; - case 0x5a: /* TV Filter Coefficient Data */ - if (s->tv_filter_idx < 0x20) - s->tv_filter_coeff[s->tv_filter_idx ++] = value; - break; - - case 0x60: /* Input YUV/RGB Translate Mode 0 */ - s->yrc[0] = value & 0xb0; - break; - case 0x62: /* Input YUV/RGB Translate Mode 1 */ - s->yrc[1] = value & 0x30; - break; - case 0x64: /* U Data Fix */ - s->u = value & 0xff; - break; - case 0x66: /* V Data Fix */ - s->v = value & 0xff; - break; - - case 0x68: /* Display Mode */ - if ((s->mode ^ value) & 3) - s->invalidate = 1; - s->mode = value & 0xb7; - s->enable = value & 1; - s->blank = (value >> 1) & 1; - if (value & (1 << 4)) - fprintf(stderr, "%s: Macrovision enable attempt!\n", __func__); - break; - - case 0x6a: /* Special Effects */ - s->effect = value & 0xfb; - break; - - case 0x6c: /* Input Window X Start Position 0 */ - s->ix[0] &= 0x300; - s->ix[0] |= (value << 0) & 0x0ff; - break; - case 0x6e: /* Input Window X Start Position 1 */ - s->ix[0] &= 0x0ff; - s->ix[0] |= (value << 8) & 0x300; - break; - case 0x70: /* Input Window Y Start Position 0 */ - s->iy[0] &= 0x300; - s->iy[0] |= (value << 0) & 0x0ff; - break; - case 0x72: /* Input Window Y Start Position 1 */ - s->iy[0] &= 0x0ff; - s->iy[0] |= (value << 8) & 0x300; - break; - case 0x74: /* Input Window X End Position 0 */ - s->ix[1] &= 0x300; - s->ix[1] |= (value << 0) & 0x0ff; - break; - case 0x76: /* Input Window X End Position 1 */ - s->ix[1] &= 0x0ff; - s->ix[1] |= (value << 8) & 0x300; - break; - case 0x78: /* Input Window Y End Position 0 */ - s->iy[1] &= 0x300; - s->iy[1] |= (value << 0) & 0x0ff; - break; - case 0x7a: /* Input Window Y End Position 1 */ - s->iy[1] &= 0x0ff; - s->iy[1] |= (value << 8) & 0x300; - break; - case 0x7c: /* Output Window X Start Position 0 */ - s->ox[0] &= 0x300; - s->ox[0] |= (value << 0) & 0x0ff; - break; - case 0x7e: /* Output Window X Start Position 1 */ - s->ox[0] &= 0x0ff; - s->ox[0] |= (value << 8) & 0x300; - break; - case 0x80: /* Output Window Y Start Position 0 */ - s->oy[0] &= 0x300; - s->oy[0] |= (value << 0) & 0x0ff; - break; - case 0x82: /* Output Window Y Start Position 1 */ - s->oy[0] &= 0x0ff; - s->oy[0] |= (value << 8) & 0x300; - break; - case 0x84: /* Output Window X End Position 0 */ - s->ox[1] &= 0x300; - s->ox[1] |= (value << 0) & 0x0ff; - break; - case 0x86: /* Output Window X End Position 1 */ - s->ox[1] &= 0x0ff; - s->ox[1] |= (value << 8) & 0x300; - break; - case 0x88: /* Output Window Y End Position 0 */ - s->oy[1] &= 0x300; - s->oy[1] |= (value << 0) & 0x0ff; - break; - case 0x8a: /* Output Window Y End Position 1 */ - s->oy[1] &= 0x0ff; - s->oy[1] |= (value << 8) & 0x300; - break; - - case 0x8c: /* Input Data Format */ - s->iformat = value & 0xf; - s->bpp = blizzard_iformat_bpp[s->iformat]; - if (!s->bpp) - fprintf(stderr, "%s: Illegal or unsupported input format %x\n", - __func__, s->iformat); - break; - case 0x8e: /* Data Source Select */ - s->source = value & 7; - /* Currently all windows will be "destructive overlays". */ - if ((!(s->effect & (1 << 3)) && (s->ix[0] != s->ox[0] || - s->iy[0] != s->oy[0] || - s->ix[1] != s->ox[1] || - s->iy[1] != s->oy[1])) || - !((s->ix[1] - s->ix[0]) & (s->iy[1] - s->iy[0]) & - (s->ox[1] - s->ox[0]) & (s->oy[1] - s->oy[0]) & 1)) - fprintf(stderr, "%s: Illegal input/output window positions\n", - __func__); - - blizzard_transfer_setup(s); - break; - - case 0x90: /* Display Memory Data Port */ - if (!s->data.len && !blizzard_transfer_setup(s)) - break; - - *s->data.ptr ++ = value; - if (-- s->data.len == 0) - blizzard_window(s); - break; - - case 0xa8: /* Border Color 0 */ - s->border_r = value; - break; - case 0xaa: /* Border Color 1 */ - s->border_g = value; - break; - case 0xac: /* Border Color 2 */ - s->border_b = value; - break; - - case 0xb4: /* Gamma Correction Enable */ - s->gamma_config = value & 0x87; - break; - case 0xb6: /* Gamma Correction Table Index */ - s->gamma_idx = value; - break; - case 0xb8: /* Gamma Correction Table Data */ - s->gamma_lut[s->gamma_idx ++] = value; - break; - - case 0xba: /* 3x3 Matrix Enable */ - s->matrix_ena = value & 1; - break; - case 0xbc ... 0xde: /* Coefficient Registers */ - s->matrix_coeff[(reg - 0xbc) >> 1] = value & ((reg & 2) ? 0x80 : 0xff); - break; - case 0xe0: /* 3x3 Matrix Red Offset */ - s->matrix_r = value; - break; - case 0xe2: /* 3x3 Matrix Green Offset */ - s->matrix_g = value; - break; - case 0xe4: /* 3x3 Matrix Blue Offset */ - s->matrix_b = value; - break; - - case 0xe6: /* Power-save */ - s->pm = value & 0x83; - if (value & s->mode & 1) - fprintf(stderr, "%s: The display must be disabled before entering " - "Standby Mode\n", __func__); - break; - case 0xe8: /* Non-display Period Control / Status */ - s->status = value & 0x1b; - break; - case 0xea: /* RGB Interface Control */ - s->rgbgpio_dir = value & 0x8f; - break; - case 0xec: /* RGB Interface Status */ - s->rgbgpio = value & 0xcf; - break; - case 0xee: /* General-purpose IO Pins Configuration */ - s->gpio_dir = value; - break; - case 0xf0: /* General-purpose IO Pins Status / Control */ - s->gpio = value; - break; - case 0xf2: /* GPIO Positive Edge Interrupt Trigger */ - s->gpio_edge[0] = value; - break; - case 0xf4: /* GPIO Negative Edge Interrupt Trigger */ - s->gpio_edge[1] = value; - break; - case 0xf6: /* GPIO Interrupt Status */ - s->gpio_irq &= value; - break; - case 0xf8: /* GPIO Pull-down Control */ - s->gpio_pdown = value; - break; - - default: - fprintf(stderr, "%s: unknown register %02x\n", __func__, reg); - break; - } -} - -uint16_t s1d13745_read(void *opaque, int dc) -{ - BlizzardState *s = (BlizzardState *) opaque; - uint16_t value = blizzard_reg_read(s, s->reg); - - if (s->swallow -- > 0) - return 0; - if (dc) - s->reg ++; - - return value; -} - -void s1d13745_write(void *opaque, int dc, uint16_t value) -{ - BlizzardState *s = (BlizzardState *) opaque; - - if (s->swallow -- > 0) - return; - if (dc) { - blizzard_reg_write(s, s->reg, value); - - if (s->reg != 0x90 && s->reg != 0x5a && s->reg != 0xb8) - s->reg += 2; - } else - s->reg = value & 0xff; -} - -void s1d13745_write_block(void *opaque, int dc, - void *buf, size_t len, int pitch) -{ - BlizzardState *s = (BlizzardState *) opaque; - - while (len > 0) { - if (s->reg == 0x90 && dc && - (s->data.len || blizzard_transfer_setup(s)) && - len >= (s->data.len << 1)) { - len -= s->data.len << 1; - s->data.len = 0; - s->data.data = buf; - if (pitch) - s->data.pitch = pitch; - blizzard_window(s); - s->data.data = s->data.buf; - continue; - } - - s1d13745_write(opaque, dc, *(uint16_t *) buf); - len -= 2; - buf += 2; - } -} - -static void blizzard_update_display(void *opaque) -{ - BlizzardState *s = (BlizzardState *) opaque; - DisplaySurface *surface = qemu_console_surface(s->con); - int y, bypp, bypl, bwidth; - uint8_t *src, *dst; - - if (!s->enable) - return; - - if (s->x != surface_width(surface) || s->y != surface_height(surface)) { - s->invalidate = 1; - qemu_console_resize(s->con, s->x, s->y); - surface = qemu_console_surface(s->con); - } - - if (s->invalidate) { - s->invalidate = 0; - - if (s->blank) { - bypp = surface_bytes_per_pixel(surface); - memset(surface_data(surface), 0, bypp * s->x * s->y); - return; - } - - s->mx[0] = 0; - s->mx[1] = s->x; - s->my[0] = 0; - s->my[1] = s->y; - } - - if (s->mx[1] <= s->mx[0]) - return; - - bypp = surface_bytes_per_pixel(surface); - bypl = bypp * s->x; - bwidth = bypp * (s->mx[1] - s->mx[0]); - y = s->my[0]; - src = s->fb + bypl * y + bypp * s->mx[0]; - dst = surface_data(surface) + bypl * y + bypp * s->mx[0]; - for (; y < s->my[1]; y ++, src += bypl, dst += bypl) - memcpy(dst, src, bwidth); - - dpy_gfx_update(s->con, s->mx[0], s->my[0], - s->mx[1] - s->mx[0], y - s->my[0]); - - s->mx[0] = s->x; - s->mx[1] = 0; - s->my[0] = s->y; - s->my[1] = 0; -} - -static void blizzard_draw_line16_32(uint32_t *dest, - const uint16_t *src, unsigned int width) -{ - uint16_t data; - unsigned int r, g, b; - const uint16_t *end = (const void *) src + width; - while (src < end) { - data = *src ++; - b = extract16(data, 0, 5) << 3; - g = extract16(data, 5, 6) << 2; - r = extract16(data, 11, 5) << 3; - *dest++ = rgb_to_pixel32(r, g, b); - } -} - -static void blizzard_draw_line24mode1_32(uint32_t *dest, - const uint8_t *src, unsigned int width) -{ - /* TODO: check if SDL 24-bit planes are not in the same format and - * if so, use memcpy */ - unsigned int r[2], g[2], b[2]; - const uint8_t *end = src + width; - while (src < end) { - g[0] = *src ++; - r[0] = *src ++; - r[1] = *src ++; - b[0] = *src ++; - *dest++ = rgb_to_pixel32(r[0], g[0], b[0]); - b[1] = *src ++; - g[1] = *src ++; - *dest++ = rgb_to_pixel32(r[1], g[1], b[1]); - } -} - -static void blizzard_draw_line24mode2_32(uint32_t *dest, - const uint8_t *src, unsigned int width) -{ - unsigned int r, g, b; - const uint8_t *end = src + width; - while (src < end) { - r = *src ++; - src ++; - b = *src ++; - g = *src ++; - *dest++ = rgb_to_pixel32(r, g, b); - } -} - -/* No rotation */ -static blizzard_fn_t blizzard_draw_fn_32[0x10] = { - NULL, - /* RGB 5:6:5*/ - (blizzard_fn_t) blizzard_draw_line16_32, - /* RGB 6:6:6 mode 1 */ - (blizzard_fn_t) blizzard_draw_line24mode1_32, - /* RGB 8:8:8 mode 1 */ - (blizzard_fn_t) blizzard_draw_line24mode1_32, - NULL, NULL, - /* RGB 6:6:6 mode 2 */ - (blizzard_fn_t) blizzard_draw_line24mode2_32, - /* RGB 8:8:8 mode 2 */ - (blizzard_fn_t) blizzard_draw_line24mode2_32, - /* YUV 4:2:2 */ - NULL, - /* YUV 4:2:0 */ - NULL, - NULL, NULL, NULL, NULL, NULL, NULL, -}; - -/* 90deg, 180deg and 270deg rotation */ -static blizzard_fn_t blizzard_draw_fn_r_32[0x10] = { - /* TODO */ - [0 ... 0xf] = NULL, -}; - -static const GraphicHwOps blizzard_ops = { - .invalidate = blizzard_invalidate_display, - .gfx_update = blizzard_update_display, -}; - -void *s1d13745_init(qemu_irq gpio_int) -{ - BlizzardState *s = g_malloc0(sizeof(*s)); - DisplaySurface *surface; - - s->fb = g_malloc(0x180000); - - s->con = graphic_console_init(NULL, 0, &blizzard_ops, s); - surface = qemu_console_surface(s->con); - - assert(surface_bits_per_pixel(surface) == 32); - - s->line_fn_tab[0] = blizzard_draw_fn_32; - s->line_fn_tab[1] = blizzard_draw_fn_r_32; - - blizzard_reset(s); - - return s; -} diff --git a/hw/display/Kconfig b/hw/display/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/display/Kconfig +++ b/hw/display/Kconfig @@ -XXX,XX +XXX,XX @@ config BOCHS_DISPLAY select VGA select EDID -config BLIZZARD - bool - config FRAMEBUFFER bool diff --git a/hw/display/meson.build b/hw/display/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_VGA_MMIO', if_true: files('vga-mmio.c')) system_ss.add(when: 'CONFIG_VMWARE_VGA', if_true: files('vmware_vga.c')) system_ss.add(when: 'CONFIG_BOCHS_DISPLAY', if_true: files('bochs-display.c')) -system_ss.add(when: 'CONFIG_BLIZZARD', if_true: files('blizzard.c')) system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210_fimd.c')) system_ss.add(when: 'CONFIG_FRAMEBUFFER', if_true: files('framebuffer.c')) -- 2.34.1 Remove the tsc2005 touchscreen controller, which was only used by the n800 and n810 machines. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20240903160751.4100218-29-peter.maydell@linaro.org --- MAINTAINERS | 1 - include/hw/input/tsc2xxx.h | 5 - hw/input/tsc2005.c | 571 ------------------------------------- hw/input/Kconfig | 3 - hw/input/meson.build | 1 - hw/input/trace-events | 3 - 6 files changed, 584 deletions(-) delete mode 100644 hw/input/tsc2005.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes F: hw/input/lm832x.c -F: hw/input/tsc2005.c F: hw/input/tsc210x.c F: hw/rtc/twl92230.c F: include/hw/input/lm832x.h diff --git a/include/hw/input/tsc2xxx.h b/include/hw/input/tsc2xxx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/input/tsc2xxx.h +++ b/include/hw/input/tsc2xxx.h @@ -XXX,XX +XXX,XX @@ uint32_t tsc210x_txrx(void *opaque, uint32_t value, int len); void tsc210x_set_transform(uWireSlave *chip, const MouseTransformInfo *info); void tsc210x_key_event(uWireSlave *chip, int key, int down); -/* tsc2005.c */ -void *tsc2005_init(qemu_irq pintdav); -uint32_t tsc2005_txrx(void *opaque, uint32_t value, int len); -void tsc2005_set_transform(void *opaque, const MouseTransformInfo *info); - #endif diff --git a/hw/input/tsc2005.c b/hw/input/tsc2005.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/input/tsc2005.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI TSC2005 emulator. - * - * Copyright (c) 2006 Andrzej Zaborowski <balrog@zabor.org> - * Copyright (C) 2008 Nokia Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "qemu/log.h" -#include "qemu/timer.h" -#include "sysemu/reset.h" -#include "ui/console.h" -#include "hw/input/tsc2xxx.h" -#include "hw/irq.h" -#include "migration/vmstate.h" -#include "trace.h" - -#define TSC_CUT_RESOLUTION(value, p) ((value) >> (16 - (p ? 12 : 10))) - -typedef struct { - qemu_irq pint; /* Combination of the nPENIRQ and DAV signals */ - QEMUTimer *timer; - uint16_t model; - - int32_t x, y; - bool pressure; - - uint8_t reg, state; - bool irq, command; - uint16_t data, dav; - - bool busy; - bool enabled; - bool host_mode; - int8_t function; - int8_t nextfunction; - bool precision; - bool nextprecision; - uint16_t filter; - uint8_t pin_func; - uint16_t timing[2]; - uint8_t noise; - bool reset; - bool pdst; - bool pnd0; - uint16_t temp_thr[2]; - uint16_t aux_thr[2]; - - int32_t tr[8]; -} TSC2005State; - -enum { - TSC_MODE_XYZ_SCAN = 0x0, - TSC_MODE_XY_SCAN, - TSC_MODE_X, - TSC_MODE_Y, - TSC_MODE_Z, - TSC_MODE_AUX, - TSC_MODE_TEMP1, - TSC_MODE_TEMP2, - TSC_MODE_AUX_SCAN, - TSC_MODE_X_TEST, - TSC_MODE_Y_TEST, - TSC_MODE_TS_TEST, - TSC_MODE_RESERVED, - TSC_MODE_XX_DRV, - TSC_MODE_YY_DRV, - TSC_MODE_YX_DRV, -}; - -static const uint16_t mode_regs[16] = { - 0xf000, /* X, Y, Z scan */ - 0xc000, /* X, Y scan */ - 0x8000, /* X */ - 0x4000, /* Y */ - 0x3000, /* Z */ - 0x0800, /* AUX */ - 0x0400, /* TEMP1 */ - 0x0200, /* TEMP2 */ - 0x0800, /* AUX scan */ - 0x0040, /* X test */ - 0x0020, /* Y test */ - 0x0080, /* Short-circuit test */ - 0x0000, /* Reserved */ - 0x0000, /* X+, X- drivers */ - 0x0000, /* Y+, Y- drivers */ - 0x0000, /* Y+, X- drivers */ -}; - -#define X_TRANSFORM(s) \ - ((s->y * s->tr[0] - s->x * s->tr[1]) / s->tr[2] + s->tr[3]) -#define Y_TRANSFORM(s) \ - ((s->y * s->tr[4] - s->x * s->tr[5]) / s->tr[6] + s->tr[7]) -#define Z1_TRANSFORM(s) \ - ((400 - ((s)->x >> 7) + ((s)->pressure << 10)) << 4) -#define Z2_TRANSFORM(s) \ - ((4000 + ((s)->y >> 7) - ((s)->pressure << 10)) << 4) - -#define AUX_VAL (700 << 4) /* +/- 3 at 12-bit */ -#define TEMP1_VAL (1264 << 4) /* +/- 5 at 12-bit */ -#define TEMP2_VAL (1531 << 4) /* +/- 5 at 12-bit */ - -static uint16_t tsc2005_read(TSC2005State *s, int reg) -{ - uint16_t ret; - - switch (reg) { - case 0x0: /* X */ - s->dav &= ~mode_regs[TSC_MODE_X]; - return TSC_CUT_RESOLUTION(X_TRANSFORM(s), s->precision) + - (s->noise & 3); - case 0x1: /* Y */ - s->dav &= ~mode_regs[TSC_MODE_Y]; - s->noise++; - return TSC_CUT_RESOLUTION(Y_TRANSFORM(s), s->precision) ^ - (s->noise & 3); - case 0x2: /* Z1 */ - s->dav &= 0xdfff; - return TSC_CUT_RESOLUTION(Z1_TRANSFORM(s), s->precision) - - (s->noise & 3); - case 0x3: /* Z2 */ - s->dav &= 0xefff; - return TSC_CUT_RESOLUTION(Z2_TRANSFORM(s), s->precision) | - (s->noise & 3); - - case 0x4: /* AUX */ - s->dav &= ~mode_regs[TSC_MODE_AUX]; - return TSC_CUT_RESOLUTION(AUX_VAL, s->precision); - - case 0x5: /* TEMP1 */ - s->dav &= ~mode_regs[TSC_MODE_TEMP1]; - return TSC_CUT_RESOLUTION(TEMP1_VAL, s->precision) - - (s->noise & 5); - case 0x6: /* TEMP2 */ - s->dav &= 0xdfff; - s->dav &= ~mode_regs[TSC_MODE_TEMP2]; - return TSC_CUT_RESOLUTION(TEMP2_VAL, s->precision) ^ - (s->noise & 3); - - case 0x7: /* Status */ - ret = s->dav | (s->reset << 7) | (s->pdst << 2) | 0x0; - s->dav &= ~(mode_regs[TSC_MODE_X_TEST] | mode_regs[TSC_MODE_Y_TEST] | - mode_regs[TSC_MODE_TS_TEST]); - s->reset = true; - return ret; - - case 0x8: /* AUX high threshold */ - return s->aux_thr[1]; - case 0x9: /* AUX low threshold */ - return s->aux_thr[0]; - - case 0xa: /* TEMP high threshold */ - return s->temp_thr[1]; - case 0xb: /* TEMP low threshold */ - return s->temp_thr[0]; - - case 0xc: /* CFR0 */ - return (s->pressure << 15) | ((!s->busy) << 14) | - (s->nextprecision << 13) | s->timing[0]; - case 0xd: /* CFR1 */ - return s->timing[1]; - case 0xe: /* CFR2 */ - return (s->pin_func << 14) | s->filter; - - case 0xf: /* Function select status */ - return s->function >= 0 ? 1 << s->function : 0; - } - - /* Never gets here */ - return 0xffff; -} - -static void tsc2005_write(TSC2005State *s, int reg, uint16_t data) -{ - switch (reg) { - case 0x8: /* AUX high threshold */ - s->aux_thr[1] = data; - break; - case 0x9: /* AUX low threshold */ - s->aux_thr[0] = data; - break; - - case 0xa: /* TEMP high threshold */ - s->temp_thr[1] = data; - break; - case 0xb: /* TEMP low threshold */ - s->temp_thr[0] = data; - break; - - case 0xc: /* CFR0 */ - s->host_mode = (data >> 15) != 0; - if (s->enabled != !(data & 0x4000)) { - s->enabled = !(data & 0x4000); - trace_tsc2005_sense(s->enabled ? "enabled" : "disabled"); - if (s->busy && !s->enabled) { - timer_del(s->timer); - } - s->busy = s->busy && s->enabled; - } - s->nextprecision = (data >> 13) & 1; - s->timing[0] = data & 0x1fff; - if ((s->timing[0] >> 11) == 3) { - qemu_log_mask(LOG_GUEST_ERROR, - "tsc2005_write: illegal conversion clock setting\n"); - } - break; - case 0xd: /* CFR1 */ - s->timing[1] = data & 0xf07; - break; - case 0xe: /* CFR2 */ - s->pin_func = (data >> 14) & 3; - s->filter = data & 0x3fff; - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: write into read-only register 0x%x\n", - __func__, reg); - } -} - -/* This handles most of the chip's logic. */ -static void tsc2005_pin_update(TSC2005State *s) -{ - int64_t expires; - bool pin_state; - - switch (s->pin_func) { - case 0: - pin_state = !s->pressure && !!s->dav; - break; - case 1: - case 3: - default: - pin_state = !s->dav; - break; - case 2: - pin_state = !s->pressure; - } - - if (pin_state != s->irq) { - s->irq = pin_state; - qemu_set_irq(s->pint, s->irq); - } - - switch (s->nextfunction) { - case TSC_MODE_XYZ_SCAN: - case TSC_MODE_XY_SCAN: - if (!s->host_mode && s->dav) { - s->enabled = false; - } - if (!s->pressure) { - return; - } - /* Fall through */ - case TSC_MODE_AUX_SCAN: - break; - - case TSC_MODE_X: - case TSC_MODE_Y: - case TSC_MODE_Z: - if (!s->pressure) { - return; - } - /* Fall through */ - case TSC_MODE_AUX: - case TSC_MODE_TEMP1: - case TSC_MODE_TEMP2: - case TSC_MODE_X_TEST: - case TSC_MODE_Y_TEST: - case TSC_MODE_TS_TEST: - if (s->dav) { - s->enabled = false; - } - break; - - case TSC_MODE_RESERVED: - case TSC_MODE_XX_DRV: - case TSC_MODE_YY_DRV: - case TSC_MODE_YX_DRV: - default: - return; - } - - if (!s->enabled || s->busy) { - return; - } - - s->busy = true; - s->precision = s->nextprecision; - s->function = s->nextfunction; - s->pdst = !s->pnd0; /* Synchronised on internal clock */ - expires = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + - (NANOSECONDS_PER_SECOND >> 7); - timer_mod(s->timer, expires); -} - -static void tsc2005_reset(TSC2005State *s) -{ - s->state = 0; - s->pin_func = 0; - s->enabled = false; - s->busy = false; - s->nextprecision = false; - s->nextfunction = 0; - s->timing[0] = 0; - s->timing[1] = 0; - s->irq = false; - s->dav = 0; - s->reset = false; - s->pdst = true; - s->pnd0 = false; - s->function = -1; - s->temp_thr[0] = 0x000; - s->temp_thr[1] = 0xfff; - s->aux_thr[0] = 0x000; - s->aux_thr[1] = 0xfff; - - tsc2005_pin_update(s); -} - -static uint8_t tsc2005_txrx_word(void *opaque, uint8_t value) -{ - TSC2005State *s = opaque; - uint32_t ret = 0; - - switch (s->state++) { - case 0: - if (value & 0x80) { - /* Command */ - if (value & (1 << 1)) - tsc2005_reset(s); - else { - s->nextfunction = (value >> 3) & 0xf; - s->nextprecision = (value >> 2) & 1; - if (s->enabled != !(value & 1)) { - s->enabled = !(value & 1); - trace_tsc2005_sense(s->enabled ? "enabled" : "disabled"); - if (s->busy && !s->enabled) { - timer_del(s->timer); - } - s->busy = s->busy && s->enabled; - } - tsc2005_pin_update(s); - } - - s->state = 0; - } else if (value) { - /* Data transfer */ - s->reg = (value >> 3) & 0xf; - s->pnd0 = (value >> 1) & 1; - s->command = value & 1; - - if (s->command) { - /* Read */ - s->data = tsc2005_read(s, s->reg); - tsc2005_pin_update(s); - } else - s->data = 0; - } else - s->state = 0; - break; - - case 1: - if (s->command) { - ret = (s->data >> 8) & 0xff; - } else { - s->data |= value << 8; - } - break; - - case 2: - if (s->command) - ret = s->data & 0xff; - else { - s->data |= value; - tsc2005_write(s, s->reg, s->data); - tsc2005_pin_update(s); - } - - s->state = 0; - break; - } - - return ret; -} - -uint32_t tsc2005_txrx(void *opaque, uint32_t value, int len) -{ - uint32_t ret = 0; - - len &= ~7; - while (len > 0) { - len -= 8; - ret |= tsc2005_txrx_word(opaque, (value >> len) & 0xff) << len; - } - - return ret; -} - -static void tsc2005_timer_tick(void *opaque) -{ - TSC2005State *s = opaque; - unsigned int function = s->function; - - assert(function < ARRAY_SIZE(mode_regs)); - - /* Timer ticked -- a set of conversions has been finished. */ - - if (!s->busy) { - return; - } - - s->busy = false; - s->dav |= mode_regs[function]; - s->function = -1; - tsc2005_pin_update(s); -} - -static void tsc2005_touchscreen_event(void *opaque, - int x, int y, int z, int buttons_state) -{ - TSC2005State *s = opaque; - int p = s->pressure; - - if (buttons_state) { - s->x = x; - s->y = y; - } - s->pressure = !!buttons_state; - - /* - * Note: We would get better responsiveness in the guest by - * signaling TS events immediately, but for now we simulate - * the first conversion delay for sake of correctness. - */ - if (p != s->pressure) { - tsc2005_pin_update(s); - } -} - -static int tsc2005_post_load(void *opaque, int version_id) -{ - TSC2005State *s = (TSC2005State *) opaque; - - s->busy = timer_pending(s->timer); - tsc2005_pin_update(s); - - return 0; -} - -static const VMStateDescription vmstate_tsc2005 = { - .name = "tsc2005", - .version_id = 2, - .minimum_version_id = 2, - .post_load = tsc2005_post_load, - .fields = (const VMStateField []) { - VMSTATE_BOOL(pressure, TSC2005State), - VMSTATE_BOOL(irq, TSC2005State), - VMSTATE_BOOL(command, TSC2005State), - VMSTATE_BOOL(enabled, TSC2005State), - VMSTATE_BOOL(host_mode, TSC2005State), - VMSTATE_BOOL(reset, TSC2005State), - VMSTATE_BOOL(pdst, TSC2005State), - VMSTATE_BOOL(pnd0, TSC2005State), - VMSTATE_BOOL(precision, TSC2005State), - VMSTATE_BOOL(nextprecision, TSC2005State), - VMSTATE_UINT8(reg, TSC2005State), - VMSTATE_UINT8(state, TSC2005State), - VMSTATE_UINT16(data, TSC2005State), - VMSTATE_UINT16(dav, TSC2005State), - VMSTATE_UINT16(filter, TSC2005State), - VMSTATE_INT8(nextfunction, TSC2005State), - VMSTATE_INT8(function, TSC2005State), - VMSTATE_INT32(x, TSC2005State), - VMSTATE_INT32(y, TSC2005State), - VMSTATE_TIMER_PTR(timer, TSC2005State), - VMSTATE_UINT8(pin_func, TSC2005State), - VMSTATE_UINT16_ARRAY(timing, TSC2005State, 2), - VMSTATE_UINT8(noise, TSC2005State), - VMSTATE_UINT16_ARRAY(temp_thr, TSC2005State, 2), - VMSTATE_UINT16_ARRAY(aux_thr, TSC2005State, 2), - VMSTATE_INT32_ARRAY(tr, TSC2005State, 8), - VMSTATE_END_OF_LIST() - } -}; - -void *tsc2005_init(qemu_irq pintdav) -{ - TSC2005State *s; - - s = g_new0(TSC2005State, 1); - s->x = 400; - s->y = 240; - s->pressure = false; - s->precision = s->nextprecision = false; - s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, tsc2005_timer_tick, s); - s->pint = pintdav; - s->model = 0x2005; - - s->tr[0] = 0; - s->tr[1] = 1; - s->tr[2] = 1; - s->tr[3] = 0; - s->tr[4] = 1; - s->tr[5] = 0; - s->tr[6] = 1; - s->tr[7] = 0; - - tsc2005_reset(s); - - qemu_add_mouse_event_handler(tsc2005_touchscreen_event, s, 1, - "QEMU TSC2005-driven Touchscreen"); - - qemu_register_reset((void *) tsc2005_reset, s); - vmstate_register(NULL, 0, &vmstate_tsc2005, s); - - return s; -} - -/* - * Use tslib generated calibration data to generate ADC input values - * from the touchscreen. Assuming 12-bit precision was used during - * tslib calibration. - */ -void tsc2005_set_transform(void *opaque, const MouseTransformInfo *info) -{ - TSC2005State *s = (TSC2005State *) opaque; - - /* This version assumes touchscreen X & Y axis are parallel or - * perpendicular to LCD's X & Y axis in some way. */ - if (abs(info->a[0]) > abs(info->a[1])) { - s->tr[0] = 0; - s->tr[1] = -info->a[6] * info->x; - s->tr[2] = info->a[0]; - s->tr[3] = -info->a[2] / info->a[0]; - s->tr[4] = info->a[6] * info->y; - s->tr[5] = 0; - s->tr[6] = info->a[4]; - s->tr[7] = -info->a[5] / info->a[4]; - } else { - s->tr[0] = info->a[6] * info->y; - s->tr[1] = 0; - s->tr[2] = info->a[1]; - s->tr[3] = -info->a[2] / info->a[1]; - s->tr[4] = 0; - s->tr[5] = -info->a[6] * info->x; - s->tr[6] = info->a[3]; - s->tr[7] = -info->a[5] / info->a[3]; - } - - s->tr[0] >>= 11; - s->tr[1] >>= 11; - s->tr[3] <<= 4; - s->tr[4] >>= 11; - s->tr[5] >>= 11; - s->tr[7] <<= 4; -} diff --git a/hw/input/Kconfig b/hw/input/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/input/Kconfig +++ b/hw/input/Kconfig @@ -XXX,XX +XXX,XX @@ config PS2 config STELLARIS_GAMEPAD bool -config TSC2005 - bool - config VIRTIO_INPUT bool default y diff --git a/hw/input/meson.build b/hw/input/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/input/meson.build +++ b/hw/input/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_PCKBD', if_true: files('pckbd.c')) system_ss.add(when: 'CONFIG_PL050', if_true: files('pl050.c')) system_ss.add(when: 'CONFIG_PS2', if_true: files('ps2.c')) system_ss.add(when: 'CONFIG_STELLARIS_GAMEPAD', if_true: files('stellaris_gamepad.c')) -system_ss.add(when: 'CONFIG_TSC2005', if_true: files('tsc2005.c')) system_ss.add(when: 'CONFIG_VIRTIO_INPUT', if_true: files('virtio-input.c')) system_ss.add(when: 'CONFIG_VIRTIO_INPUT', if_true: files('virtio-input-hid.c')) diff --git a/hw/input/trace-events b/hw/input/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/input/trace-events +++ b/hw/input/trace-events @@ -XXX,XX +XXX,XX @@ ps2_mouse_reset(void *opaque) "%p" hid_kbd_queue_full(void) "queue full" hid_kbd_queue_empty(void) "queue empty" -# tsc2005.c -tsc2005_sense(const char *state) "touchscreen sense %s" - # virtio-input.c virtio_input_queue_full(void) "queue full" -- 2.34.1 Remove the tsc210x touchscreen controller device, which was only used by the n800 and n810 and cheetah. The uWireSlave struct is still used in omap1.c (at least for compilation purposes -- nothing any longer calls omap_uwire_attach() and so the struct's members will not be used at runtime), so we move it into omap.h so we can delete tsc2xxx.h. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20240903160751.4100218-30-peter.maydell@linaro.org --- MAINTAINERS | 2 - include/hw/arm/omap.h | 7 +- include/hw/input/tsc2xxx.h | 36 -- hw/input/tsc210x.c | 1241 ------------------------------------ hw/input/Kconfig | 3 - hw/input/meson.build | 1 - 6 files changed, 6 insertions(+), 1284 deletions(-) delete mode 100644 include/hw/input/tsc2xxx.h delete mode 100644 hw/input/tsc210x.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes F: hw/input/lm832x.c -F: hw/input/tsc210x.c F: hw/rtc/twl92230.c F: include/hw/input/lm832x.h -F: include/hw/input/tsc2xxx.h Raspberry Pi M: Peter Maydell <peter.maydell@linaro.org> diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ #define HW_ARM_OMAP_H #include "exec/memory.h" -#include "hw/input/tsc2xxx.h" #include "target/arm/cpu-qom.h" #include "qemu/log.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ qemu_irq *omap_mpuio_in_get(struct omap_mpuio_s *s); void omap_mpuio_out_set(struct omap_mpuio_s *s, int line, qemu_irq handler); void omap_mpuio_key(struct omap_mpuio_s *s, int row, int col, int down); +typedef struct uWireSlave { + uint16_t (*receive)(void *opaque); + void (*send)(void *opaque, uint16_t data); + void *opaque; +} uWireSlave; + struct omap_uwire_s; void omap_uwire_attach(struct omap_uwire_s *s, uWireSlave *slave, int chipselect); diff --git a/include/hw/input/tsc2xxx.h b/include/hw/input/tsc2xxx.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/hw/input/tsc2xxx.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI touchscreen controller - * - * Copyright (c) 2006 Andrzej Zaborowski - * Copyright (C) 2008 Nokia Corporation - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - */ - -#ifndef HW_INPUT_TSC2XXX_H -#define HW_INPUT_TSC2XXX_H - -typedef struct MouseTransformInfo { - /* Touchscreen resolution */ - int x; - int y; - /* Calibration values as used/generated by tslib */ - int a[7]; -} MouseTransformInfo; - -typedef struct uWireSlave { - uint16_t (*receive)(void *opaque); - void (*send)(void *opaque, uint16_t data); - void *opaque; -} uWireSlave; - -/* tsc210x.c */ -uWireSlave *tsc2102_init(qemu_irq pint); -uWireSlave *tsc2301_init(qemu_irq penirq, qemu_irq kbirq, qemu_irq dav); -I2SCodec *tsc210x_codec(uWireSlave *chip); -uint32_t tsc210x_txrx(void *opaque, uint32_t value, int len); -void tsc210x_set_transform(uWireSlave *chip, const MouseTransformInfo *info); -void tsc210x_key_event(uWireSlave *chip, int key, int down); - -#endif diff --git a/hw/input/tsc210x.c b/hw/input/tsc210x.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/input/tsc210x.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI TSC2102 (touchscreen/sensors/audio controller) emulator. - * TI TSC2301 (touchscreen/sensors/keypad). - * - * Copyright (c) 2006 Andrzej Zaborowski <balrog@zabor.org> - * Copyright (C) 2008 Nokia Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "hw/hw.h" -#include "audio/audio.h" -#include "qemu/timer.h" -#include "qemu/log.h" -#include "sysemu/reset.h" -#include "ui/console.h" -#include "hw/arm/omap.h" /* For I2SCodec */ -#include "hw/boards.h" /* for current_machine */ -#include "hw/input/tsc2xxx.h" -#include "hw/irq.h" -#include "migration/vmstate.h" -#include "qapi/error.h" - -#define TSC_DATA_REGISTERS_PAGE 0x0 -#define TSC_CONTROL_REGISTERS_PAGE 0x1 -#define TSC_AUDIO_REGISTERS_PAGE 0x2 - -#define TSC_VERBOSE - -#define TSC_CUT_RESOLUTION(value, p) ((value) >> (16 - resolution[p])) - -typedef struct { - qemu_irq pint; - qemu_irq kbint; - qemu_irq davint; - QEMUTimer *timer; - QEMUSoundCard card; - uWireSlave chip; - I2SCodec codec; - uint8_t in_fifo[16384]; - uint8_t out_fifo[16384]; - uint16_t model; - - int32_t x, y; - bool pressure; - - uint8_t page, offset; - uint16_t dav; - - bool state; - bool irq; - bool command; - bool busy; - bool enabled; - bool host_mode; - uint8_t function, nextfunction; - uint8_t precision, nextprecision; - uint8_t filter; - uint8_t pin_func; - uint8_t ref; - uint8_t timing; - uint8_t noise; - - uint16_t audio_ctrl1; - uint16_t audio_ctrl2; - uint16_t audio_ctrl3; - uint16_t pll[3]; - uint16_t volume; - int64_t volume_change; - bool softstep; - uint16_t dac_power; - int64_t powerdown; - uint16_t filter_data[0x14]; - - const char *name; - SWVoiceIn *adc_voice[1]; - SWVoiceOut *dac_voice[1]; - int i2s_rx_rate; - int i2s_tx_rate; - - int tr[8]; - - struct { - uint16_t down; - uint16_t mask; - int scan; - int debounce; - int mode; - int intr; - } kb; - int64_t now; /* Time at migration */ -} TSC210xState; - -static const int resolution[4] = { 12, 8, 10, 12 }; - -#define TSC_MODE_NO_SCAN 0x0 -#define TSC_MODE_XY_SCAN 0x1 -#define TSC_MODE_XYZ_SCAN 0x2 -#define TSC_MODE_X 0x3 -#define TSC_MODE_Y 0x4 -#define TSC_MODE_Z 0x5 -#define TSC_MODE_BAT1 0x6 -#define TSC_MODE_BAT2 0x7 -#define TSC_MODE_AUX 0x8 -#define TSC_MODE_AUX_SCAN 0x9 -#define TSC_MODE_TEMP1 0xa -#define TSC_MODE_PORT_SCAN 0xb -#define TSC_MODE_TEMP2 0xc -#define TSC_MODE_XX_DRV 0xd -#define TSC_MODE_YY_DRV 0xe -#define TSC_MODE_YX_DRV 0xf - -static const uint16_t mode_regs[16] = { - 0x0000, /* No scan */ - 0x0600, /* X, Y scan */ - 0x0780, /* X, Y, Z scan */ - 0x0400, /* X */ - 0x0200, /* Y */ - 0x0180, /* Z */ - 0x0040, /* BAT1 */ - 0x0030, /* BAT2 */ - 0x0010, /* AUX */ - 0x0010, /* AUX scan */ - 0x0004, /* TEMP1 */ - 0x0070, /* Port scan */ - 0x0002, /* TEMP2 */ - 0x0000, /* X+, X- drivers */ - 0x0000, /* Y+, Y- drivers */ - 0x0000, /* Y+, X- drivers */ -}; - -#define X_TRANSFORM(s) \ - ((s->y * s->tr[0] - s->x * s->tr[1]) / s->tr[2] + s->tr[3]) -#define Y_TRANSFORM(s) \ - ((s->y * s->tr[4] - s->x * s->tr[5]) / s->tr[6] + s->tr[7]) -#define Z1_TRANSFORM(s) \ - ((400 - ((s)->x >> 7) + ((s)->pressure << 10)) << 4) -#define Z2_TRANSFORM(s) \ - ((4000 + ((s)->y >> 7) - ((s)->pressure << 10)) << 4) - -#define BAT1_VAL 0x8660 -#define BAT2_VAL 0x0000 -#define AUX1_VAL 0x35c0 -#define AUX2_VAL 0xffff -#define TEMP1_VAL 0x8c70 -#define TEMP2_VAL 0xa5b0 - -#define TSC_POWEROFF_DELAY 50 -#define TSC_SOFTSTEP_DELAY 50 - -static void tsc210x_reset(TSC210xState *s) -{ - s->state = false; - s->pin_func = 2; - s->enabled = false; - s->busy = false; - s->nextfunction = 0; - s->ref = 0; - s->timing = 0; - s->irq = false; - s->dav = 0; - - s->audio_ctrl1 = 0x0000; - s->audio_ctrl2 = 0x4410; - s->audio_ctrl3 = 0x0000; - s->pll[0] = 0x1004; - s->pll[1] = 0x0000; - s->pll[2] = 0x1fff; - s->volume = 0xffff; - s->dac_power = 0x8540; - s->softstep = true; - s->volume_change = 0; - s->powerdown = 0; - s->filter_data[0x00] = 0x6be3; - s->filter_data[0x01] = 0x9666; - s->filter_data[0x02] = 0x675d; - s->filter_data[0x03] = 0x6be3; - s->filter_data[0x04] = 0x9666; - s->filter_data[0x05] = 0x675d; - s->filter_data[0x06] = 0x7d83; - s->filter_data[0x07] = 0x84ee; - s->filter_data[0x08] = 0x7d83; - s->filter_data[0x09] = 0x84ee; - s->filter_data[0x0a] = 0x6be3; - s->filter_data[0x0b] = 0x9666; - s->filter_data[0x0c] = 0x675d; - s->filter_data[0x0d] = 0x6be3; - s->filter_data[0x0e] = 0x9666; - s->filter_data[0x0f] = 0x675d; - s->filter_data[0x10] = 0x7d83; - s->filter_data[0x11] = 0x84ee; - s->filter_data[0x12] = 0x7d83; - s->filter_data[0x13] = 0x84ee; - - s->i2s_tx_rate = 0; - s->i2s_rx_rate = 0; - - s->kb.scan = 1; - s->kb.debounce = 0; - s->kb.mask = 0x0000; - s->kb.mode = 3; - s->kb.intr = 0; - - qemu_set_irq(s->pint, !s->irq); - qemu_set_irq(s->davint, !s->dav); - qemu_irq_raise(s->kbint); -} - -typedef struct { - int rate; - int dsor; - int fsref; -} TSC210xRateInfo; - -/* { rate, dsor, fsref } */ -static const TSC210xRateInfo tsc2102_rates[] = { - /* Fsref / 6.0 */ - { 7350, 63, 1 }, - { 8000, 63, 0 }, - /* Fsref / 6.0 */ - { 7350, 54, 1 }, - { 8000, 54, 0 }, - /* Fsref / 5.0 */ - { 8820, 45, 1 }, - { 9600, 45, 0 }, - /* Fsref / 4.0 */ - { 11025, 36, 1 }, - { 12000, 36, 0 }, - /* Fsref / 3.0 */ - { 14700, 27, 1 }, - { 16000, 27, 0 }, - /* Fsref / 2.0 */ - { 22050, 18, 1 }, - { 24000, 18, 0 }, - /* Fsref / 1.5 */ - { 29400, 9, 1 }, - { 32000, 9, 0 }, - /* Fsref */ - { 44100, 0, 1 }, - { 48000, 0, 0 }, - - { 0, 0, 0 }, -}; - -static inline void tsc210x_out_flush(TSC210xState *s, int len) -{ - uint8_t *data = s->codec.out.fifo + s->codec.out.start; - uint8_t *end = data + len; - - while (data < end) - data += AUD_write(s->dac_voice[0], data, end - data) ?: (end - data); - - s->codec.out.len -= len; - if (s->codec.out.len) - memmove(s->codec.out.fifo, end, s->codec.out.len); - s->codec.out.start = 0; -} - -static void tsc210x_audio_out_cb(TSC210xState *s, int free_b) -{ - if (s->codec.out.len >= free_b) { - tsc210x_out_flush(s, free_b); - return; - } - - s->codec.out.size = MIN(free_b, 16384); - qemu_irq_raise(s->codec.tx_start); -} - -static void tsc2102_audio_rate_update(TSC210xState *s) -{ - const TSC210xRateInfo *rate; - - s->codec.tx_rate = 0; - s->codec.rx_rate = 0; - if (s->dac_power & (1 << 15)) /* PWDNC */ - return; - - for (rate = tsc2102_rates; rate->rate; rate ++) - if (rate->dsor == (s->audio_ctrl1 & 0x3f) && /* DACFS */ - rate->fsref == ((s->audio_ctrl3 >> 13) & 1))/* REFFS */ - break; - if (!rate->rate) { - printf("%s: unknown sampling rate configured\n", __func__); - return; - } - - s->codec.tx_rate = rate->rate; -} - -static void tsc2102_audio_output_update(TSC210xState *s) -{ - int enable; - struct audsettings fmt; - - if (s->dac_voice[0]) { - tsc210x_out_flush(s, s->codec.out.len); - s->codec.out.size = 0; - AUD_set_active_out(s->dac_voice[0], 0); - AUD_close_out(&s->card, s->dac_voice[0]); - s->dac_voice[0] = NULL; - } - s->codec.cts = 0; - - enable = - (~s->dac_power & (1 << 15)) && /* PWDNC */ - (~s->dac_power & (1 << 10)); /* DAPWDN */ - if (!enable || !s->codec.tx_rate) - return; - - /* Force our own sampling rate even in slave DAC mode */ - fmt.endianness = 0; - fmt.nchannels = 2; - fmt.freq = s->codec.tx_rate; - fmt.fmt = AUDIO_FORMAT_S16; - - s->dac_voice[0] = AUD_open_out(&s->card, s->dac_voice[0], - "tsc2102.sink", s, (void *) tsc210x_audio_out_cb, &fmt); - if (s->dac_voice[0]) { - s->codec.cts = 1; - AUD_set_active_out(s->dac_voice[0], 1); - } -} - -static uint16_t tsc2102_data_register_read(TSC210xState *s, int reg) -{ - switch (reg) { - case 0x00: /* X */ - s->dav &= 0xfbff; - return TSC_CUT_RESOLUTION(X_TRANSFORM(s), s->precision) + - (s->noise & 3); - - case 0x01: /* Y */ - s->noise ++; - s->dav &= 0xfdff; - return TSC_CUT_RESOLUTION(Y_TRANSFORM(s), s->precision) ^ - (s->noise & 3); - - case 0x02: /* Z1 */ - s->dav &= 0xfeff; - return TSC_CUT_RESOLUTION(Z1_TRANSFORM(s), s->precision) - - (s->noise & 3); - - case 0x03: /* Z2 */ - s->dav &= 0xff7f; - return TSC_CUT_RESOLUTION(Z2_TRANSFORM(s), s->precision) | - (s->noise & 3); - - case 0x04: /* KPData */ - if ((s->model & 0xff00) == 0x2300) { - if (s->kb.intr && (s->kb.mode & 2)) { - s->kb.intr = 0; - qemu_irq_raise(s->kbint); - } - return s->kb.down; - } - - return 0xffff; - - case 0x05: /* BAT1 */ - s->dav &= 0xffbf; - return TSC_CUT_RESOLUTION(BAT1_VAL, s->precision) + - (s->noise & 6); - - case 0x06: /* BAT2 */ - s->dav &= 0xffdf; - return TSC_CUT_RESOLUTION(BAT2_VAL, s->precision); - - case 0x07: /* AUX1 */ - s->dav &= 0xffef; - return TSC_CUT_RESOLUTION(AUX1_VAL, s->precision); - - case 0x08: /* AUX2 */ - s->dav &= 0xfff7; - return 0xffff; - - case 0x09: /* TEMP1 */ - s->dav &= 0xfffb; - return TSC_CUT_RESOLUTION(TEMP1_VAL, s->precision) - - (s->noise & 5); - - case 0x0a: /* TEMP2 */ - s->dav &= 0xfffd; - return TSC_CUT_RESOLUTION(TEMP2_VAL, s->precision) ^ - (s->noise & 3); - - case 0x0b: /* DAC */ - s->dav &= 0xfffe; - return 0xffff; - - default: -#ifdef TSC_VERBOSE - fprintf(stderr, "tsc2102_data_register_read: " - "no such register: 0x%02x\n", reg); -#endif - return 0xffff; - } -} - -static uint16_t tsc2102_control_register_read( - TSC210xState *s, int reg) -{ - switch (reg) { - case 0x00: /* TSC ADC */ - return (s->pressure << 15) | ((!s->busy) << 14) | - (s->nextfunction << 10) | (s->nextprecision << 8) | s->filter; - - case 0x01: /* Status / Keypad Control */ - if ((s->model & 0xff00) == 0x2100) - return (s->pin_func << 14) | ((!s->enabled) << 13) | - (s->host_mode << 12) | ((!!s->dav) << 11) | s->dav; - else - return (s->kb.intr << 15) | ((s->kb.scan || !s->kb.down) << 14) | - (s->kb.debounce << 11); - - case 0x02: /* DAC Control */ - if ((s->model & 0xff00) == 0x2300) - return s->dac_power & 0x8000; - else - goto bad_reg; - - case 0x03: /* Reference */ - return s->ref; - - case 0x04: /* Reset */ - return 0xffff; - - case 0x05: /* Configuration */ - return s->timing; - - case 0x06: /* Secondary configuration */ - if ((s->model & 0xff00) == 0x2100) - goto bad_reg; - return ((!s->dav) << 15) | ((s->kb.mode & 1) << 14) | s->pll[2]; - - case 0x10: /* Keypad Mask */ - if ((s->model & 0xff00) == 0x2100) - goto bad_reg; - return s->kb.mask; - - default: - bad_reg: -#ifdef TSC_VERBOSE - fprintf(stderr, "tsc2102_control_register_read: " - "no such register: 0x%02x\n", reg); -#endif - return 0xffff; - } -} - -static uint16_t tsc2102_audio_register_read(TSC210xState *s, int reg) -{ - int l_ch, r_ch; - uint16_t val; - - switch (reg) { - case 0x00: /* Audio Control 1 */ - return s->audio_ctrl1; - - case 0x01: - return 0xff00; - - case 0x02: /* DAC Volume Control */ - return s->volume; - - case 0x03: - return 0x8b00; - - case 0x04: /* Audio Control 2 */ - l_ch = 1; - r_ch = 1; - if (s->softstep && !(s->dac_power & (1 << 10))) { - l_ch = (qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) > - s->volume_change + TSC_SOFTSTEP_DELAY); - r_ch = (qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) > - s->volume_change + TSC_SOFTSTEP_DELAY); - } - - return s->audio_ctrl2 | (l_ch << 3) | (r_ch << 2); - - case 0x05: /* Stereo DAC Power Control */ - return 0x2aa0 | s->dac_power | - (((s->dac_power & (1 << 10)) && - (qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) > - s->powerdown + TSC_POWEROFF_DELAY)) << 6); - - case 0x06: /* Audio Control 3 */ - val = s->audio_ctrl3 | 0x0001; - s->audio_ctrl3 &= 0xff3f; - return val; - - case 0x07: /* LCH_BASS_BOOST_N0 */ - case 0x08: /* LCH_BASS_BOOST_N1 */ - case 0x09: /* LCH_BASS_BOOST_N2 */ - case 0x0a: /* LCH_BASS_BOOST_N3 */ - case 0x0b: /* LCH_BASS_BOOST_N4 */ - case 0x0c: /* LCH_BASS_BOOST_N5 */ - case 0x0d: /* LCH_BASS_BOOST_D1 */ - case 0x0e: /* LCH_BASS_BOOST_D2 */ - case 0x0f: /* LCH_BASS_BOOST_D4 */ - case 0x10: /* LCH_BASS_BOOST_D5 */ - case 0x11: /* RCH_BASS_BOOST_N0 */ - case 0x12: /* RCH_BASS_BOOST_N1 */ - case 0x13: /* RCH_BASS_BOOST_N2 */ - case 0x14: /* RCH_BASS_BOOST_N3 */ - case 0x15: /* RCH_BASS_BOOST_N4 */ - case 0x16: /* RCH_BASS_BOOST_N5 */ - case 0x17: /* RCH_BASS_BOOST_D1 */ - case 0x18: /* RCH_BASS_BOOST_D2 */ - case 0x19: /* RCH_BASS_BOOST_D4 */ - case 0x1a: /* RCH_BASS_BOOST_D5 */ - return s->filter_data[reg - 0x07]; - - case 0x1b: /* PLL Programmability 1 */ - return s->pll[0]; - - case 0x1c: /* PLL Programmability 2 */ - return s->pll[1]; - - case 0x1d: /* Audio Control 4 */ - return (!s->softstep) << 14; - - default: -#ifdef TSC_VERBOSE - fprintf(stderr, "tsc2102_audio_register_read: " - "no such register: 0x%02x\n", reg); -#endif - return 0xffff; - } -} - -static void tsc2102_data_register_write( - TSC210xState *s, int reg, uint16_t value) -{ - switch (reg) { - case 0x00: /* X */ - case 0x01: /* Y */ - case 0x02: /* Z1 */ - case 0x03: /* Z2 */ - case 0x05: /* BAT1 */ - case 0x06: /* BAT2 */ - case 0x07: /* AUX1 */ - case 0x08: /* AUX2 */ - case 0x09: /* TEMP1 */ - case 0x0a: /* TEMP2 */ - return; - - default: - qemu_log_mask(LOG_GUEST_ERROR, "tsc2102_data_register_write: " - "no such register: 0x%02x\n", reg); - } -} - -static void tsc2102_control_register_write( - TSC210xState *s, int reg, uint16_t value) -{ - switch (reg) { - case 0x00: /* TSC ADC */ - s->host_mode = value >> 15; - s->enabled = !(value & 0x4000); - if (s->busy && !s->enabled) - timer_del(s->timer); - s->busy = s->busy && s->enabled; - s->nextfunction = (value >> 10) & 0xf; - s->nextprecision = (value >> 8) & 3; - s->filter = value & 0xff; - return; - - case 0x01: /* Status / Keypad Control */ - if ((s->model & 0xff00) == 0x2100) - s->pin_func = value >> 14; - else { - s->kb.scan = (value >> 14) & 1; - s->kb.debounce = (value >> 11) & 7; - if (s->kb.intr && s->kb.scan) { - s->kb.intr = 0; - qemu_irq_raise(s->kbint); - } - } - return; - - case 0x02: /* DAC Control */ - if ((s->model & 0xff00) == 0x2300) { - s->dac_power &= 0x7fff; - s->dac_power |= 0x8000 & value; - } else - goto bad_reg; - break; - - case 0x03: /* Reference */ - s->ref = value & 0x1f; - return; - - case 0x04: /* Reset */ - if (value == 0xbb00) { - if (s->busy) - timer_del(s->timer); - tsc210x_reset(s); -#ifdef TSC_VERBOSE - } else { - fprintf(stderr, "tsc2102_control_register_write: " - "wrong value written into RESET\n"); -#endif - } - return; - - case 0x05: /* Configuration */ - s->timing = value & 0x3f; -#ifdef TSC_VERBOSE - if (value & ~0x3f) - fprintf(stderr, "tsc2102_control_register_write: " - "wrong value written into CONFIG\n"); -#endif - return; - - case 0x06: /* Secondary configuration */ - if ((s->model & 0xff00) == 0x2100) - goto bad_reg; - s->kb.mode = value >> 14; - s->pll[2] = value & 0x3ffff; - return; - - case 0x10: /* Keypad Mask */ - if ((s->model & 0xff00) == 0x2100) - goto bad_reg; - s->kb.mask = value; - return; - - default: - bad_reg: - qemu_log_mask(LOG_GUEST_ERROR, "tsc2102_control_register_write: " - "no such register: 0x%02x\n", reg); - } -} - -static void tsc2102_audio_register_write( - TSC210xState *s, int reg, uint16_t value) -{ - switch (reg) { - case 0x00: /* Audio Control 1 */ - s->audio_ctrl1 = value & 0x0f3f; -#ifdef TSC_VERBOSE - if ((value & ~0x0f3f) || ((value & 7) != ((value >> 3) & 7))) - fprintf(stderr, "tsc2102_audio_register_write: " - "wrong value written into Audio 1\n"); -#endif - tsc2102_audio_rate_update(s); - tsc2102_audio_output_update(s); - return; - - case 0x01: -#ifdef TSC_VERBOSE - if (value != 0xff00) - fprintf(stderr, "tsc2102_audio_register_write: " - "wrong value written into reg 0x01\n"); -#endif - return; - - case 0x02: /* DAC Volume Control */ - s->volume = value; - s->volume_change = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - return; - - case 0x03: -#ifdef TSC_VERBOSE - if (value != 0x8b00) - fprintf(stderr, "tsc2102_audio_register_write: " - "wrong value written into reg 0x03\n"); -#endif - return; - - case 0x04: /* Audio Control 2 */ - s->audio_ctrl2 = value & 0xf7f2; -#ifdef TSC_VERBOSE - if (value & ~0xf7fd) - fprintf(stderr, "tsc2102_audio_register_write: " - "wrong value written into Audio 2\n"); -#endif - return; - - case 0x05: /* Stereo DAC Power Control */ - if ((value & ~s->dac_power) & (1 << 10)) - s->powerdown = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - - s->dac_power = value & 0x9543; -#ifdef TSC_VERBOSE - if ((value & ~0x9543) != 0x2aa0) - fprintf(stderr, "tsc2102_audio_register_write: " - "wrong value written into Power\n"); -#endif - tsc2102_audio_rate_update(s); - tsc2102_audio_output_update(s); - return; - - case 0x06: /* Audio Control 3 */ - s->audio_ctrl3 &= 0x00c0; - s->audio_ctrl3 |= value & 0xf800; -#ifdef TSC_VERBOSE - if (value & ~0xf8c7) - fprintf(stderr, "tsc2102_audio_register_write: " - "wrong value written into Audio 3\n"); -#endif - tsc2102_audio_output_update(s); - return; - - case 0x07: /* LCH_BASS_BOOST_N0 */ - case 0x08: /* LCH_BASS_BOOST_N1 */ - case 0x09: /* LCH_BASS_BOOST_N2 */ - case 0x0a: /* LCH_BASS_BOOST_N3 */ - case 0x0b: /* LCH_BASS_BOOST_N4 */ - case 0x0c: /* LCH_BASS_BOOST_N5 */ - case 0x0d: /* LCH_BASS_BOOST_D1 */ - case 0x0e: /* LCH_BASS_BOOST_D2 */ - case 0x0f: /* LCH_BASS_BOOST_D4 */ - case 0x10: /* LCH_BASS_BOOST_D5 */ - case 0x11: /* RCH_BASS_BOOST_N0 */ - case 0x12: /* RCH_BASS_BOOST_N1 */ - case 0x13: /* RCH_BASS_BOOST_N2 */ - case 0x14: /* RCH_BASS_BOOST_N3 */ - case 0x15: /* RCH_BASS_BOOST_N4 */ - case 0x16: /* RCH_BASS_BOOST_N5 */ - case 0x17: /* RCH_BASS_BOOST_D1 */ - case 0x18: /* RCH_BASS_BOOST_D2 */ - case 0x19: /* RCH_BASS_BOOST_D4 */ - case 0x1a: /* RCH_BASS_BOOST_D5 */ - s->filter_data[reg - 0x07] = value; - return; - - case 0x1b: /* PLL Programmability 1 */ - s->pll[0] = value & 0xfffc; -#ifdef TSC_VERBOSE - if (value & ~0xfffc) - fprintf(stderr, "tsc2102_audio_register_write: " - "wrong value written into PLL 1\n"); -#endif - return; - - case 0x1c: /* PLL Programmability 2 */ - s->pll[1] = value & 0xfffc; -#ifdef TSC_VERBOSE - if (value & ~0xfffc) - fprintf(stderr, "tsc2102_audio_register_write: " - "wrong value written into PLL 2\n"); -#endif - return; - - case 0x1d: /* Audio Control 4 */ - s->softstep = !(value & 0x4000); -#ifdef TSC_VERBOSE - if (value & ~0x4000) - fprintf(stderr, "tsc2102_audio_register_write: " - "wrong value written into Audio 4\n"); -#endif - return; - - default: - qemu_log_mask(LOG_GUEST_ERROR, "tsc2102_audio_register_write: " - "no such register: 0x%02x\n", reg); - } -} - -/* This handles most of the chip logic. */ -static void tsc210x_pin_update(TSC210xState *s) -{ - int64_t expires; - bool pin_state; - - switch (s->pin_func) { - case 0: - pin_state = s->pressure; - break; - case 1: - pin_state = !!s->dav; - break; - case 2: - default: - pin_state = s->pressure && !s->dav; - } - - if (!s->enabled) - pin_state = false; - - if (pin_state != s->irq) { - s->irq = pin_state; - qemu_set_irq(s->pint, !s->irq); - } - - switch (s->nextfunction) { - case TSC_MODE_XY_SCAN: - case TSC_MODE_XYZ_SCAN: - if (!s->pressure) - return; - break; - - case TSC_MODE_X: - case TSC_MODE_Y: - case TSC_MODE_Z: - if (!s->pressure) - return; - /* Fall through */ - case TSC_MODE_BAT1: - case TSC_MODE_BAT2: - case TSC_MODE_AUX: - case TSC_MODE_TEMP1: - case TSC_MODE_TEMP2: - if (s->dav) - s->enabled = false; - break; - - case TSC_MODE_AUX_SCAN: - case TSC_MODE_PORT_SCAN: - break; - - case TSC_MODE_NO_SCAN: - case TSC_MODE_XX_DRV: - case TSC_MODE_YY_DRV: - case TSC_MODE_YX_DRV: - default: - return; - } - - if (!s->enabled || s->busy || s->dav) - return; - - s->busy = true; - s->precision = s->nextprecision; - s->function = s->nextfunction; - expires = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + - (NANOSECONDS_PER_SECOND >> 10); - timer_mod(s->timer, expires); -} - -static uint16_t tsc210x_read(TSC210xState *s) -{ - uint16_t ret = 0x0000; - - if (!s->command) - fprintf(stderr, "tsc210x_read: SPI underrun!\n"); - - switch (s->page) { - case TSC_DATA_REGISTERS_PAGE: - ret = tsc2102_data_register_read(s, s->offset); - if (!s->dav) - qemu_irq_raise(s->davint); - break; - case TSC_CONTROL_REGISTERS_PAGE: - ret = tsc2102_control_register_read(s, s->offset); - break; - case TSC_AUDIO_REGISTERS_PAGE: - ret = tsc2102_audio_register_read(s, s->offset); - break; - default: - hw_error("tsc210x_read: wrong memory page\n"); - } - - tsc210x_pin_update(s); - - /* Allow sequential reads. */ - s->offset ++; - s->state = false; - return ret; -} - -static void tsc210x_write(TSC210xState *s, uint16_t value) -{ - /* - * This is a two-state state machine for reading - * command and data every second time. - */ - if (!s->state) { - s->command = (value >> 15) != 0; - s->page = (value >> 11) & 0x0f; - s->offset = (value >> 5) & 0x3f; - s->state = true; - } else { - if (s->command) - fprintf(stderr, "tsc210x_write: SPI overrun!\n"); - else - switch (s->page) { - case TSC_DATA_REGISTERS_PAGE: - tsc2102_data_register_write(s, s->offset, value); - break; - case TSC_CONTROL_REGISTERS_PAGE: - tsc2102_control_register_write(s, s->offset, value); - break; - case TSC_AUDIO_REGISTERS_PAGE: - tsc2102_audio_register_write(s, s->offset, value); - break; - default: - hw_error("tsc210x_write: wrong memory page\n"); - } - - tsc210x_pin_update(s); - s->state = false; - } -} - -uint32_t tsc210x_txrx(void *opaque, uint32_t value, int len) -{ - TSC210xState *s = opaque; - uint32_t ret = 0; - - if (len != 16) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: bad SPI word width %i\n", __func__, len); - return 0; - } - - /* TODO: sequential reads etc - how do we make sure the host doesn't - * unintentionally read out a conversion result from a register while - * transmitting the command word of the next command? */ - if (!value || (s->state && s->command)) - ret = tsc210x_read(s); - if (value || (s->state && !s->command)) - tsc210x_write(s, value); - - return ret; -} - -static void tsc210x_timer_tick(void *opaque) -{ - TSC210xState *s = opaque; - - /* Timer ticked -- a set of conversions has been finished. */ - - if (!s->busy) - return; - - s->busy = false; - s->dav |= mode_regs[s->function]; - tsc210x_pin_update(s); - qemu_irq_lower(s->davint); -} - -static void tsc210x_touchscreen_event(void *opaque, - int x, int y, int z, int buttons_state) -{ - TSC210xState *s = opaque; - int p = s->pressure; - - if (buttons_state) { - s->x = x; - s->y = y; - } - s->pressure = !!buttons_state; - - /* - * Note: We would get better responsiveness in the guest by - * signaling TS events immediately, but for now we simulate - * the first conversion delay for sake of correctness. - */ - if (p != s->pressure) - tsc210x_pin_update(s); -} - -static void tsc210x_i2s_swallow(TSC210xState *s) -{ - if (s->dac_voice[0]) - tsc210x_out_flush(s, s->codec.out.len); - else - s->codec.out.len = 0; -} - -static void tsc210x_i2s_set_rate(TSC210xState *s, int in, int out) -{ - s->i2s_tx_rate = out; - s->i2s_rx_rate = in; -} - -static int tsc210x_pre_save(void *opaque) -{ - TSC210xState *s = (TSC210xState *) opaque; - s->now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - - return 0; -} - -static int tsc210x_post_load(void *opaque, int version_id) -{ - TSC210xState *s = (TSC210xState *) opaque; - int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - - if (s->function >= ARRAY_SIZE(mode_regs)) { - return -EINVAL; - } - if (s->nextfunction >= ARRAY_SIZE(mode_regs)) { - return -EINVAL; - } - if (s->precision >= ARRAY_SIZE(resolution)) { - return -EINVAL; - } - if (s->nextprecision >= ARRAY_SIZE(resolution)) { - return -EINVAL; - } - - s->volume_change -= s->now; - s->volume_change += now; - s->powerdown -= s->now; - s->powerdown += now; - - s->busy = timer_pending(s->timer); - qemu_set_irq(s->pint, !s->irq); - qemu_set_irq(s->davint, !s->dav); - - return 0; -} - -static const VMStateField vmstatefields_tsc210x[] = { - VMSTATE_BOOL(enabled, TSC210xState), - VMSTATE_BOOL(host_mode, TSC210xState), - VMSTATE_BOOL(irq, TSC210xState), - VMSTATE_BOOL(command, TSC210xState), - VMSTATE_BOOL(pressure, TSC210xState), - VMSTATE_BOOL(softstep, TSC210xState), - VMSTATE_BOOL(state, TSC210xState), - VMSTATE_UINT16(dav, TSC210xState), - VMSTATE_INT32(x, TSC210xState), - VMSTATE_INT32(y, TSC210xState), - VMSTATE_UINT8(offset, TSC210xState), - VMSTATE_UINT8(page, TSC210xState), - VMSTATE_UINT8(filter, TSC210xState), - VMSTATE_UINT8(pin_func, TSC210xState), - VMSTATE_UINT8(ref, TSC210xState), - VMSTATE_UINT8(timing, TSC210xState), - VMSTATE_UINT8(noise, TSC210xState), - VMSTATE_UINT8(function, TSC210xState), - VMSTATE_UINT8(nextfunction, TSC210xState), - VMSTATE_UINT8(precision, TSC210xState), - VMSTATE_UINT8(nextprecision, TSC210xState), - VMSTATE_UINT16(audio_ctrl1, TSC210xState), - VMSTATE_UINT16(audio_ctrl2, TSC210xState), - VMSTATE_UINT16(audio_ctrl3, TSC210xState), - VMSTATE_UINT16_ARRAY(pll, TSC210xState, 3), - VMSTATE_UINT16(volume, TSC210xState), - VMSTATE_UINT16(dac_power, TSC210xState), - VMSTATE_INT64(volume_change, TSC210xState), - VMSTATE_INT64(powerdown, TSC210xState), - VMSTATE_INT64(now, TSC210xState), - VMSTATE_UINT16_ARRAY(filter_data, TSC210xState, 0x14), - VMSTATE_TIMER_PTR(timer, TSC210xState), - VMSTATE_END_OF_LIST() -}; - -static const VMStateDescription vmstate_tsc2102 = { - .name = "tsc2102", - .version_id = 1, - .minimum_version_id = 1, - .pre_save = tsc210x_pre_save, - .post_load = tsc210x_post_load, - .fields = vmstatefields_tsc210x, -}; - -static const VMStateDescription vmstate_tsc2301 = { - .name = "tsc2301", - .version_id = 1, - .minimum_version_id = 1, - .pre_save = tsc210x_pre_save, - .post_load = tsc210x_post_load, - .fields = vmstatefields_tsc210x, -}; - -static void tsc210x_init(TSC210xState *s, - const char *name, - const VMStateDescription *vmsd) -{ - s->tr[0] = 0; - s->tr[1] = 1; - s->tr[2] = 1; - s->tr[3] = 0; - s->tr[4] = 1; - s->tr[5] = 0; - s->tr[6] = 1; - s->tr[7] = 0; - - s->chip.opaque = s; - s->chip.send = (void *) tsc210x_write; - s->chip.receive = (void *) tsc210x_read; - - s->codec.opaque = s; - s->codec.tx_swallow = (void *) tsc210x_i2s_swallow; - s->codec.set_rate = (void *) tsc210x_i2s_set_rate; - s->codec.in.fifo = s->in_fifo; - s->codec.out.fifo = s->out_fifo; - - tsc210x_reset(s); - - qemu_add_mouse_event_handler(tsc210x_touchscreen_event, s, 1, name); - - if (current_machine->audiodev) { - s->card.name = g_strdup(current_machine->audiodev); - s->card.state = audio_state_by_name(s->card.name, &error_fatal); - } - AUD_register_card(s->name, &s->card, &error_fatal); - - qemu_register_reset((void *) tsc210x_reset, s); - vmstate_register(NULL, 0, vmsd, s); -} - -uWireSlave *tsc2102_init(qemu_irq pint) -{ - TSC210xState *s; - - s = g_new0(TSC210xState, 1); - s->x = 160; - s->y = 160; - s->pressure = 0; - s->precision = s->nextprecision = 0; - s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, tsc210x_timer_tick, s); - s->pint = pint; - s->model = 0x2102; - s->name = "tsc2102"; - - tsc210x_init(s, "QEMU TSC2102-driven Touchscreen", &vmstate_tsc2102); - - return &s->chip; -} - -uWireSlave *tsc2301_init(qemu_irq penirq, qemu_irq kbirq, qemu_irq dav) -{ - TSC210xState *s; - - s = g_new0(TSC210xState, 1); - s->x = 400; - s->y = 240; - s->pressure = 0; - s->precision = s->nextprecision = 0; - s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, tsc210x_timer_tick, s); - s->pint = penirq; - s->kbint = kbirq; - s->davint = dav; - s->model = 0x2301; - s->name = "tsc2301"; - - tsc210x_init(s, "QEMU TSC2301-driven Touchscreen", &vmstate_tsc2301); - - return &s->chip; -} - -I2SCodec *tsc210x_codec(uWireSlave *chip) -{ - TSC210xState *s = (TSC210xState *) chip->opaque; - - return &s->codec; -} - -/* - * Use tslib generated calibration data to generate ADC input values - * from the touchscreen. Assuming 12-bit precision was used during - * tslib calibration. - */ -void tsc210x_set_transform(uWireSlave *chip, const MouseTransformInfo *info) -{ - TSC210xState *s = (TSC210xState *) chip->opaque; -#if 0 - int64_t ltr[8]; - - ltr[0] = (int64_t) info->a[1] * info->y; - ltr[1] = (int64_t) info->a[4] * info->x; - ltr[2] = (int64_t) info->a[1] * info->a[3] - - (int64_t) info->a[4] * info->a[0]; - ltr[3] = (int64_t) info->a[2] * info->a[4] - - (int64_t) info->a[5] * info->a[1]; - ltr[4] = (int64_t) info->a[0] * info->y; - ltr[5] = (int64_t) info->a[3] * info->x; - ltr[6] = (int64_t) info->a[4] * info->a[0] - - (int64_t) info->a[1] * info->a[3]; - ltr[7] = (int64_t) info->a[2] * info->a[3] - - (int64_t) info->a[5] * info->a[0]; - - /* Avoid integer overflow */ - s->tr[0] = ltr[0] >> 11; - s->tr[1] = ltr[1] >> 11; - s->tr[2] = muldiv64(ltr[2], 1, info->a[6]); - s->tr[3] = muldiv64(ltr[3], 1 << 4, ltr[2]); - s->tr[4] = ltr[4] >> 11; - s->tr[5] = ltr[5] >> 11; - s->tr[6] = muldiv64(ltr[6], 1, info->a[6]); - s->tr[7] = muldiv64(ltr[7], 1 << 4, ltr[6]); -#else - - /* This version assumes touchscreen X & Y axis are parallel or - * perpendicular to LCD's X & Y axis in some way. */ - if (abs(info->a[0]) > abs(info->a[1])) { - s->tr[0] = 0; - s->tr[1] = -info->a[6] * info->x; - s->tr[2] = info->a[0]; - s->tr[3] = -info->a[2] / info->a[0]; - s->tr[4] = info->a[6] * info->y; - s->tr[5] = 0; - s->tr[6] = info->a[4]; - s->tr[7] = -info->a[5] / info->a[4]; - } else { - s->tr[0] = info->a[6] * info->y; - s->tr[1] = 0; - s->tr[2] = info->a[1]; - s->tr[3] = -info->a[2] / info->a[1]; - s->tr[4] = 0; - s->tr[5] = -info->a[6] * info->x; - s->tr[6] = info->a[3]; - s->tr[7] = -info->a[5] / info->a[3]; - } - - s->tr[0] >>= 11; - s->tr[1] >>= 11; - s->tr[3] <<= 4; - s->tr[4] >>= 11; - s->tr[5] >>= 11; - s->tr[7] <<= 4; -#endif -} - -void tsc210x_key_event(uWireSlave *chip, int key, int down) -{ - TSC210xState *s = (TSC210xState *) chip->opaque; - - if (down) - s->kb.down |= 1 << key; - else - s->kb.down &= ~(1 << key); - - if (down && (s->kb.down & ~s->kb.mask) && !s->kb.intr) { - s->kb.intr = 1; - qemu_irq_lower(s->kbint); - } else if (s->kb.intr && !(s->kb.down & ~s->kb.mask) && - !(s->kb.mode & 1)) { - s->kb.intr = 0; - qemu_irq_raise(s->kbint); - } -} diff --git a/hw/input/Kconfig b/hw/input/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/input/Kconfig +++ b/hw/input/Kconfig @@ -XXX,XX +XXX,XX @@ config VHOST_USER_INPUT default y depends on VIRTIO_INPUT && VHOST_USER -config TSC210X - bool - config LASIPS2 select PS2 diff --git a/hw/input/meson.build b/hw/input/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/input/meson.build +++ b/hw/input/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_VIRTIO_INPUT', if_true: files('virtio-input.c')) system_ss.add(when: 'CONFIG_VIRTIO_INPUT', if_true: files('virtio-input-hid.c')) system_ss.add(when: 'CONFIG_VIRTIO_INPUT_HOST', if_true: files('virtio-input-host.c')) -system_ss.add(when: 'CONFIG_TSC210X', if_true: files('tsc210x.c')) system_ss.add(when: 'CONFIG_LASIPS2', if_true: files('lasips2.c')) -- 2.34.1 Remove the TWL92230 RTC device, which was used only by the n800 and n810. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20240903160751.4100218-31-peter.maydell@linaro.org --- MAINTAINERS | 1 - hw/rtc/twl92230.c | 882 --------------------------------------------- hw/rtc/Kconfig | 4 - hw/rtc/meson.build | 1 - 4 files changed, 888 deletions(-) delete mode 100644 hw/rtc/twl92230.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes F: hw/input/lm832x.c -F: hw/rtc/twl92230.c F: include/hw/input/lm832x.h Raspberry Pi diff --git a/hw/rtc/twl92230.c b/hw/rtc/twl92230.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/rtc/twl92230.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI TWL92230C energy-management companion device for the OMAP24xx. - * Aka. Menelaus (N4200 MENELAUS1_V2.2) - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "qemu/timer.h" -#include "hw/i2c/i2c.h" -#include "hw/irq.h" -#include "migration/qemu-file-types.h" -#include "migration/vmstate.h" -#include "sysemu/sysemu.h" -#include "sysemu/rtc.h" -#include "qemu/bcd.h" -#include "qemu/module.h" -#include "qom/object.h" - -#define VERBOSE 1 - -#define TYPE_TWL92230 "twl92230" -OBJECT_DECLARE_SIMPLE_TYPE(MenelausState, TWL92230) - -struct MenelausState { - I2CSlave parent_obj; - - int firstbyte; - uint8_t reg; - - uint8_t vcore[5]; - uint8_t dcdc[3]; - uint8_t ldo[8]; - uint8_t sleep[2]; - uint8_t osc; - uint8_t detect; - uint16_t mask; - uint16_t status; - uint8_t dir; - uint8_t inputs; - uint8_t outputs; - uint8_t bbsms; - uint8_t pull[4]; - uint8_t mmc_ctrl[3]; - uint8_t mmc_debounce; - struct { - uint8_t ctrl; - uint16_t comp; - QEMUTimer *hz_tm; - int64_t next; - struct tm tm; - struct tm new; - struct tm alm; - int64_t sec_offset; - int64_t alm_sec; - int next_comp; - } rtc; - uint16_t rtc_next_vmstate; - qemu_irq out[4]; - uint8_t pwrbtn_state; -}; - -static inline void menelaus_update(MenelausState *s) -{ - qemu_set_irq(s->out[3], s->status & ~s->mask); -} - -static inline void menelaus_rtc_start(MenelausState *s) -{ - s->rtc.next += qemu_clock_get_ms(rtc_clock); - timer_mod(s->rtc.hz_tm, s->rtc.next); -} - -static inline void menelaus_rtc_stop(MenelausState *s) -{ - timer_del(s->rtc.hz_tm); - s->rtc.next -= qemu_clock_get_ms(rtc_clock); - if (s->rtc.next < 1) - s->rtc.next = 1; -} - -static void menelaus_rtc_update(MenelausState *s) -{ - qemu_get_timedate(&s->rtc.tm, s->rtc.sec_offset); -} - -static void menelaus_alm_update(MenelausState *s) -{ - if ((s->rtc.ctrl & 3) == 3) - s->rtc.alm_sec = qemu_timedate_diff(&s->rtc.alm) - s->rtc.sec_offset; -} - -static void menelaus_rtc_hz(void *opaque) -{ - MenelausState *s = (MenelausState *) opaque; - - s->rtc.next_comp --; - s->rtc.alm_sec --; - s->rtc.next += 1000; - timer_mod(s->rtc.hz_tm, s->rtc.next); - if ((s->rtc.ctrl >> 3) & 3) { /* EVERY */ - menelaus_rtc_update(s); - if (((s->rtc.ctrl >> 3) & 3) == 1 && !s->rtc.tm.tm_sec) - s->status |= 1 << 8; /* RTCTMR */ - else if (((s->rtc.ctrl >> 3) & 3) == 2 && !s->rtc.tm.tm_min) - s->status |= 1 << 8; /* RTCTMR */ - else if (!s->rtc.tm.tm_hour) - s->status |= 1 << 8; /* RTCTMR */ - } else - s->status |= 1 << 8; /* RTCTMR */ - if ((s->rtc.ctrl >> 1) & 1) { /* RTC_AL_EN */ - if (s->rtc.alm_sec == 0) - s->status |= 1 << 9; /* RTCALM */ - /* TODO: wake-up */ - } - if (s->rtc.next_comp <= 0) { - s->rtc.next -= muldiv64((int16_t) s->rtc.comp, 1000, 0x8000); - s->rtc.next_comp = 3600; - } - menelaus_update(s); -} - -static void menelaus_reset(I2CSlave *i2c) -{ - MenelausState *s = TWL92230(i2c); - - s->reg = 0x00; - - s->vcore[0] = 0x0c; /* XXX: X-loader needs 0x8c? check! */ - s->vcore[1] = 0x05; - s->vcore[2] = 0x02; - s->vcore[3] = 0x0c; - s->vcore[4] = 0x03; - s->dcdc[0] = 0x33; /* Depends on wiring */ - s->dcdc[1] = 0x03; - s->dcdc[2] = 0x00; - s->ldo[0] = 0x95; - s->ldo[1] = 0x7e; - s->ldo[2] = 0x00; - s->ldo[3] = 0x00; /* Depends on wiring */ - s->ldo[4] = 0x03; /* Depends on wiring */ - s->ldo[5] = 0x00; - s->ldo[6] = 0x00; - s->ldo[7] = 0x00; - s->sleep[0] = 0x00; - s->sleep[1] = 0x00; - s->osc = 0x01; - s->detect = 0x09; - s->mask = 0x0fff; - s->status = 0; - s->dir = 0x07; - s->outputs = 0x00; - s->bbsms = 0x00; - s->pull[0] = 0x00; - s->pull[1] = 0x00; - s->pull[2] = 0x00; - s->pull[3] = 0x00; - s->mmc_ctrl[0] = 0x03; - s->mmc_ctrl[1] = 0xc0; - s->mmc_ctrl[2] = 0x00; - s->mmc_debounce = 0x05; - - if (s->rtc.ctrl & 1) - menelaus_rtc_stop(s); - s->rtc.ctrl = 0x00; - s->rtc.comp = 0x0000; - s->rtc.next = 1000; - s->rtc.sec_offset = 0; - s->rtc.next_comp = 1800; - s->rtc.alm_sec = 1800; - s->rtc.alm.tm_sec = 0x00; - s->rtc.alm.tm_min = 0x00; - s->rtc.alm.tm_hour = 0x00; - s->rtc.alm.tm_mday = 0x01; - s->rtc.alm.tm_mon = 0x00; - s->rtc.alm.tm_year = 2004; - menelaus_update(s); -} - -static void menelaus_gpio_set(void *opaque, int line, int level) -{ - MenelausState *s = (MenelausState *) opaque; - - if (line < 3) { - /* No interrupt generated */ - s->inputs &= ~(1 << line); - s->inputs |= level << line; - return; - } - - if (!s->pwrbtn_state && level) { - s->status |= 1 << 11; /* PSHBTN */ - menelaus_update(s); - } - s->pwrbtn_state = level; -} - -#define MENELAUS_REV 0x01 -#define MENELAUS_VCORE_CTRL1 0x02 -#define MENELAUS_VCORE_CTRL2 0x03 -#define MENELAUS_VCORE_CTRL3 0x04 -#define MENELAUS_VCORE_CTRL4 0x05 -#define MENELAUS_VCORE_CTRL5 0x06 -#define MENELAUS_DCDC_CTRL1 0x07 -#define MENELAUS_DCDC_CTRL2 0x08 -#define MENELAUS_DCDC_CTRL3 0x09 -#define MENELAUS_LDO_CTRL1 0x0a -#define MENELAUS_LDO_CTRL2 0x0b -#define MENELAUS_LDO_CTRL3 0x0c -#define MENELAUS_LDO_CTRL4 0x0d -#define MENELAUS_LDO_CTRL5 0x0e -#define MENELAUS_LDO_CTRL6 0x0f -#define MENELAUS_LDO_CTRL7 0x10 -#define MENELAUS_LDO_CTRL8 0x11 -#define MENELAUS_SLEEP_CTRL1 0x12 -#define MENELAUS_SLEEP_CTRL2 0x13 -#define MENELAUS_DEVICE_OFF 0x14 -#define MENELAUS_OSC_CTRL 0x15 -#define MENELAUS_DETECT_CTRL 0x16 -#define MENELAUS_INT_MASK1 0x17 -#define MENELAUS_INT_MASK2 0x18 -#define MENELAUS_INT_STATUS1 0x19 -#define MENELAUS_INT_STATUS2 0x1a -#define MENELAUS_INT_ACK1 0x1b -#define MENELAUS_INT_ACK2 0x1c -#define MENELAUS_GPIO_CTRL 0x1d -#define MENELAUS_GPIO_IN 0x1e -#define MENELAUS_GPIO_OUT 0x1f -#define MENELAUS_BBSMS 0x20 -#define MENELAUS_RTC_CTRL 0x21 -#define MENELAUS_RTC_UPDATE 0x22 -#define MENELAUS_RTC_SEC 0x23 -#define MENELAUS_RTC_MIN 0x24 -#define MENELAUS_RTC_HR 0x25 -#define MENELAUS_RTC_DAY 0x26 -#define MENELAUS_RTC_MON 0x27 -#define MENELAUS_RTC_YR 0x28 -#define MENELAUS_RTC_WKDAY 0x29 -#define MENELAUS_RTC_AL_SEC 0x2a -#define MENELAUS_RTC_AL_MIN 0x2b -#define MENELAUS_RTC_AL_HR 0x2c -#define MENELAUS_RTC_AL_DAY 0x2d -#define MENELAUS_RTC_AL_MON 0x2e -#define MENELAUS_RTC_AL_YR 0x2f -#define MENELAUS_RTC_COMP_MSB 0x30 -#define MENELAUS_RTC_COMP_LSB 0x31 -#define MENELAUS_S1_PULL_EN 0x32 -#define MENELAUS_S1_PULL_DIR 0x33 -#define MENELAUS_S2_PULL_EN 0x34 -#define MENELAUS_S2_PULL_DIR 0x35 -#define MENELAUS_MCT_CTRL1 0x36 -#define MENELAUS_MCT_CTRL2 0x37 -#define MENELAUS_MCT_CTRL3 0x38 -#define MENELAUS_MCT_PIN_ST 0x39 -#define MENELAUS_DEBOUNCE1 0x3a - -static uint8_t menelaus_read(void *opaque, uint8_t addr) -{ - MenelausState *s = (MenelausState *) opaque; - - switch (addr) { - case MENELAUS_REV: - return 0x22; - - case MENELAUS_VCORE_CTRL1 ... MENELAUS_VCORE_CTRL5: - return s->vcore[addr - MENELAUS_VCORE_CTRL1]; - - case MENELAUS_DCDC_CTRL1 ... MENELAUS_DCDC_CTRL3: - return s->dcdc[addr - MENELAUS_DCDC_CTRL1]; - - case MENELAUS_LDO_CTRL1 ... MENELAUS_LDO_CTRL8: - return s->ldo[addr - MENELAUS_LDO_CTRL1]; - - case MENELAUS_SLEEP_CTRL1: - case MENELAUS_SLEEP_CTRL2: - return s->sleep[addr - MENELAUS_SLEEP_CTRL1]; - - case MENELAUS_DEVICE_OFF: - return 0; - - case MENELAUS_OSC_CTRL: - return s->osc | (1 << 7); /* CLK32K_GOOD */ - - case MENELAUS_DETECT_CTRL: - return s->detect; - - case MENELAUS_INT_MASK1: - return (s->mask >> 0) & 0xff; - case MENELAUS_INT_MASK2: - return (s->mask >> 8) & 0xff; - - case MENELAUS_INT_STATUS1: - return (s->status >> 0) & 0xff; - case MENELAUS_INT_STATUS2: - return (s->status >> 8) & 0xff; - - case MENELAUS_INT_ACK1: - case MENELAUS_INT_ACK2: - return 0; - - case MENELAUS_GPIO_CTRL: - return s->dir; - case MENELAUS_GPIO_IN: - return s->inputs | (~s->dir & s->outputs); - case MENELAUS_GPIO_OUT: - return s->outputs; - - case MENELAUS_BBSMS: - return s->bbsms; - - case MENELAUS_RTC_CTRL: - return s->rtc.ctrl; - case MENELAUS_RTC_UPDATE: - return 0x00; - case MENELAUS_RTC_SEC: - menelaus_rtc_update(s); - return to_bcd(s->rtc.tm.tm_sec); - case MENELAUS_RTC_MIN: - menelaus_rtc_update(s); - return to_bcd(s->rtc.tm.tm_min); - case MENELAUS_RTC_HR: - menelaus_rtc_update(s); - if ((s->rtc.ctrl >> 2) & 1) /* MODE12_n24 */ - return to_bcd((s->rtc.tm.tm_hour % 12) + 1) | - (!!(s->rtc.tm.tm_hour >= 12) << 7); /* PM_nAM */ - else - return to_bcd(s->rtc.tm.tm_hour); - case MENELAUS_RTC_DAY: - menelaus_rtc_update(s); - return to_bcd(s->rtc.tm.tm_mday); - case MENELAUS_RTC_MON: - menelaus_rtc_update(s); - return to_bcd(s->rtc.tm.tm_mon + 1); - case MENELAUS_RTC_YR: - menelaus_rtc_update(s); - return to_bcd(s->rtc.tm.tm_year - 2000); - case MENELAUS_RTC_WKDAY: - menelaus_rtc_update(s); - return to_bcd(s->rtc.tm.tm_wday); - case MENELAUS_RTC_AL_SEC: - return to_bcd(s->rtc.alm.tm_sec); - case MENELAUS_RTC_AL_MIN: - return to_bcd(s->rtc.alm.tm_min); - case MENELAUS_RTC_AL_HR: - if ((s->rtc.ctrl >> 2) & 1) /* MODE12_n24 */ - return to_bcd((s->rtc.alm.tm_hour % 12) + 1) | - (!!(s->rtc.alm.tm_hour >= 12) << 7);/* AL_PM_nAM */ - else - return to_bcd(s->rtc.alm.tm_hour); - case MENELAUS_RTC_AL_DAY: - return to_bcd(s->rtc.alm.tm_mday); - case MENELAUS_RTC_AL_MON: - return to_bcd(s->rtc.alm.tm_mon + 1); - case MENELAUS_RTC_AL_YR: - return to_bcd(s->rtc.alm.tm_year - 2000); - case MENELAUS_RTC_COMP_MSB: - return (s->rtc.comp >> 8) & 0xff; - case MENELAUS_RTC_COMP_LSB: - return (s->rtc.comp >> 0) & 0xff; - - case MENELAUS_S1_PULL_EN: - return s->pull[0]; - case MENELAUS_S1_PULL_DIR: - return s->pull[1]; - case MENELAUS_S2_PULL_EN: - return s->pull[2]; - case MENELAUS_S2_PULL_DIR: - return s->pull[3]; - - case MENELAUS_MCT_CTRL1 ... MENELAUS_MCT_CTRL3: - return s->mmc_ctrl[addr - MENELAUS_MCT_CTRL1]; - case MENELAUS_MCT_PIN_ST: - /* TODO: return the real Card Detect */ - return 0; - case MENELAUS_DEBOUNCE1: - return s->mmc_debounce; - - default: -#ifdef VERBOSE - printf("%s: unknown register %02x\n", __func__, addr); -#endif - break; - } - return 0; -} - -static void menelaus_write(void *opaque, uint8_t addr, uint8_t value) -{ - MenelausState *s = (MenelausState *) opaque; - int line; - struct tm tm; - - switch (addr) { - case MENELAUS_VCORE_CTRL1: - s->vcore[0] = (value & 0xe) | MIN(value & 0x1f, 0x12); - break; - case MENELAUS_VCORE_CTRL2: - s->vcore[1] = value; - break; - case MENELAUS_VCORE_CTRL3: - s->vcore[2] = MIN(value & 0x1f, 0x12); - break; - case MENELAUS_VCORE_CTRL4: - s->vcore[3] = MIN(value & 0x1f, 0x12); - break; - case MENELAUS_VCORE_CTRL5: - s->vcore[4] = value & 3; - /* XXX - * auto set to 3 on M_Active, nRESWARM - * auto set to 0 on M_WaitOn, M_Backup - */ - break; - - case MENELAUS_DCDC_CTRL1: - s->dcdc[0] = value & 0x3f; - break; - case MENELAUS_DCDC_CTRL2: - s->dcdc[1] = value & 0x07; - /* XXX - * auto set to 3 on M_Active, nRESWARM - * auto set to 0 on M_WaitOn, M_Backup - */ - break; - case MENELAUS_DCDC_CTRL3: - s->dcdc[2] = value & 0x07; - break; - - case MENELAUS_LDO_CTRL1: - s->ldo[0] = value; - break; - case MENELAUS_LDO_CTRL2: - s->ldo[1] = value & 0x7f; - /* XXX - * auto set to 0x7e on M_WaitOn, M_Backup - */ - break; - case MENELAUS_LDO_CTRL3: - s->ldo[2] = value & 3; - /* XXX - * auto set to 3 on M_Active, nRESWARM - * auto set to 0 on M_WaitOn, M_Backup - */ - break; - case MENELAUS_LDO_CTRL4: - s->ldo[3] = value & 3; - /* XXX - * auto set to 3 on M_Active, nRESWARM - * auto set to 0 on M_WaitOn, M_Backup - */ - break; - case MENELAUS_LDO_CTRL5: - s->ldo[4] = value & 3; - /* XXX - * auto set to 3 on M_Active, nRESWARM - * auto set to 0 on M_WaitOn, M_Backup - */ - break; - case MENELAUS_LDO_CTRL6: - s->ldo[5] = value & 3; - break; - case MENELAUS_LDO_CTRL7: - s->ldo[6] = value & 3; - break; - case MENELAUS_LDO_CTRL8: - s->ldo[7] = value & 3; - break; - - case MENELAUS_SLEEP_CTRL1: - case MENELAUS_SLEEP_CTRL2: - s->sleep[addr - MENELAUS_SLEEP_CTRL1] = value; - break; - - case MENELAUS_DEVICE_OFF: - if (value & 1) { - menelaus_reset(I2C_SLAVE(s)); - } - break; - - case MENELAUS_OSC_CTRL: - s->osc = value & 7; - break; - - case MENELAUS_DETECT_CTRL: - s->detect = value & 0x7f; - break; - - case MENELAUS_INT_MASK1: - s->mask &= 0xf00; - s->mask |= value << 0; - menelaus_update(s); - break; - case MENELAUS_INT_MASK2: - s->mask &= 0x0ff; - s->mask |= value << 8; - menelaus_update(s); - break; - - case MENELAUS_INT_ACK1: - s->status &= ~(((uint16_t) value) << 0); - menelaus_update(s); - break; - case MENELAUS_INT_ACK2: - s->status &= ~(((uint16_t) value) << 8); - menelaus_update(s); - break; - - case MENELAUS_GPIO_CTRL: - for (line = 0; line < 3; line ++) { - if (((s->dir ^ value) >> line) & 1) { - qemu_set_irq(s->out[line], - ((s->outputs & ~s->dir) >> line) & 1); - } - } - s->dir = value & 0x67; - break; - case MENELAUS_GPIO_OUT: - for (line = 0; line < 3; line ++) { - if ((((s->outputs ^ value) & ~s->dir) >> line) & 1) { - qemu_set_irq(s->out[line], (s->outputs >> line) & 1); - } - } - s->outputs = value & 0x07; - break; - - case MENELAUS_BBSMS: - s->bbsms = 0x0d; - break; - - case MENELAUS_RTC_CTRL: - if ((s->rtc.ctrl ^ value) & 1) { /* RTC_EN */ - if (value & 1) - menelaus_rtc_start(s); - else - menelaus_rtc_stop(s); - } - s->rtc.ctrl = value & 0x1f; - menelaus_alm_update(s); - break; - case MENELAUS_RTC_UPDATE: - menelaus_rtc_update(s); - memcpy(&tm, &s->rtc.tm, sizeof(tm)); - switch (value & 0xf) { - case 0: - break; - case 1: - tm.tm_sec = s->rtc.new.tm_sec; - break; - case 2: - tm.tm_min = s->rtc.new.tm_min; - break; - case 3: - if (s->rtc.new.tm_hour > 23) - goto rtc_badness; - tm.tm_hour = s->rtc.new.tm_hour; - break; - case 4: - if (s->rtc.new.tm_mday < 1) - goto rtc_badness; - /* TODO check range */ - tm.tm_mday = s->rtc.new.tm_mday; - break; - case 5: - if (s->rtc.new.tm_mon < 0 || s->rtc.new.tm_mon > 11) - goto rtc_badness; - tm.tm_mon = s->rtc.new.tm_mon; - break; - case 6: - tm.tm_year = s->rtc.new.tm_year; - break; - case 7: - /* TODO set .tm_mday instead */ - tm.tm_wday = s->rtc.new.tm_wday; - break; - case 8: - if (s->rtc.new.tm_hour > 23) - goto rtc_badness; - if (s->rtc.new.tm_mday < 1) - goto rtc_badness; - if (s->rtc.new.tm_mon < 0 || s->rtc.new.tm_mon > 11) - goto rtc_badness; - tm.tm_sec = s->rtc.new.tm_sec; - tm.tm_min = s->rtc.new.tm_min; - tm.tm_hour = s->rtc.new.tm_hour; - tm.tm_mday = s->rtc.new.tm_mday; - tm.tm_mon = s->rtc.new.tm_mon; - tm.tm_year = s->rtc.new.tm_year; - break; - rtc_badness: - default: - fprintf(stderr, "%s: bad RTC_UPDATE value %02x\n", - __func__, value); - s->status |= 1 << 10; /* RTCERR */ - menelaus_update(s); - } - s->rtc.sec_offset = qemu_timedate_diff(&tm); - break; - case MENELAUS_RTC_SEC: - s->rtc.tm.tm_sec = from_bcd(value & 0x7f); - break; - case MENELAUS_RTC_MIN: - s->rtc.tm.tm_min = from_bcd(value & 0x7f); - break; - case MENELAUS_RTC_HR: - s->rtc.tm.tm_hour = (s->rtc.ctrl & (1 << 2)) ? /* MODE12_n24 */ - MIN(from_bcd(value & 0x3f), 12) + ((value >> 7) ? 11 : -1) : - from_bcd(value & 0x3f); - break; - case MENELAUS_RTC_DAY: - s->rtc.tm.tm_mday = from_bcd(value); - break; - case MENELAUS_RTC_MON: - s->rtc.tm.tm_mon = MAX(1, from_bcd(value)) - 1; - break; - case MENELAUS_RTC_YR: - s->rtc.tm.tm_year = 2000 + from_bcd(value); - break; - case MENELAUS_RTC_WKDAY: - s->rtc.tm.tm_mday = from_bcd(value); - break; - case MENELAUS_RTC_AL_SEC: - s->rtc.alm.tm_sec = from_bcd(value & 0x7f); - menelaus_alm_update(s); - break; - case MENELAUS_RTC_AL_MIN: - s->rtc.alm.tm_min = from_bcd(value & 0x7f); - menelaus_alm_update(s); - break; - case MENELAUS_RTC_AL_HR: - s->rtc.alm.tm_hour = (s->rtc.ctrl & (1 << 2)) ? /* MODE12_n24 */ - MIN(from_bcd(value & 0x3f), 12) + ((value >> 7) ? 11 : -1) : - from_bcd(value & 0x3f); - menelaus_alm_update(s); - break; - case MENELAUS_RTC_AL_DAY: - s->rtc.alm.tm_mday = from_bcd(value); - menelaus_alm_update(s); - break; - case MENELAUS_RTC_AL_MON: - s->rtc.alm.tm_mon = MAX(1, from_bcd(value)) - 1; - menelaus_alm_update(s); - break; - case MENELAUS_RTC_AL_YR: - s->rtc.alm.tm_year = 2000 + from_bcd(value); - menelaus_alm_update(s); - break; - case MENELAUS_RTC_COMP_MSB: - s->rtc.comp &= 0xff; - s->rtc.comp |= value << 8; - break; - case MENELAUS_RTC_COMP_LSB: - s->rtc.comp &= 0xff << 8; - s->rtc.comp |= value; - break; - - case MENELAUS_S1_PULL_EN: - s->pull[0] = value; - break; - case MENELAUS_S1_PULL_DIR: - s->pull[1] = value & 0x1f; - break; - case MENELAUS_S2_PULL_EN: - s->pull[2] = value; - break; - case MENELAUS_S2_PULL_DIR: - s->pull[3] = value & 0x1f; - break; - - case MENELAUS_MCT_CTRL1: - s->mmc_ctrl[0] = value & 0x7f; - break; - case MENELAUS_MCT_CTRL2: - s->mmc_ctrl[1] = value; - /* TODO update Card Detect interrupts */ - break; - case MENELAUS_MCT_CTRL3: - s->mmc_ctrl[2] = value & 0xf; - break; - case MENELAUS_DEBOUNCE1: - s->mmc_debounce = value & 0x3f; - break; - - default: -#ifdef VERBOSE - printf("%s: unknown register %02x\n", __func__, addr); -#endif - break; - } -} - -static int menelaus_event(I2CSlave *i2c, enum i2c_event event) -{ - MenelausState *s = TWL92230(i2c); - - if (event == I2C_START_SEND) - s->firstbyte = 1; - - return 0; -} - -static int menelaus_tx(I2CSlave *i2c, uint8_t data) -{ - MenelausState *s = TWL92230(i2c); - - /* Interpret register address byte */ - if (s->firstbyte) { - s->reg = data; - s->firstbyte = 0; - } else - menelaus_write(s, s->reg ++, data); - - return 0; -} - -static uint8_t menelaus_rx(I2CSlave *i2c) -{ - MenelausState *s = TWL92230(i2c); - - return menelaus_read(s, s->reg ++); -} - -/* Save restore 32 bit int as uint16_t - This is a Big hack, but it is how the old state did it. - Or we broke compatibility in the state, or we can't use struct tm - */ - -static int get_int32_as_uint16(QEMUFile *f, void *pv, size_t size, - const VMStateField *field) -{ - int *v = pv; - *v = qemu_get_be16(f); - return 0; -} - -static int put_int32_as_uint16(QEMUFile *f, void *pv, size_t size, - const VMStateField *field, JSONWriter *vmdesc) -{ - int *v = pv; - qemu_put_be16(f, *v); - - return 0; -} - -static const VMStateInfo vmstate_hack_int32_as_uint16 = { - .name = "int32_as_uint16", - .get = get_int32_as_uint16, - .put = put_int32_as_uint16, -}; - -#define VMSTATE_UINT16_HACK(_f, _s) \ - VMSTATE_SINGLE(_f, _s, 0, vmstate_hack_int32_as_uint16, int32_t) - - -static const VMStateDescription vmstate_menelaus_tm = { - .name = "menelaus_tm", - .version_id = 0, - .minimum_version_id = 0, - .fields = (const VMStateField[]) { - VMSTATE_UINT16_HACK(tm_sec, struct tm), - VMSTATE_UINT16_HACK(tm_min, struct tm), - VMSTATE_UINT16_HACK(tm_hour, struct tm), - VMSTATE_UINT16_HACK(tm_mday, struct tm), - VMSTATE_UINT16_HACK(tm_min, struct tm), - VMSTATE_UINT16_HACK(tm_year, struct tm), - VMSTATE_END_OF_LIST() - } -}; - -static int menelaus_pre_save(void *opaque) -{ - MenelausState *s = opaque; - /* Should be <= 1000 */ - s->rtc_next_vmstate = s->rtc.next - qemu_clock_get_ms(rtc_clock); - - return 0; -} - -static int menelaus_post_load(void *opaque, int version_id) -{ - MenelausState *s = opaque; - - if (s->rtc.ctrl & 1) /* RTC_EN */ - menelaus_rtc_stop(s); - - s->rtc.next = s->rtc_next_vmstate; - - menelaus_alm_update(s); - menelaus_update(s); - if (s->rtc.ctrl & 1) /* RTC_EN */ - menelaus_rtc_start(s); - return 0; -} - -static const VMStateDescription vmstate_menelaus = { - .name = "menelaus", - .version_id = 0, - .minimum_version_id = 0, - .pre_save = menelaus_pre_save, - .post_load = menelaus_post_load, - .fields = (const VMStateField[]) { - VMSTATE_INT32(firstbyte, MenelausState), - VMSTATE_UINT8(reg, MenelausState), - VMSTATE_UINT8_ARRAY(vcore, MenelausState, 5), - VMSTATE_UINT8_ARRAY(dcdc, MenelausState, 3), - VMSTATE_UINT8_ARRAY(ldo, MenelausState, 8), - VMSTATE_UINT8_ARRAY(sleep, MenelausState, 2), - VMSTATE_UINT8(osc, MenelausState), - VMSTATE_UINT8(detect, MenelausState), - VMSTATE_UINT16(mask, MenelausState), - VMSTATE_UINT16(status, MenelausState), - VMSTATE_UINT8(dir, MenelausState), - VMSTATE_UINT8(inputs, MenelausState), - VMSTATE_UINT8(outputs, MenelausState), - VMSTATE_UINT8(bbsms, MenelausState), - VMSTATE_UINT8_ARRAY(pull, MenelausState, 4), - VMSTATE_UINT8_ARRAY(mmc_ctrl, MenelausState, 3), - VMSTATE_UINT8(mmc_debounce, MenelausState), - VMSTATE_UINT8(rtc.ctrl, MenelausState), - VMSTATE_UINT16(rtc.comp, MenelausState), - VMSTATE_UINT16(rtc_next_vmstate, MenelausState), - VMSTATE_STRUCT(rtc.new, MenelausState, 0, vmstate_menelaus_tm, - struct tm), - VMSTATE_STRUCT(rtc.alm, MenelausState, 0, vmstate_menelaus_tm, - struct tm), - VMSTATE_UINT8(pwrbtn_state, MenelausState), - VMSTATE_I2C_SLAVE(parent_obj, MenelausState), - VMSTATE_END_OF_LIST() - } -}; - -static void twl92230_realize(DeviceState *dev, Error **errp) -{ - MenelausState *s = TWL92230(dev); - - s->rtc.hz_tm = timer_new_ms(rtc_clock, menelaus_rtc_hz, s); - /* Three output pins plus one interrupt pin. */ - qdev_init_gpio_out(dev, s->out, 4); - - /* Three input pins plus one power-button pin. */ - qdev_init_gpio_in(dev, menelaus_gpio_set, 4); - - menelaus_reset(I2C_SLAVE(dev)); -} - -static void twl92230_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - I2CSlaveClass *sc = I2C_SLAVE_CLASS(klass); - - dc->realize = twl92230_realize; - sc->event = menelaus_event; - sc->recv = menelaus_rx; - sc->send = menelaus_tx; - dc->vmsd = &vmstate_menelaus; -} - -static const TypeInfo twl92230_info = { - .name = TYPE_TWL92230, - .parent = TYPE_I2C_SLAVE, - .instance_size = sizeof(MenelausState), - .class_init = twl92230_class_init, -}; - -static void twl92230_register_types(void) -{ - type_register_static(&twl92230_info); -} - -type_init(twl92230_register_types) diff --git a/hw/rtc/Kconfig b/hw/rtc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/Kconfig +++ b/hw/rtc/Kconfig @@ -XXX,XX +XXX,XX @@ config M48T59 config PL031 bool -config TWL92230 - bool - depends on I2C - config MC146818RTC depends on ISA_BUS bool diff --git a/hw/rtc/meson.build b/hw/rtc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/meson.build +++ b/hw/rtc/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_DS1338', if_true: files('ds1338.c')) system_ss.add(when: 'CONFIG_M41T80', if_true: files('m41t80.c')) system_ss.add(when: 'CONFIG_M48T59', if_true: files('m48t59.c')) system_ss.add(when: 'CONFIG_PL031', if_true: files('pl031.c')) -system_ss.add(when: 'CONFIG_TWL92230', if_true: files('twl92230.c')) system_ss.add(when: ['CONFIG_ISA_BUS', 'CONFIG_M48T59'], if_true: files('m48t59-isa.c')) system_ss.add(when: 'CONFIG_XLNX_ZYNQMP', if_true: files('xlnx-zynqmp-rtc.c')) -- 2.34.1 Remove the lm832x keyboard-and-pwm i2c device model. This was only used by the n800 and n810 machines. (Although this is an i2c device and so in theory available to create on the command line, in practice it has an outbound IRQ line that the machine model needs to wire up, and the only way to inject keys events into it is to call the lm832x_key_event() function, so it isn't in practice possible to use it separately from the n800/n810.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20240903160751.4100218-32-peter.maydell@linaro.org --- MAINTAINERS | 7 - include/hw/input/lm832x.h | 28 -- hw/input/lm832x.c | 528 -------------------------------------- hw/input/Kconfig | 4 - hw/input/meson.build | 1 - 5 files changed, 568 deletions(-) delete mode 100644 include/hw/input/lm832x.h delete mode 100644 hw/input/lm832x.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: pc-bios/npcm7xx_bootrom.bin F: roms/vbootrom F: docs/system/arm/nuvoton.rst -nSeries -M: Peter Maydell <peter.maydell@linaro.org> -L: qemu-arm@nongnu.org -S: Odd Fixes -F: hw/input/lm832x.c -F: include/hw/input/lm832x.h - Raspberry Pi M: Peter Maydell <peter.maydell@linaro.org> R: Philippe Mathieu-Daudé <philmd@linaro.org> diff --git a/include/hw/input/lm832x.h b/include/hw/input/lm832x.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/hw/input/lm832x.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * National Semiconductor LM8322/8323 GPIO keyboard & PWM chips. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef HW_INPUT_LM832X_H -#define HW_INPUT_LM832X_H - -#define TYPE_LM8323 "lm8323" - -void lm832x_key_event(DeviceState *dev, int key, int state); - -#endif diff --git a/hw/input/lm832x.c b/hw/input/lm832x.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/input/lm832x.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * National Semiconductor LM8322/8323 GPIO keyboard & PWM chips. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "hw/input/lm832x.h" -#include "hw/i2c/i2c.h" -#include "hw/irq.h" -#include "migration/vmstate.h" -#include "qemu/module.h" -#include "qemu/timer.h" -#include "ui/console.h" -#include "qom/object.h" - -OBJECT_DECLARE_SIMPLE_TYPE(LM823KbdState, LM8323) - -struct LM823KbdState { - I2CSlave parent_obj; - - uint8_t i2c_dir; - uint8_t i2c_cycle; - uint8_t reg; - - qemu_irq nirq; - uint16_t model; - - struct { - qemu_irq out[2]; - int in[2][2]; - } mux; - - uint8_t config; - uint8_t status; - uint8_t acttime; - uint8_t error; - uint8_t clock; - - struct { - uint16_t pull; - uint16_t mask; - uint16_t dir; - uint16_t level; - qemu_irq out[16]; - } gpio; - - struct { - uint8_t dbnctime; - uint8_t size; - uint8_t start; - uint8_t len; - uint8_t fifo[16]; - } kbd; - - struct { - uint16_t file[256]; - uint8_t faddr; - uint8_t addr[3]; - QEMUTimer *tm[3]; - } pwm; -}; - -#define INT_KEYPAD (1 << 0) -#define INT_ERROR (1 << 3) -#define INT_NOINIT (1 << 4) -#define INT_PWMEND(n) (1 << (5 + n)) - -#define ERR_BADPAR (1 << 0) -#define ERR_CMDUNK (1 << 1) -#define ERR_KEYOVR (1 << 2) -#define ERR_FIFOOVR (1 << 6) - -static void lm_kbd_irq_update(LM823KbdState *s) -{ - qemu_set_irq(s->nirq, !s->status); -} - -static void lm_kbd_gpio_update(LM823KbdState *s) -{ -} - -static void lm_kbd_reset(DeviceState *dev) -{ - LM823KbdState *s = LM8323(dev); - - s->config = 0x80; - s->status = INT_NOINIT; - s->acttime = 125; - s->kbd.dbnctime = 3; - s->kbd.size = 0x33; - s->clock = 0x08; - - lm_kbd_irq_update(s); - lm_kbd_gpio_update(s); -} - -static void lm_kbd_error(LM823KbdState *s, int err) -{ - s->error |= err; - s->status |= INT_ERROR; - lm_kbd_irq_update(s); -} - -static void lm_kbd_pwm_tick(LM823KbdState *s, int line) -{ -} - -static void lm_kbd_pwm_start(LM823KbdState *s, int line) -{ - lm_kbd_pwm_tick(s, line); -} - -static void lm_kbd_pwm0_tick(void *opaque) -{ - lm_kbd_pwm_tick(opaque, 0); -} -static void lm_kbd_pwm1_tick(void *opaque) -{ - lm_kbd_pwm_tick(opaque, 1); -} -static void lm_kbd_pwm2_tick(void *opaque) -{ - lm_kbd_pwm_tick(opaque, 2); -} - -enum { - LM832x_CMD_READ_ID = 0x80, /* Read chip ID. */ - LM832x_CMD_WRITE_CFG = 0x81, /* Set configuration item. */ - LM832x_CMD_READ_INT = 0x82, /* Get interrupt status. */ - LM832x_CMD_RESET = 0x83, /* Reset, same as external one */ - LM823x_CMD_WRITE_PULL_DOWN = 0x84, /* Select GPIO pull-up/down. */ - LM832x_CMD_WRITE_PORT_SEL = 0x85, /* Select GPIO in/out. */ - LM832x_CMD_WRITE_PORT_STATE = 0x86, /* Set GPIO pull-up/down. */ - LM832x_CMD_READ_PORT_SEL = 0x87, /* Get GPIO in/out. */ - LM832x_CMD_READ_PORT_STATE = 0x88, /* Get GPIO pull-up/down. */ - LM832x_CMD_READ_FIFO = 0x89, /* Read byte from FIFO. */ - LM832x_CMD_RPT_READ_FIFO = 0x8a, /* Read FIFO (no increment). */ - LM832x_CMD_SET_ACTIVE = 0x8b, /* Set active time. */ - LM832x_CMD_READ_ERROR = 0x8c, /* Get error status. */ - LM832x_CMD_READ_ROTATOR = 0x8e, /* Read rotator status. */ - LM832x_CMD_SET_DEBOUNCE = 0x8f, /* Set debouncing time. */ - LM832x_CMD_SET_KEY_SIZE = 0x90, /* Set keypad size. */ - LM832x_CMD_READ_KEY_SIZE = 0x91, /* Get keypad size. */ - LM832x_CMD_READ_CFG = 0x92, /* Get configuration item. */ - LM832x_CMD_WRITE_CLOCK = 0x93, /* Set clock config. */ - LM832x_CMD_READ_CLOCK = 0x94, /* Get clock config. */ - LM832x_CMD_PWM_WRITE = 0x95, /* Write PWM script. */ - LM832x_CMD_PWM_START = 0x96, /* Start PWM engine. */ - LM832x_CMD_PWM_STOP = 0x97, /* Stop PWM engine. */ - LM832x_GENERAL_ERROR = 0xff, /* There was one error. - Previously was represented by -1 - This is not a command */ -}; - -#define LM832x_MAX_KPX 8 -#define LM832x_MAX_KPY 12 - -static uint8_t lm_kbd_read(LM823KbdState *s, int reg, int byte) -{ - int ret; - - switch (reg) { - case LM832x_CMD_READ_ID: - ret = 0x0400; - break; - - case LM832x_CMD_READ_INT: - ret = s->status; - if (!(s->status & INT_NOINIT)) { - s->status = 0; - lm_kbd_irq_update(s); - } - break; - - case LM832x_CMD_READ_PORT_SEL: - ret = s->gpio.dir; - break; - case LM832x_CMD_READ_PORT_STATE: - ret = s->gpio.mask; - break; - - case LM832x_CMD_READ_FIFO: - if (s->kbd.len <= 1) - return 0x00; - - /* Example response from the two commands after a INT_KEYPAD - * interrupt caused by the key 0x3c being pressed: - * RPT_READ_FIFO: 55 bc 00 4e ff 0a 50 08 00 29 d9 08 01 c9 01 - * READ_FIFO: bc 00 00 4e ff 0a 50 08 00 29 d9 08 01 c9 01 - * RPT_READ_FIFO: bc 00 00 4e ff 0a 50 08 00 29 d9 08 01 c9 01 - * - * 55 is the code of the key release event serviced in the previous - * interrupt handling. - * - * TODO: find out whether the FIFO is advanced a single character - * before reading every byte or the whole size of the FIFO at the - * last LM832x_CMD_READ_FIFO. This affects LM832x_CMD_RPT_READ_FIFO - * output in cases where there are more than one event in the FIFO. - * Assume 0xbc and 0x3c events are in the FIFO: - * RPT_READ_FIFO: 55 bc 3c 00 4e ff 0a 50 08 00 29 d9 08 01 c9 - * READ_FIFO: bc 3c 00 00 4e ff 0a 50 08 00 29 d9 08 01 c9 - * Does RPT_READ_FIFO now return 0xbc and 0x3c or only 0x3c? - */ - s->kbd.start ++; - s->kbd.start &= sizeof(s->kbd.fifo) - 1; - s->kbd.len --; - - return s->kbd.fifo[s->kbd.start]; - case LM832x_CMD_RPT_READ_FIFO: - if (byte >= s->kbd.len) - return 0x00; - - return s->kbd.fifo[(s->kbd.start + byte) & (sizeof(s->kbd.fifo) - 1)]; - - case LM832x_CMD_READ_ERROR: - return s->error; - - case LM832x_CMD_READ_ROTATOR: - return 0; - - case LM832x_CMD_READ_KEY_SIZE: - return s->kbd.size; - - case LM832x_CMD_READ_CFG: - return s->config & 0xf; - - case LM832x_CMD_READ_CLOCK: - return (s->clock & 0xfc) | 2; - - default: - lm_kbd_error(s, ERR_CMDUNK); - fprintf(stderr, "%s: unknown command %02x\n", __func__, reg); - return 0x00; - } - - return ret >> (byte << 3); -} - -static void lm_kbd_write(LM823KbdState *s, int reg, int byte, uint8_t value) -{ - switch (reg) { - case LM832x_CMD_WRITE_CFG: - s->config = value; - /* This must be done whenever s->mux.in is updated (never). */ - if ((s->config >> 1) & 1) /* MUX1EN */ - qemu_set_irq(s->mux.out[0], s->mux.in[0][(s->config >> 0) & 1]); - if ((s->config >> 3) & 1) /* MUX2EN */ - qemu_set_irq(s->mux.out[0], s->mux.in[0][(s->config >> 2) & 1]); - /* TODO: check that this is issued only following the chip reset - * and not in the middle of operation and that it is followed by - * the GPIO ports re-resablishing through WRITE_PORT_SEL and - * WRITE_PORT_STATE (using a timer perhaps) and otherwise output - * warnings. */ - s->status = 0; - lm_kbd_irq_update(s); - s->kbd.len = 0; - s->kbd.start = 0; - s->reg = LM832x_GENERAL_ERROR; - break; - - case LM832x_CMD_RESET: - if (value == 0xaa) - lm_kbd_reset(DEVICE(s)); - else - lm_kbd_error(s, ERR_BADPAR); - s->reg = LM832x_GENERAL_ERROR; - break; - - case LM823x_CMD_WRITE_PULL_DOWN: - if (!byte) - s->gpio.pull = value; - else { - s->gpio.pull |= value << 8; - lm_kbd_gpio_update(s); - s->reg = LM832x_GENERAL_ERROR; - } - break; - case LM832x_CMD_WRITE_PORT_SEL: - if (!byte) - s->gpio.dir = value; - else { - s->gpio.dir |= value << 8; - lm_kbd_gpio_update(s); - s->reg = LM832x_GENERAL_ERROR; - } - break; - case LM832x_CMD_WRITE_PORT_STATE: - if (!byte) - s->gpio.mask = value; - else { - s->gpio.mask |= value << 8; - lm_kbd_gpio_update(s); - s->reg = LM832x_GENERAL_ERROR; - } - break; - - case LM832x_CMD_SET_ACTIVE: - s->acttime = value; - s->reg = LM832x_GENERAL_ERROR; - break; - - case LM832x_CMD_SET_DEBOUNCE: - s->kbd.dbnctime = value; - s->reg = LM832x_GENERAL_ERROR; - if (!value) - lm_kbd_error(s, ERR_BADPAR); - break; - - case LM832x_CMD_SET_KEY_SIZE: - s->kbd.size = value; - s->reg = LM832x_GENERAL_ERROR; - if ( - (value & 0xf) < 3 || (value & 0xf) > LM832x_MAX_KPY || - (value >> 4) < 3 || (value >> 4) > LM832x_MAX_KPX) - lm_kbd_error(s, ERR_BADPAR); - break; - - case LM832x_CMD_WRITE_CLOCK: - s->clock = value; - s->reg = LM832x_GENERAL_ERROR; - if ((value & 3) && (value & 3) != 3) { - lm_kbd_error(s, ERR_BADPAR); - fprintf(stderr, "%s: invalid clock setting in RCPWM\n", - __func__); - } - /* TODO: Validate that the command is only issued once */ - break; - - case LM832x_CMD_PWM_WRITE: - if (byte == 0) { - if (!(value & 3) || (value >> 2) > 59) { - lm_kbd_error(s, ERR_BADPAR); - s->reg = LM832x_GENERAL_ERROR; - break; - } - - s->pwm.faddr = value; - s->pwm.file[s->pwm.faddr] = 0; - } else if (byte == 1) { - s->pwm.file[s->pwm.faddr] |= value << 8; - } else if (byte == 2) { - s->pwm.file[s->pwm.faddr] |= value << 0; - s->reg = LM832x_GENERAL_ERROR; - } - break; - case LM832x_CMD_PWM_START: - s->reg = LM832x_GENERAL_ERROR; - if (!(value & 3) || (value >> 2) > 59) { - lm_kbd_error(s, ERR_BADPAR); - break; - } - - s->pwm.addr[(value & 3) - 1] = value >> 2; - lm_kbd_pwm_start(s, (value & 3) - 1); - break; - case LM832x_CMD_PWM_STOP: - s->reg = LM832x_GENERAL_ERROR; - if (!(value & 3)) { - lm_kbd_error(s, ERR_BADPAR); - break; - } - - timer_del(s->pwm.tm[(value & 3) - 1]); - break; - - case LM832x_GENERAL_ERROR: - lm_kbd_error(s, ERR_BADPAR); - break; - default: - lm_kbd_error(s, ERR_CMDUNK); - fprintf(stderr, "%s: unknown command %02x\n", __func__, reg); - break; - } -} - -static int lm_i2c_event(I2CSlave *i2c, enum i2c_event event) -{ - LM823KbdState *s = LM8323(i2c); - - switch (event) { - case I2C_START_RECV: - case I2C_START_SEND: - s->i2c_cycle = 0; - s->i2c_dir = (event == I2C_START_SEND); - break; - - default: - break; - } - - return 0; -} - -static uint8_t lm_i2c_rx(I2CSlave *i2c) -{ - LM823KbdState *s = LM8323(i2c); - - return lm_kbd_read(s, s->reg, s->i2c_cycle ++); -} - -static int lm_i2c_tx(I2CSlave *i2c, uint8_t data) -{ - LM823KbdState *s = LM8323(i2c); - - if (!s->i2c_cycle) - s->reg = data; - else - lm_kbd_write(s, s->reg, s->i2c_cycle - 1, data); - s->i2c_cycle ++; - - return 0; -} - -static int lm_kbd_post_load(void *opaque, int version_id) -{ - LM823KbdState *s = opaque; - - lm_kbd_irq_update(s); - lm_kbd_gpio_update(s); - - return 0; -} - -static const VMStateDescription vmstate_lm_kbd = { - .name = "LM8323", - .version_id = 0, - .minimum_version_id = 0, - .post_load = lm_kbd_post_load, - .fields = (const VMStateField[]) { - VMSTATE_I2C_SLAVE(parent_obj, LM823KbdState), - VMSTATE_UINT8(i2c_dir, LM823KbdState), - VMSTATE_UINT8(i2c_cycle, LM823KbdState), - VMSTATE_UINT8(reg, LM823KbdState), - VMSTATE_UINT8(config, LM823KbdState), - VMSTATE_UINT8(status, LM823KbdState), - VMSTATE_UINT8(acttime, LM823KbdState), - VMSTATE_UINT8(error, LM823KbdState), - VMSTATE_UINT8(clock, LM823KbdState), - VMSTATE_UINT16(gpio.pull, LM823KbdState), - VMSTATE_UINT16(gpio.mask, LM823KbdState), - VMSTATE_UINT16(gpio.dir, LM823KbdState), - VMSTATE_UINT16(gpio.level, LM823KbdState), - VMSTATE_UINT8(kbd.dbnctime, LM823KbdState), - VMSTATE_UINT8(kbd.size, LM823KbdState), - VMSTATE_UINT8(kbd.start, LM823KbdState), - VMSTATE_UINT8(kbd.len, LM823KbdState), - VMSTATE_BUFFER(kbd.fifo, LM823KbdState), - VMSTATE_UINT16_ARRAY(pwm.file, LM823KbdState, 256), - VMSTATE_UINT8(pwm.faddr, LM823KbdState), - VMSTATE_BUFFER(pwm.addr, LM823KbdState), - VMSTATE_TIMER_PTR_ARRAY(pwm.tm, LM823KbdState, 3), - VMSTATE_END_OF_LIST() - } -}; - - -static void lm8323_realize(DeviceState *dev, Error **errp) -{ - LM823KbdState *s = LM8323(dev); - - s->model = 0x8323; - s->pwm.tm[0] = timer_new_ns(QEMU_CLOCK_VIRTUAL, lm_kbd_pwm0_tick, s); - s->pwm.tm[1] = timer_new_ns(QEMU_CLOCK_VIRTUAL, lm_kbd_pwm1_tick, s); - s->pwm.tm[2] = timer_new_ns(QEMU_CLOCK_VIRTUAL, lm_kbd_pwm2_tick, s); - qdev_init_gpio_out(dev, &s->nirq, 1); -} - -void lm832x_key_event(DeviceState *dev, int key, int state) -{ - LM823KbdState *s = LM8323(dev); - - if ((s->status & INT_ERROR) && (s->error & ERR_FIFOOVR)) - return; - - if (s->kbd.len >= sizeof(s->kbd.fifo)) { - lm_kbd_error(s, ERR_FIFOOVR); - return; - } - - s->kbd.fifo[(s->kbd.start + s->kbd.len ++) & (sizeof(s->kbd.fifo) - 1)] = - key | (state << 7); - - /* We never set ERR_KEYOVR because we support multiple keys fine. */ - s->status |= INT_KEYPAD; - lm_kbd_irq_update(s); -} - -static void lm8323_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); - - device_class_set_legacy_reset(dc, lm_kbd_reset); - dc->realize = lm8323_realize; - k->event = lm_i2c_event; - k->recv = lm_i2c_rx; - k->send = lm_i2c_tx; - dc->vmsd = &vmstate_lm_kbd; -} - -static const TypeInfo lm8323_info = { - .name = TYPE_LM8323, - .parent = TYPE_I2C_SLAVE, - .instance_size = sizeof(LM823KbdState), - .class_init = lm8323_class_init, -}; - -static void lm832x_register_types(void) -{ - type_register_static(&lm8323_info); -} - -type_init(lm832x_register_types) diff --git a/hw/input/Kconfig b/hw/input/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/input/Kconfig +++ b/hw/input/Kconfig @@ -XXX,XX +XXX,XX @@ config ADB bool -config LM832X - bool - depends on I2C - config PCKBD bool select PS2 diff --git a/hw/input/meson.build b/hw/input/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/input/meson.build +++ b/hw/input/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(files('hid.c')) system_ss.add(when: 'CONFIG_ADB', if_true: files('adb.c', 'adb-mouse.c', 'adb-kbd.c')) -system_ss.add(when: 'CONFIG_LM832X', if_true: files('lm832x.c')) system_ss.add(when: 'CONFIG_PCKBD', if_true: files('pckbd.c')) system_ss.add(when: 'CONFIG_PL050', if_true: files('pl050.c')) system_ss.add(when: 'CONFIG_PS2', if_true: files('ps2.c')) -- 2.34.1 The OneNAND devices were only used by n800/n810, so they can be removed now. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20240903160751.4100218-33-peter.maydell@linaro.org --- include/hw/block/flash.h | 3 - hw/block/onenand.c | 872 --------------------------------------- hw/block/Kconfig | 3 - hw/block/meson.build | 1 - 4 files changed, 879 deletions(-) delete mode 100644 hw/block/onenand.c diff --git a/include/hw/block/flash.h b/include/hw/block/flash.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/block/flash.h +++ b/include/hw/block/flash.h @@ -XXX,XX +XXX,XX @@ uint32_t nand_getbuswidth(DeviceState *dev); #define NAND_MFR_HYNIX 0xad #define NAND_MFR_MICRON 0x2c -/* onenand.c */ -void *onenand_raw_otp(DeviceState *onenand_device); - /* ecc.c */ typedef struct { uint8_t cp; /* Column parity */ diff --git a/hw/block/onenand.c b/hw/block/onenand.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/block/onenand.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * OneNAND flash memories emulation. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "hw/hw.h" -#include "hw/block/flash.h" -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "hw/qdev-properties-system.h" -#include "sysemu/block-backend.h" -#include "exec/memory.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "qemu/error-report.h" -#include "qemu/log.h" -#include "qemu/module.h" -#include "qom/object.h" - -/* 11 for 2kB-page OneNAND ("2nd generation") and 10 for 1kB-page chips */ -#define PAGE_SHIFT 11 - -/* Fixed */ -#define BLOCK_SHIFT (PAGE_SHIFT + 6) - -#define TYPE_ONE_NAND "onenand" -OBJECT_DECLARE_SIMPLE_TYPE(OneNANDState, ONE_NAND) - -struct OneNANDState { - SysBusDevice parent_obj; - - struct { - uint16_t man; - uint16_t dev; - uint16_t ver; - } id; - int shift; - hwaddr base; - qemu_irq intr; - qemu_irq rdy; - BlockBackend *blk; - BlockBackend *blk_cur; - uint8_t *image; - uint8_t *otp; - uint8_t *current; - MemoryRegion ram; - MemoryRegion mapped_ram; - uint8_t current_direction; - uint8_t *boot[2]; - uint8_t *data[2][2]; - MemoryRegion iomem; - MemoryRegion container; - int cycle; - int otpmode; - - uint16_t addr[8]; - uint16_t unladdr[8]; - int bufaddr; - int count; - uint16_t command; - uint16_t config[2]; - uint16_t status; - uint16_t intstatus; - uint16_t wpstatus; - - ECCState ecc; - - int density_mask; - int secs; - int secs_cur; - int blocks; - uint8_t *blockwp; -}; - -enum { - ONEN_BUF_BLOCK = 0, - ONEN_BUF_BLOCK2 = 1, - ONEN_BUF_DEST_BLOCK = 2, - ONEN_BUF_DEST_PAGE = 3, - ONEN_BUF_PAGE = 7, -}; - -enum { - ONEN_ERR_CMD = 1 << 10, - ONEN_ERR_ERASE = 1 << 11, - ONEN_ERR_PROG = 1 << 12, - ONEN_ERR_LOAD = 1 << 13, -}; - -enum { - ONEN_INT_RESET = 1 << 4, - ONEN_INT_ERASE = 1 << 5, - ONEN_INT_PROG = 1 << 6, - ONEN_INT_LOAD = 1 << 7, - ONEN_INT = 1 << 15, -}; - -enum { - ONEN_LOCK_LOCKTIGHTEN = 1 << 0, - ONEN_LOCK_LOCKED = 1 << 1, - ONEN_LOCK_UNLOCKED = 1 << 2, -}; - -static void onenand_mem_setup(OneNANDState *s) -{ - /* XXX: We should use IO_MEM_ROMD but we broke it earlier... - * Both 0x0000 ... 0x01ff and 0x8000 ... 0x800f can be used to - * write boot commands. Also take note of the BWPS bit. */ - memory_region_init(&s->container, OBJECT(s), "onenand", - 0x10000 << s->shift); - memory_region_add_subregion(&s->container, 0, &s->iomem); - memory_region_init_alias(&s->mapped_ram, OBJECT(s), "onenand-mapped-ram", - &s->ram, 0x0200 << s->shift, - 0xbe00 << s->shift); - memory_region_add_subregion_overlap(&s->container, - 0x0200 << s->shift, - &s->mapped_ram, - 1); -} - -static void onenand_intr_update(OneNANDState *s) -{ - qemu_set_irq(s->intr, ((s->intstatus >> 15) ^ (~s->config[0] >> 6)) & 1); -} - -static int onenand_pre_save(void *opaque) -{ - OneNANDState *s = opaque; - if (s->current == s->otp) { - s->current_direction = 1; - } else if (s->current == s->image) { - s->current_direction = 2; - } else { - s->current_direction = 0; - } - - return 0; -} - -static int onenand_post_load(void *opaque, int version_id) -{ - OneNANDState *s = opaque; - switch (s->current_direction) { - case 0: - break; - case 1: - s->current = s->otp; - break; - case 2: - s->current = s->image; - break; - default: - return -1; - } - onenand_intr_update(s); - return 0; -} - -static const VMStateDescription vmstate_onenand = { - .name = "onenand", - .version_id = 1, - .minimum_version_id = 1, - .pre_save = onenand_pre_save, - .post_load = onenand_post_load, - .fields = (const VMStateField[]) { - VMSTATE_UINT8(current_direction, OneNANDState), - VMSTATE_INT32(cycle, OneNANDState), - VMSTATE_INT32(otpmode, OneNANDState), - VMSTATE_UINT16_ARRAY(addr, OneNANDState, 8), - VMSTATE_UINT16_ARRAY(unladdr, OneNANDState, 8), - VMSTATE_INT32(bufaddr, OneNANDState), - VMSTATE_INT32(count, OneNANDState), - VMSTATE_UINT16(command, OneNANDState), - VMSTATE_UINT16_ARRAY(config, OneNANDState, 2), - VMSTATE_UINT16(status, OneNANDState), - VMSTATE_UINT16(intstatus, OneNANDState), - VMSTATE_UINT16(wpstatus, OneNANDState), - VMSTATE_INT32(secs_cur, OneNANDState), - VMSTATE_PARTIAL_VBUFFER(blockwp, OneNANDState, blocks), - VMSTATE_UINT8(ecc.cp, OneNANDState), - VMSTATE_UINT16_ARRAY(ecc.lp, OneNANDState, 2), - VMSTATE_UINT16(ecc.count, OneNANDState), - VMSTATE_BUFFER_POINTER_UNSAFE(otp, OneNANDState, 0, - ((64 + 2) << PAGE_SHIFT)), - VMSTATE_END_OF_LIST() - } -}; - -/* Hot reset (Reset OneNAND command) or warm reset (RP pin low) */ -static void onenand_reset(OneNANDState *s, int cold) -{ - memset(&s->addr, 0, sizeof(s->addr)); - s->command = 0; - s->count = 1; - s->bufaddr = 0; - s->config[0] = 0x40c0; - s->config[1] = 0x0000; - onenand_intr_update(s); - qemu_irq_raise(s->rdy); - s->status = 0x0000; - s->intstatus = cold ? 0x8080 : 0x8010; - s->unladdr[0] = 0; - s->unladdr[1] = 0; - s->wpstatus = 0x0002; - s->cycle = 0; - s->otpmode = 0; - s->blk_cur = s->blk; - s->current = s->image; - s->secs_cur = s->secs; - - if (cold) { - /* Lock the whole flash */ - memset(s->blockwp, ONEN_LOCK_LOCKED, s->blocks); - - if (s->blk_cur && blk_pread(s->blk_cur, 0, 8 << BDRV_SECTOR_BITS, - s->boot[0], 0) < 0) { - hw_error("%s: Loading the BootRAM failed.\n", __func__); - } - } -} - -static void onenand_system_reset(DeviceState *dev) -{ - OneNANDState *s = ONE_NAND(dev); - - onenand_reset(s, 1); -} - -static inline int onenand_load_main(OneNANDState *s, int sec, int secn, - void *dest) -{ - assert(UINT32_MAX >> BDRV_SECTOR_BITS > sec); - assert(UINT32_MAX >> BDRV_SECTOR_BITS > secn); - if (s->blk_cur) { - return blk_pread(s->blk_cur, sec << BDRV_SECTOR_BITS, - secn << BDRV_SECTOR_BITS, dest, 0) < 0; - } else if (sec + secn > s->secs_cur) { - return 1; - } - - memcpy(dest, s->current + (sec << 9), secn << 9); - - return 0; -} - -static inline int onenand_prog_main(OneNANDState *s, int sec, int secn, - void *src) -{ - int result = 0; - - if (secn > 0) { - uint32_t size = secn << BDRV_SECTOR_BITS; - uint32_t offset = sec << BDRV_SECTOR_BITS; - assert(UINT32_MAX >> BDRV_SECTOR_BITS > sec); - assert(UINT32_MAX >> BDRV_SECTOR_BITS > secn); - const uint8_t *sp = (const uint8_t *)src; - uint8_t *dp = 0; - if (s->blk_cur) { - dp = g_malloc(size); - if (!dp || blk_pread(s->blk_cur, offset, size, dp, 0) < 0) { - result = 1; - } - } else { - if (sec + secn > s->secs_cur) { - result = 1; - } else { - dp = (uint8_t *)s->current + offset; - } - } - if (!result) { - uint32_t i; - for (i = 0; i < size; i++) { - dp[i] &= sp[i]; - } - if (s->blk_cur) { - result = blk_pwrite(s->blk_cur, offset, size, dp, 0) < 0; - } - } - if (dp && s->blk_cur) { - g_free(dp); - } - } - - return result; -} - -static inline int onenand_load_spare(OneNANDState *s, int sec, int secn, - void *dest) -{ - uint8_t buf[512]; - - if (s->blk_cur) { - uint32_t offset = (s->secs_cur + (sec >> 5)) << BDRV_SECTOR_BITS; - if (blk_pread(s->blk_cur, offset, BDRV_SECTOR_SIZE, buf, 0) < 0) { - return 1; - } - memcpy(dest, buf + ((sec & 31) << 4), secn << 4); - } else if (sec + secn > s->secs_cur) { - return 1; - } else { - memcpy(dest, s->current + (s->secs_cur << 9) + (sec << 4), secn << 4); - } - - return 0; -} - -static inline int onenand_prog_spare(OneNANDState *s, int sec, int secn, - void *src) -{ - int result = 0; - if (secn > 0) { - const uint8_t *sp = (const uint8_t *)src; - uint8_t *dp = 0, *dpp = 0; - uint32_t offset = (s->secs_cur + (sec >> 5)) << BDRV_SECTOR_BITS; - assert(UINT32_MAX >> BDRV_SECTOR_BITS > s->secs_cur + (sec >> 5)); - if (s->blk_cur) { - dp = g_malloc(512); - if (!dp - || blk_pread(s->blk_cur, offset, BDRV_SECTOR_SIZE, dp, 0) < 0) { - result = 1; - } else { - dpp = dp + ((sec & 31) << 4); - } - } else { - if (sec + secn > s->secs_cur) { - result = 1; - } else { - dpp = s->current + (s->secs_cur << 9) + (sec << 4); - } - } - if (!result) { - uint32_t i; - for (i = 0; i < (secn << 4); i++) { - dpp[i] &= sp[i]; - } - if (s->blk_cur) { - result = blk_pwrite(s->blk_cur, offset, BDRV_SECTOR_SIZE, dp, - 0) < 0; - } - } - g_free(dp); - } - return result; -} - -static inline int onenand_erase(OneNANDState *s, int sec, int num) -{ - uint8_t *blankbuf, *tmpbuf; - - blankbuf = g_malloc(512); - tmpbuf = g_malloc(512); - memset(blankbuf, 0xff, 512); - for (; num > 0; num--, sec++) { - if (s->blk_cur) { - int erasesec = s->secs_cur + (sec >> 5); - if (blk_pwrite(s->blk_cur, sec << BDRV_SECTOR_BITS, - BDRV_SECTOR_SIZE, blankbuf, 0) < 0) { - goto fail; - } - if (blk_pread(s->blk_cur, erasesec << BDRV_SECTOR_BITS, - BDRV_SECTOR_SIZE, tmpbuf, 0) < 0) { - goto fail; - } - memcpy(tmpbuf + ((sec & 31) << 4), blankbuf, 1 << 4); - if (blk_pwrite(s->blk_cur, erasesec << BDRV_SECTOR_BITS, - BDRV_SECTOR_SIZE, tmpbuf, 0) < 0) { - goto fail; - } - } else { - if (sec + 1 > s->secs_cur) { - goto fail; - } - memcpy(s->current + (sec << 9), blankbuf, 512); - memcpy(s->current + (s->secs_cur << 9) + (sec << 4), - blankbuf, 1 << 4); - } - } - - g_free(tmpbuf); - g_free(blankbuf); - return 0; - -fail: - g_free(tmpbuf); - g_free(blankbuf); - return 1; -} - -static void onenand_command(OneNANDState *s) -{ - int b; - int sec; - void *buf; -#define SETADDR(block, page) \ - sec = (s->addr[page] & 3) + \ - ((((s->addr[page] >> 2) & 0x3f) + \ - (((s->addr[block] & 0xfff) | \ - (s->addr[block] >> 15 ? s->density_mask : 0)) \ - << 6)) \ - << (PAGE_SHIFT - 9)); -#define SETBUF_M() \ - buf = (s->bufaddr & 8) ? s->data[(s->bufaddr >> 2) & 1][0] : s->boot[0]; \ - buf += (s->bufaddr & 3) << 9; -#define SETBUF_S() \ - buf = (s->bufaddr & 8) ? \ - s->data[(s->bufaddr >> 2) & 1][1] : s->boot[1]; \ - buf += (s->bufaddr & 3) << 4; - - switch (s->command) { - case 0x00: /* Load single/multiple sector data unit into buffer */ - SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE) - - SETBUF_M() - if (onenand_load_main(s, sec, s->count, buf)) - s->status |= ONEN_ERR_CMD | ONEN_ERR_LOAD; - -#if 0 - SETBUF_S() - if (onenand_load_spare(s, sec, s->count, buf)) - s->status |= ONEN_ERR_CMD | ONEN_ERR_LOAD; -#endif - - /* TODO: if (s->bufaddr & 3) + s->count was > 4 (2k-pages) - * or if (s->bufaddr & 1) + s->count was > 2 (1k-pages) - * then we need two split the read/write into two chunks. - */ - s->intstatus |= ONEN_INT | ONEN_INT_LOAD; - break; - case 0x13: /* Load single/multiple spare sector into buffer */ - SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE) - - SETBUF_S() - if (onenand_load_spare(s, sec, s->count, buf)) - s->status |= ONEN_ERR_CMD | ONEN_ERR_LOAD; - - /* TODO: if (s->bufaddr & 3) + s->count was > 4 (2k-pages) - * or if (s->bufaddr & 1) + s->count was > 2 (1k-pages) - * then we need two split the read/write into two chunks. - */ - s->intstatus |= ONEN_INT | ONEN_INT_LOAD; - break; - case 0x80: /* Program single/multiple sector data unit from buffer */ - SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE) - - SETBUF_M() - if (onenand_prog_main(s, sec, s->count, buf)) - s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG; - -#if 0 - SETBUF_S() - if (onenand_prog_spare(s, sec, s->count, buf)) - s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG; -#endif - - /* TODO: if (s->bufaddr & 3) + s->count was > 4 (2k-pages) - * or if (s->bufaddr & 1) + s->count was > 2 (1k-pages) - * then we need two split the read/write into two chunks. - */ - s->intstatus |= ONEN_INT | ONEN_INT_PROG; - break; - case 0x1a: /* Program single/multiple spare area sector from buffer */ - SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE) - - SETBUF_S() - if (onenand_prog_spare(s, sec, s->count, buf)) - s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG; - - /* TODO: if (s->bufaddr & 3) + s->count was > 4 (2k-pages) - * or if (s->bufaddr & 1) + s->count was > 2 (1k-pages) - * then we need two split the read/write into two chunks. - */ - s->intstatus |= ONEN_INT | ONEN_INT_PROG; - break; - case 0x1b: /* Copy-back program */ - SETBUF_S() - - SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE) - if (onenand_load_main(s, sec, s->count, buf)) - s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG; - - SETADDR(ONEN_BUF_DEST_BLOCK, ONEN_BUF_DEST_PAGE) - if (onenand_prog_main(s, sec, s->count, buf)) - s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG; - - /* TODO: spare areas */ - - s->intstatus |= ONEN_INT | ONEN_INT_PROG; - break; - - case 0x23: /* Unlock NAND array block(s) */ - s->intstatus |= ONEN_INT; - - /* XXX the previous (?) area should be locked automatically */ - for (b = s->unladdr[0]; b <= s->unladdr[1]; b ++) { - if (b >= s->blocks) { - s->status |= ONEN_ERR_CMD; - break; - } - if (s->blockwp[b] == ONEN_LOCK_LOCKTIGHTEN) - break; - - s->wpstatus = s->blockwp[b] = ONEN_LOCK_UNLOCKED; - } - break; - case 0x27: /* Unlock All NAND array blocks */ - s->intstatus |= ONEN_INT; - - for (b = 0; b < s->blocks; b ++) { - if (s->blockwp[b] == ONEN_LOCK_LOCKTIGHTEN) - break; - - s->wpstatus = s->blockwp[b] = ONEN_LOCK_UNLOCKED; - } - break; - - case 0x2a: /* Lock NAND array block(s) */ - s->intstatus |= ONEN_INT; - - for (b = s->unladdr[0]; b <= s->unladdr[1]; b ++) { - if (b >= s->blocks) { - s->status |= ONEN_ERR_CMD; - break; - } - if (s->blockwp[b] == ONEN_LOCK_LOCKTIGHTEN) - break; - - s->wpstatus = s->blockwp[b] = ONEN_LOCK_LOCKED; - } - break; - case 0x2c: /* Lock-tight NAND array block(s) */ - s->intstatus |= ONEN_INT; - - for (b = s->unladdr[0]; b <= s->unladdr[1]; b ++) { - if (b >= s->blocks) { - s->status |= ONEN_ERR_CMD; - break; - } - if (s->blockwp[b] == ONEN_LOCK_UNLOCKED) - continue; - - s->wpstatus = s->blockwp[b] = ONEN_LOCK_LOCKTIGHTEN; - } - break; - - case 0x71: /* Erase-Verify-Read */ - s->intstatus |= ONEN_INT; - break; - case 0x95: /* Multi-block erase */ - qemu_irq_pulse(s->intr); - /* Fall through. */ - case 0x94: /* Block erase */ - sec = ((s->addr[ONEN_BUF_BLOCK] & 0xfff) | - (s->addr[ONEN_BUF_BLOCK] >> 15 ? s->density_mask : 0)) - << (BLOCK_SHIFT - 9); - if (onenand_erase(s, sec, 1 << (BLOCK_SHIFT - 9))) - s->status |= ONEN_ERR_CMD | ONEN_ERR_ERASE; - - s->intstatus |= ONEN_INT | ONEN_INT_ERASE; - break; - case 0xb0: /* Erase suspend */ - break; - case 0x30: /* Erase resume */ - s->intstatus |= ONEN_INT | ONEN_INT_ERASE; - break; - - case 0xf0: /* Reset NAND Flash core */ - onenand_reset(s, 0); - break; - case 0xf3: /* Reset OneNAND */ - onenand_reset(s, 0); - break; - - case 0x65: /* OTP Access */ - s->intstatus |= ONEN_INT; - s->blk_cur = NULL; - s->current = s->otp; - s->secs_cur = 1 << (BLOCK_SHIFT - 9); - s->addr[ONEN_BUF_BLOCK] = 0; - s->otpmode = 1; - break; - - default: - s->status |= ONEN_ERR_CMD; - s->intstatus |= ONEN_INT; - qemu_log_mask(LOG_GUEST_ERROR, "unknown OneNAND command %x\n", - s->command); - } - - onenand_intr_update(s); -} - -static uint64_t onenand_read(void *opaque, hwaddr addr, - unsigned size) -{ - OneNANDState *s = (OneNANDState *) opaque; - int offset = addr >> s->shift; - - switch (offset) { - case 0x0000 ... 0xbffe: - return lduw_le_p(s->boot[0] + addr); - - case 0xf000: /* Manufacturer ID */ - return s->id.man; - case 0xf001: /* Device ID */ - return s->id.dev; - case 0xf002: /* Version ID */ - return s->id.ver; - /* TODO: get the following values from a real chip! */ - case 0xf003: /* Data Buffer size */ - return 1 << PAGE_SHIFT; - case 0xf004: /* Boot Buffer size */ - return 0x200; - case 0xf005: /* Amount of buffers */ - return 1 | (2 << 8); - case 0xf006: /* Technology */ - return 0; - - case 0xf100 ... 0xf107: /* Start addresses */ - return s->addr[offset - 0xf100]; - - case 0xf200: /* Start buffer */ - return (s->bufaddr << 8) | ((s->count - 1) & (1 << (PAGE_SHIFT - 10))); - - case 0xf220: /* Command */ - return s->command; - case 0xf221: /* System Configuration 1 */ - return s->config[0] & 0xffe0; - case 0xf222: /* System Configuration 2 */ - return s->config[1]; - - case 0xf240: /* Controller Status */ - return s->status; - case 0xf241: /* Interrupt */ - return s->intstatus; - case 0xf24c: /* Unlock Start Block Address */ - return s->unladdr[0]; - case 0xf24d: /* Unlock End Block Address */ - return s->unladdr[1]; - case 0xf24e: /* Write Protection Status */ - return s->wpstatus; - - case 0xff00: /* ECC Status */ - return 0x00; - case 0xff01: /* ECC Result of main area data */ - case 0xff02: /* ECC Result of spare area data */ - case 0xff03: /* ECC Result of main area data */ - case 0xff04: /* ECC Result of spare area data */ - qemu_log_mask(LOG_UNIMP, - "onenand: ECC result registers unimplemented\n"); - return 0x0000; - } - - qemu_log_mask(LOG_GUEST_ERROR, "read of unknown OneNAND register 0x%x\n", - offset); - return 0; -} - -static void onenand_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - OneNANDState *s = (OneNANDState *) opaque; - int offset = addr >> s->shift; - int sec; - - switch (offset) { - case 0x0000 ... 0x01ff: - case 0x8000 ... 0x800f: - if (s->cycle) { - s->cycle = 0; - - if (value == 0x0000) { - SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE) - onenand_load_main(s, sec, - 1 << (PAGE_SHIFT - 9), s->data[0][0]); - s->addr[ONEN_BUF_PAGE] += 4; - s->addr[ONEN_BUF_PAGE] &= 0xff; - } - break; - } - - switch (value) { - case 0x00f0: /* Reset OneNAND */ - onenand_reset(s, 0); - break; - - case 0x00e0: /* Load Data into Buffer */ - s->cycle = 1; - break; - - case 0x0090: /* Read Identification Data */ - memset(s->boot[0], 0, 3 << s->shift); - s->boot[0][0 << s->shift] = s->id.man & 0xff; - s->boot[0][1 << s->shift] = s->id.dev & 0xff; - s->boot[0][2 << s->shift] = s->wpstatus & 0xff; - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "unknown OneNAND boot command %" PRIx64 "\n", - value); - } - break; - - case 0xf100 ... 0xf107: /* Start addresses */ - s->addr[offset - 0xf100] = value; - break; - - case 0xf200: /* Start buffer */ - s->bufaddr = (value >> 8) & 0xf; - if (PAGE_SHIFT == 11) - s->count = (value & 3) ?: 4; - else if (PAGE_SHIFT == 10) - s->count = (value & 1) ?: 2; - break; - - case 0xf220: /* Command */ - if (s->intstatus & (1 << 15)) - break; - s->command = value; - onenand_command(s); - break; - case 0xf221: /* System Configuration 1 */ - s->config[0] = value; - onenand_intr_update(s); - qemu_set_irq(s->rdy, (s->config[0] >> 7) & 1); - break; - case 0xf222: /* System Configuration 2 */ - s->config[1] = value; - break; - - case 0xf241: /* Interrupt */ - s->intstatus &= value; - if ((1 << 15) & ~s->intstatus) - s->status &= ~(ONEN_ERR_CMD | ONEN_ERR_ERASE | - ONEN_ERR_PROG | ONEN_ERR_LOAD); - onenand_intr_update(s); - break; - case 0xf24c: /* Unlock Start Block Address */ - s->unladdr[0] = value & (s->blocks - 1); - /* For some reason we have to set the end address to by default - * be same as start because the software forgets to write anything - * in there. */ - s->unladdr[1] = value & (s->blocks - 1); - break; - case 0xf24d: /* Unlock End Block Address */ - s->unladdr[1] = value & (s->blocks - 1); - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "write to unknown OneNAND register 0x%x\n", - offset); - } -} - -static const MemoryRegionOps onenand_ops = { - .read = onenand_read, - .write = onenand_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void onenand_realize(DeviceState *dev, Error **errp) -{ - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - OneNANDState *s = ONE_NAND(dev); - uint32_t size = 1 << (24 + ((s->id.dev >> 4) & 7)); - void *ram; - Error *local_err = NULL; - - s->base = (hwaddr)-1; - s->rdy = NULL; - s->blocks = size >> BLOCK_SHIFT; - s->secs = size >> 9; - s->blockwp = g_malloc(s->blocks); - s->density_mask = (s->id.dev & 0x08) - ? (1 << (6 + ((s->id.dev >> 4) & 7))) : 0; - memory_region_init_io(&s->iomem, OBJECT(s), &onenand_ops, s, "onenand", - 0x10000 << s->shift); - if (!s->blk) { - s->image = memset(g_malloc(size + (size >> 5)), - 0xff, size + (size >> 5)); - } else { - if (!blk_supports_write_perm(s->blk)) { - error_setg(errp, "Can't use a read-only drive"); - return; - } - blk_set_perm(s->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE, - BLK_PERM_ALL, &local_err); - if (local_err) { - error_propagate(errp, local_err); - return; - } - s->blk_cur = s->blk; - } - s->otp = memset(g_malloc((64 + 2) << PAGE_SHIFT), - 0xff, (64 + 2) << PAGE_SHIFT); - memory_region_init_ram_nomigrate(&s->ram, OBJECT(s), "onenand.ram", - 0xc000 << s->shift, &error_fatal); - vmstate_register_ram_global(&s->ram); - ram = memory_region_get_ram_ptr(&s->ram); - s->boot[0] = ram + (0x0000 << s->shift); - s->boot[1] = ram + (0x8000 << s->shift); - s->data[0][0] = ram + ((0x0200 + (0 << (PAGE_SHIFT - 1))) << s->shift); - s->data[0][1] = ram + ((0x8010 + (0 << (PAGE_SHIFT - 6))) << s->shift); - s->data[1][0] = ram + ((0x0200 + (1 << (PAGE_SHIFT - 1))) << s->shift); - s->data[1][1] = ram + ((0x8010 + (1 << (PAGE_SHIFT - 6))) << s->shift); - onenand_mem_setup(s); - sysbus_init_irq(sbd, &s->intr); - sysbus_init_mmio(sbd, &s->container); - vmstate_register(VMSTATE_IF(dev), - ((s->shift & 0x7f) << 24) - | ((s->id.man & 0xff) << 16) - | ((s->id.dev & 0xff) << 8) - | (s->id.ver & 0xff), - &vmstate_onenand, s); -} - -static Property onenand_properties[] = { - DEFINE_PROP_UINT16("manufacturer_id", OneNANDState, id.man, 0), - DEFINE_PROP_UINT16("device_id", OneNANDState, id.dev, 0), - DEFINE_PROP_UINT16("version_id", OneNANDState, id.ver, 0), - DEFINE_PROP_INT32("shift", OneNANDState, shift, 0), - DEFINE_PROP_DRIVE("drive", OneNANDState, blk), - DEFINE_PROP_END_OF_LIST(), -}; - -static void onenand_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = onenand_realize; - device_class_set_legacy_reset(dc, onenand_system_reset); - device_class_set_props(dc, onenand_properties); -} - -static const TypeInfo onenand_info = { - .name = TYPE_ONE_NAND, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(OneNANDState), - .class_init = onenand_class_init, -}; - -static void onenand_register_types(void) -{ - type_register_static(&onenand_info); -} - -void *onenand_raw_otp(DeviceState *onenand_device) -{ - OneNANDState *s = ONE_NAND(onenand_device); - - return s->otp; -} - -type_init(onenand_register_types) diff --git a/hw/block/Kconfig b/hw/block/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/block/Kconfig +++ b/hw/block/Kconfig @@ -XXX,XX +XXX,XX @@ config PFLASH_CFI02 config ECC bool -config ONENAND - bool - config VIRTIO_BLK bool default y diff --git a/hw/block/meson.build b/hw/block/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/block/meson.build +++ b/hw/block/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_FDC', if_true: files('fdc.c')) system_ss.add(when: 'CONFIG_FDC_ISA', if_true: files('fdc-isa.c')) system_ss.add(when: 'CONFIG_FDC_SYSBUS', if_true: files('fdc-sysbus.c')) system_ss.add(when: 'CONFIG_NAND', if_true: files('nand.c')) -system_ss.add(when: 'CONFIG_ONENAND', if_true: files('onenand.c')) system_ss.add(when: 'CONFIG_PFLASH_CFI01', if_true: files('pflash_cfi01.c')) system_ss.add(when: 'CONFIG_PFLASH_CFI02', if_true: files('pflash_cfi02.c')) system_ss.add(when: 'CONFIG_SSI_M25P80', if_true: files('m25p80.c')) -- 2.34.1 The tusb6010 was only used by the n800/n810 machines, so it can be removed now. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20240903160751.4100218-34-peter.maydell@linaro.org --- hw/usb/tusb6010.c | 850 --------------------------------------------- hw/usb/Kconfig | 4 - hw/usb/meson.build | 1 - 3 files changed, 855 deletions(-) delete mode 100644 hw/usb/tusb6010.c diff --git a/hw/usb/tusb6010.c b/hw/usb/tusb6010.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/usb/tusb6010.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Texas Instruments TUSB6010 emulation. - * Based on reverse-engineering of a linux driver. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "qemu/module.h" -#include "qemu/timer.h" -#include "hw/usb.h" -#include "hw/usb/hcd-musb.h" -#include "hw/arm/omap.h" -#include "hw/hw.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "qom/object.h" - -#define TYPE_TUSB6010 "tusb6010" -OBJECT_DECLARE_SIMPLE_TYPE(TUSBState, TUSB6010) - -struct TUSBState { - SysBusDevice parent_obj; - - MemoryRegion iomem[2]; - qemu_irq irq; - MUSBState *musb; - QEMUTimer *otg_timer; - QEMUTimer *pwr_timer; - - int power; - uint32_t scratch; - uint16_t test_reset; - uint32_t prcm_config; - uint32_t prcm_mngmt; - uint16_t otg_status; - uint32_t dev_config; - int host_mode; - uint32_t intr; - uint32_t intr_ok; - uint32_t mask; - uint32_t usbip_intr; - uint32_t usbip_mask; - uint32_t gpio_intr; - uint32_t gpio_mask; - uint32_t gpio_config; - uint32_t dma_intr; - uint32_t dma_mask; - uint32_t dma_map; - uint32_t dma_config; - uint32_t ep0_config; - uint32_t rx_config[15]; - uint32_t tx_config[15]; - uint32_t wkup_mask; - uint32_t pullup[2]; - uint32_t control_config; - uint32_t otg_timer_val; -}; - -#define TUSB_DEVCLOCK 60000000 /* 60 MHz */ - -#define TUSB_VLYNQ_CTRL 0x004 - -/* Mentor Graphics OTG core registers. */ -#define TUSB_BASE_OFFSET 0x400 - -/* FIFO registers, 32-bit. */ -#define TUSB_FIFO_BASE 0x600 - -/* Device System & Control registers, 32-bit. */ -#define TUSB_SYS_REG_BASE 0x800 - -#define TUSB_DEV_CONF (TUSB_SYS_REG_BASE + 0x000) -#define TUSB_DEV_CONF_USB_HOST_MODE (1 << 16) -#define TUSB_DEV_CONF_PROD_TEST_MODE (1 << 15) -#define TUSB_DEV_CONF_SOFT_ID (1 << 1) -#define TUSB_DEV_CONF_ID_SEL (1 << 0) - -#define TUSB_PHY_OTG_CTRL_ENABLE (TUSB_SYS_REG_BASE + 0x004) -#define TUSB_PHY_OTG_CTRL (TUSB_SYS_REG_BASE + 0x008) -#define TUSB_PHY_OTG_CTRL_WRPROTECT (0xa5 << 24) -#define TUSB_PHY_OTG_CTRL_O_ID_PULLUP (1 << 23) -#define TUSB_PHY_OTG_CTRL_O_VBUS_DET_EN (1 << 19) -#define TUSB_PHY_OTG_CTRL_O_SESS_END_EN (1 << 18) -#define TUSB_PHY_OTG_CTRL_TESTM2 (1 << 17) -#define TUSB_PHY_OTG_CTRL_TESTM1 (1 << 16) -#define TUSB_PHY_OTG_CTRL_TESTM0 (1 << 15) -#define TUSB_PHY_OTG_CTRL_TX_DATA2 (1 << 14) -#define TUSB_PHY_OTG_CTRL_TX_GZ2 (1 << 13) -#define TUSB_PHY_OTG_CTRL_TX_ENABLE2 (1 << 12) -#define TUSB_PHY_OTG_CTRL_DM_PULLDOWN (1 << 11) -#define TUSB_PHY_OTG_CTRL_DP_PULLDOWN (1 << 10) -#define TUSB_PHY_OTG_CTRL_OSC_EN (1 << 9) -#define TUSB_PHY_OTG_CTRL_PHYREF_CLK(v) (((v) & 3) << 7) -#define TUSB_PHY_OTG_CTRL_PD (1 << 6) -#define TUSB_PHY_OTG_CTRL_PLL_ON (1 << 5) -#define TUSB_PHY_OTG_CTRL_EXT_RPU (1 << 4) -#define TUSB_PHY_OTG_CTRL_PWR_GOOD (1 << 3) -#define TUSB_PHY_OTG_CTRL_RESET (1 << 2) -#define TUSB_PHY_OTG_CTRL_SUSPENDM (1 << 1) -#define TUSB_PHY_OTG_CTRL_CLK_MODE (1 << 0) - -/* OTG status register */ -#define TUSB_DEV_OTG_STAT (TUSB_SYS_REG_BASE + 0x00c) -#define TUSB_DEV_OTG_STAT_PWR_CLK_GOOD (1 << 8) -#define TUSB_DEV_OTG_STAT_SESS_END (1 << 7) -#define TUSB_DEV_OTG_STAT_SESS_VALID (1 << 6) -#define TUSB_DEV_OTG_STAT_VBUS_VALID (1 << 5) -#define TUSB_DEV_OTG_STAT_VBUS_SENSE (1 << 4) -#define TUSB_DEV_OTG_STAT_ID_STATUS (1 << 3) -#define TUSB_DEV_OTG_STAT_HOST_DISCON (1 << 2) -#define TUSB_DEV_OTG_STAT_LINE_STATE (3 << 0) -#define TUSB_DEV_OTG_STAT_DP_ENABLE (1 << 1) -#define TUSB_DEV_OTG_STAT_DM_ENABLE (1 << 0) - -#define TUSB_DEV_OTG_TIMER (TUSB_SYS_REG_BASE + 0x010) -#define TUSB_DEV_OTG_TIMER_ENABLE (1 << 31) -#define TUSB_DEV_OTG_TIMER_VAL(v) ((v) & 0x07ffffff) -#define TUSB_PRCM_REV (TUSB_SYS_REG_BASE + 0x014) - -/* PRCM configuration register */ -#define TUSB_PRCM_CONF (TUSB_SYS_REG_BASE + 0x018) -#define TUSB_PRCM_CONF_SFW_CPEN (1 << 24) -#define TUSB_PRCM_CONF_SYS_CLKSEL(v) (((v) & 3) << 16) - -/* PRCM management register */ -#define TUSB_PRCM_MNGMT (TUSB_SYS_REG_BASE + 0x01c) -#define TUSB_PRCM_MNGMT_SRP_FIX_TMR(v) (((v) & 0xf) << 25) -#define TUSB_PRCM_MNGMT_SRP_FIX_EN (1 << 24) -#define TUSB_PRCM_MNGMT_VBUS_VAL_TMR(v) (((v) & 0xf) << 20) -#define TUSB_PRCM_MNGMT_VBUS_VAL_FLT_EN (1 << 19) -#define TUSB_PRCM_MNGMT_DFT_CLK_DIS (1 << 18) -#define TUSB_PRCM_MNGMT_VLYNQ_CLK_DIS (1 << 17) -#define TUSB_PRCM_MNGMT_OTG_SESS_END_EN (1 << 10) -#define TUSB_PRCM_MNGMT_OTG_VBUS_DET_EN (1 << 9) -#define TUSB_PRCM_MNGMT_OTG_ID_PULLUP (1 << 8) -#define TUSB_PRCM_MNGMT_15_SW_EN (1 << 4) -#define TUSB_PRCM_MNGMT_33_SW_EN (1 << 3) -#define TUSB_PRCM_MNGMT_5V_CPEN (1 << 2) -#define TUSB_PRCM_MNGMT_PM_IDLE (1 << 1) -#define TUSB_PRCM_MNGMT_DEV_IDLE (1 << 0) - -/* Wake-up source clear and mask registers */ -#define TUSB_PRCM_WAKEUP_SOURCE (TUSB_SYS_REG_BASE + 0x020) -#define TUSB_PRCM_WAKEUP_CLEAR (TUSB_SYS_REG_BASE + 0x028) -#define TUSB_PRCM_WAKEUP_MASK (TUSB_SYS_REG_BASE + 0x02c) -#define TUSB_PRCM_WAKEUP_RESERVED_BITS (0xffffe << 13) -#define TUSB_PRCM_WGPIO_7 (1 << 12) -#define TUSB_PRCM_WGPIO_6 (1 << 11) -#define TUSB_PRCM_WGPIO_5 (1 << 10) -#define TUSB_PRCM_WGPIO_4 (1 << 9) -#define TUSB_PRCM_WGPIO_3 (1 << 8) -#define TUSB_PRCM_WGPIO_2 (1 << 7) -#define TUSB_PRCM_WGPIO_1 (1 << 6) -#define TUSB_PRCM_WGPIO_0 (1 << 5) -#define TUSB_PRCM_WHOSTDISCON (1 << 4) /* Host disconnect */ -#define TUSB_PRCM_WBUS (1 << 3) /* USB bus resume */ -#define TUSB_PRCM_WNORCS (1 << 2) /* NOR chip select */ -#define TUSB_PRCM_WVBUS (1 << 1) /* OTG PHY VBUS */ -#define TUSB_PRCM_WID (1 << 0) /* OTG PHY ID detect */ - -#define TUSB_PULLUP_1_CTRL (TUSB_SYS_REG_BASE + 0x030) -#define TUSB_PULLUP_2_CTRL (TUSB_SYS_REG_BASE + 0x034) -#define TUSB_INT_CTRL_REV (TUSB_SYS_REG_BASE + 0x038) -#define TUSB_INT_CTRL_CONF (TUSB_SYS_REG_BASE + 0x03c) -#define TUSB_USBIP_INT_SRC (TUSB_SYS_REG_BASE + 0x040) -#define TUSB_USBIP_INT_SET (TUSB_SYS_REG_BASE + 0x044) -#define TUSB_USBIP_INT_CLEAR (TUSB_SYS_REG_BASE + 0x048) -#define TUSB_USBIP_INT_MASK (TUSB_SYS_REG_BASE + 0x04c) -#define TUSB_DMA_INT_SRC (TUSB_SYS_REG_BASE + 0x050) -#define TUSB_DMA_INT_SET (TUSB_SYS_REG_BASE + 0x054) -#define TUSB_DMA_INT_CLEAR (TUSB_SYS_REG_BASE + 0x058) -#define TUSB_DMA_INT_MASK (TUSB_SYS_REG_BASE + 0x05c) -#define TUSB_GPIO_INT_SRC (TUSB_SYS_REG_BASE + 0x060) -#define TUSB_GPIO_INT_SET (TUSB_SYS_REG_BASE + 0x064) -#define TUSB_GPIO_INT_CLEAR (TUSB_SYS_REG_BASE + 0x068) -#define TUSB_GPIO_INT_MASK (TUSB_SYS_REG_BASE + 0x06c) - -/* NOR flash interrupt source registers */ -#define TUSB_INT_SRC (TUSB_SYS_REG_BASE + 0x070) -#define TUSB_INT_SRC_SET (TUSB_SYS_REG_BASE + 0x074) -#define TUSB_INT_SRC_CLEAR (TUSB_SYS_REG_BASE + 0x078) -#define TUSB_INT_MASK (TUSB_SYS_REG_BASE + 0x07c) -#define TUSB_INT_SRC_TXRX_DMA_DONE (1 << 24) -#define TUSB_INT_SRC_USB_IP_CORE (1 << 17) -#define TUSB_INT_SRC_OTG_TIMEOUT (1 << 16) -#define TUSB_INT_SRC_VBUS_SENSE_CHNG (1 << 15) -#define TUSB_INT_SRC_ID_STATUS_CHNG (1 << 14) -#define TUSB_INT_SRC_DEV_WAKEUP (1 << 13) -#define TUSB_INT_SRC_DEV_READY (1 << 12) -#define TUSB_INT_SRC_USB_IP_TX (1 << 9) -#define TUSB_INT_SRC_USB_IP_RX (1 << 8) -#define TUSB_INT_SRC_USB_IP_VBUS_ERR (1 << 7) -#define TUSB_INT_SRC_USB_IP_VBUS_REQ (1 << 6) -#define TUSB_INT_SRC_USB_IP_DISCON (1 << 5) -#define TUSB_INT_SRC_USB_IP_CONN (1 << 4) -#define TUSB_INT_SRC_USB_IP_SOF (1 << 3) -#define TUSB_INT_SRC_USB_IP_RST_BABBLE (1 << 2) -#define TUSB_INT_SRC_USB_IP_RESUME (1 << 1) -#define TUSB_INT_SRC_USB_IP_SUSPEND (1 << 0) - -#define TUSB_GPIO_REV (TUSB_SYS_REG_BASE + 0x080) -#define TUSB_GPIO_CONF (TUSB_SYS_REG_BASE + 0x084) -#define TUSB_DMA_CTRL_REV (TUSB_SYS_REG_BASE + 0x100) -#define TUSB_DMA_REQ_CONF (TUSB_SYS_REG_BASE + 0x104) -#define TUSB_EP0_CONF (TUSB_SYS_REG_BASE + 0x108) -#define TUSB_EP_IN_SIZE (TUSB_SYS_REG_BASE + 0x10c) -#define TUSB_DMA_EP_MAP (TUSB_SYS_REG_BASE + 0x148) -#define TUSB_EP_OUT_SIZE (TUSB_SYS_REG_BASE + 0x14c) -#define TUSB_EP_MAX_PACKET_SIZE_OFFSET (TUSB_SYS_REG_BASE + 0x188) -#define TUSB_SCRATCH_PAD (TUSB_SYS_REG_BASE + 0x1c4) -#define TUSB_WAIT_COUNT (TUSB_SYS_REG_BASE + 0x1c8) -#define TUSB_PROD_TEST_RESET (TUSB_SYS_REG_BASE + 0x1d8) - -#define TUSB_DIDR1_LO (TUSB_SYS_REG_BASE + 0x1f8) -#define TUSB_DIDR1_HI (TUSB_SYS_REG_BASE + 0x1fc) - -/* Device System & Control register bitfields */ -#define TUSB_INT_CTRL_CONF_INT_RLCYC(v) (((v) & 0x7) << 18) -#define TUSB_INT_CTRL_CONF_INT_POLARITY (1 << 17) -#define TUSB_INT_CTRL_CONF_INT_MODE (1 << 16) -#define TUSB_GPIO_CONF_DMAREQ(v) (((v) & 0x3f) << 24) -#define TUSB_DMA_REQ_CONF_BURST_SIZE(v) (((v) & 3) << 26) -#define TUSB_DMA_REQ_CONF_DMA_RQ_EN(v) (((v) & 0x3f) << 20) -#define TUSB_DMA_REQ_CONF_DMA_RQ_ASR(v) (((v) & 0xf) << 16) -#define TUSB_EP0_CONFIG_SW_EN (1 << 8) -#define TUSB_EP0_CONFIG_DIR_TX (1 << 7) -#define TUSB_EP0_CONFIG_XFR_SIZE(v) ((v) & 0x7f) -#define TUSB_EP_CONFIG_SW_EN (1 << 31) -#define TUSB_EP_CONFIG_XFR_SIZE(v) ((v) & 0x7fffffff) -#define TUSB_PROD_TEST_RESET_VAL 0xa596 - -static void tusb_intr_update(TUSBState *s) -{ - if (s->control_config & TUSB_INT_CTRL_CONF_INT_POLARITY) - qemu_set_irq(s->irq, s->intr & ~s->mask & s->intr_ok); - else - qemu_set_irq(s->irq, (!(s->intr & ~s->mask)) & s->intr_ok); -} - -static void tusb_usbip_intr_update(TUSBState *s) -{ - /* TX interrupt in the MUSB */ - if (s->usbip_intr & 0x0000ffff & ~s->usbip_mask) - s->intr |= TUSB_INT_SRC_USB_IP_TX; - else - s->intr &= ~TUSB_INT_SRC_USB_IP_TX; - - /* RX interrupt in the MUSB */ - if (s->usbip_intr & 0xffff0000 & ~s->usbip_mask) - s->intr |= TUSB_INT_SRC_USB_IP_RX; - else - s->intr &= ~TUSB_INT_SRC_USB_IP_RX; - - /* XXX: What about TUSB_INT_SRC_USB_IP_CORE? */ - - tusb_intr_update(s); -} - -static void tusb_dma_intr_update(TUSBState *s) -{ - if (s->dma_intr & ~s->dma_mask) - s->intr |= TUSB_INT_SRC_TXRX_DMA_DONE; - else - s->intr &= ~TUSB_INT_SRC_TXRX_DMA_DONE; - - tusb_intr_update(s); -} - -static void tusb_gpio_intr_update(TUSBState *s) -{ - /* TODO: How is this signalled? */ -} - -static uint32_t tusb_async_readb(void *opaque, hwaddr addr) -{ - TUSBState *s = (TUSBState *) opaque; - - switch (addr & 0xfff) { - case TUSB_BASE_OFFSET ... (TUSB_BASE_OFFSET | 0x1ff): - return musb_read[0](s->musb, addr & 0x1ff); - - case TUSB_FIFO_BASE ... (TUSB_FIFO_BASE | 0x1ff): - return musb_read[0](s->musb, 0x20 + ((addr >> 3) & 0x3c)); - } - - printf("%s: unknown register at %03x\n", - __func__, (int) (addr & 0xfff)); - return 0; -} - -static uint32_t tusb_async_readh(void *opaque, hwaddr addr) -{ - TUSBState *s = (TUSBState *) opaque; - - switch (addr & 0xfff) { - case TUSB_BASE_OFFSET ... (TUSB_BASE_OFFSET | 0x1ff): - return musb_read[1](s->musb, addr & 0x1ff); - - case TUSB_FIFO_BASE ... (TUSB_FIFO_BASE | 0x1ff): - return musb_read[1](s->musb, 0x20 + ((addr >> 3) & 0x3c)); - } - - printf("%s: unknown register at %03x\n", - __func__, (int) (addr & 0xfff)); - return 0; -} - -static uint32_t tusb_async_readw(void *opaque, hwaddr addr) -{ - TUSBState *s = (TUSBState *) opaque; - int offset = addr & 0xfff; - int epnum; - uint32_t ret; - - switch (offset) { - case TUSB_DEV_CONF: - return s->dev_config; - - case TUSB_BASE_OFFSET ... (TUSB_BASE_OFFSET | 0x1ff): - return musb_read[2](s->musb, offset & 0x1ff); - - case TUSB_FIFO_BASE ... (TUSB_FIFO_BASE | 0x1ff): - return musb_read[2](s->musb, 0x20 + ((addr >> 3) & 0x3c)); - - case TUSB_PHY_OTG_CTRL_ENABLE: - case TUSB_PHY_OTG_CTRL: - return 0x00; /* TODO */ - - case TUSB_DEV_OTG_STAT: - ret = s->otg_status; -#if 0 - if (!(s->prcm_mngmt & TUSB_PRCM_MNGMT_OTG_VBUS_DET_EN)) - ret &= ~TUSB_DEV_OTG_STAT_VBUS_VALID; -#endif - return ret; - case TUSB_DEV_OTG_TIMER: - return s->otg_timer_val; - - case TUSB_PRCM_REV: - return 0x20; - case TUSB_PRCM_CONF: - return s->prcm_config; - case TUSB_PRCM_MNGMT: - return s->prcm_mngmt; - case TUSB_PRCM_WAKEUP_SOURCE: - case TUSB_PRCM_WAKEUP_CLEAR: /* TODO: What does this one return? */ - return 0x00000000; - case TUSB_PRCM_WAKEUP_MASK: - return s->wkup_mask; - - case TUSB_PULLUP_1_CTRL: - return s->pullup[0]; - case TUSB_PULLUP_2_CTRL: - return s->pullup[1]; - - case TUSB_INT_CTRL_REV: - return 0x20; - case TUSB_INT_CTRL_CONF: - return s->control_config; - - case TUSB_USBIP_INT_SRC: - case TUSB_USBIP_INT_SET: /* TODO: What do these two return? */ - case TUSB_USBIP_INT_CLEAR: - return s->usbip_intr; - case TUSB_USBIP_INT_MASK: - return s->usbip_mask; - - case TUSB_DMA_INT_SRC: - case TUSB_DMA_INT_SET: /* TODO: What do these two return? */ - case TUSB_DMA_INT_CLEAR: - return s->dma_intr; - case TUSB_DMA_INT_MASK: - return s->dma_mask; - - case TUSB_GPIO_INT_SRC: /* TODO: What do these two return? */ - case TUSB_GPIO_INT_SET: - case TUSB_GPIO_INT_CLEAR: - return s->gpio_intr; - case TUSB_GPIO_INT_MASK: - return s->gpio_mask; - - case TUSB_INT_SRC: - case TUSB_INT_SRC_SET: /* TODO: What do these two return? */ - case TUSB_INT_SRC_CLEAR: - return s->intr; - case TUSB_INT_MASK: - return s->mask; - - case TUSB_GPIO_REV: - return 0x30; - case TUSB_GPIO_CONF: - return s->gpio_config; - - case TUSB_DMA_CTRL_REV: - return 0x30; - case TUSB_DMA_REQ_CONF: - return s->dma_config; - case TUSB_EP0_CONF: - return s->ep0_config; - case TUSB_EP_IN_SIZE ... (TUSB_EP_IN_SIZE + 0x3b): - epnum = (offset - TUSB_EP_IN_SIZE) >> 2; - return s->tx_config[epnum]; - case TUSB_DMA_EP_MAP: - return s->dma_map; - case TUSB_EP_OUT_SIZE ... (TUSB_EP_OUT_SIZE + 0x3b): - epnum = (offset - TUSB_EP_OUT_SIZE) >> 2; - return s->rx_config[epnum]; - case TUSB_EP_MAX_PACKET_SIZE_OFFSET ... - (TUSB_EP_MAX_PACKET_SIZE_OFFSET + 0x3b): - return 0x00000000; /* TODO */ - case TUSB_WAIT_COUNT: - return 0x00; /* TODO */ - - case TUSB_SCRATCH_PAD: - return s->scratch; - - case TUSB_PROD_TEST_RESET: - return s->test_reset; - - /* DIE IDs */ - case TUSB_DIDR1_LO: - return 0xa9453c59; - case TUSB_DIDR1_HI: - return 0x54059adf; - } - - printf("%s: unknown register at %03x\n", __func__, offset); - return 0; -} - -static void tusb_async_writeb(void *opaque, hwaddr addr, - uint32_t value) -{ - TUSBState *s = (TUSBState *) opaque; - - switch (addr & 0xfff) { - case TUSB_BASE_OFFSET ... (TUSB_BASE_OFFSET | 0x1ff): - musb_write[0](s->musb, addr & 0x1ff, value); - break; - - case TUSB_FIFO_BASE ... (TUSB_FIFO_BASE | 0x1ff): - musb_write[0](s->musb, 0x20 + ((addr >> 3) & 0x3c), value); - break; - - default: - printf("%s: unknown register at %03x\n", - __func__, (int) (addr & 0xfff)); - return; - } -} - -static void tusb_async_writeh(void *opaque, hwaddr addr, - uint32_t value) -{ - TUSBState *s = (TUSBState *) opaque; - - switch (addr & 0xfff) { - case TUSB_BASE_OFFSET ... (TUSB_BASE_OFFSET | 0x1ff): - musb_write[1](s->musb, addr & 0x1ff, value); - break; - - case TUSB_FIFO_BASE ... (TUSB_FIFO_BASE | 0x1ff): - musb_write[1](s->musb, 0x20 + ((addr >> 3) & 0x3c), value); - break; - - default: - printf("%s: unknown register at %03x\n", - __func__, (int) (addr & 0xfff)); - return; - } -} - -static void tusb_async_writew(void *opaque, hwaddr addr, - uint32_t value) -{ - TUSBState *s = (TUSBState *) opaque; - int offset = addr & 0xfff; - int epnum; - - switch (offset) { - case TUSB_VLYNQ_CTRL: - break; - - case TUSB_BASE_OFFSET ... (TUSB_BASE_OFFSET | 0x1ff): - musb_write[2](s->musb, offset & 0x1ff, value); - break; - - case TUSB_FIFO_BASE ... (TUSB_FIFO_BASE | 0x1ff): - musb_write[2](s->musb, 0x20 + ((addr >> 3) & 0x3c), value); - break; - - case TUSB_DEV_CONF: - s->dev_config = value; - s->host_mode = (value & TUSB_DEV_CONF_USB_HOST_MODE); - if (value & TUSB_DEV_CONF_PROD_TEST_MODE) - hw_error("%s: Product Test mode not allowed\n", __func__); - break; - - case TUSB_PHY_OTG_CTRL_ENABLE: - case TUSB_PHY_OTG_CTRL: - return; /* TODO */ - case TUSB_DEV_OTG_TIMER: - s->otg_timer_val = value; - if (value & TUSB_DEV_OTG_TIMER_ENABLE) - timer_mod(s->otg_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + - muldiv64(TUSB_DEV_OTG_TIMER_VAL(value), - NANOSECONDS_PER_SECOND, TUSB_DEVCLOCK)); - else - timer_del(s->otg_timer); - break; - - case TUSB_PRCM_CONF: - s->prcm_config = value; - break; - case TUSB_PRCM_MNGMT: - s->prcm_mngmt = value; - break; - case TUSB_PRCM_WAKEUP_CLEAR: - break; - case TUSB_PRCM_WAKEUP_MASK: - s->wkup_mask = value; - break; - - case TUSB_PULLUP_1_CTRL: - s->pullup[0] = value; - break; - case TUSB_PULLUP_2_CTRL: - s->pullup[1] = value; - break; - case TUSB_INT_CTRL_CONF: - s->control_config = value; - tusb_intr_update(s); - break; - - case TUSB_USBIP_INT_SET: - s->usbip_intr |= value; - tusb_usbip_intr_update(s); - break; - case TUSB_USBIP_INT_CLEAR: - s->usbip_intr &= ~value; - tusb_usbip_intr_update(s); - musb_core_intr_clear(s->musb, ~value); - break; - case TUSB_USBIP_INT_MASK: - s->usbip_mask = value; - tusb_usbip_intr_update(s); - break; - - case TUSB_DMA_INT_SET: - s->dma_intr |= value; - tusb_dma_intr_update(s); - break; - case TUSB_DMA_INT_CLEAR: - s->dma_intr &= ~value; - tusb_dma_intr_update(s); - break; - case TUSB_DMA_INT_MASK: - s->dma_mask = value; - tusb_dma_intr_update(s); - break; - - case TUSB_GPIO_INT_SET: - s->gpio_intr |= value; - tusb_gpio_intr_update(s); - break; - case TUSB_GPIO_INT_CLEAR: - s->gpio_intr &= ~value; - tusb_gpio_intr_update(s); - break; - case TUSB_GPIO_INT_MASK: - s->gpio_mask = value; - tusb_gpio_intr_update(s); - break; - - case TUSB_INT_SRC_SET: - s->intr |= value; - tusb_intr_update(s); - break; - case TUSB_INT_SRC_CLEAR: - s->intr &= ~value; - tusb_intr_update(s); - break; - case TUSB_INT_MASK: - s->mask = value; - tusb_intr_update(s); - break; - - case TUSB_GPIO_CONF: - s->gpio_config = value; - break; - case TUSB_DMA_REQ_CONF: - s->dma_config = value; - break; - case TUSB_EP0_CONF: - s->ep0_config = value & 0x1ff; - musb_set_size(s->musb, 0, TUSB_EP0_CONFIG_XFR_SIZE(value), - value & TUSB_EP0_CONFIG_DIR_TX); - break; - case TUSB_EP_IN_SIZE ... (TUSB_EP_IN_SIZE + 0x3b): - epnum = (offset - TUSB_EP_IN_SIZE) >> 2; - s->tx_config[epnum] = value; - musb_set_size(s->musb, epnum + 1, TUSB_EP_CONFIG_XFR_SIZE(value), 1); - break; - case TUSB_DMA_EP_MAP: - s->dma_map = value; - break; - case TUSB_EP_OUT_SIZE ... (TUSB_EP_OUT_SIZE + 0x3b): - epnum = (offset - TUSB_EP_OUT_SIZE) >> 2; - s->rx_config[epnum] = value; - musb_set_size(s->musb, epnum + 1, TUSB_EP_CONFIG_XFR_SIZE(value), 0); - break; - case TUSB_EP_MAX_PACKET_SIZE_OFFSET ... - (TUSB_EP_MAX_PACKET_SIZE_OFFSET + 0x3b): - return; /* TODO */ - case TUSB_WAIT_COUNT: - return; /* TODO */ - - case TUSB_SCRATCH_PAD: - s->scratch = value; - break; - - case TUSB_PROD_TEST_RESET: - s->test_reset = value; - break; - - default: - printf("%s: unknown register at %03x\n", __func__, offset); - return; - } -} - -static uint64_t tusb_async_readfn(void *opaque, hwaddr addr, unsigned size) -{ - switch (size) { - case 1: - return tusb_async_readb(opaque, addr); - case 2: - return tusb_async_readh(opaque, addr); - case 4: - return tusb_async_readw(opaque, addr); - default: - g_assert_not_reached(); - } -} - -static void tusb_async_writefn(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - switch (size) { - case 1: - tusb_async_writeb(opaque, addr, value); - break; - case 2: - tusb_async_writeh(opaque, addr, value); - break; - case 4: - tusb_async_writew(opaque, addr, value); - break; - default: - g_assert_not_reached(); - } -} - -static const MemoryRegionOps tusb_async_ops = { - .read = tusb_async_readfn, - .write = tusb_async_writefn, - .valid.min_access_size = 1, - .valid.max_access_size = 4, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void tusb_otg_tick(void *opaque) -{ - TUSBState *s = (TUSBState *) opaque; - - s->otg_timer_val = 0; - s->intr |= TUSB_INT_SRC_OTG_TIMEOUT; - tusb_intr_update(s); -} - -static void tusb_power_tick(void *opaque) -{ - TUSBState *s = (TUSBState *) opaque; - - if (s->power) { - s->intr_ok = ~0; - tusb_intr_update(s); - } -} - -static void tusb_musb_core_intr(void *opaque, int source, int level) -{ - TUSBState *s = (TUSBState *) opaque; - uint16_t otg_status = s->otg_status; - - switch (source) { - case musb_set_vbus: - if (level) - otg_status |= TUSB_DEV_OTG_STAT_VBUS_VALID; - else - otg_status &= ~TUSB_DEV_OTG_STAT_VBUS_VALID; - - /* XXX: only if TUSB_PHY_OTG_CTRL_OTG_VBUS_DET_EN set? */ - /* XXX: only if TUSB_PRCM_MNGMT_OTG_VBUS_DET_EN set? */ - if (s->otg_status != otg_status) { - s->otg_status = otg_status; - s->intr |= TUSB_INT_SRC_VBUS_SENSE_CHNG; - tusb_intr_update(s); - } - break; - - case musb_set_session: - /* XXX: only if TUSB_PHY_OTG_CTRL_OTG_SESS_END_EN set? */ - /* XXX: only if TUSB_PRCM_MNGMT_OTG_SESS_END_EN set? */ - if (level) { - s->otg_status |= TUSB_DEV_OTG_STAT_SESS_VALID; - s->otg_status &= ~TUSB_DEV_OTG_STAT_SESS_END; - } else { - s->otg_status &= ~TUSB_DEV_OTG_STAT_SESS_VALID; - s->otg_status |= TUSB_DEV_OTG_STAT_SESS_END; - } - - /* XXX: some IRQ or anything? */ - break; - - case musb_irq_tx: - case musb_irq_rx: - s->usbip_intr = musb_core_intr_get(s->musb); - /* Fall through. */ - default: - if (level) - s->intr |= 1 << source; - else - s->intr &= ~(1 << source); - tusb_intr_update(s); - break; - } -} - -static void tusb6010_power(TUSBState *s, int on) -{ - if (!on) { - s->power = 0; - } else if (!s->power && on) { - s->power = 1; - /* Pull the interrupt down after TUSB6010 comes up. */ - s->intr_ok = 0; - tusb_intr_update(s); - timer_mod(s->pwr_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + - NANOSECONDS_PER_SECOND / 2); - } -} - -static void tusb6010_irq(void *opaque, int source, int level) -{ - if (source) { - tusb_musb_core_intr(opaque, source - 1, level); - } else { - tusb6010_power(opaque, level); - } -} - -static void tusb6010_reset(DeviceState *dev) -{ - TUSBState *s = TUSB6010(dev); - int i; - - s->test_reset = TUSB_PROD_TEST_RESET_VAL; - s->host_mode = 0; - s->dev_config = 0; - s->otg_status = 0; /* !TUSB_DEV_OTG_STAT_ID_STATUS means host mode */ - s->power = 0; - s->mask = 0xffffffff; - s->intr = 0x00000000; - s->otg_timer_val = 0; - s->scratch = 0; - s->prcm_config = 0; - s->prcm_mngmt = 0; - s->intr_ok = 0; - s->usbip_intr = 0; - s->usbip_mask = 0; - s->gpio_intr = 0; - s->gpio_mask = 0; - s->gpio_config = 0; - s->dma_intr = 0; - s->dma_mask = 0; - s->dma_map = 0; - s->dma_config = 0; - s->ep0_config = 0; - s->wkup_mask = 0; - s->pullup[0] = s->pullup[1] = 0; - s->control_config = 0; - for (i = 0; i < 15; i++) { - s->rx_config[i] = s->tx_config[i] = 0; - } - musb_reset(s->musb); -} - -static void tusb6010_realize(DeviceState *dev, Error **errp) -{ - TUSBState *s = TUSB6010(dev); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - - s->otg_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, tusb_otg_tick, s); - s->pwr_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, tusb_power_tick, s); - memory_region_init_io(&s->iomem[1], OBJECT(s), &tusb_async_ops, s, - "tusb-async", UINT32_MAX); - sysbus_init_mmio(sbd, &s->iomem[0]); - sysbus_init_mmio(sbd, &s->iomem[1]); - sysbus_init_irq(sbd, &s->irq); - qdev_init_gpio_in(dev, tusb6010_irq, musb_irq_max + 1); - s->musb = musb_init(dev, 1); -} - -static void tusb6010_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = tusb6010_realize; - device_class_set_legacy_reset(dc, tusb6010_reset); -} - -static const TypeInfo tusb6010_info = { - .name = TYPE_TUSB6010, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(TUSBState), - .class_init = tusb6010_class_init, -}; - -static void tusb6010_register_types(void) -{ - type_register_static(&tusb6010_info); -} - -type_init(tusb6010_register_types) diff --git a/hw/usb/Kconfig b/hw/usb/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/Kconfig +++ b/hw/usb/Kconfig @@ -XXX,XX +XXX,XX @@ config USB_DWC2 bool select USB -config TUSB6010 - bool - select USB_MUSB - config USB_HUB bool default y diff --git a/hw/usb/meson.build b/hw/usb/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/meson.build +++ b/hw/usb/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_USB_MUSB', if_true: files('hcd-musb.c')) system_ss.add(when: 'CONFIG_USB_DWC2', if_true: files('hcd-dwc2.c')) system_ss.add(when: 'CONFIG_USB_DWC3', if_true: files('hcd-dwc3.c')) -system_ss.add(when: 'CONFIG_TUSB6010', if_true: files('tusb6010.c')) system_ss.add(when: 'CONFIG_IMX', if_true: files('chipidea.c')) system_ss.add(when: 'CONFIG_IMX_USBPHY', if_true: files('imx-usb-phy.c')) system_ss.add(when: 'CONFIG_VT82C686', if_true: files('vt82c686-uhci-pci.c')) -- 2.34.1 Remove the MUSB USB2.0 OTG-compliant USB host controller device model. This was only used by the tusb6010 USB controller in the n800/n810 machines. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20240903160751.4100218-35-peter.maydell@linaro.org --- include/hw/usb/hcd-musb.h | 49 -- hw/usb/hcd-musb.c | 1553 ------------------------------------- hw/usb/Kconfig | 4 - hw/usb/meson.build | 1 - 4 files changed, 1607 deletions(-) delete mode 100644 include/hw/usb/hcd-musb.h delete mode 100644 hw/usb/hcd-musb.c diff --git a/include/hw/usb/hcd-musb.h b/include/hw/usb/hcd-musb.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/hw/usb/hcd-musb.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * "Inventra" High-speed Dual-Role Controller (MUSB-HDRC), Mentor Graphics, - * USB2.0 OTG compliant core used in various chips. - * - * Only host-mode and non-DMA accesses are currently supported. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * SPDX-License-Identifier: GPL-2.0-or-later - */ - -#ifndef HW_USB_HCD_MUSB_H -#define HW_USB_HCD_MUSB_H - -#include "exec/hwaddr.h" - -enum musb_irq_source_e { - musb_irq_suspend = 0, - musb_irq_resume, - musb_irq_rst_babble, - musb_irq_sof, - musb_irq_connect, - musb_irq_disconnect, - musb_irq_vbus_request, - musb_irq_vbus_error, - musb_irq_rx, - musb_irq_tx, - musb_set_vbus, - musb_set_session, - /* Add new interrupts here */ - musb_irq_max /* total number of interrupts defined */ -}; - -/* TODO convert hcd-musb to QOM/qdev and remove MUSBReadFunc/MUSBWriteFunc */ -typedef void MUSBWriteFunc(void *opaque, hwaddr addr, uint32_t value); -typedef uint32_t MUSBReadFunc(void *opaque, hwaddr addr); -extern MUSBReadFunc * const musb_read[]; -extern MUSBWriteFunc * const musb_write[]; - -typedef struct MUSBState MUSBState; - -MUSBState *musb_init(DeviceState *parent_device, int gpio_base); -void musb_reset(MUSBState *s); -uint32_t musb_core_intr_get(MUSBState *s); -void musb_core_intr_clear(MUSBState *s, uint32_t mask); -void musb_set_size(MUSBState *s, int epnum, int size, int is_tx); - -#endif diff --git a/hw/usb/hcd-musb.c b/hw/usb/hcd-musb.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/usb/hcd-musb.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * "Inventra" High-speed Dual-Role Controller (MUSB-HDRC), Mentor Graphics, - * USB2.0 OTG compliant core used in various chips. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - * - * Only host-mode and non-DMA accesses are currently supported. - */ -#include "qemu/osdep.h" -#include "qemu/timer.h" -#include "hw/usb.h" -#include "hw/usb/hcd-musb.h" -#include "hw/irq.h" -#include "hw/hw.h" - -/* Common USB registers */ -#define MUSB_HDRC_FADDR 0x00 /* 8-bit */ -#define MUSB_HDRC_POWER 0x01 /* 8-bit */ - -#define MUSB_HDRC_INTRTX 0x02 /* 16-bit */ -#define MUSB_HDRC_INTRRX 0x04 -#define MUSB_HDRC_INTRTXE 0x06 -#define MUSB_HDRC_INTRRXE 0x08 -#define MUSB_HDRC_INTRUSB 0x0a /* 8 bit */ -#define MUSB_HDRC_INTRUSBE 0x0b /* 8 bit */ -#define MUSB_HDRC_FRAME 0x0c /* 16-bit */ -#define MUSB_HDRC_INDEX 0x0e /* 8 bit */ -#define MUSB_HDRC_TESTMODE 0x0f /* 8 bit */ - -/* Per-EP registers in indexed mode */ -#define MUSB_HDRC_EP_IDX 0x10 /* 8-bit */ - -/* EP FIFOs */ -#define MUSB_HDRC_FIFO 0x20 - -/* Additional Control Registers */ -#define MUSB_HDRC_DEVCTL 0x60 /* 8 bit */ - -/* These are indexed */ -#define MUSB_HDRC_TXFIFOSZ 0x62 /* 8 bit (see masks) */ -#define MUSB_HDRC_RXFIFOSZ 0x63 /* 8 bit (see masks) */ -#define MUSB_HDRC_TXFIFOADDR 0x64 /* 16 bit offset shifted right 3 */ -#define MUSB_HDRC_RXFIFOADDR 0x66 /* 16 bit offset shifted right 3 */ - -/* Some more registers */ -#define MUSB_HDRC_VCTRL 0x68 /* 8 bit */ -#define MUSB_HDRC_HWVERS 0x6c /* 8 bit */ - -/* Added in HDRC 1.9(?) & MHDRC 1.4 */ -/* ULPI pass-through */ -#define MUSB_HDRC_ULPI_VBUSCTL 0x70 -#define MUSB_HDRC_ULPI_REGDATA 0x74 -#define MUSB_HDRC_ULPI_REGADDR 0x75 -#define MUSB_HDRC_ULPI_REGCTL 0x76 - -/* Extended config & PHY control */ -#define MUSB_HDRC_ENDCOUNT 0x78 /* 8 bit */ -#define MUSB_HDRC_DMARAMCFG 0x79 /* 8 bit */ -#define MUSB_HDRC_PHYWAIT 0x7a /* 8 bit */ -#define MUSB_HDRC_PHYVPLEN 0x7b /* 8 bit */ -#define MUSB_HDRC_HS_EOF1 0x7c /* 8 bit, units of 546.1 us */ -#define MUSB_HDRC_FS_EOF1 0x7d /* 8 bit, units of 533.3 ns */ -#define MUSB_HDRC_LS_EOF1 0x7e /* 8 bit, units of 1.067 us */ - -/* Per-EP BUSCTL registers */ -#define MUSB_HDRC_BUSCTL 0x80 - -/* Per-EP registers in flat mode */ -#define MUSB_HDRC_EP 0x100 - -/* offsets to registers in flat model */ -#define MUSB_HDRC_TXMAXP 0x00 /* 16 bit apparently */ -#define MUSB_HDRC_TXCSR 0x02 /* 16 bit apparently */ -#define MUSB_HDRC_CSR0 MUSB_HDRC_TXCSR /* re-used for EP0 */ -#define MUSB_HDRC_RXMAXP 0x04 /* 16 bit apparently */ -#define MUSB_HDRC_RXCSR 0x06 /* 16 bit apparently */ -#define MUSB_HDRC_RXCOUNT 0x08 /* 16 bit apparently */ -#define MUSB_HDRC_COUNT0 MUSB_HDRC_RXCOUNT /* re-used for EP0 */ -#define MUSB_HDRC_TXTYPE 0x0a /* 8 bit apparently */ -#define MUSB_HDRC_TYPE0 MUSB_HDRC_TXTYPE /* re-used for EP0 */ -#define MUSB_HDRC_TXINTERVAL 0x0b /* 8 bit apparently */ -#define MUSB_HDRC_NAKLIMIT0 MUSB_HDRC_TXINTERVAL /* re-used for EP0 */ -#define MUSB_HDRC_RXTYPE 0x0c /* 8 bit apparently */ -#define MUSB_HDRC_RXINTERVAL 0x0d /* 8 bit apparently */ -#define MUSB_HDRC_FIFOSIZE 0x0f /* 8 bit apparently */ -#define MUSB_HDRC_CONFIGDATA MGC_O_HDRC_FIFOSIZE /* re-used for EP0 */ - -/* "Bus control" registers */ -#define MUSB_HDRC_TXFUNCADDR 0x00 -#define MUSB_HDRC_TXHUBADDR 0x02 -#define MUSB_HDRC_TXHUBPORT 0x03 - -#define MUSB_HDRC_RXFUNCADDR 0x04 -#define MUSB_HDRC_RXHUBADDR 0x06 -#define MUSB_HDRC_RXHUBPORT 0x07 - -/* - * MUSBHDRC Register bit masks - */ - -/* POWER */ -#define MGC_M_POWER_ISOUPDATE 0x80 -#define MGC_M_POWER_SOFTCONN 0x40 -#define MGC_M_POWER_HSENAB 0x20 -#define MGC_M_POWER_HSMODE 0x10 -#define MGC_M_POWER_RESET 0x08 -#define MGC_M_POWER_RESUME 0x04 -#define MGC_M_POWER_SUSPENDM 0x02 -#define MGC_M_POWER_ENSUSPEND 0x01 - -/* INTRUSB */ -#define MGC_M_INTR_SUSPEND 0x01 -#define MGC_M_INTR_RESUME 0x02 -#define MGC_M_INTR_RESET 0x04 -#define MGC_M_INTR_BABBLE 0x04 -#define MGC_M_INTR_SOF 0x08 -#define MGC_M_INTR_CONNECT 0x10 -#define MGC_M_INTR_DISCONNECT 0x20 -#define MGC_M_INTR_SESSREQ 0x40 -#define MGC_M_INTR_VBUSERROR 0x80 /* FOR SESSION END */ -#define MGC_M_INTR_EP0 0x01 /* FOR EP0 INTERRUPT */ - -/* DEVCTL */ -#define MGC_M_DEVCTL_BDEVICE 0x80 -#define MGC_M_DEVCTL_FSDEV 0x40 -#define MGC_M_DEVCTL_LSDEV 0x20 -#define MGC_M_DEVCTL_VBUS 0x18 -#define MGC_S_DEVCTL_VBUS 3 -#define MGC_M_DEVCTL_HM 0x04 -#define MGC_M_DEVCTL_HR 0x02 -#define MGC_M_DEVCTL_SESSION 0x01 - -/* TESTMODE */ -#define MGC_M_TEST_FORCE_HOST 0x80 -#define MGC_M_TEST_FIFO_ACCESS 0x40 -#define MGC_M_TEST_FORCE_FS 0x20 -#define MGC_M_TEST_FORCE_HS 0x10 -#define MGC_M_TEST_PACKET 0x08 -#define MGC_M_TEST_K 0x04 -#define MGC_M_TEST_J 0x02 -#define MGC_M_TEST_SE0_NAK 0x01 - -/* CSR0 */ -#define MGC_M_CSR0_FLUSHFIFO 0x0100 -#define MGC_M_CSR0_TXPKTRDY 0x0002 -#define MGC_M_CSR0_RXPKTRDY 0x0001 - -/* CSR0 in Peripheral mode */ -#define MGC_M_CSR0_P_SVDSETUPEND 0x0080 -#define MGC_M_CSR0_P_SVDRXPKTRDY 0x0040 -#define MGC_M_CSR0_P_SENDSTALL 0x0020 -#define MGC_M_CSR0_P_SETUPEND 0x0010 -#define MGC_M_CSR0_P_DATAEND 0x0008 -#define MGC_M_CSR0_P_SENTSTALL 0x0004 - -/* CSR0 in Host mode */ -#define MGC_M_CSR0_H_NO_PING 0x0800 -#define MGC_M_CSR0_H_WR_DATATOGGLE 0x0400 /* set to allow setting: */ -#define MGC_M_CSR0_H_DATATOGGLE 0x0200 /* data toggle control */ -#define MGC_M_CSR0_H_NAKTIMEOUT 0x0080 -#define MGC_M_CSR0_H_STATUSPKT 0x0040 -#define MGC_M_CSR0_H_REQPKT 0x0020 -#define MGC_M_CSR0_H_ERROR 0x0010 -#define MGC_M_CSR0_H_SETUPPKT 0x0008 -#define MGC_M_CSR0_H_RXSTALL 0x0004 - -/* CONFIGDATA */ -#define MGC_M_CONFIGDATA_MPRXE 0x80 /* auto bulk pkt combining */ -#define MGC_M_CONFIGDATA_MPTXE 0x40 /* auto bulk pkt splitting */ -#define MGC_M_CONFIGDATA_BIGENDIAN 0x20 -#define MGC_M_CONFIGDATA_HBRXE 0x10 /* HB-ISO for RX */ -#define MGC_M_CONFIGDATA_HBTXE 0x08 /* HB-ISO for TX */ -#define MGC_M_CONFIGDATA_DYNFIFO 0x04 /* dynamic FIFO sizing */ -#define MGC_M_CONFIGDATA_SOFTCONE 0x02 /* SoftConnect */ -#define MGC_M_CONFIGDATA_UTMIDW 0x01 /* Width, 0 => 8b, 1 => 16b */ - -/* TXCSR in Peripheral and Host mode */ -#define MGC_M_TXCSR_AUTOSET 0x8000 -#define MGC_M_TXCSR_ISO 0x4000 -#define MGC_M_TXCSR_MODE 0x2000 -#define MGC_M_TXCSR_DMAENAB 0x1000 -#define MGC_M_TXCSR_FRCDATATOG 0x0800 -#define MGC_M_TXCSR_DMAMODE 0x0400 -#define MGC_M_TXCSR_CLRDATATOG 0x0040 -#define MGC_M_TXCSR_FLUSHFIFO 0x0008 -#define MGC_M_TXCSR_FIFONOTEMPTY 0x0002 -#define MGC_M_TXCSR_TXPKTRDY 0x0001 - -/* TXCSR in Peripheral mode */ -#define MGC_M_TXCSR_P_INCOMPTX 0x0080 -#define MGC_M_TXCSR_P_SENTSTALL 0x0020 -#define MGC_M_TXCSR_P_SENDSTALL 0x0010 -#define MGC_M_TXCSR_P_UNDERRUN 0x0004 - -/* TXCSR in Host mode */ -#define MGC_M_TXCSR_H_WR_DATATOGGLE 0x0200 -#define MGC_M_TXCSR_H_DATATOGGLE 0x0100 -#define MGC_M_TXCSR_H_NAKTIMEOUT 0x0080 -#define MGC_M_TXCSR_H_RXSTALL 0x0020 -#define MGC_M_TXCSR_H_ERROR 0x0004 - -/* RXCSR in Peripheral and Host mode */ -#define MGC_M_RXCSR_AUTOCLEAR 0x8000 -#define MGC_M_RXCSR_DMAENAB 0x2000 -#define MGC_M_RXCSR_DISNYET 0x1000 -#define MGC_M_RXCSR_DMAMODE 0x0800 -#define MGC_M_RXCSR_INCOMPRX 0x0100 -#define MGC_M_RXCSR_CLRDATATOG 0x0080 -#define MGC_M_RXCSR_FLUSHFIFO 0x0010 -#define MGC_M_RXCSR_DATAERROR 0x0008 -#define MGC_M_RXCSR_FIFOFULL 0x0002 -#define MGC_M_RXCSR_RXPKTRDY 0x0001 - -/* RXCSR in Peripheral mode */ -#define MGC_M_RXCSR_P_ISO 0x4000 -#define MGC_M_RXCSR_P_SENTSTALL 0x0040 -#define MGC_M_RXCSR_P_SENDSTALL 0x0020 -#define MGC_M_RXCSR_P_OVERRUN 0x0004 - -/* RXCSR in Host mode */ -#define MGC_M_RXCSR_H_AUTOREQ 0x4000 -#define MGC_M_RXCSR_H_WR_DATATOGGLE 0x0400 -#define MGC_M_RXCSR_H_DATATOGGLE 0x0200 -#define MGC_M_RXCSR_H_RXSTALL 0x0040 -#define MGC_M_RXCSR_H_REQPKT 0x0020 -#define MGC_M_RXCSR_H_ERROR 0x0004 - -/* HUBADDR */ -#define MGC_M_HUBADDR_MULTI_TT 0x80 - -/* ULPI: Added in HDRC 1.9(?) & MHDRC 1.4 */ -#define MGC_M_ULPI_VBCTL_USEEXTVBUSIND 0x02 -#define MGC_M_ULPI_VBCTL_USEEXTVBUS 0x01 -#define MGC_M_ULPI_REGCTL_INT_ENABLE 0x08 -#define MGC_M_ULPI_REGCTL_READNOTWRITE 0x04 -#define MGC_M_ULPI_REGCTL_COMPLETE 0x02 -#define MGC_M_ULPI_REGCTL_REG 0x01 - -/* #define MUSB_DEBUG */ - -#ifdef MUSB_DEBUG -#define TRACE(fmt, ...) fprintf(stderr, "%s@%d: " fmt "\n", __func__, \ - __LINE__, ##__VA_ARGS__) -#else -#define TRACE(...) -#endif - - -static void musb_attach(USBPort *port); -static void musb_detach(USBPort *port); -static void musb_child_detach(USBPort *port, USBDevice *child); -static void musb_schedule_cb(USBPort *port, USBPacket *p); -static void musb_async_cancel_device(MUSBState *s, USBDevice *dev); - -static USBPortOps musb_port_ops = { - .attach = musb_attach, - .detach = musb_detach, - .child_detach = musb_child_detach, - .complete = musb_schedule_cb, -}; - -static USBBusOps musb_bus_ops = { -}; - -typedef struct MUSBPacket MUSBPacket; -typedef struct MUSBEndPoint MUSBEndPoint; - -struct MUSBPacket { - USBPacket p; - MUSBEndPoint *ep; - int dir; -}; - -struct MUSBEndPoint { - uint16_t faddr[2]; - uint8_t haddr[2]; - uint8_t hport[2]; - uint16_t csr[2]; - uint16_t maxp[2]; - uint16_t rxcount; - uint8_t type[2]; - uint8_t interval[2]; - uint8_t config; - uint8_t fifosize; - int timeout[2]; /* Always in microframes */ - - uint8_t *buf[2]; - int fifolen[2]; - int fifostart[2]; - int fifoaddr[2]; - MUSBPacket packey[2]; - int status[2]; - int ext_size[2]; - - /* For callbacks' use */ - int epnum; - int interrupt[2]; - MUSBState *musb; - USBCallback *delayed_cb[2]; - QEMUTimer *intv_timer[2]; -}; - -struct MUSBState { - qemu_irq irqs[musb_irq_max]; - USBBus bus; - USBPort port; - - int idx; - uint8_t devctl; - uint8_t power; - uint8_t faddr; - - uint8_t intr; - uint8_t mask; - uint16_t tx_intr; - uint16_t tx_mask; - uint16_t rx_intr; - uint16_t rx_mask; - - int setup_len; - int session; - - uint8_t buf[0x8000]; - - /* Duplicating the world since 2008!... probably we should have 32 - * logical, single endpoints instead. */ - MUSBEndPoint ep[16]; -}; - -void musb_reset(MUSBState *s) -{ - int i; - - s->faddr = 0x00; - s->devctl = 0; - s->power = MGC_M_POWER_HSENAB; - s->tx_intr = 0x0000; - s->rx_intr = 0x0000; - s->tx_mask = 0xffff; - s->rx_mask = 0xffff; - s->intr = 0x00; - s->mask = 0x06; - s->idx = 0; - - s->setup_len = 0; - s->session = 0; - memset(s->buf, 0, sizeof(s->buf)); - - /* TODO: _DW */ - s->ep[0].config = MGC_M_CONFIGDATA_SOFTCONE | MGC_M_CONFIGDATA_DYNFIFO; - for (i = 0; i < 16; i ++) { - s->ep[i].fifosize = 64; - s->ep[i].maxp[0] = 0x40; - s->ep[i].maxp[1] = 0x40; - s->ep[i].musb = s; - s->ep[i].epnum = i; - usb_packet_init(&s->ep[i].packey[0].p); - usb_packet_init(&s->ep[i].packey[1].p); - } -} - -struct MUSBState *musb_init(DeviceState *parent_device, int gpio_base) -{ - MUSBState *s = g_malloc0(sizeof(*s)); - int i; - - for (i = 0; i < musb_irq_max; i++) { - s->irqs[i] = qdev_get_gpio_in(parent_device, gpio_base + i); - } - - musb_reset(s); - - usb_bus_new(&s->bus, sizeof(s->bus), &musb_bus_ops, parent_device); - usb_register_port(&s->bus, &s->port, s, 0, &musb_port_ops, - USB_SPEED_MASK_LOW | USB_SPEED_MASK_FULL); - - return s; -} - -static void musb_vbus_set(MUSBState *s, int level) -{ - if (level) - s->devctl |= 3 << MGC_S_DEVCTL_VBUS; - else - s->devctl &= ~MGC_M_DEVCTL_VBUS; - - qemu_set_irq(s->irqs[musb_set_vbus], level); -} - -static void musb_intr_set(MUSBState *s, int line, int level) -{ - if (!level) { - s->intr &= ~(1 << line); - qemu_irq_lower(s->irqs[line]); - } else if (s->mask & (1 << line)) { - s->intr |= 1 << line; - qemu_irq_raise(s->irqs[line]); - } -} - -static void musb_tx_intr_set(MUSBState *s, int line, int level) -{ - if (!level) { - s->tx_intr &= ~(1 << line); - if (!s->tx_intr) - qemu_irq_lower(s->irqs[musb_irq_tx]); - } else if (s->tx_mask & (1 << line)) { - s->tx_intr |= 1 << line; - qemu_irq_raise(s->irqs[musb_irq_tx]); - } -} - -static void musb_rx_intr_set(MUSBState *s, int line, int level) -{ - if (line) { - if (!level) { - s->rx_intr &= ~(1 << line); - if (!s->rx_intr) - qemu_irq_lower(s->irqs[musb_irq_rx]); - } else if (s->rx_mask & (1 << line)) { - s->rx_intr |= 1 << line; - qemu_irq_raise(s->irqs[musb_irq_rx]); - } - } else - musb_tx_intr_set(s, line, level); -} - -uint32_t musb_core_intr_get(MUSBState *s) -{ - return (s->rx_intr << 15) | s->tx_intr; -} - -void musb_core_intr_clear(MUSBState *s, uint32_t mask) -{ - if (s->rx_intr) { - s->rx_intr &= mask >> 15; - if (!s->rx_intr) - qemu_irq_lower(s->irqs[musb_irq_rx]); - } - - if (s->tx_intr) { - s->tx_intr &= mask & 0xffff; - if (!s->tx_intr) - qemu_irq_lower(s->irqs[musb_irq_tx]); - } -} - -void musb_set_size(MUSBState *s, int epnum, int size, int is_tx) -{ - s->ep[epnum].ext_size[!is_tx] = size; - s->ep[epnum].fifostart[0] = 0; - s->ep[epnum].fifostart[1] = 0; - s->ep[epnum].fifolen[0] = 0; - s->ep[epnum].fifolen[1] = 0; -} - -static void musb_session_update(MUSBState *s, int prev_dev, int prev_sess) -{ - int detect_prev = prev_dev && prev_sess; - int detect = !!s->port.dev && s->session; - - if (detect && !detect_prev) { - /* Let's skip the ID pin sense and VBUS sense formalities and - * and signal a successful SRP directly. This should work at least - * for the Linux driver stack. */ - musb_intr_set(s, musb_irq_connect, 1); - - if (s->port.dev->speed == USB_SPEED_LOW) { - s->devctl &= ~MGC_M_DEVCTL_FSDEV; - s->devctl |= MGC_M_DEVCTL_LSDEV; - } else { - s->devctl |= MGC_M_DEVCTL_FSDEV; - s->devctl &= ~MGC_M_DEVCTL_LSDEV; - } - - /* A-mode? */ - s->devctl &= ~MGC_M_DEVCTL_BDEVICE; - - /* Host-mode bit? */ - s->devctl |= MGC_M_DEVCTL_HM; -#if 1 - musb_vbus_set(s, 1); -#endif - } else if (!detect && detect_prev) { -#if 1 - musb_vbus_set(s, 0); -#endif - } -} - -/* Attach or detach a device on our only port. */ -static void musb_attach(USBPort *port) -{ - MUSBState *s = (MUSBState *) port->opaque; - - musb_intr_set(s, musb_irq_vbus_request, 1); - musb_session_update(s, 0, s->session); -} - -static void musb_detach(USBPort *port) -{ - MUSBState *s = (MUSBState *) port->opaque; - - musb_async_cancel_device(s, port->dev); - - musb_intr_set(s, musb_irq_disconnect, 1); - musb_session_update(s, 1, s->session); -} - -static void musb_child_detach(USBPort *port, USBDevice *child) -{ - MUSBState *s = (MUSBState *) port->opaque; - - musb_async_cancel_device(s, child); -} - -static void musb_cb_tick0(void *opaque) -{ - MUSBEndPoint *ep = (MUSBEndPoint *) opaque; - - ep->delayed_cb[0](&ep->packey[0].p, opaque); -} - -static void musb_cb_tick1(void *opaque) -{ - MUSBEndPoint *ep = (MUSBEndPoint *) opaque; - - ep->delayed_cb[1](&ep->packey[1].p, opaque); -} - -#define musb_cb_tick (dir ? musb_cb_tick1 : musb_cb_tick0) - -static void musb_schedule_cb(USBPort *port, USBPacket *packey) -{ - MUSBPacket *p = container_of(packey, MUSBPacket, p); - MUSBEndPoint *ep = p->ep; - int dir = p->dir; - int timeout = 0; - - if (ep->status[dir] == USB_RET_NAK) - timeout = ep->timeout[dir]; - else if (ep->interrupt[dir]) - timeout = 8; - else { - musb_cb_tick(ep); - return; - } - - if (!ep->intv_timer[dir]) - ep->intv_timer[dir] = timer_new_ns(QEMU_CLOCK_VIRTUAL, musb_cb_tick, ep); - - timer_mod(ep->intv_timer[dir], qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + - muldiv64(timeout, NANOSECONDS_PER_SECOND, 8000)); -} - -static int musb_timeout(int ttype, int speed, int val) -{ -#if 1 - return val << 3; -#endif - - switch (ttype) { - case USB_ENDPOINT_XFER_CONTROL: - if (val < 2) - return 0; - else if (speed == USB_SPEED_HIGH) - return 1 << (val - 1); - else - return 8 << (val - 1); - - case USB_ENDPOINT_XFER_INT: - if (speed == USB_SPEED_HIGH) - if (val < 2) - return 0; - else - return 1 << (val - 1); - else - return val << 3; - - case USB_ENDPOINT_XFER_BULK: - case USB_ENDPOINT_XFER_ISOC: - if (val < 2) - return 0; - else if (speed == USB_SPEED_HIGH) - return 1 << (val - 1); - else - return 8 << (val - 1); - /* TODO: what with low-speed Bulk and Isochronous? */ - } - - hw_error("bad interval\n"); -} - -static void musb_packet(MUSBState *s, MUSBEndPoint *ep, - int epnum, int pid, int len, USBCallback cb, int dir) -{ - USBDevice *dev; - USBEndpoint *uep; - int idx = epnum && dir; - int id; - int ttype; - - /* ep->type[0,1] contains: - * in bits 7:6 the speed (0 - invalid, 1 - high, 2 - full, 3 - slow) - * in bits 5:4 the transfer type (BULK / INT) - * in bits 3:0 the EP num - */ - ttype = epnum ? (ep->type[idx] >> 4) & 3 : 0; - - ep->timeout[dir] = musb_timeout(ttype, - ep->type[idx] >> 6, ep->interval[idx]); - ep->interrupt[dir] = ttype == USB_ENDPOINT_XFER_INT; - ep->delayed_cb[dir] = cb; - - /* A wild guess on the FADDR semantics... */ - dev = usb_find_device(&s->port, ep->faddr[idx]); - if (dev == NULL) { - return; - } - uep = usb_ep_get(dev, pid, ep->type[idx] & 0xf); - id = pid | (dev->addr << 16) | (uep->nr << 8); - usb_packet_setup(&ep->packey[dir].p, pid, uep, 0, id, false, true); - usb_packet_addbuf(&ep->packey[dir].p, ep->buf[idx], len); - ep->packey[dir].ep = ep; - ep->packey[dir].dir = dir; - - usb_handle_packet(dev, &ep->packey[dir].p); - - if (ep->packey[dir].p.status == USB_RET_ASYNC) { - usb_device_flush_ep_queue(dev, uep); - ep->status[dir] = len; - return; - } - - if (ep->packey[dir].p.status == USB_RET_SUCCESS) { - ep->status[dir] = ep->packey[dir].p.actual_length; - } else { - ep->status[dir] = ep->packey[dir].p.status; - } - musb_schedule_cb(&s->port, &ep->packey[dir].p); -} - -static void musb_tx_packet_complete(USBPacket *packey, void *opaque) -{ - /* Unfortunately we can't use packey->devep because that's the remote - * endpoint number and may be different than our local. */ - MUSBEndPoint *ep = (MUSBEndPoint *) opaque; - int epnum = ep->epnum; - MUSBState *s = ep->musb; - - ep->fifostart[0] = 0; - ep->fifolen[0] = 0; -#ifdef CLEAR_NAK - if (ep->status[0] != USB_RET_NAK) { -#endif - if (epnum) - ep->csr[0] &= ~(MGC_M_TXCSR_FIFONOTEMPTY | MGC_M_TXCSR_TXPKTRDY); - else - ep->csr[0] &= ~MGC_M_CSR0_TXPKTRDY; -#ifdef CLEAR_NAK - } -#endif - - /* Clear all of the error bits first */ - if (epnum) - ep->csr[0] &= ~(MGC_M_TXCSR_H_ERROR | MGC_M_TXCSR_H_RXSTALL | - MGC_M_TXCSR_H_NAKTIMEOUT); - else - ep->csr[0] &= ~(MGC_M_CSR0_H_ERROR | MGC_M_CSR0_H_RXSTALL | - MGC_M_CSR0_H_NAKTIMEOUT | MGC_M_CSR0_H_NO_PING); - - if (ep->status[0] == USB_RET_STALL) { - /* Command not supported by target! */ - ep->status[0] = 0; - - if (epnum) - ep->csr[0] |= MGC_M_TXCSR_H_RXSTALL; - else - ep->csr[0] |= MGC_M_CSR0_H_RXSTALL; - } - - if (ep->status[0] == USB_RET_NAK) { - ep->status[0] = 0; - - /* NAK timeouts are only generated in Bulk transfers and - * Data-errors in Isochronous. */ - if (ep->interrupt[0]) { - return; - } - - if (epnum) - ep->csr[0] |= MGC_M_TXCSR_H_NAKTIMEOUT; - else - ep->csr[0] |= MGC_M_CSR0_H_NAKTIMEOUT; - } - - if (ep->status[0] < 0) { - if (ep->status[0] == USB_RET_BABBLE) - musb_intr_set(s, musb_irq_rst_babble, 1); - - /* Pretend we've tried three times already and failed (in - * case of USB_TOKEN_SETUP). */ - if (epnum) - ep->csr[0] |= MGC_M_TXCSR_H_ERROR; - else - ep->csr[0] |= MGC_M_CSR0_H_ERROR; - - musb_tx_intr_set(s, epnum, 1); - return; - } - /* TODO: check len for over/underruns of an OUT packet? */ - -#ifdef SETUPLEN_HACK - if (!epnum && ep->packey[0].pid == USB_TOKEN_SETUP) - s->setup_len = ep->packey[0].data[6]; -#endif - - /* In DMA mode: if no error, assert DMA request for this EP, - * and skip the interrupt. */ - musb_tx_intr_set(s, epnum, 1); -} - -static void musb_rx_packet_complete(USBPacket *packey, void *opaque) -{ - /* Unfortunately we can't use packey->devep because that's the remote - * endpoint number and may be different than our local. */ - MUSBEndPoint *ep = (MUSBEndPoint *) opaque; - int epnum = ep->epnum; - MUSBState *s = ep->musb; - - ep->fifostart[1] = 0; - ep->fifolen[1] = 0; - -#ifdef CLEAR_NAK - if (ep->status[1] != USB_RET_NAK) { -#endif - ep->csr[1] &= ~MGC_M_RXCSR_H_REQPKT; - if (!epnum) - ep->csr[0] &= ~MGC_M_CSR0_H_REQPKT; -#ifdef CLEAR_NAK - } -#endif - - /* Clear all of the imaginable error bits first */ - ep->csr[1] &= ~(MGC_M_RXCSR_H_ERROR | MGC_M_RXCSR_H_RXSTALL | - MGC_M_RXCSR_DATAERROR); - if (!epnum) - ep->csr[0] &= ~(MGC_M_CSR0_H_ERROR | MGC_M_CSR0_H_RXSTALL | - MGC_M_CSR0_H_NAKTIMEOUT | MGC_M_CSR0_H_NO_PING); - - if (ep->status[1] == USB_RET_STALL) { - ep->status[1] = 0; - - ep->csr[1] |= MGC_M_RXCSR_H_RXSTALL; - if (!epnum) - ep->csr[0] |= MGC_M_CSR0_H_RXSTALL; - } - - if (ep->status[1] == USB_RET_NAK) { - ep->status[1] = 0; - - /* NAK timeouts are only generated in Bulk transfers and - * Data-errors in Isochronous. */ - if (ep->interrupt[1]) { - musb_packet(s, ep, epnum, USB_TOKEN_IN, - packey->iov.size, musb_rx_packet_complete, 1); - return; - } - - ep->csr[1] |= MGC_M_RXCSR_DATAERROR; - if (!epnum) - ep->csr[0] |= MGC_M_CSR0_H_NAKTIMEOUT; - } - - if (ep->status[1] < 0) { - if (ep->status[1] == USB_RET_BABBLE) { - musb_intr_set(s, musb_irq_rst_babble, 1); - return; - } - - /* Pretend we've tried three times already and failed (in - * case of a control transfer). */ - ep->csr[1] |= MGC_M_RXCSR_H_ERROR; - if (!epnum) - ep->csr[0] |= MGC_M_CSR0_H_ERROR; - - musb_rx_intr_set(s, epnum, 1); - return; - } - /* TODO: check len for over/underruns of an OUT packet? */ - /* TODO: perhaps make use of e->ext_size[1] here. */ - - if (!(ep->csr[1] & (MGC_M_RXCSR_H_RXSTALL | MGC_M_RXCSR_DATAERROR))) { - ep->csr[1] |= MGC_M_RXCSR_FIFOFULL | MGC_M_RXCSR_RXPKTRDY; - if (!epnum) - ep->csr[0] |= MGC_M_CSR0_RXPKTRDY; - - ep->rxcount = ep->status[1]; /* XXX: MIN(packey->len, ep->maxp[1]); */ - /* In DMA mode: assert DMA request for this EP */ - } - - /* Only if DMA has not been asserted */ - musb_rx_intr_set(s, epnum, 1); -} - -static void musb_async_cancel_device(MUSBState *s, USBDevice *dev) -{ - int ep, dir; - - for (ep = 0; ep < 16; ep++) { - for (dir = 0; dir < 2; dir++) { - if (!usb_packet_is_inflight(&s->ep[ep].packey[dir].p) || - s->ep[ep].packey[dir].p.ep->dev != dev) { - continue; - } - usb_cancel_packet(&s->ep[ep].packey[dir].p); - /* status updates needed here? */ - } - } -} - -static void musb_tx_rdy(MUSBState *s, int epnum) -{ - MUSBEndPoint *ep = s->ep + epnum; - int pid; - int total, valid = 0; - TRACE("start %d, len %d", ep->fifostart[0], ep->fifolen[0] ); - ep->fifostart[0] += ep->fifolen[0]; - ep->fifolen[0] = 0; - - /* XXX: how's the total size of the packet retrieved exactly in - * the generic case? */ - total = ep->maxp[0] & 0x3ff; - - if (ep->ext_size[0]) { - total = ep->ext_size[0]; - ep->ext_size[0] = 0; - valid = 1; - } - - /* If the packet is not fully ready yet, wait for a next segment. */ - if (epnum && (ep->fifostart[0]) < total) - return; - - if (!valid) - total = ep->fifostart[0]; - - pid = USB_TOKEN_OUT; - if (!epnum && (ep->csr[0] & MGC_M_CSR0_H_SETUPPKT)) { - pid = USB_TOKEN_SETUP; - if (total != 8) { - TRACE("illegal SETUPPKT length of %i bytes", total); - } - /* Controller should retry SETUP packets three times on errors - * but it doesn't make sense for us to do that. */ - } - - musb_packet(s, ep, epnum, pid, total, musb_tx_packet_complete, 0); -} - -static void musb_rx_req(MUSBState *s, int epnum) -{ - MUSBEndPoint *ep = s->ep + epnum; - int total; - - /* If we already have a packet, which didn't fit into the - * 64 bytes of the FIFO, only move the FIFO start and return. (Obsolete) */ - if (ep->packey[1].p.pid == USB_TOKEN_IN && ep->status[1] >= 0 && - (ep->fifostart[1]) + ep->rxcount < - ep->packey[1].p.iov.size) { - TRACE("0x%08x, %d", ep->fifostart[1], ep->rxcount ); - ep->fifostart[1] += ep->rxcount; - ep->fifolen[1] = 0; - - ep->rxcount = MIN(ep->packey[0].p.iov.size - (ep->fifostart[1]), - ep->maxp[1]); - - ep->csr[1] &= ~MGC_M_RXCSR_H_REQPKT; - if (!epnum) - ep->csr[0] &= ~MGC_M_CSR0_H_REQPKT; - - /* Clear all of the error bits first */ - ep->csr[1] &= ~(MGC_M_RXCSR_H_ERROR | MGC_M_RXCSR_H_RXSTALL | - MGC_M_RXCSR_DATAERROR); - if (!epnum) - ep->csr[0] &= ~(MGC_M_CSR0_H_ERROR | MGC_M_CSR0_H_RXSTALL | - MGC_M_CSR0_H_NAKTIMEOUT | MGC_M_CSR0_H_NO_PING); - - ep->csr[1] |= MGC_M_RXCSR_FIFOFULL | MGC_M_RXCSR_RXPKTRDY; - if (!epnum) - ep->csr[0] |= MGC_M_CSR0_RXPKTRDY; - musb_rx_intr_set(s, epnum, 1); - return; - } - - /* The driver sets maxp[1] to 64 or less because it knows the hardware - * FIFO is this deep. Bigger packets get split in - * usb_generic_handle_packet but we can also do the splitting locally - * for performance. It turns out we can also have a bigger FIFO and - * ignore the limit set in ep->maxp[1]. The Linux MUSB driver deals - * OK with single packets of even 32KB and we avoid splitting, however - * usb_msd.c sometimes sends a packet bigger than what Linux expects - * (e.g. 8192 bytes instead of 4096) and we get an OVERRUN. Splitting - * hides this overrun from Linux. Up to 4096 everything is fine - * though. Currently this is disabled. - * - * XXX: mind ep->fifosize. */ - total = MIN(ep->maxp[1] & 0x3ff, sizeof(s->buf)); - -#ifdef SETUPLEN_HACK - /* Why should *we* do that instead of Linux? */ - if (!epnum) { - if (ep->packey[0].p.devaddr == 2) { - total = MIN(s->setup_len, 8); - } else { - total = MIN(s->setup_len, 64); - } - s->setup_len -= total; - } -#endif - - musb_packet(s, ep, epnum, USB_TOKEN_IN, total, musb_rx_packet_complete, 1); -} - -static uint8_t musb_read_fifo(MUSBEndPoint *ep) -{ - uint8_t value; - if (ep->fifolen[1] >= 64) { - /* We have a FIFO underrun */ - TRACE("EP%d FIFO is now empty, stop reading", ep->epnum); - return 0x00000000; - } - /* In DMA mode clear RXPKTRDY and set REQPKT automatically - * (if AUTOREQ is set) */ - - ep->csr[1] &= ~MGC_M_RXCSR_FIFOFULL; - value=ep->buf[1][ep->fifostart[1] + ep->fifolen[1] ++]; - TRACE("EP%d 0x%02x, %d", ep->epnum, value, ep->fifolen[1] ); - return value; -} - -static void musb_write_fifo(MUSBEndPoint *ep, uint8_t value) -{ - TRACE("EP%d = %02x", ep->epnum, value); - if (ep->fifolen[0] >= 64) { - /* We have a FIFO overrun */ - TRACE("EP%d FIFO exceeded 64 bytes, stop feeding data", ep->epnum); - return; - } - - ep->buf[0][ep->fifostart[0] + ep->fifolen[0] ++] = value; - ep->csr[0] |= MGC_M_TXCSR_FIFONOTEMPTY; -} - -static void musb_ep_frame_cancel(MUSBEndPoint *ep, int dir) -{ - if (ep->intv_timer[dir]) - timer_del(ep->intv_timer[dir]); -} - -/* Bus control */ -static uint8_t musb_busctl_readb(void *opaque, int ep, int addr) -{ - MUSBState *s = (MUSBState *) opaque; - - switch (addr) { - /* For USB2.0 HS hubs only */ - case MUSB_HDRC_TXHUBADDR: - return s->ep[ep].haddr[0]; - case MUSB_HDRC_TXHUBPORT: - return s->ep[ep].hport[0]; - case MUSB_HDRC_RXHUBADDR: - return s->ep[ep].haddr[1]; - case MUSB_HDRC_RXHUBPORT: - return s->ep[ep].hport[1]; - - default: - TRACE("unknown register 0x%02x", addr); - return 0x00; - }; -} - -static void musb_busctl_writeb(void *opaque, int ep, int addr, uint8_t value) -{ - MUSBState *s = (MUSBState *) opaque; - - switch (addr) { - case MUSB_HDRC_TXFUNCADDR: - s->ep[ep].faddr[0] = value; - break; - case MUSB_HDRC_RXFUNCADDR: - s->ep[ep].faddr[1] = value; - break; - case MUSB_HDRC_TXHUBADDR: - s->ep[ep].haddr[0] = value; - break; - case MUSB_HDRC_TXHUBPORT: - s->ep[ep].hport[0] = value; - break; - case MUSB_HDRC_RXHUBADDR: - s->ep[ep].haddr[1] = value; - break; - case MUSB_HDRC_RXHUBPORT: - s->ep[ep].hport[1] = value; - break; - - default: - TRACE("unknown register 0x%02x", addr); - break; - }; -} - -static uint16_t musb_busctl_readh(void *opaque, int ep, int addr) -{ - MUSBState *s = (MUSBState *) opaque; - - switch (addr) { - case MUSB_HDRC_TXFUNCADDR: - return s->ep[ep].faddr[0]; - case MUSB_HDRC_RXFUNCADDR: - return s->ep[ep].faddr[1]; - - default: - return musb_busctl_readb(s, ep, addr) | - (musb_busctl_readb(s, ep, addr | 1) << 8); - }; -} - -static void musb_busctl_writeh(void *opaque, int ep, int addr, uint16_t value) -{ - MUSBState *s = (MUSBState *) opaque; - - switch (addr) { - case MUSB_HDRC_TXFUNCADDR: - s->ep[ep].faddr[0] = value; - break; - case MUSB_HDRC_RXFUNCADDR: - s->ep[ep].faddr[1] = value; - break; - - default: - musb_busctl_writeb(s, ep, addr, value & 0xff); - musb_busctl_writeb(s, ep, addr | 1, value >> 8); - }; -} - -/* Endpoint control */ -static uint8_t musb_ep_readb(void *opaque, int ep, int addr) -{ - MUSBState *s = (MUSBState *) opaque; - - switch (addr) { - case MUSB_HDRC_TXTYPE: - return s->ep[ep].type[0]; - case MUSB_HDRC_TXINTERVAL: - return s->ep[ep].interval[0]; - case MUSB_HDRC_RXTYPE: - return s->ep[ep].type[1]; - case MUSB_HDRC_RXINTERVAL: - return s->ep[ep].interval[1]; - case (MUSB_HDRC_FIFOSIZE & ~1): - return 0x00; - case MUSB_HDRC_FIFOSIZE: - return ep ? s->ep[ep].fifosize : s->ep[ep].config; - case MUSB_HDRC_RXCOUNT: - return s->ep[ep].rxcount; - - default: - TRACE("unknown register 0x%02x", addr); - return 0x00; - }; -} - -static void musb_ep_writeb(void *opaque, int ep, int addr, uint8_t value) -{ - MUSBState *s = (MUSBState *) opaque; - - switch (addr) { - case MUSB_HDRC_TXTYPE: - s->ep[ep].type[0] = value; - break; - case MUSB_HDRC_TXINTERVAL: - s->ep[ep].interval[0] = value; - musb_ep_frame_cancel(&s->ep[ep], 0); - break; - case MUSB_HDRC_RXTYPE: - s->ep[ep].type[1] = value; - break; - case MUSB_HDRC_RXINTERVAL: - s->ep[ep].interval[1] = value; - musb_ep_frame_cancel(&s->ep[ep], 1); - break; - case (MUSB_HDRC_FIFOSIZE & ~1): - break; - case MUSB_HDRC_FIFOSIZE: - TRACE("somebody messes with fifosize (now %i bytes)", value); - s->ep[ep].fifosize = value; - break; - default: - TRACE("unknown register 0x%02x", addr); - break; - }; -} - -static uint16_t musb_ep_readh(void *opaque, int ep, int addr) -{ - MUSBState *s = (MUSBState *) opaque; - uint16_t ret; - - switch (addr) { - case MUSB_HDRC_TXMAXP: - return s->ep[ep].maxp[0]; - case MUSB_HDRC_TXCSR: - return s->ep[ep].csr[0]; - case MUSB_HDRC_RXMAXP: - return s->ep[ep].maxp[1]; - case MUSB_HDRC_RXCSR: - ret = s->ep[ep].csr[1]; - - /* TODO: This and other bits probably depend on - * ep->csr[1] & MGC_M_RXCSR_AUTOCLEAR. */ - if (s->ep[ep].csr[1] & MGC_M_RXCSR_AUTOCLEAR) - s->ep[ep].csr[1] &= ~MGC_M_RXCSR_RXPKTRDY; - - return ret; - case MUSB_HDRC_RXCOUNT: - return s->ep[ep].rxcount; - - default: - return musb_ep_readb(s, ep, addr) | - (musb_ep_readb(s, ep, addr | 1) << 8); - }; -} - -static void musb_ep_writeh(void *opaque, int ep, int addr, uint16_t value) -{ - MUSBState *s = (MUSBState *) opaque; - - switch (addr) { - case MUSB_HDRC_TXMAXP: - s->ep[ep].maxp[0] = value; - break; - case MUSB_HDRC_TXCSR: - if (ep) { - s->ep[ep].csr[0] &= value & 0xa6; - s->ep[ep].csr[0] |= value & 0xff59; - } else { - s->ep[ep].csr[0] &= value & 0x85; - s->ep[ep].csr[0] |= value & 0xf7a; - } - - musb_ep_frame_cancel(&s->ep[ep], 0); - - if ((ep && (value & MGC_M_TXCSR_FLUSHFIFO)) || - (!ep && (value & MGC_M_CSR0_FLUSHFIFO))) { - s->ep[ep].fifolen[0] = 0; - s->ep[ep].fifostart[0] = 0; - if (ep) - s->ep[ep].csr[0] &= - ~(MGC_M_TXCSR_FIFONOTEMPTY | MGC_M_TXCSR_TXPKTRDY); - else - s->ep[ep].csr[0] &= - ~(MGC_M_CSR0_TXPKTRDY | MGC_M_CSR0_RXPKTRDY); - } - if ( - (ep && -#ifdef CLEAR_NAK - (value & MGC_M_TXCSR_TXPKTRDY) && - !(value & MGC_M_TXCSR_H_NAKTIMEOUT)) || -#else - (value & MGC_M_TXCSR_TXPKTRDY)) || -#endif - (!ep && -#ifdef CLEAR_NAK - (value & MGC_M_CSR0_TXPKTRDY) && - !(value & MGC_M_CSR0_H_NAKTIMEOUT))) -#else - (value & MGC_M_CSR0_TXPKTRDY))) -#endif - musb_tx_rdy(s, ep); - if (!ep && - (value & MGC_M_CSR0_H_REQPKT) && -#ifdef CLEAR_NAK - !(value & (MGC_M_CSR0_H_NAKTIMEOUT | - MGC_M_CSR0_RXPKTRDY))) -#else - !(value & MGC_M_CSR0_RXPKTRDY)) -#endif - musb_rx_req(s, ep); - break; - - case MUSB_HDRC_RXMAXP: - s->ep[ep].maxp[1] = value; - break; - case MUSB_HDRC_RXCSR: - /* (DMA mode only) */ - if ( - (value & MGC_M_RXCSR_H_AUTOREQ) && - !(value & MGC_M_RXCSR_RXPKTRDY) && - (s->ep[ep].csr[1] & MGC_M_RXCSR_RXPKTRDY)) - value |= MGC_M_RXCSR_H_REQPKT; - - s->ep[ep].csr[1] &= 0x102 | (value & 0x4d); - s->ep[ep].csr[1] |= value & 0xfeb0; - - musb_ep_frame_cancel(&s->ep[ep], 1); - - if (value & MGC_M_RXCSR_FLUSHFIFO) { - s->ep[ep].fifolen[1] = 0; - s->ep[ep].fifostart[1] = 0; - s->ep[ep].csr[1] &= ~(MGC_M_RXCSR_FIFOFULL | MGC_M_RXCSR_RXPKTRDY); - /* If double buffering and we have two packets ready, flush - * only the first one and set up the fifo at the second packet. */ - } -#ifdef CLEAR_NAK - if ((value & MGC_M_RXCSR_H_REQPKT) && !(value & MGC_M_RXCSR_DATAERROR)) -#else - if (value & MGC_M_RXCSR_H_REQPKT) -#endif - musb_rx_req(s, ep); - break; - case MUSB_HDRC_RXCOUNT: - s->ep[ep].rxcount = value; - break; - - default: - musb_ep_writeb(s, ep, addr, value & 0xff); - musb_ep_writeb(s, ep, addr | 1, value >> 8); - }; -} - -/* Generic control */ -static uint32_t musb_readb(void *opaque, hwaddr addr) -{ - MUSBState *s = (MUSBState *) opaque; - int ep, i; - uint8_t ret; - - switch (addr) { - case MUSB_HDRC_FADDR: - return s->faddr; - case MUSB_HDRC_POWER: - return s->power; - case MUSB_HDRC_INTRUSB: - ret = s->intr; - for (i = 0; i < sizeof(ret) * 8; i ++) - if (ret & (1 << i)) - musb_intr_set(s, i, 0); - return ret; - case MUSB_HDRC_INTRUSBE: - return s->mask; - case MUSB_HDRC_INDEX: - return s->idx; - case MUSB_HDRC_TESTMODE: - return 0x00; - - case MUSB_HDRC_EP_IDX ... (MUSB_HDRC_EP_IDX + 0xf): - return musb_ep_readb(s, s->idx, addr & 0xf); - - case MUSB_HDRC_DEVCTL: - return s->devctl; - - case MUSB_HDRC_TXFIFOSZ: - case MUSB_HDRC_RXFIFOSZ: - case MUSB_HDRC_VCTRL: - /* TODO */ - return 0x00; - - case MUSB_HDRC_HWVERS: - return (1 << 10) | 400; - - case (MUSB_HDRC_VCTRL | 1): - case (MUSB_HDRC_HWVERS | 1): - case (MUSB_HDRC_DEVCTL | 1): - return 0x00; - - case MUSB_HDRC_BUSCTL ... (MUSB_HDRC_BUSCTL + 0x7f): - ep = (addr >> 3) & 0xf; - return musb_busctl_readb(s, ep, addr & 0x7); - - case MUSB_HDRC_EP ... (MUSB_HDRC_EP + 0xff): - ep = (addr >> 4) & 0xf; - return musb_ep_readb(s, ep, addr & 0xf); - - case MUSB_HDRC_FIFO ... (MUSB_HDRC_FIFO + 0x3f): - ep = ((addr - MUSB_HDRC_FIFO) >> 2) & 0xf; - return musb_read_fifo(s->ep + ep); - - default: - TRACE("unknown register 0x%02x", (int) addr); - return 0x00; - }; -} - -static void musb_writeb(void *opaque, hwaddr addr, uint32_t value) -{ - MUSBState *s = (MUSBState *) opaque; - int ep; - - switch (addr) { - case MUSB_HDRC_FADDR: - s->faddr = value & 0x7f; - break; - case MUSB_HDRC_POWER: - s->power = (value & 0xef) | (s->power & 0x10); - /* MGC_M_POWER_RESET is also read-only in Peripheral Mode */ - if ((value & MGC_M_POWER_RESET) && s->port.dev) { - usb_device_reset(s->port.dev); - /* Negotiate high-speed operation if MGC_M_POWER_HSENAB is set. */ - if ((value & MGC_M_POWER_HSENAB) && - s->port.dev->speed == USB_SPEED_HIGH) - s->power |= MGC_M_POWER_HSMODE; /* Success */ - /* Restart frame counting. */ - } - if (value & MGC_M_POWER_SUSPENDM) { - /* When all transfers finish, suspend and if MGC_M_POWER_ENSUSPEND - * is set, also go into low power mode. Frame counting stops. */ - /* XXX: Cleared when the interrupt register is read */ - } - if (value & MGC_M_POWER_RESUME) { - /* Wait 20ms and signal resuming on the bus. Frame counting - * restarts. */ - } - break; - case MUSB_HDRC_INTRUSB: - break; - case MUSB_HDRC_INTRUSBE: - s->mask = value & 0xff; - break; - case MUSB_HDRC_INDEX: - s->idx = value & 0xf; - break; - case MUSB_HDRC_TESTMODE: - break; - - case MUSB_HDRC_EP_IDX ... (MUSB_HDRC_EP_IDX + 0xf): - musb_ep_writeb(s, s->idx, addr & 0xf, value); - break; - - case MUSB_HDRC_DEVCTL: - s->session = !!(value & MGC_M_DEVCTL_SESSION); - musb_session_update(s, - !!s->port.dev, - !!(s->devctl & MGC_M_DEVCTL_SESSION)); - - /* It seems this is the only R/W bit in this register? */ - s->devctl &= ~MGC_M_DEVCTL_SESSION; - s->devctl |= value & MGC_M_DEVCTL_SESSION; - break; - - case MUSB_HDRC_TXFIFOSZ: - case MUSB_HDRC_RXFIFOSZ: - case MUSB_HDRC_VCTRL: - /* TODO */ - break; - - case (MUSB_HDRC_VCTRL | 1): - case (MUSB_HDRC_DEVCTL | 1): - break; - - case MUSB_HDRC_BUSCTL ... (MUSB_HDRC_BUSCTL + 0x7f): - ep = (addr >> 3) & 0xf; - musb_busctl_writeb(s, ep, addr & 0x7, value); - break; - - case MUSB_HDRC_EP ... (MUSB_HDRC_EP + 0xff): - ep = (addr >> 4) & 0xf; - musb_ep_writeb(s, ep, addr & 0xf, value); - break; - - case MUSB_HDRC_FIFO ... (MUSB_HDRC_FIFO + 0x3f): - ep = ((addr - MUSB_HDRC_FIFO) >> 2) & 0xf; - musb_write_fifo(s->ep + ep, value & 0xff); - break; - - default: - TRACE("unknown register 0x%02x", (int) addr); - break; - }; -} - -static uint32_t musb_readh(void *opaque, hwaddr addr) -{ - MUSBState *s = (MUSBState *) opaque; - int ep, i; - uint16_t ret; - - switch (addr) { - case MUSB_HDRC_INTRTX: - ret = s->tx_intr; - /* Auto clear */ - for (i = 0; i < sizeof(ret) * 8; i ++) - if (ret & (1 << i)) - musb_tx_intr_set(s, i, 0); - return ret; - case MUSB_HDRC_INTRRX: - ret = s->rx_intr; - /* Auto clear */ - for (i = 0; i < sizeof(ret) * 8; i ++) - if (ret & (1 << i)) - musb_rx_intr_set(s, i, 0); - return ret; - case MUSB_HDRC_INTRTXE: - return s->tx_mask; - case MUSB_HDRC_INTRRXE: - return s->rx_mask; - - case MUSB_HDRC_FRAME: - /* TODO */ - return 0x0000; - case MUSB_HDRC_TXFIFOADDR: - return s->ep[s->idx].fifoaddr[0]; - case MUSB_HDRC_RXFIFOADDR: - return s->ep[s->idx].fifoaddr[1]; - - case MUSB_HDRC_EP_IDX ... (MUSB_HDRC_EP_IDX + 0xf): - return musb_ep_readh(s, s->idx, addr & 0xf); - - case MUSB_HDRC_BUSCTL ... (MUSB_HDRC_BUSCTL + 0x7f): - ep = (addr >> 3) & 0xf; - return musb_busctl_readh(s, ep, addr & 0x7); - - case MUSB_HDRC_EP ... (MUSB_HDRC_EP + 0xff): - ep = (addr >> 4) & 0xf; - return musb_ep_readh(s, ep, addr & 0xf); - - case MUSB_HDRC_FIFO ... (MUSB_HDRC_FIFO + 0x3f): - ep = ((addr - MUSB_HDRC_FIFO) >> 2) & 0xf; - return (musb_read_fifo(s->ep + ep) | musb_read_fifo(s->ep + ep) << 8); - - default: - return musb_readb(s, addr) | (musb_readb(s, addr | 1) << 8); - }; -} - -static void musb_writeh(void *opaque, hwaddr addr, uint32_t value) -{ - MUSBState *s = (MUSBState *) opaque; - int ep; - - switch (addr) { - case MUSB_HDRC_INTRTXE: - s->tx_mask = value; - /* XXX: the masks seem to apply on the raising edge like with - * edge-triggered interrupts, thus no need to update. I may be - * wrong though. */ - break; - case MUSB_HDRC_INTRRXE: - s->rx_mask = value; - break; - - case MUSB_HDRC_FRAME: - /* TODO */ - break; - case MUSB_HDRC_TXFIFOADDR: - s->ep[s->idx].fifoaddr[0] = value; - s->ep[s->idx].buf[0] = - s->buf + ((value << 3) & 0x7ff ); - break; - case MUSB_HDRC_RXFIFOADDR: - s->ep[s->idx].fifoaddr[1] = value; - s->ep[s->idx].buf[1] = - s->buf + ((value << 3) & 0x7ff); - break; - - case MUSB_HDRC_EP_IDX ... (MUSB_HDRC_EP_IDX + 0xf): - musb_ep_writeh(s, s->idx, addr & 0xf, value); - break; - - case MUSB_HDRC_BUSCTL ... (MUSB_HDRC_BUSCTL + 0x7f): - ep = (addr >> 3) & 0xf; - musb_busctl_writeh(s, ep, addr & 0x7, value); - break; - - case MUSB_HDRC_EP ... (MUSB_HDRC_EP + 0xff): - ep = (addr >> 4) & 0xf; - musb_ep_writeh(s, ep, addr & 0xf, value); - break; - - case MUSB_HDRC_FIFO ... (MUSB_HDRC_FIFO + 0x3f): - ep = ((addr - MUSB_HDRC_FIFO) >> 2) & 0xf; - musb_write_fifo(s->ep + ep, value & 0xff); - musb_write_fifo(s->ep + ep, (value >> 8) & 0xff); - break; - - default: - musb_writeb(s, addr, value & 0xff); - musb_writeb(s, addr | 1, value >> 8); - }; -} - -static uint32_t musb_readw(void *opaque, hwaddr addr) -{ - MUSBState *s = (MUSBState *) opaque; - int ep; - - switch (addr) { - case MUSB_HDRC_FIFO ... (MUSB_HDRC_FIFO + 0x3f): - ep = ((addr - MUSB_HDRC_FIFO) >> 2) & 0xf; - return ( musb_read_fifo(s->ep + ep) | - musb_read_fifo(s->ep + ep) << 8 | - musb_read_fifo(s->ep + ep) << 16 | - musb_read_fifo(s->ep + ep) << 24 ); - default: - TRACE("unknown register 0x%02x", (int) addr); - return 0x00000000; - }; -} - -static void musb_writew(void *opaque, hwaddr addr, uint32_t value) -{ - MUSBState *s = (MUSBState *) opaque; - int ep; - - switch (addr) { - case MUSB_HDRC_FIFO ... (MUSB_HDRC_FIFO + 0x3f): - ep = ((addr - MUSB_HDRC_FIFO) >> 2) & 0xf; - musb_write_fifo(s->ep + ep, value & 0xff); - musb_write_fifo(s->ep + ep, (value >> 8 ) & 0xff); - musb_write_fifo(s->ep + ep, (value >> 16) & 0xff); - musb_write_fifo(s->ep + ep, (value >> 24) & 0xff); - break; - default: - TRACE("unknown register 0x%02x", (int) addr); - break; - }; -} - -MUSBReadFunc * const musb_read[] = { - musb_readb, - musb_readh, - musb_readw, -}; - -MUSBWriteFunc * const musb_write[] = { - musb_writeb, - musb_writeh, - musb_writew, -}; diff --git a/hw/usb/Kconfig b/hw/usb/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/Kconfig +++ b/hw/usb/Kconfig @@ -XXX,XX +XXX,XX @@ config USB_XHCI_SYSBUS bool select USB_XHCI -config USB_MUSB - bool - select USB - config USB_DWC2 bool select USB diff --git a/hw/usb/meson.build b/hw/usb/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/meson.build +++ b/hw/usb/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_USB_XHCI', if_true: files('hcd-xhci.c')) system_ss.add(when: 'CONFIG_USB_XHCI_PCI', if_true: files('hcd-xhci-pci.c')) system_ss.add(when: 'CONFIG_USB_XHCI_SYSBUS', if_true: files('hcd-xhci-sysbus.c')) system_ss.add(when: 'CONFIG_USB_XHCI_NEC', if_true: files('hcd-xhci-nec.c')) -system_ss.add(when: 'CONFIG_USB_MUSB', if_true: files('hcd-musb.c')) system_ss.add(when: 'CONFIG_USB_DWC2', if_true: files('hcd-dwc2.c')) system_ss.add(when: 'CONFIG_USB_DWC3', if_true: files('hcd-dwc3.c')) -- 2.34.1 Now we have removed all the board types that it covers, we can move the text about old Arm boards from deprecated.rst to removed-features.rst, tweaking it appropriately. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-37-peter.maydell@linaro.org --- docs/about/deprecated.rst | 15 --------------- docs/about/removed-features.rst | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 15 deletions(-) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -XXX,XX +XXX,XX @@ to correct issues, mostly regarding migration compatibility. These are no longer maintained and removing them will make the code easier to read and maintain. Use versions 3.0 and above as a replacement. -Arm machines ``akita``, ``borzoi``, ``cheetah``, ``connex``, ``mainstone``, ``n800``, ``n810``, ``spitz``, ``terrier``, ``tosa``, ``verdex``, ``z2`` (since 9.0) -'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' - -QEMU includes models of some machine types where the QEMU code that -emulates their SoCs is very old and unmaintained. This code is now -blocking our ability to move forward with various changes across -the codebase, and over many years nobody has been interested in -trying to modernise it. We don't expect any of these machines to have -a large number of users, because they're all modelling hardware that -has now passed away into history. We are therefore dropping support -for all machine types using the PXA2xx and OMAP2 SoCs. We are also -dropping the ``cheetah`` OMAP1 board, because we don't have any -test images for it and don't know of anybody who does; the ``sx1`` -and ``sx1-v1`` OMAP1 machines remain supported for now. - PPC 405 ``ref405ep`` machine (since 9.1) '''''''''''''''''''''''''''''''''''''''' diff --git a/docs/about/removed-features.rst b/docs/about/removed-features.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/removed-features.rst +++ b/docs/about/removed-features.rst @@ -XXX,XX +XXX,XX @@ The Nios II architecture was orphan. The machine was unmaintained. +Arm machines ``akita``, ``borzoi``, ``cheetah``, ``connex``, ``mainstone``, ``n800``, ``n810``, ``spitz``, ``terrier``, ``tosa``, ``verdex``, ``z2`` (removed in 9.2) +''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +QEMU included models of some machine types where the QEMU code that +emulates their SoCs was very old and unmaintained. This code was +blocking our ability to move forward with various changes across +the codebase, and over many years nobody has been interested in +trying to modernise it. We don't expect any of these machines to have +a large number of users, because they're all modelling hardware that +has now passed away into history. We are therefore dropping support +for all machine types using the PXA2xx and OMAP2 SoCs. We are also +dropping the ``cheetah`` OMAP1 board, because we don't have any +test images for it and don't know of anybody who does. + linux-user mode CPUs -------------------- -- 2.34.1 The users of the OMAP2 SoC emulation have been removed, so we can delete omap2.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-38-peter.maydell@linaro.org --- include/hw/arm/omap.h | 8 - hw/arm/omap2.c | 2715 ----------------------------------------- hw/arm/meson.build | 1 - 3 files changed, 2724 deletions(-) delete mode 100644 hw/arm/omap2.c diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s { struct omap_gp_timer_s *gptimer[12]; struct omap_synctimer_s *synctimer; - struct omap_prcm_s *prcm; struct omap_sdrc_s *sdrc; struct omap_gpmc_s *gpmc; - struct omap_sysctl_s *sysc; struct omap_mcspi_s *mcspi[2]; struct omap_dss_s *dss; - - struct omap_eac_s *eac; }; /* omap1.c */ struct omap_mpu_state_s *omap310_mpu_init(MemoryRegion *sdram, const char *core); -/* omap2.c */ -struct omap_mpu_state_s *omap2420_mpu_init(MemoryRegion *sdram, - const char *core); - uint32_t omap_badwidth_read8(void *opaque, hwaddr addr); void omap_badwidth_write8(void *opaque, hwaddr addr, uint32_t value); diff --git a/hw/arm/omap2.c b/hw/arm/omap2.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/arm/omap2.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI OMAP processors emulation. - * - * Copyright (C) 2007-2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "qemu/error-report.h" -#include "qapi/error.h" -#include "exec/address-spaces.h" -#include "sysemu/blockdev.h" -#include "sysemu/qtest.h" -#include "sysemu/reset.h" -#include "sysemu/runstate.h" -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "hw/arm/boot.h" -#include "hw/arm/omap.h" -#include "sysemu/sysemu.h" -#include "qemu/timer.h" -#include "chardev/char-fe.h" -#include "hw/block/flash.h" -#include "hw/arm/soc_dma.h" -#include "hw/sysbus.h" -#include "hw/boards.h" -#include "audio/audio.h" -#include "target/arm/cpu-qom.h" - -/* Enhanced Audio Controller (CODEC only) */ -struct omap_eac_s { - qemu_irq irq; - MemoryRegion iomem; - - uint16_t sysconfig; - uint8_t config[4]; - uint8_t control; - uint8_t address; - uint16_t data; - uint8_t vtol; - uint8_t vtsl; - uint16_t mixer; - uint16_t gain[4]; - uint8_t att; - uint16_t max[7]; - - struct { - qemu_irq txdrq; - qemu_irq rxdrq; - uint32_t (*txrx)(void *opaque, uint32_t, int); - void *opaque; - -#define EAC_BUF_LEN 1024 - uint32_t rxbuf[EAC_BUF_LEN]; - int rxoff; - int rxlen; - int rxavail; - uint32_t txbuf[EAC_BUF_LEN]; - int txlen; - int txavail; - - int enable; - int rate; - - uint16_t config[4]; - - /* These need to be moved to the actual codec */ - QEMUSoundCard card; - SWVoiceIn *in_voice; - SWVoiceOut *out_voice; - int hw_enable; - } codec; - - struct { - uint8_t control; - uint16_t config; - } modem, bt; -}; - -static inline void omap_eac_interrupt_update(struct omap_eac_s *s) -{ - qemu_set_irq(s->irq, (s->codec.config[1] >> 14) & 1); /* AURDI */ -} - -static inline void omap_eac_in_dmarequest_update(struct omap_eac_s *s) -{ - qemu_set_irq(s->codec.rxdrq, (s->codec.rxavail || s->codec.rxlen) && - ((s->codec.config[1] >> 12) & 1)); /* DMAREN */ -} - -static inline void omap_eac_out_dmarequest_update(struct omap_eac_s *s) -{ - qemu_set_irq(s->codec.txdrq, s->codec.txlen < s->codec.txavail && - ((s->codec.config[1] >> 11) & 1)); /* DMAWEN */ -} - -static inline void omap_eac_in_refill(struct omap_eac_s *s) -{ - int left = MIN(EAC_BUF_LEN - s->codec.rxlen, s->codec.rxavail) << 2; - int start = ((s->codec.rxoff + s->codec.rxlen) & (EAC_BUF_LEN - 1)) << 2; - int leftwrap = MIN(left, (EAC_BUF_LEN << 2) - start); - int recv = 1; - uint8_t *buf = (uint8_t *) s->codec.rxbuf + start; - - left -= leftwrap; - start = 0; - while (leftwrap && (recv = AUD_read(s->codec.in_voice, buf + start, - leftwrap)) > 0) { /* Be defensive */ - start += recv; - leftwrap -= recv; - } - if (recv <= 0) - s->codec.rxavail = 0; - else - s->codec.rxavail -= start >> 2; - s->codec.rxlen += start >> 2; - - if (recv > 0 && left > 0) { - start = 0; - while (left && (recv = AUD_read(s->codec.in_voice, - (uint8_t *) s->codec.rxbuf + start, - left)) > 0) { /* Be defensive */ - start += recv; - left -= recv; - } - if (recv <= 0) - s->codec.rxavail = 0; - else - s->codec.rxavail -= start >> 2; - s->codec.rxlen += start >> 2; - } -} - -static inline void omap_eac_out_empty(struct omap_eac_s *s) -{ - int left = s->codec.txlen << 2; - int start = 0; - int sent = 1; - - while (left && (sent = AUD_write(s->codec.out_voice, - (uint8_t *) s->codec.txbuf + start, - left)) > 0) { /* Be defensive */ - start += sent; - left -= sent; - } - - if (!sent) { - s->codec.txavail = 0; - omap_eac_out_dmarequest_update(s); - } - - if (start) - s->codec.txlen = 0; -} - -static void omap_eac_in_cb(void *opaque, int avail_b) -{ - struct omap_eac_s *s = opaque; - - s->codec.rxavail = avail_b >> 2; - omap_eac_in_refill(s); - /* TODO: possibly discard current buffer if overrun */ - omap_eac_in_dmarequest_update(s); -} - -static void omap_eac_out_cb(void *opaque, int free_b) -{ - struct omap_eac_s *s = opaque; - - s->codec.txavail = free_b >> 2; - if (s->codec.txlen) - omap_eac_out_empty(s); - else - omap_eac_out_dmarequest_update(s); -} - -static void omap_eac_enable_update(struct omap_eac_s *s) -{ - s->codec.enable = !(s->codec.config[1] & 1) && /* EACPWD */ - (s->codec.config[1] & 2) && /* AUDEN */ - s->codec.hw_enable; -} - -static const int omap_eac_fsint[4] = { - 8000, - 11025, - 22050, - 44100, -}; - -static const int omap_eac_fsint2[8] = { - 8000, - 11025, - 22050, - 44100, - 48000, - 0, 0, 0, -}; - -static const int omap_eac_fsint3[16] = { - 8000, - 11025, - 16000, - 22050, - 24000, - 32000, - 44100, - 48000, - 0, 0, 0, 0, 0, 0, 0, 0, -}; - -static void omap_eac_rate_update(struct omap_eac_s *s) -{ - int fsint[3]; - - fsint[2] = (s->codec.config[3] >> 9) & 0xf; - fsint[1] = (s->codec.config[2] >> 0) & 0x7; - fsint[0] = (s->codec.config[0] >> 6) & 0x3; - if (fsint[2] < 0xf) - s->codec.rate = omap_eac_fsint3[fsint[2]]; - else if (fsint[1] < 0x7) - s->codec.rate = omap_eac_fsint2[fsint[1]]; - else - s->codec.rate = omap_eac_fsint[fsint[0]]; -} - -static void omap_eac_volume_update(struct omap_eac_s *s) -{ - /* TODO */ -} - -static void omap_eac_format_update(struct omap_eac_s *s) -{ - struct audsettings fmt; - - /* The hardware buffers at most one sample */ - if (s->codec.rxlen) - s->codec.rxlen = 1; - - if (s->codec.in_voice) { - AUD_set_active_in(s->codec.in_voice, 0); - AUD_close_in(&s->codec.card, s->codec.in_voice); - s->codec.in_voice = NULL; - } - if (s->codec.out_voice) { - omap_eac_out_empty(s); - AUD_set_active_out(s->codec.out_voice, 0); - AUD_close_out(&s->codec.card, s->codec.out_voice); - s->codec.out_voice = NULL; - s->codec.txavail = 0; - } - /* Discard what couldn't be written */ - s->codec.txlen = 0; - - omap_eac_enable_update(s); - if (!s->codec.enable) - return; - - omap_eac_rate_update(s); - fmt.endianness = ((s->codec.config[0] >> 8) & 1); /* LI_BI */ - fmt.nchannels = ((s->codec.config[0] >> 10) & 1) ? 2 : 1; /* MN_ST */ - fmt.freq = s->codec.rate; - /* TODO: signedness possibly depends on the CODEC hardware - or - * does I2S specify it? */ - /* All register writes are 16 bits so we store 16-bit samples - * in the buffers regardless of AGCFR[B8_16] value. */ - fmt.fmt = AUDIO_FORMAT_U16; - - s->codec.in_voice = AUD_open_in(&s->codec.card, s->codec.in_voice, - "eac.codec.in", s, omap_eac_in_cb, &fmt); - s->codec.out_voice = AUD_open_out(&s->codec.card, s->codec.out_voice, - "eac.codec.out", s, omap_eac_out_cb, &fmt); - - omap_eac_volume_update(s); - - AUD_set_active_in(s->codec.in_voice, 1); - AUD_set_active_out(s->codec.out_voice, 1); -} - -static void omap_eac_reset(struct omap_eac_s *s) -{ - s->sysconfig = 0; - s->config[0] = 0x0c; - s->config[1] = 0x09; - s->config[2] = 0xab; - s->config[3] = 0x03; - s->control = 0x00; - s->address = 0x00; - s->data = 0x0000; - s->vtol = 0x00; - s->vtsl = 0x00; - s->mixer = 0x0000; - s->gain[0] = 0xe7e7; - s->gain[1] = 0x6767; - s->gain[2] = 0x6767; - s->gain[3] = 0x6767; - s->att = 0xce; - s->max[0] = 0; - s->max[1] = 0; - s->max[2] = 0; - s->max[3] = 0; - s->max[4] = 0; - s->max[5] = 0; - s->max[6] = 0; - - s->modem.control = 0x00; - s->modem.config = 0x0000; - s->bt.control = 0x00; - s->bt.config = 0x0000; - s->codec.config[0] = 0x0649; - s->codec.config[1] = 0x0000; - s->codec.config[2] = 0x0007; - s->codec.config[3] = 0x1ffc; - s->codec.rxoff = 0; - s->codec.rxlen = 0; - s->codec.txlen = 0; - s->codec.rxavail = 0; - s->codec.txavail = 0; - - omap_eac_format_update(s); - omap_eac_interrupt_update(s); -} - -static uint64_t omap_eac_read(void *opaque, hwaddr addr, unsigned size) -{ - struct omap_eac_s *s = opaque; - uint32_t ret; - - if (size != 2) { - return omap_badwidth_read16(opaque, addr); - } - - switch (addr) { - case 0x000: /* CPCFR1 */ - return s->config[0]; - case 0x004: /* CPCFR2 */ - return s->config[1]; - case 0x008: /* CPCFR3 */ - return s->config[2]; - case 0x00c: /* CPCFR4 */ - return s->config[3]; - - case 0x010: /* CPTCTL */ - return s->control | ((s->codec.rxavail + s->codec.rxlen > 0) << 7) | - ((s->codec.txlen < s->codec.txavail) << 5); - - case 0x014: /* CPTTADR */ - return s->address; - case 0x018: /* CPTDATL */ - return s->data & 0xff; - case 0x01c: /* CPTDATH */ - return s->data >> 8; - case 0x020: /* CPTVSLL */ - return s->vtol; - case 0x024: /* CPTVSLH */ - return s->vtsl | (3 << 5); /* CRDY1 | CRDY2 */ - case 0x040: /* MPCTR */ - return s->modem.control; - case 0x044: /* MPMCCFR */ - return s->modem.config; - case 0x060: /* BPCTR */ - return s->bt.control; - case 0x064: /* BPMCCFR */ - return s->bt.config; - case 0x080: /* AMSCFR */ - return s->mixer; - case 0x084: /* AMVCTR */ - return s->gain[0]; - case 0x088: /* AM1VCTR */ - return s->gain[1]; - case 0x08c: /* AM2VCTR */ - return s->gain[2]; - case 0x090: /* AM3VCTR */ - return s->gain[3]; - case 0x094: /* ASTCTR */ - return s->att; - case 0x098: /* APD1LCR */ - return s->max[0]; - case 0x09c: /* APD1RCR */ - return s->max[1]; - case 0x0a0: /* APD2LCR */ - return s->max[2]; - case 0x0a4: /* APD2RCR */ - return s->max[3]; - case 0x0a8: /* APD3LCR */ - return s->max[4]; - case 0x0ac: /* APD3RCR */ - return s->max[5]; - case 0x0b0: /* APD4R */ - return s->max[6]; - case 0x0b4: /* ADWR */ - /* This should be write-only? Docs list it as read-only. */ - return 0x0000; - case 0x0b8: /* ADRDR */ - if (likely(s->codec.rxlen > 1)) { - ret = s->codec.rxbuf[s->codec.rxoff ++]; - s->codec.rxlen --; - s->codec.rxoff &= EAC_BUF_LEN - 1; - return ret; - } else if (s->codec.rxlen) { - ret = s->codec.rxbuf[s->codec.rxoff ++]; - s->codec.rxlen --; - s->codec.rxoff &= EAC_BUF_LEN - 1; - if (s->codec.rxavail) - omap_eac_in_refill(s); - omap_eac_in_dmarequest_update(s); - return ret; - } - return 0x0000; - case 0x0bc: /* AGCFR */ - return s->codec.config[0]; - case 0x0c0: /* AGCTR */ - return s->codec.config[1] | ((s->codec.config[1] & 2) << 14); - case 0x0c4: /* AGCFR2 */ - return s->codec.config[2]; - case 0x0c8: /* AGCFR3 */ - return s->codec.config[3]; - case 0x0cc: /* MBPDMACTR */ - case 0x0d0: /* MPDDMARR */ - case 0x0d8: /* MPUDMARR */ - case 0x0e4: /* BPDDMARR */ - case 0x0ec: /* BPUDMARR */ - return 0x0000; - - case 0x100: /* VERSION_NUMBER */ - return 0x0010; - - case 0x104: /* SYSCONFIG */ - return s->sysconfig; - - case 0x108: /* SYSSTATUS */ - return 1 | 0xe; /* RESETDONE | stuff */ - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_eac_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_eac_s *s = opaque; - - if (size != 2) { - omap_badwidth_write16(opaque, addr, value); - return; - } - - switch (addr) { - case 0x098: /* APD1LCR */ - case 0x09c: /* APD1RCR */ - case 0x0a0: /* APD2LCR */ - case 0x0a4: /* APD2RCR */ - case 0x0a8: /* APD3LCR */ - case 0x0ac: /* APD3RCR */ - case 0x0b0: /* APD4R */ - case 0x0b8: /* ADRDR */ - case 0x0d0: /* MPDDMARR */ - case 0x0d8: /* MPUDMARR */ - case 0x0e4: /* BPDDMARR */ - case 0x0ec: /* BPUDMARR */ - case 0x100: /* VERSION_NUMBER */ - case 0x108: /* SYSSTATUS */ - OMAP_RO_REG(addr); - return; - - case 0x000: /* CPCFR1 */ - s->config[0] = value & 0xff; - omap_eac_format_update(s); - break; - case 0x004: /* CPCFR2 */ - s->config[1] = value & 0xff; - omap_eac_format_update(s); - break; - case 0x008: /* CPCFR3 */ - s->config[2] = value & 0xff; - omap_eac_format_update(s); - break; - case 0x00c: /* CPCFR4 */ - s->config[3] = value & 0xff; - omap_eac_format_update(s); - break; - - case 0x010: /* CPTCTL */ - /* Assuming TXF and TXE bits are read-only... */ - s->control = value & 0x5f; - omap_eac_interrupt_update(s); - break; - - case 0x014: /* CPTTADR */ - s->address = value & 0xff; - break; - case 0x018: /* CPTDATL */ - s->data &= 0xff00; - s->data |= value & 0xff; - break; - case 0x01c: /* CPTDATH */ - s->data &= 0x00ff; - s->data |= value << 8; - break; - case 0x020: /* CPTVSLL */ - s->vtol = value & 0xf8; - break; - case 0x024: /* CPTVSLH */ - s->vtsl = value & 0x9f; - break; - case 0x040: /* MPCTR */ - s->modem.control = value & 0x8f; - break; - case 0x044: /* MPMCCFR */ - s->modem.config = value & 0x7fff; - break; - case 0x060: /* BPCTR */ - s->bt.control = value & 0x8f; - break; - case 0x064: /* BPMCCFR */ - s->bt.config = value & 0x7fff; - break; - case 0x080: /* AMSCFR */ - s->mixer = value & 0x0fff; - break; - case 0x084: /* AMVCTR */ - s->gain[0] = value & 0xffff; - break; - case 0x088: /* AM1VCTR */ - s->gain[1] = value & 0xff7f; - break; - case 0x08c: /* AM2VCTR */ - s->gain[2] = value & 0xff7f; - break; - case 0x090: /* AM3VCTR */ - s->gain[3] = value & 0xff7f; - break; - case 0x094: /* ASTCTR */ - s->att = value & 0xff; - break; - - case 0x0b4: /* ADWR */ - s->codec.txbuf[s->codec.txlen ++] = value; - if (unlikely(s->codec.txlen == EAC_BUF_LEN || - s->codec.txlen == s->codec.txavail)) { - if (s->codec.txavail) - omap_eac_out_empty(s); - /* Discard what couldn't be written */ - s->codec.txlen = 0; - } - break; - - case 0x0bc: /* AGCFR */ - s->codec.config[0] = value & 0x07ff; - omap_eac_format_update(s); - break; - case 0x0c0: /* AGCTR */ - s->codec.config[1] = value & 0x780f; - omap_eac_format_update(s); - break; - case 0x0c4: /* AGCFR2 */ - s->codec.config[2] = value & 0x003f; - omap_eac_format_update(s); - break; - case 0x0c8: /* AGCFR3 */ - s->codec.config[3] = value & 0xffff; - omap_eac_format_update(s); - break; - case 0x0cc: /* MBPDMACTR */ - case 0x0d4: /* MPDDMAWR */ - case 0x0e0: /* MPUDMAWR */ - case 0x0e8: /* BPDDMAWR */ - case 0x0f0: /* BPUDMAWR */ - break; - - case 0x104: /* SYSCONFIG */ - if (value & (1 << 1)) /* SOFTRESET */ - omap_eac_reset(s); - s->sysconfig = value & 0x31d; - break; - - default: - OMAP_BAD_REG(addr); - return; - } -} - -static const MemoryRegionOps omap_eac_ops = { - .read = omap_eac_read, - .write = omap_eac_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static struct omap_eac_s *omap_eac_init(struct omap_target_agent_s *ta, - qemu_irq irq, qemu_irq *drq, omap_clk fclk, omap_clk iclk) -{ - struct omap_eac_s *s = g_new0(struct omap_eac_s, 1); - - s->irq = irq; - s->codec.rxdrq = *drq ++; - s->codec.txdrq = *drq; - omap_eac_reset(s); - - if (current_machine->audiodev) { - s->codec.card.name = g_strdup(current_machine->audiodev); - s->codec.card.state = audio_state_by_name(s->codec.card.name, &error_fatal); - } - AUD_register_card("OMAP EAC", &s->codec.card, &error_fatal); - - memory_region_init_io(&s->iomem, NULL, &omap_eac_ops, s, "omap.eac", - omap_l4_region_size(ta, 0)); - omap_l4_attach(ta, 0, &s->iomem); - - return s; -} - -/* STI/XTI (emulation interface) console - reverse engineered only */ -struct omap_sti_s { - qemu_irq irq; - MemoryRegion iomem; - MemoryRegion iomem_fifo; - CharBackend chr; - - uint32_t sysconfig; - uint32_t systest; - uint32_t irqst; - uint32_t irqen; - uint32_t clkcontrol; - uint32_t serial_config; -}; - -#define STI_TRACE_CONSOLE_CHANNEL 239 -#define STI_TRACE_CONTROL_CHANNEL 253 - -static inline void omap_sti_interrupt_update(struct omap_sti_s *s) -{ - qemu_set_irq(s->irq, s->irqst & s->irqen); -} - -static void omap_sti_reset(struct omap_sti_s *s) -{ - s->sysconfig = 0; - s->irqst = 0; - s->irqen = 0; - s->clkcontrol = 0; - s->serial_config = 0; - - omap_sti_interrupt_update(s); -} - -static uint64_t omap_sti_read(void *opaque, hwaddr addr, - unsigned size) -{ - struct omap_sti_s *s = opaque; - - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x00: /* STI_REVISION */ - return 0x10; - - case 0x10: /* STI_SYSCONFIG */ - return s->sysconfig; - - case 0x14: /* STI_SYSSTATUS / STI_RX_STATUS / XTI_SYSSTATUS */ - return 0x00; - - case 0x18: /* STI_IRQSTATUS */ - return s->irqst; - - case 0x1c: /* STI_IRQSETEN / STI_IRQCLREN */ - return s->irqen; - - case 0x24: /* STI_ER / STI_DR / XTI_TRACESELECT */ - case 0x28: /* STI_RX_DR / XTI_RXDATA */ - /* TODO */ - return 0; - - case 0x2c: /* STI_CLK_CTRL / XTI_SCLKCRTL */ - return s->clkcontrol; - - case 0x30: /* STI_SERIAL_CFG / XTI_SCONFIG */ - return s->serial_config; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_sti_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_sti_s *s = opaque; - - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x00: /* STI_REVISION */ - case 0x14: /* STI_SYSSTATUS / STI_RX_STATUS / XTI_SYSSTATUS */ - OMAP_RO_REG(addr); - return; - - case 0x10: /* STI_SYSCONFIG */ - if (value & (1 << 1)) /* SOFTRESET */ - omap_sti_reset(s); - s->sysconfig = value & 0xfe; - break; - - case 0x18: /* STI_IRQSTATUS */ - s->irqst &= ~value; - omap_sti_interrupt_update(s); - break; - - case 0x1c: /* STI_IRQSETEN / STI_IRQCLREN */ - s->irqen = value & 0xffff; - omap_sti_interrupt_update(s); - break; - - case 0x2c: /* STI_CLK_CTRL / XTI_SCLKCRTL */ - s->clkcontrol = value & 0xff; - break; - - case 0x30: /* STI_SERIAL_CFG / XTI_SCONFIG */ - s->serial_config = value & 0xff; - break; - - case 0x24: /* STI_ER / STI_DR / XTI_TRACESELECT */ - case 0x28: /* STI_RX_DR / XTI_RXDATA */ - /* TODO */ - return; - - default: - OMAP_BAD_REG(addr); - return; - } -} - -static const MemoryRegionOps omap_sti_ops = { - .read = omap_sti_read, - .write = omap_sti_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, unsigned size) -{ - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_sti_fifo_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_sti_s *s = opaque; - int ch = addr >> 6; - uint8_t byte = value; - - if (size != 1) { - omap_badwidth_write8(opaque, addr, size); - return; - } - - if (ch == STI_TRACE_CONTROL_CHANNEL) { - /* Flush channel <i>value</i>. */ - /* XXX this blocks entire thread. Rewrite to use - * qemu_chr_fe_write and background I/O callbacks */ - qemu_chr_fe_write_all(&s->chr, (const uint8_t *) "\r", 1); - } else if (ch == STI_TRACE_CONSOLE_CHANNEL || 1) { - if (value == 0xc0 || value == 0xc3) { - /* Open channel <i>ch</i>. */ - } else if (value == 0x00) { - qemu_chr_fe_write_all(&s->chr, (const uint8_t *) "\n", 1); - } else { - qemu_chr_fe_write_all(&s->chr, &byte, 1); - } - } -} - -static const MemoryRegionOps omap_sti_fifo_ops = { - .read = omap_sti_fifo_read, - .write = omap_sti_fifo_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static struct omap_sti_s *omap_sti_init(struct omap_target_agent_s *ta, - MemoryRegion *sysmem, - hwaddr channel_base, qemu_irq irq, omap_clk clk, - Chardev *chr) -{ - struct omap_sti_s *s = g_new0(struct omap_sti_s, 1); - - s->irq = irq; - omap_sti_reset(s); - - qemu_chr_fe_init(&s->chr, chr ?: qemu_chr_new("null", "null", NULL), - &error_abort); - - memory_region_init_io(&s->iomem, NULL, &omap_sti_ops, s, "omap.sti", - omap_l4_region_size(ta, 0)); - omap_l4_attach(ta, 0, &s->iomem); - - memory_region_init_io(&s->iomem_fifo, NULL, &omap_sti_fifo_ops, s, - "omap.sti.fifo", 0x10000); - memory_region_add_subregion(sysmem, channel_base, &s->iomem_fifo); - - return s; -} - -/* L4 Interconnect */ -#define L4TA(n) (n) -#define L4TAO(n) ((n) + 39) - -static const struct omap_l4_region_s omap_l4_region[125] = { - [ 1] = { 0x40800, 0x800, 32 }, /* Initiator agent */ - [ 2] = { 0x41000, 0x1000, 32 }, /* Link agent */ - [ 0] = { 0x40000, 0x800, 32 }, /* Address and protection */ - [ 3] = { 0x00000, 0x1000, 32 | 16 | 8 }, /* System Control and Pinout */ - [ 4] = { 0x01000, 0x1000, 32 | 16 | 8 }, /* L4TAO1 */ - [ 5] = { 0x04000, 0x1000, 32 | 16 }, /* 32K Timer */ - [ 6] = { 0x05000, 0x1000, 32 | 16 | 8 }, /* L4TAO2 */ - [ 7] = { 0x08000, 0x800, 32 }, /* PRCM Region A */ - [ 8] = { 0x08800, 0x800, 32 }, /* PRCM Region B */ - [ 9] = { 0x09000, 0x1000, 32 | 16 | 8 }, /* L4TAO */ - [ 10] = { 0x12000, 0x1000, 32 | 16 | 8 }, /* Test (BCM) */ - [ 11] = { 0x13000, 0x1000, 32 | 16 | 8 }, /* L4TA1 */ - [ 12] = { 0x14000, 0x1000, 32 }, /* Test/emulation (TAP) */ - [ 13] = { 0x15000, 0x1000, 32 | 16 | 8 }, /* L4TA2 */ - [ 14] = { 0x18000, 0x1000, 32 | 16 | 8 }, /* GPIO1 */ - [ 16] = { 0x1a000, 0x1000, 32 | 16 | 8 }, /* GPIO2 */ - [ 18] = { 0x1c000, 0x1000, 32 | 16 | 8 }, /* GPIO3 */ - [ 19] = { 0x1e000, 0x1000, 32 | 16 | 8 }, /* GPIO4 */ - [ 15] = { 0x19000, 0x1000, 32 | 16 | 8 }, /* Quad GPIO TOP */ - [ 17] = { 0x1b000, 0x1000, 32 | 16 | 8 }, /* L4TA3 */ - [ 20] = { 0x20000, 0x1000, 32 | 16 | 8 }, /* WD Timer 1 (Secure) */ - [ 22] = { 0x22000, 0x1000, 32 | 16 | 8 }, /* WD Timer 2 (OMAP) */ - [ 21] = { 0x21000, 0x1000, 32 | 16 | 8 }, /* Dual WD timer TOP */ - [ 23] = { 0x23000, 0x1000, 32 | 16 | 8 }, /* L4TA4 */ - [ 24] = { 0x28000, 0x1000, 32 | 16 | 8 }, /* GP Timer 1 */ - [ 25] = { 0x29000, 0x1000, 32 | 16 | 8 }, /* L4TA7 */ - [ 26] = { 0x48000, 0x2000, 32 | 16 | 8 }, /* Emulation (ARM11ETB) */ - [ 27] = { 0x4a000, 0x1000, 32 | 16 | 8 }, /* L4TA9 */ - [ 28] = { 0x50000, 0x400, 32 | 16 | 8 }, /* Display top */ - [ 29] = { 0x50400, 0x400, 32 | 16 | 8 }, /* Display control */ - [ 30] = { 0x50800, 0x400, 32 | 16 | 8 }, /* Display RFBI */ - [ 31] = { 0x50c00, 0x400, 32 | 16 | 8 }, /* Display encoder */ - [ 32] = { 0x51000, 0x1000, 32 | 16 | 8 }, /* L4TA10 */ - [ 33] = { 0x52000, 0x400, 32 | 16 | 8 }, /* Camera top */ - [ 34] = { 0x52400, 0x400, 32 | 16 | 8 }, /* Camera core */ - [ 35] = { 0x52800, 0x400, 32 | 16 | 8 }, /* Camera DMA */ - [ 36] = { 0x52c00, 0x400, 32 | 16 | 8 }, /* Camera MMU */ - [ 37] = { 0x53000, 0x1000, 32 | 16 | 8 }, /* L4TA11 */ - [ 38] = { 0x56000, 0x1000, 32 | 16 | 8 }, /* sDMA */ - [ 39] = { 0x57000, 0x1000, 32 | 16 | 8 }, /* L4TA12 */ - [ 40] = { 0x58000, 0x1000, 32 | 16 | 8 }, /* SSI top */ - [ 41] = { 0x59000, 0x1000, 32 | 16 | 8 }, /* SSI GDD */ - [ 42] = { 0x5a000, 0x1000, 32 | 16 | 8 }, /* SSI Port1 */ - [ 43] = { 0x5b000, 0x1000, 32 | 16 | 8 }, /* SSI Port2 */ - [ 44] = { 0x5c000, 0x1000, 32 | 16 | 8 }, /* L4TA13 */ - [ 45] = { 0x5e000, 0x1000, 32 | 16 | 8 }, /* USB OTG */ - [ 46] = { 0x5f000, 0x1000, 32 | 16 | 8 }, /* L4TAO4 */ - [ 47] = { 0x60000, 0x1000, 32 | 16 | 8 }, /* Emulation (WIN_TRACER1SDRC) */ - [ 48] = { 0x61000, 0x1000, 32 | 16 | 8 }, /* L4TA14 */ - [ 49] = { 0x62000, 0x1000, 32 | 16 | 8 }, /* Emulation (WIN_TRACER2GPMC) */ - [ 50] = { 0x63000, 0x1000, 32 | 16 | 8 }, /* L4TA15 */ - [ 51] = { 0x64000, 0x1000, 32 | 16 | 8 }, /* Emulation (WIN_TRACER3OCM) */ - [ 52] = { 0x65000, 0x1000, 32 | 16 | 8 }, /* L4TA16 */ - [ 53] = { 0x66000, 0x300, 32 | 16 | 8 }, /* Emulation (WIN_TRACER4L4) */ - [ 54] = { 0x67000, 0x1000, 32 | 16 | 8 }, /* L4TA17 */ - [ 55] = { 0x68000, 0x1000, 32 | 16 | 8 }, /* Emulation (XTI) */ - [ 56] = { 0x69000, 0x1000, 32 | 16 | 8 }, /* L4TA18 */ - [ 57] = { 0x6a000, 0x1000, 16 | 8 }, /* UART1 */ - [ 58] = { 0x6b000, 0x1000, 32 | 16 | 8 }, /* L4TA19 */ - [ 59] = { 0x6c000, 0x1000, 16 | 8 }, /* UART2 */ - [ 60] = { 0x6d000, 0x1000, 32 | 16 | 8 }, /* L4TA20 */ - [ 61] = { 0x6e000, 0x1000, 16 | 8 }, /* UART3 */ - [ 62] = { 0x6f000, 0x1000, 32 | 16 | 8 }, /* L4TA21 */ - [ 63] = { 0x70000, 0x1000, 16 }, /* I2C1 */ - [ 64] = { 0x71000, 0x1000, 32 | 16 | 8 }, /* L4TAO5 */ - [ 65] = { 0x72000, 0x1000, 16 }, /* I2C2 */ - [ 66] = { 0x73000, 0x1000, 32 | 16 | 8 }, /* L4TAO6 */ - [ 67] = { 0x74000, 0x1000, 16 }, /* McBSP1 */ - [ 68] = { 0x75000, 0x1000, 32 | 16 | 8 }, /* L4TAO7 */ - [ 69] = { 0x76000, 0x1000, 16 }, /* McBSP2 */ - [ 70] = { 0x77000, 0x1000, 32 | 16 | 8 }, /* L4TAO8 */ - [ 71] = { 0x24000, 0x1000, 32 | 16 | 8 }, /* WD Timer 3 (DSP) */ - [ 72] = { 0x25000, 0x1000, 32 | 16 | 8 }, /* L4TA5 */ - [ 73] = { 0x26000, 0x1000, 32 | 16 | 8 }, /* WD Timer 4 (IVA) */ - [ 74] = { 0x27000, 0x1000, 32 | 16 | 8 }, /* L4TA6 */ - [ 75] = { 0x2a000, 0x1000, 32 | 16 | 8 }, /* GP Timer 2 */ - [ 76] = { 0x2b000, 0x1000, 32 | 16 | 8 }, /* L4TA8 */ - [ 77] = { 0x78000, 0x1000, 32 | 16 | 8 }, /* GP Timer 3 */ - [ 78] = { 0x79000, 0x1000, 32 | 16 | 8 }, /* L4TA22 */ - [ 79] = { 0x7a000, 0x1000, 32 | 16 | 8 }, /* GP Timer 4 */ - [ 80] = { 0x7b000, 0x1000, 32 | 16 | 8 }, /* L4TA23 */ - [ 81] = { 0x7c000, 0x1000, 32 | 16 | 8 }, /* GP Timer 5 */ - [ 82] = { 0x7d000, 0x1000, 32 | 16 | 8 }, /* L4TA24 */ - [ 83] = { 0x7e000, 0x1000, 32 | 16 | 8 }, /* GP Timer 6 */ - [ 84] = { 0x7f000, 0x1000, 32 | 16 | 8 }, /* L4TA25 */ - [ 85] = { 0x80000, 0x1000, 32 | 16 | 8 }, /* GP Timer 7 */ - [ 86] = { 0x81000, 0x1000, 32 | 16 | 8 }, /* L4TA26 */ - [ 87] = { 0x82000, 0x1000, 32 | 16 | 8 }, /* GP Timer 8 */ - [ 88] = { 0x83000, 0x1000, 32 | 16 | 8 }, /* L4TA27 */ - [ 89] = { 0x84000, 0x1000, 32 | 16 | 8 }, /* GP Timer 9 */ - [ 90] = { 0x85000, 0x1000, 32 | 16 | 8 }, /* L4TA28 */ - [ 91] = { 0x86000, 0x1000, 32 | 16 | 8 }, /* GP Timer 10 */ - [ 92] = { 0x87000, 0x1000, 32 | 16 | 8 }, /* L4TA29 */ - [ 93] = { 0x88000, 0x1000, 32 | 16 | 8 }, /* GP Timer 11 */ - [ 94] = { 0x89000, 0x1000, 32 | 16 | 8 }, /* L4TA30 */ - [ 95] = { 0x8a000, 0x1000, 32 | 16 | 8 }, /* GP Timer 12 */ - [ 96] = { 0x8b000, 0x1000, 32 | 16 | 8 }, /* L4TA31 */ - [ 97] = { 0x90000, 0x1000, 16 }, /* EAC */ - [ 98] = { 0x91000, 0x1000, 32 | 16 | 8 }, /* L4TA32 */ - [ 99] = { 0x92000, 0x1000, 16 }, /* FAC */ - [100] = { 0x93000, 0x1000, 32 | 16 | 8 }, /* L4TA33 */ - [101] = { 0x94000, 0x1000, 32 | 16 | 8 }, /* IPC (MAILBOX) */ - [102] = { 0x95000, 0x1000, 32 | 16 | 8 }, /* L4TA34 */ - [103] = { 0x98000, 0x1000, 32 | 16 | 8 }, /* SPI1 */ - [104] = { 0x99000, 0x1000, 32 | 16 | 8 }, /* L4TA35 */ - [105] = { 0x9a000, 0x1000, 32 | 16 | 8 }, /* SPI2 */ - [106] = { 0x9b000, 0x1000, 32 | 16 | 8 }, /* L4TA36 */ - [107] = { 0x9c000, 0x1000, 16 | 8 }, /* MMC SDIO */ - [108] = { 0x9d000, 0x1000, 32 | 16 | 8 }, /* L4TAO9 */ - [109] = { 0x9e000, 0x1000, 32 | 16 | 8 }, /* MS_PRO */ - [110] = { 0x9f000, 0x1000, 32 | 16 | 8 }, /* L4TAO10 */ - [111] = { 0xa0000, 0x1000, 32 }, /* RNG */ - [112] = { 0xa1000, 0x1000, 32 | 16 | 8 }, /* L4TAO11 */ - [113] = { 0xa2000, 0x1000, 32 }, /* DES3DES */ - [114] = { 0xa3000, 0x1000, 32 | 16 | 8 }, /* L4TAO12 */ - [115] = { 0xa4000, 0x1000, 32 }, /* SHA1MD5 */ - [116] = { 0xa5000, 0x1000, 32 | 16 | 8 }, /* L4TAO13 */ - [117] = { 0xa6000, 0x1000, 32 }, /* AES */ - [118] = { 0xa7000, 0x1000, 32 | 16 | 8 }, /* L4TA37 */ - [119] = { 0xa8000, 0x2000, 32 }, /* PKA */ - [120] = { 0xaa000, 0x1000, 32 | 16 | 8 }, /* L4TA38 */ - [121] = { 0xb0000, 0x1000, 32 }, /* MG */ - [122] = { 0xb1000, 0x1000, 32 | 16 | 8 }, - [123] = { 0xb2000, 0x1000, 32 }, /* HDQ/1-Wire */ - [124] = { 0xb3000, 0x1000, 32 | 16 | 8 }, /* L4TA39 */ -}; - -static const struct omap_l4_agent_info_s omap_l4_agent_info[54] = { - { 0, 0, 3, 2 }, /* L4IA initiatior agent */ - { L4TAO(1), 3, 2, 1 }, /* Control and pinout module */ - { L4TAO(2), 5, 2, 1 }, /* 32K timer */ - { L4TAO(3), 7, 3, 2 }, /* PRCM */ - { L4TA(1), 10, 2, 1 }, /* BCM */ - { L4TA(2), 12, 2, 1 }, /* Test JTAG */ - { L4TA(3), 14, 6, 3 }, /* Quad GPIO */ - { L4TA(4), 20, 4, 3 }, /* WD timer 1/2 */ - { L4TA(7), 24, 2, 1 }, /* GP timer 1 */ - { L4TA(9), 26, 2, 1 }, /* ATM11 ETB */ - { L4TA(10), 28, 5, 4 }, /* Display subsystem */ - { L4TA(11), 33, 5, 4 }, /* Camera subsystem */ - { L4TA(12), 38, 2, 1 }, /* sDMA */ - { L4TA(13), 40, 5, 4 }, /* SSI */ - { L4TAO(4), 45, 2, 1 }, /* USB */ - { L4TA(14), 47, 2, 1 }, /* Win Tracer1 */ - { L4TA(15), 49, 2, 1 }, /* Win Tracer2 */ - { L4TA(16), 51, 2, 1 }, /* Win Tracer3 */ - { L4TA(17), 53, 2, 1 }, /* Win Tracer4 */ - { L4TA(18), 55, 2, 1 }, /* XTI */ - { L4TA(19), 57, 2, 1 }, /* UART1 */ - { L4TA(20), 59, 2, 1 }, /* UART2 */ - { L4TA(21), 61, 2, 1 }, /* UART3 */ - { L4TAO(5), 63, 2, 1 }, /* I2C1 */ - { L4TAO(6), 65, 2, 1 }, /* I2C2 */ - { L4TAO(7), 67, 2, 1 }, /* McBSP1 */ - { L4TAO(8), 69, 2, 1 }, /* McBSP2 */ - { L4TA(5), 71, 2, 1 }, /* WD Timer 3 (DSP) */ - { L4TA(6), 73, 2, 1 }, /* WD Timer 4 (IVA) */ - { L4TA(8), 75, 2, 1 }, /* GP Timer 2 */ - { L4TA(22), 77, 2, 1 }, /* GP Timer 3 */ - { L4TA(23), 79, 2, 1 }, /* GP Timer 4 */ - { L4TA(24), 81, 2, 1 }, /* GP Timer 5 */ - { L4TA(25), 83, 2, 1 }, /* GP Timer 6 */ - { L4TA(26), 85, 2, 1 }, /* GP Timer 7 */ - { L4TA(27), 87, 2, 1 }, /* GP Timer 8 */ - { L4TA(28), 89, 2, 1 }, /* GP Timer 9 */ - { L4TA(29), 91, 2, 1 }, /* GP Timer 10 */ - { L4TA(30), 93, 2, 1 }, /* GP Timer 11 */ - { L4TA(31), 95, 2, 1 }, /* GP Timer 12 */ - { L4TA(32), 97, 2, 1 }, /* EAC */ - { L4TA(33), 99, 2, 1 }, /* FAC */ - { L4TA(34), 101, 2, 1 }, /* IPC */ - { L4TA(35), 103, 2, 1 }, /* SPI1 */ - { L4TA(36), 105, 2, 1 }, /* SPI2 */ - { L4TAO(9), 107, 2, 1 }, /* MMC SDIO */ - { L4TAO(10), 109, 2, 1 }, - { L4TAO(11), 111, 2, 1 }, /* RNG */ - { L4TAO(12), 113, 2, 1 }, /* DES3DES */ - { L4TAO(13), 115, 2, 1 }, /* SHA1MD5 */ - { L4TA(37), 117, 2, 1 }, /* AES */ - { L4TA(38), 119, 2, 1 }, /* PKA */ - { -1, 121, 2, 1 }, - { L4TA(39), 123, 2, 1 }, /* HDQ/1-Wire */ -}; - -#define omap_l4ta(bus, cs) \ - omap_l4ta_get(bus, omap_l4_region, omap_l4_agent_info, L4TA(cs)) -#define omap_l4tao(bus, cs) \ - omap_l4ta_get(bus, omap_l4_region, omap_l4_agent_info, L4TAO(cs)) - -/* Power, Reset, and Clock Management */ -struct omap_prcm_s { - qemu_irq irq[3]; - struct omap_mpu_state_s *mpu; - MemoryRegion iomem0; - MemoryRegion iomem1; - - uint32_t irqst[3]; - uint32_t irqen[3]; - - uint32_t sysconfig; - uint32_t voltctrl; - uint32_t scratch[20]; - - uint32_t clksrc[1]; - uint32_t clkout[1]; - uint32_t clkemul[1]; - uint32_t clkpol[1]; - uint32_t clksel[8]; - uint32_t clken[12]; - uint32_t clkctrl[4]; - uint32_t clkidle[7]; - uint32_t setuptime[2]; - - uint32_t wkup[3]; - uint32_t wken[3]; - uint32_t wkst[3]; - uint32_t rst[4]; - uint32_t rstctrl[1]; - uint32_t power[4]; - uint32_t rsttime_wkup; - - uint32_t ev; - uint32_t evtime[2]; - - int dpll_lock, apll_lock[2]; -}; - -static void omap_prcm_int_update(struct omap_prcm_s *s, int dom) -{ - qemu_set_irq(s->irq[dom], s->irqst[dom] & s->irqen[dom]); - /* XXX or is the mask applied before PRCM_IRQSTATUS_* ? */ -} - -static uint64_t omap_prcm_read(void *opaque, hwaddr addr, - unsigned size) -{ - struct omap_prcm_s *s = opaque; - uint32_t ret; - - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x000: /* PRCM_REVISION */ - return 0x10; - - case 0x010: /* PRCM_SYSCONFIG */ - return s->sysconfig; - - case 0x018: /* PRCM_IRQSTATUS_MPU */ - return s->irqst[0]; - - case 0x01c: /* PRCM_IRQENABLE_MPU */ - return s->irqen[0]; - - case 0x050: /* PRCM_VOLTCTRL */ - return s->voltctrl; - case 0x054: /* PRCM_VOLTST */ - return s->voltctrl & 3; - - case 0x060: /* PRCM_CLKSRC_CTRL */ - return s->clksrc[0]; - case 0x070: /* PRCM_CLKOUT_CTRL */ - return s->clkout[0]; - case 0x078: /* PRCM_CLKEMUL_CTRL */ - return s->clkemul[0]; - case 0x080: /* PRCM_CLKCFG_CTRL */ - case 0x084: /* PRCM_CLKCFG_STATUS */ - return 0; - - case 0x090: /* PRCM_VOLTSETUP */ - return s->setuptime[0]; - - case 0x094: /* PRCM_CLKSSETUP */ - return s->setuptime[1]; - - case 0x098: /* PRCM_POLCTRL */ - return s->clkpol[0]; - - case 0x0b0: /* GENERAL_PURPOSE1 */ - case 0x0b4: /* GENERAL_PURPOSE2 */ - case 0x0b8: /* GENERAL_PURPOSE3 */ - case 0x0bc: /* GENERAL_PURPOSE4 */ - case 0x0c0: /* GENERAL_PURPOSE5 */ - case 0x0c4: /* GENERAL_PURPOSE6 */ - case 0x0c8: /* GENERAL_PURPOSE7 */ - case 0x0cc: /* GENERAL_PURPOSE8 */ - case 0x0d0: /* GENERAL_PURPOSE9 */ - case 0x0d4: /* GENERAL_PURPOSE10 */ - case 0x0d8: /* GENERAL_PURPOSE11 */ - case 0x0dc: /* GENERAL_PURPOSE12 */ - case 0x0e0: /* GENERAL_PURPOSE13 */ - case 0x0e4: /* GENERAL_PURPOSE14 */ - case 0x0e8: /* GENERAL_PURPOSE15 */ - case 0x0ec: /* GENERAL_PURPOSE16 */ - case 0x0f0: /* GENERAL_PURPOSE17 */ - case 0x0f4: /* GENERAL_PURPOSE18 */ - case 0x0f8: /* GENERAL_PURPOSE19 */ - case 0x0fc: /* GENERAL_PURPOSE20 */ - return s->scratch[(addr - 0xb0) >> 2]; - - case 0x140: /* CM_CLKSEL_MPU */ - return s->clksel[0]; - case 0x148: /* CM_CLKSTCTRL_MPU */ - return s->clkctrl[0]; - - case 0x158: /* RM_RSTST_MPU */ - return s->rst[0]; - case 0x1c8: /* PM_WKDEP_MPU */ - return s->wkup[0]; - case 0x1d4: /* PM_EVGENCTRL_MPU */ - return s->ev; - case 0x1d8: /* PM_EVEGENONTIM_MPU */ - return s->evtime[0]; - case 0x1dc: /* PM_EVEGENOFFTIM_MPU */ - return s->evtime[1]; - case 0x1e0: /* PM_PWSTCTRL_MPU */ - return s->power[0]; - case 0x1e4: /* PM_PWSTST_MPU */ - return 0; - - case 0x200: /* CM_FCLKEN1_CORE */ - return s->clken[0]; - case 0x204: /* CM_FCLKEN2_CORE */ - return s->clken[1]; - case 0x210: /* CM_ICLKEN1_CORE */ - return s->clken[2]; - case 0x214: /* CM_ICLKEN2_CORE */ - return s->clken[3]; - case 0x21c: /* CM_ICLKEN4_CORE */ - return s->clken[4]; - - case 0x220: /* CM_IDLEST1_CORE */ - /* TODO: check the actual iclk status */ - return 0x7ffffff9; - case 0x224: /* CM_IDLEST2_CORE */ - /* TODO: check the actual iclk status */ - return 0x00000007; - case 0x22c: /* CM_IDLEST4_CORE */ - /* TODO: check the actual iclk status */ - return 0x0000001f; - - case 0x230: /* CM_AUTOIDLE1_CORE */ - return s->clkidle[0]; - case 0x234: /* CM_AUTOIDLE2_CORE */ - return s->clkidle[1]; - case 0x238: /* CM_AUTOIDLE3_CORE */ - return s->clkidle[2]; - case 0x23c: /* CM_AUTOIDLE4_CORE */ - return s->clkidle[3]; - - case 0x240: /* CM_CLKSEL1_CORE */ - return s->clksel[1]; - case 0x244: /* CM_CLKSEL2_CORE */ - return s->clksel[2]; - - case 0x248: /* CM_CLKSTCTRL_CORE */ - return s->clkctrl[1]; - - case 0x2a0: /* PM_WKEN1_CORE */ - return s->wken[0]; - case 0x2a4: /* PM_WKEN2_CORE */ - return s->wken[1]; - - case 0x2b0: /* PM_WKST1_CORE */ - return s->wkst[0]; - case 0x2b4: /* PM_WKST2_CORE */ - return s->wkst[1]; - case 0x2c8: /* PM_WKDEP_CORE */ - return 0x1e; - - case 0x2e0: /* PM_PWSTCTRL_CORE */ - return s->power[1]; - case 0x2e4: /* PM_PWSTST_CORE */ - return 0x000030 | (s->power[1] & 0xfc00); - - case 0x300: /* CM_FCLKEN_GFX */ - return s->clken[5]; - case 0x310: /* CM_ICLKEN_GFX */ - return s->clken[6]; - case 0x320: /* CM_IDLEST_GFX */ - /* TODO: check the actual iclk status */ - return 0x00000001; - case 0x340: /* CM_CLKSEL_GFX */ - return s->clksel[3]; - case 0x348: /* CM_CLKSTCTRL_GFX */ - return s->clkctrl[2]; - case 0x350: /* RM_RSTCTRL_GFX */ - return s->rstctrl[0]; - case 0x358: /* RM_RSTST_GFX */ - return s->rst[1]; - case 0x3c8: /* PM_WKDEP_GFX */ - return s->wkup[1]; - - case 0x3e0: /* PM_PWSTCTRL_GFX */ - return s->power[2]; - case 0x3e4: /* PM_PWSTST_GFX */ - return s->power[2] & 3; - - case 0x400: /* CM_FCLKEN_WKUP */ - return s->clken[7]; - case 0x410: /* CM_ICLKEN_WKUP */ - return s->clken[8]; - case 0x420: /* CM_IDLEST_WKUP */ - /* TODO: check the actual iclk status */ - return 0x0000003f; - case 0x430: /* CM_AUTOIDLE_WKUP */ - return s->clkidle[4]; - case 0x440: /* CM_CLKSEL_WKUP */ - return s->clksel[4]; - case 0x450: /* RM_RSTCTRL_WKUP */ - return 0; - case 0x454: /* RM_RSTTIME_WKUP */ - return s->rsttime_wkup; - case 0x458: /* RM_RSTST_WKUP */ - return s->rst[2]; - case 0x4a0: /* PM_WKEN_WKUP */ - return s->wken[2]; - case 0x4b0: /* PM_WKST_WKUP */ - return s->wkst[2]; - - case 0x500: /* CM_CLKEN_PLL */ - return s->clken[9]; - case 0x520: /* CM_IDLEST_CKGEN */ - ret = 0x0000070 | (s->apll_lock[0] << 9) | (s->apll_lock[1] << 8); - if (!(s->clksel[6] & 3)) - /* Core uses 32-kHz clock */ - ret |= 3 << 0; - else if (!s->dpll_lock) - /* DPLL not locked, core uses ref_clk */ - ret |= 1 << 0; - else - /* Core uses DPLL */ - ret |= 2 << 0; - return ret; - case 0x530: /* CM_AUTOIDLE_PLL */ - return s->clkidle[5]; - case 0x540: /* CM_CLKSEL1_PLL */ - return s->clksel[5]; - case 0x544: /* CM_CLKSEL2_PLL */ - return s->clksel[6]; - - case 0x800: /* CM_FCLKEN_DSP */ - return s->clken[10]; - case 0x810: /* CM_ICLKEN_DSP */ - return s->clken[11]; - case 0x820: /* CM_IDLEST_DSP */ - /* TODO: check the actual iclk status */ - return 0x00000103; - case 0x830: /* CM_AUTOIDLE_DSP */ - return s->clkidle[6]; - case 0x840: /* CM_CLKSEL_DSP */ - return s->clksel[7]; - case 0x848: /* CM_CLKSTCTRL_DSP */ - return s->clkctrl[3]; - case 0x850: /* RM_RSTCTRL_DSP */ - return 0; - case 0x858: /* RM_RSTST_DSP */ - return s->rst[3]; - case 0x8c8: /* PM_WKDEP_DSP */ - return s->wkup[2]; - case 0x8e0: /* PM_PWSTCTRL_DSP */ - return s->power[3]; - case 0x8e4: /* PM_PWSTST_DSP */ - return 0x008030 | (s->power[3] & 0x3003); - - case 0x8f0: /* PRCM_IRQSTATUS_DSP */ - return s->irqst[1]; - case 0x8f4: /* PRCM_IRQENABLE_DSP */ - return s->irqen[1]; - - case 0x8f8: /* PRCM_IRQSTATUS_IVA */ - return s->irqst[2]; - case 0x8fc: /* PRCM_IRQENABLE_IVA */ - return s->irqen[2]; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_prcm_apll_update(struct omap_prcm_s *s) -{ - int mode[2]; - - mode[0] = (s->clken[9] >> 6) & 3; - s->apll_lock[0] = (mode[0] == 3); - mode[1] = (s->clken[9] >> 2) & 3; - s->apll_lock[1] = (mode[1] == 3); - /* TODO: update clocks */ - - if (mode[0] == 1 || mode[0] == 2 || mode[1] == 1 || mode[1] == 2) - fprintf(stderr, "%s: bad EN_54M_PLL or bad EN_96M_PLL\n", - __func__); -} - -static void omap_prcm_dpll_update(struct omap_prcm_s *s) -{ - omap_clk dpll = omap_findclk(s->mpu, "dpll"); - omap_clk dpll_x2 = omap_findclk(s->mpu, "dpll"); - omap_clk core = omap_findclk(s->mpu, "core_clk"); - int mode = (s->clken[9] >> 0) & 3; - int mult, div; - - mult = (s->clksel[5] >> 12) & 0x3ff; - div = (s->clksel[5] >> 8) & 0xf; - if (mult == 0 || mult == 1) - mode = 1; /* Bypass */ - - s->dpll_lock = 0; - switch (mode) { - case 0: - fprintf(stderr, "%s: bad EN_DPLL\n", __func__); - break; - case 1: /* Low-power bypass mode (Default) */ - case 2: /* Fast-relock bypass mode */ - omap_clk_setrate(dpll, 1, 1); - omap_clk_setrate(dpll_x2, 1, 1); - break; - case 3: /* Lock mode */ - s->dpll_lock = 1; /* After 20 FINT cycles (ref_clk / (div + 1)). */ - - omap_clk_setrate(dpll, div + 1, mult); - omap_clk_setrate(dpll_x2, div + 1, mult * 2); - break; - } - - switch ((s->clksel[6] >> 0) & 3) { - case 0: - omap_clk_reparent(core, omap_findclk(s->mpu, "clk32-kHz")); - break; - case 1: - omap_clk_reparent(core, dpll); - break; - case 2: - /* Default */ - omap_clk_reparent(core, dpll_x2); - break; - case 3: - fprintf(stderr, "%s: bad CORE_CLK_SRC\n", __func__); - break; - } -} - -static void omap_prcm_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_prcm_s *s = opaque; - - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x000: /* PRCM_REVISION */ - case 0x054: /* PRCM_VOLTST */ - case 0x084: /* PRCM_CLKCFG_STATUS */ - case 0x1e4: /* PM_PWSTST_MPU */ - case 0x220: /* CM_IDLEST1_CORE */ - case 0x224: /* CM_IDLEST2_CORE */ - case 0x22c: /* CM_IDLEST4_CORE */ - case 0x2c8: /* PM_WKDEP_CORE */ - case 0x2e4: /* PM_PWSTST_CORE */ - case 0x320: /* CM_IDLEST_GFX */ - case 0x3e4: /* PM_PWSTST_GFX */ - case 0x420: /* CM_IDLEST_WKUP */ - case 0x520: /* CM_IDLEST_CKGEN */ - case 0x820: /* CM_IDLEST_DSP */ - case 0x8e4: /* PM_PWSTST_DSP */ - OMAP_RO_REG(addr); - return; - - case 0x010: /* PRCM_SYSCONFIG */ - s->sysconfig = value & 1; - break; - - case 0x018: /* PRCM_IRQSTATUS_MPU */ - s->irqst[0] &= ~value; - omap_prcm_int_update(s, 0); - break; - case 0x01c: /* PRCM_IRQENABLE_MPU */ - s->irqen[0] = value & 0x3f; - omap_prcm_int_update(s, 0); - break; - - case 0x050: /* PRCM_VOLTCTRL */ - s->voltctrl = value & 0xf1c3; - break; - - case 0x060: /* PRCM_CLKSRC_CTRL */ - s->clksrc[0] = value & 0xdb; - /* TODO update clocks */ - break; - - case 0x070: /* PRCM_CLKOUT_CTRL */ - s->clkout[0] = value & 0xbbbb; - /* TODO update clocks */ - break; - - case 0x078: /* PRCM_CLKEMUL_CTRL */ - s->clkemul[0] = value & 1; - /* TODO update clocks */ - break; - - case 0x080: /* PRCM_CLKCFG_CTRL */ - break; - - case 0x090: /* PRCM_VOLTSETUP */ - s->setuptime[0] = value & 0xffff; - break; - case 0x094: /* PRCM_CLKSSETUP */ - s->setuptime[1] = value & 0xffff; - break; - - case 0x098: /* PRCM_POLCTRL */ - s->clkpol[0] = value & 0x701; - break; - - case 0x0b0: /* GENERAL_PURPOSE1 */ - case 0x0b4: /* GENERAL_PURPOSE2 */ - case 0x0b8: /* GENERAL_PURPOSE3 */ - case 0x0bc: /* GENERAL_PURPOSE4 */ - case 0x0c0: /* GENERAL_PURPOSE5 */ - case 0x0c4: /* GENERAL_PURPOSE6 */ - case 0x0c8: /* GENERAL_PURPOSE7 */ - case 0x0cc: /* GENERAL_PURPOSE8 */ - case 0x0d0: /* GENERAL_PURPOSE9 */ - case 0x0d4: /* GENERAL_PURPOSE10 */ - case 0x0d8: /* GENERAL_PURPOSE11 */ - case 0x0dc: /* GENERAL_PURPOSE12 */ - case 0x0e0: /* GENERAL_PURPOSE13 */ - case 0x0e4: /* GENERAL_PURPOSE14 */ - case 0x0e8: /* GENERAL_PURPOSE15 */ - case 0x0ec: /* GENERAL_PURPOSE16 */ - case 0x0f0: /* GENERAL_PURPOSE17 */ - case 0x0f4: /* GENERAL_PURPOSE18 */ - case 0x0f8: /* GENERAL_PURPOSE19 */ - case 0x0fc: /* GENERAL_PURPOSE20 */ - s->scratch[(addr - 0xb0) >> 2] = value; - break; - - case 0x140: /* CM_CLKSEL_MPU */ - s->clksel[0] = value & 0x1f; - /* TODO update clocks */ - break; - case 0x148: /* CM_CLKSTCTRL_MPU */ - s->clkctrl[0] = value & 0x1f; - break; - - case 0x158: /* RM_RSTST_MPU */ - s->rst[0] &= ~value; - break; - case 0x1c8: /* PM_WKDEP_MPU */ - s->wkup[0] = value & 0x15; - break; - - case 0x1d4: /* PM_EVGENCTRL_MPU */ - s->ev = value & 0x1f; - break; - case 0x1d8: /* PM_EVEGENONTIM_MPU */ - s->evtime[0] = value; - break; - case 0x1dc: /* PM_EVEGENOFFTIM_MPU */ - s->evtime[1] = value; - break; - - case 0x1e0: /* PM_PWSTCTRL_MPU */ - s->power[0] = value & 0xc0f; - break; - - case 0x200: /* CM_FCLKEN1_CORE */ - s->clken[0] = value & 0xbfffffff; - /* TODO update clocks */ - /* The EN_EAC bit only gets/puts func_96m_clk. */ - break; - case 0x204: /* CM_FCLKEN2_CORE */ - s->clken[1] = value & 0x00000007; - /* TODO update clocks */ - break; - case 0x210: /* CM_ICLKEN1_CORE */ - s->clken[2] = value & 0xfffffff9; - /* TODO update clocks */ - /* The EN_EAC bit only gets/puts core_l4_iclk. */ - break; - case 0x214: /* CM_ICLKEN2_CORE */ - s->clken[3] = value & 0x00000007; - /* TODO update clocks */ - break; - case 0x21c: /* CM_ICLKEN4_CORE */ - s->clken[4] = value & 0x0000001f; - /* TODO update clocks */ - break; - - case 0x230: /* CM_AUTOIDLE1_CORE */ - s->clkidle[0] = value & 0xfffffff9; - /* TODO update clocks */ - break; - case 0x234: /* CM_AUTOIDLE2_CORE */ - s->clkidle[1] = value & 0x00000007; - /* TODO update clocks */ - break; - case 0x238: /* CM_AUTOIDLE3_CORE */ - s->clkidle[2] = value & 0x00000007; - /* TODO update clocks */ - break; - case 0x23c: /* CM_AUTOIDLE4_CORE */ - s->clkidle[3] = value & 0x0000001f; - /* TODO update clocks */ - break; - - case 0x240: /* CM_CLKSEL1_CORE */ - s->clksel[1] = value & 0x0fffbf7f; - /* TODO update clocks */ - break; - - case 0x244: /* CM_CLKSEL2_CORE */ - s->clksel[2] = value & 0x00fffffc; - /* TODO update clocks */ - break; - - case 0x248: /* CM_CLKSTCTRL_CORE */ - s->clkctrl[1] = value & 0x7; - break; - - case 0x2a0: /* PM_WKEN1_CORE */ - s->wken[0] = value & 0x04667ff8; - break; - case 0x2a4: /* PM_WKEN2_CORE */ - s->wken[1] = value & 0x00000005; - break; - - case 0x2b0: /* PM_WKST1_CORE */ - s->wkst[0] &= ~value; - break; - case 0x2b4: /* PM_WKST2_CORE */ - s->wkst[1] &= ~value; - break; - - case 0x2e0: /* PM_PWSTCTRL_CORE */ - s->power[1] = (value & 0x00fc3f) | (1 << 2); - break; - - case 0x300: /* CM_FCLKEN_GFX */ - s->clken[5] = value & 6; - /* TODO update clocks */ - break; - case 0x310: /* CM_ICLKEN_GFX */ - s->clken[6] = value & 1; - /* TODO update clocks */ - break; - case 0x340: /* CM_CLKSEL_GFX */ - s->clksel[3] = value & 7; - /* TODO update clocks */ - break; - case 0x348: /* CM_CLKSTCTRL_GFX */ - s->clkctrl[2] = value & 1; - break; - case 0x350: /* RM_RSTCTRL_GFX */ - s->rstctrl[0] = value & 1; - /* TODO: reset */ - break; - case 0x358: /* RM_RSTST_GFX */ - s->rst[1] &= ~value; - break; - case 0x3c8: /* PM_WKDEP_GFX */ - s->wkup[1] = value & 0x13; - break; - case 0x3e0: /* PM_PWSTCTRL_GFX */ - s->power[2] = (value & 0x00c0f) | (3 << 2); - break; - - case 0x400: /* CM_FCLKEN_WKUP */ - s->clken[7] = value & 0xd; - /* TODO update clocks */ - break; - case 0x410: /* CM_ICLKEN_WKUP */ - s->clken[8] = value & 0x3f; - /* TODO update clocks */ - break; - case 0x430: /* CM_AUTOIDLE_WKUP */ - s->clkidle[4] = value & 0x0000003f; - /* TODO update clocks */ - break; - case 0x440: /* CM_CLKSEL_WKUP */ - s->clksel[4] = value & 3; - /* TODO update clocks */ - break; - case 0x450: /* RM_RSTCTRL_WKUP */ - /* TODO: reset */ - if (value & 2) - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); - break; - case 0x454: /* RM_RSTTIME_WKUP */ - s->rsttime_wkup = value & 0x1fff; - break; - case 0x458: /* RM_RSTST_WKUP */ - s->rst[2] &= ~value; - break; - case 0x4a0: /* PM_WKEN_WKUP */ - s->wken[2] = value & 0x00000005; - break; - case 0x4b0: /* PM_WKST_WKUP */ - s->wkst[2] &= ~value; - break; - - case 0x500: /* CM_CLKEN_PLL */ - if (value & 0xffffff30) - fprintf(stderr, "%s: write 0s in CM_CLKEN_PLL for " - "future compatibility\n", __func__); - if ((s->clken[9] ^ value) & 0xcc) { - s->clken[9] &= ~0xcc; - s->clken[9] |= value & 0xcc; - omap_prcm_apll_update(s); - } - if ((s->clken[9] ^ value) & 3) { - s->clken[9] &= ~3; - s->clken[9] |= value & 3; - omap_prcm_dpll_update(s); - } - break; - case 0x530: /* CM_AUTOIDLE_PLL */ - s->clkidle[5] = value & 0x000000cf; - /* TODO update clocks */ - break; - case 0x540: /* CM_CLKSEL1_PLL */ - if (value & 0xfc4000d7) - fprintf(stderr, "%s: write 0s in CM_CLKSEL1_PLL for " - "future compatibility\n", __func__); - if ((s->clksel[5] ^ value) & 0x003fff00) { - s->clksel[5] = value & 0x03bfff28; - omap_prcm_dpll_update(s); - } - /* TODO update the other clocks */ - - s->clksel[5] = value & 0x03bfff28; - break; - case 0x544: /* CM_CLKSEL2_PLL */ - if (value & ~3) - fprintf(stderr, "%s: write 0s in CM_CLKSEL2_PLL[31:2] for " - "future compatibility\n", __func__); - if (s->clksel[6] != (value & 3)) { - s->clksel[6] = value & 3; - omap_prcm_dpll_update(s); - } - break; - - case 0x800: /* CM_FCLKEN_DSP */ - s->clken[10] = value & 0x501; - /* TODO update clocks */ - break; - case 0x810: /* CM_ICLKEN_DSP */ - s->clken[11] = value & 0x2; - /* TODO update clocks */ - break; - case 0x830: /* CM_AUTOIDLE_DSP */ - s->clkidle[6] = value & 0x2; - /* TODO update clocks */ - break; - case 0x840: /* CM_CLKSEL_DSP */ - s->clksel[7] = value & 0x3fff; - /* TODO update clocks */ - break; - case 0x848: /* CM_CLKSTCTRL_DSP */ - s->clkctrl[3] = value & 0x101; - break; - case 0x850: /* RM_RSTCTRL_DSP */ - /* TODO: reset */ - break; - case 0x858: /* RM_RSTST_DSP */ - s->rst[3] &= ~value; - break; - case 0x8c8: /* PM_WKDEP_DSP */ - s->wkup[2] = value & 0x13; - break; - case 0x8e0: /* PM_PWSTCTRL_DSP */ - s->power[3] = (value & 0x03017) | (3 << 2); - break; - - case 0x8f0: /* PRCM_IRQSTATUS_DSP */ - s->irqst[1] &= ~value; - omap_prcm_int_update(s, 1); - break; - case 0x8f4: /* PRCM_IRQENABLE_DSP */ - s->irqen[1] = value & 0x7; - omap_prcm_int_update(s, 1); - break; - - case 0x8f8: /* PRCM_IRQSTATUS_IVA */ - s->irqst[2] &= ~value; - omap_prcm_int_update(s, 2); - break; - case 0x8fc: /* PRCM_IRQENABLE_IVA */ - s->irqen[2] = value & 0x7; - omap_prcm_int_update(s, 2); - break; - - default: - OMAP_BAD_REG(addr); - return; - } -} - -static const MemoryRegionOps omap_prcm_ops = { - .read = omap_prcm_read, - .write = omap_prcm_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void omap_prcm_reset(struct omap_prcm_s *s) -{ - s->sysconfig = 0; - s->irqst[0] = 0; - s->irqst[1] = 0; - s->irqst[2] = 0; - s->irqen[0] = 0; - s->irqen[1] = 0; - s->irqen[2] = 0; - s->voltctrl = 0x1040; - s->ev = 0x14; - s->evtime[0] = 0; - s->evtime[1] = 0; - s->clkctrl[0] = 0; - s->clkctrl[1] = 0; - s->clkctrl[2] = 0; - s->clkctrl[3] = 0; - s->clken[1] = 7; - s->clken[3] = 7; - s->clken[4] = 0; - s->clken[5] = 0; - s->clken[6] = 0; - s->clken[7] = 0xc; - s->clken[8] = 0x3e; - s->clken[9] = 0x0d; - s->clken[10] = 0; - s->clken[11] = 0; - s->clkidle[0] = 0; - s->clkidle[2] = 7; - s->clkidle[3] = 0; - s->clkidle[4] = 0; - s->clkidle[5] = 0x0c; - s->clkidle[6] = 0; - s->clksel[0] = 0x01; - s->clksel[1] = 0x02100121; - s->clksel[2] = 0x00000000; - s->clksel[3] = 0x01; - s->clksel[4] = 0; - s->clksel[7] = 0x0121; - s->wkup[0] = 0x15; - s->wkup[1] = 0x13; - s->wkup[2] = 0x13; - s->wken[0] = 0x04667ff8; - s->wken[1] = 0x00000005; - s->wken[2] = 5; - s->wkst[0] = 0; - s->wkst[1] = 0; - s->wkst[2] = 0; - s->power[0] = 0x00c; - s->power[1] = 4; - s->power[2] = 0x0000c; - s->power[3] = 0x14; - s->rstctrl[0] = 1; - s->rst[3] = 1; - omap_prcm_apll_update(s); - omap_prcm_dpll_update(s); -} - -static void omap_prcm_coldreset(struct omap_prcm_s *s) -{ - s->setuptime[0] = 0; - s->setuptime[1] = 0; - memset(&s->scratch, 0, sizeof(s->scratch)); - s->rst[0] = 0x01; - s->rst[1] = 0x00; - s->rst[2] = 0x01; - s->clken[0] = 0; - s->clken[2] = 0; - s->clkidle[1] = 0; - s->clksel[5] = 0; - s->clksel[6] = 2; - s->clksrc[0] = 0x43; - s->clkout[0] = 0x0303; - s->clkemul[0] = 0; - s->clkpol[0] = 0x100; - s->rsttime_wkup = 0x1002; - - omap_prcm_reset(s); -} - -static struct omap_prcm_s *omap_prcm_init(struct omap_target_agent_s *ta, - qemu_irq mpu_int, qemu_irq dsp_int, qemu_irq iva_int, - struct omap_mpu_state_s *mpu) -{ - struct omap_prcm_s *s = g_new0(struct omap_prcm_s, 1); - - s->irq[0] = mpu_int; - s->irq[1] = dsp_int; - s->irq[2] = iva_int; - s->mpu = mpu; - omap_prcm_coldreset(s); - - memory_region_init_io(&s->iomem0, NULL, &omap_prcm_ops, s, "omap.pcrm0", - omap_l4_region_size(ta, 0)); - memory_region_init_io(&s->iomem1, NULL, &omap_prcm_ops, s, "omap.pcrm1", - omap_l4_region_size(ta, 1)); - omap_l4_attach(ta, 0, &s->iomem0); - omap_l4_attach(ta, 1, &s->iomem1); - - return s; -} - -/* System and Pinout control */ -struct omap_sysctl_s { - struct omap_mpu_state_s *mpu; - MemoryRegion iomem; - - uint32_t sysconfig; - uint32_t devconfig; - uint32_t psaconfig; - uint32_t padconf[0x45]; - uint8_t obs; - uint32_t msuspendmux[5]; -}; - -static uint32_t omap_sysctl_read8(void *opaque, hwaddr addr) -{ - - struct omap_sysctl_s *s = opaque; - int pad_offset, byte_offset; - int value; - - switch (addr) { - case 0x030 ... 0x140: /* CONTROL_PADCONF - only used in the POP */ - pad_offset = (addr - 0x30) >> 2; - byte_offset = (addr - 0x30) & (4 - 1); - - value = s->padconf[pad_offset]; - value = (value >> (byte_offset * 8)) & 0xff; - - return value; - - default: - break; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static uint32_t omap_sysctl_read(void *opaque, hwaddr addr) -{ - struct omap_sysctl_s *s = opaque; - - switch (addr) { - case 0x000: /* CONTROL_REVISION */ - return 0x20; - - case 0x010: /* CONTROL_SYSCONFIG */ - return s->sysconfig; - - case 0x030 ... 0x140: /* CONTROL_PADCONF - only used in the POP */ - return s->padconf[(addr - 0x30) >> 2]; - - case 0x270: /* CONTROL_DEBOBS */ - return s->obs; - - case 0x274: /* CONTROL_DEVCONF */ - return s->devconfig; - - case 0x28c: /* CONTROL_EMU_SUPPORT */ - return 0; - - case 0x290: /* CONTROL_MSUSPENDMUX_0 */ - return s->msuspendmux[0]; - case 0x294: /* CONTROL_MSUSPENDMUX_1 */ - return s->msuspendmux[1]; - case 0x298: /* CONTROL_MSUSPENDMUX_2 */ - return s->msuspendmux[2]; - case 0x29c: /* CONTROL_MSUSPENDMUX_3 */ - return s->msuspendmux[3]; - case 0x2a0: /* CONTROL_MSUSPENDMUX_4 */ - return s->msuspendmux[4]; - case 0x2a4: /* CONTROL_MSUSPENDMUX_5 */ - return 0; - - case 0x2b8: /* CONTROL_PSA_CTRL */ - return s->psaconfig; - case 0x2bc: /* CONTROL_PSA_CMD */ - case 0x2c0: /* CONTROL_PSA_VALUE */ - return 0; - - case 0x2b0: /* CONTROL_SEC_CTRL */ - return 0x800000f1; - case 0x2d0: /* CONTROL_SEC_EMU */ - return 0x80000015; - case 0x2d4: /* CONTROL_SEC_TAP */ - return 0x8000007f; - case 0x2b4: /* CONTROL_SEC_TEST */ - case 0x2f0: /* CONTROL_SEC_STATUS */ - case 0x2f4: /* CONTROL_SEC_ERR_STATUS */ - /* Secure mode is not present on general-pusrpose device. Outside - * secure mode these values cannot be read or written. */ - return 0; - - case 0x2d8: /* CONTROL_OCM_RAM_PERM */ - return 0xff; - case 0x2dc: /* CONTROL_OCM_PUB_RAM_ADD */ - case 0x2e0: /* CONTROL_EXT_SEC_RAM_START_ADD */ - case 0x2e4: /* CONTROL_EXT_SEC_RAM_STOP_ADD */ - /* No secure mode so no Extended Secure RAM present. */ - return 0; - - case 0x2f8: /* CONTROL_STATUS */ - /* Device Type => General-purpose */ - return 0x0300; - case 0x2fc: /* CONTROL_GENERAL_PURPOSE_STATUS */ - - case 0x300: /* CONTROL_RPUB_KEY_H_0 */ - case 0x304: /* CONTROL_RPUB_KEY_H_1 */ - case 0x308: /* CONTROL_RPUB_KEY_H_2 */ - case 0x30c: /* CONTROL_RPUB_KEY_H_3 */ - return 0xdecafbad; - - case 0x310: /* CONTROL_RAND_KEY_0 */ - case 0x314: /* CONTROL_RAND_KEY_1 */ - case 0x318: /* CONTROL_RAND_KEY_2 */ - case 0x31c: /* CONTROL_RAND_KEY_3 */ - case 0x320: /* CONTROL_CUST_KEY_0 */ - case 0x324: /* CONTROL_CUST_KEY_1 */ - case 0x330: /* CONTROL_TEST_KEY_0 */ - case 0x334: /* CONTROL_TEST_KEY_1 */ - case 0x338: /* CONTROL_TEST_KEY_2 */ - case 0x33c: /* CONTROL_TEST_KEY_3 */ - case 0x340: /* CONTROL_TEST_KEY_4 */ - case 0x344: /* CONTROL_TEST_KEY_5 */ - case 0x348: /* CONTROL_TEST_KEY_6 */ - case 0x34c: /* CONTROL_TEST_KEY_7 */ - case 0x350: /* CONTROL_TEST_KEY_8 */ - case 0x354: /* CONTROL_TEST_KEY_9 */ - /* Can only be accessed in secure mode and when C_FieldAccEnable - * bit is set in CONTROL_SEC_CTRL. - * TODO: otherwise an interconnect access error is generated. */ - return 0; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_sysctl_write8(void *opaque, hwaddr addr, uint32_t value) -{ - struct omap_sysctl_s *s = opaque; - int pad_offset, byte_offset; - int prev_value; - - switch (addr) { - case 0x030 ... 0x140: /* CONTROL_PADCONF - only used in the POP */ - pad_offset = (addr - 0x30) >> 2; - byte_offset = (addr - 0x30) & (4 - 1); - - prev_value = s->padconf[pad_offset]; - prev_value &= ~(0xff << (byte_offset * 8)); - prev_value |= ((value & 0x1f1f1f1f) << (byte_offset * 8)) & 0x1f1f1f1f; - s->padconf[pad_offset] = prev_value; - break; - - default: - OMAP_BAD_REG(addr); - break; - } -} - -static void omap_sysctl_write(void *opaque, hwaddr addr, uint32_t value) -{ - struct omap_sysctl_s *s = opaque; - - switch (addr) { - case 0x000: /* CONTROL_REVISION */ - case 0x2a4: /* CONTROL_MSUSPENDMUX_5 */ - case 0x2c0: /* CONTROL_PSA_VALUE */ - case 0x2f8: /* CONTROL_STATUS */ - case 0x2fc: /* CONTROL_GENERAL_PURPOSE_STATUS */ - case 0x300: /* CONTROL_RPUB_KEY_H_0 */ - case 0x304: /* CONTROL_RPUB_KEY_H_1 */ - case 0x308: /* CONTROL_RPUB_KEY_H_2 */ - case 0x30c: /* CONTROL_RPUB_KEY_H_3 */ - case 0x310: /* CONTROL_RAND_KEY_0 */ - case 0x314: /* CONTROL_RAND_KEY_1 */ - case 0x318: /* CONTROL_RAND_KEY_2 */ - case 0x31c: /* CONTROL_RAND_KEY_3 */ - case 0x320: /* CONTROL_CUST_KEY_0 */ - case 0x324: /* CONTROL_CUST_KEY_1 */ - case 0x330: /* CONTROL_TEST_KEY_0 */ - case 0x334: /* CONTROL_TEST_KEY_1 */ - case 0x338: /* CONTROL_TEST_KEY_2 */ - case 0x33c: /* CONTROL_TEST_KEY_3 */ - case 0x340: /* CONTROL_TEST_KEY_4 */ - case 0x344: /* CONTROL_TEST_KEY_5 */ - case 0x348: /* CONTROL_TEST_KEY_6 */ - case 0x34c: /* CONTROL_TEST_KEY_7 */ - case 0x350: /* CONTROL_TEST_KEY_8 */ - case 0x354: /* CONTROL_TEST_KEY_9 */ - OMAP_RO_REG(addr); - return; - - case 0x010: /* CONTROL_SYSCONFIG */ - s->sysconfig = value & 0x1e; - break; - - case 0x030 ... 0x140: /* CONTROL_PADCONF - only used in the POP */ - /* XXX: should check constant bits */ - s->padconf[(addr - 0x30) >> 2] = value & 0x1f1f1f1f; - break; - - case 0x270: /* CONTROL_DEBOBS */ - s->obs = value & 0xff; - break; - - case 0x274: /* CONTROL_DEVCONF */ - s->devconfig = value & 0xffffc7ff; - break; - - case 0x28c: /* CONTROL_EMU_SUPPORT */ - break; - - case 0x290: /* CONTROL_MSUSPENDMUX_0 */ - s->msuspendmux[0] = value & 0x3fffffff; - break; - case 0x294: /* CONTROL_MSUSPENDMUX_1 */ - s->msuspendmux[1] = value & 0x3fffffff; - break; - case 0x298: /* CONTROL_MSUSPENDMUX_2 */ - s->msuspendmux[2] = value & 0x3fffffff; - break; - case 0x29c: /* CONTROL_MSUSPENDMUX_3 */ - s->msuspendmux[3] = value & 0x3fffffff; - break; - case 0x2a0: /* CONTROL_MSUSPENDMUX_4 */ - s->msuspendmux[4] = value & 0x3fffffff; - break; - - case 0x2b8: /* CONTROL_PSA_CTRL */ - s->psaconfig = value & 0x1c; - s->psaconfig |= (value & 0x20) ? 2 : 1; - break; - case 0x2bc: /* CONTROL_PSA_CMD */ - break; - - case 0x2b0: /* CONTROL_SEC_CTRL */ - case 0x2b4: /* CONTROL_SEC_TEST */ - case 0x2d0: /* CONTROL_SEC_EMU */ - case 0x2d4: /* CONTROL_SEC_TAP */ - case 0x2d8: /* CONTROL_OCM_RAM_PERM */ - case 0x2dc: /* CONTROL_OCM_PUB_RAM_ADD */ - case 0x2e0: /* CONTROL_EXT_SEC_RAM_START_ADD */ - case 0x2e4: /* CONTROL_EXT_SEC_RAM_STOP_ADD */ - case 0x2f0: /* CONTROL_SEC_STATUS */ - case 0x2f4: /* CONTROL_SEC_ERR_STATUS */ - break; - - default: - OMAP_BAD_REG(addr); - return; - } -} - -static uint64_t omap_sysctl_readfn(void *opaque, hwaddr addr, - unsigned size) -{ - switch (size) { - case 1: - return omap_sysctl_read8(opaque, addr); - case 2: - return omap_badwidth_read32(opaque, addr); /* TODO */ - case 4: - return omap_sysctl_read(opaque, addr); - default: - g_assert_not_reached(); - } -} - -static void omap_sysctl_writefn(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - switch (size) { - case 1: - omap_sysctl_write8(opaque, addr, value); - break; - case 2: - omap_badwidth_write32(opaque, addr, value); /* TODO */ - break; - case 4: - omap_sysctl_write(opaque, addr, value); - break; - default: - g_assert_not_reached(); - } -} - -static const MemoryRegionOps omap_sysctl_ops = { - .read = omap_sysctl_readfn, - .write = omap_sysctl_writefn, - .valid.min_access_size = 1, - .valid.max_access_size = 4, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void omap_sysctl_reset(struct omap_sysctl_s *s) -{ - /* (power-on reset) */ - s->sysconfig = 0; - s->obs = 0; - s->devconfig = 0x0c000000; - s->msuspendmux[0] = 0x00000000; - s->msuspendmux[1] = 0x00000000; - s->msuspendmux[2] = 0x00000000; - s->msuspendmux[3] = 0x00000000; - s->msuspendmux[4] = 0x00000000; - s->psaconfig = 1; - - s->padconf[0x00] = 0x000f0f0f; - s->padconf[0x01] = 0x00000000; - s->padconf[0x02] = 0x00000000; - s->padconf[0x03] = 0x00000000; - s->padconf[0x04] = 0x00000000; - s->padconf[0x05] = 0x00000000; - s->padconf[0x06] = 0x00000000; - s->padconf[0x07] = 0x00000000; - s->padconf[0x08] = 0x08080800; - s->padconf[0x09] = 0x08080808; - s->padconf[0x0a] = 0x08080808; - s->padconf[0x0b] = 0x08080808; - s->padconf[0x0c] = 0x08080808; - s->padconf[0x0d] = 0x08080800; - s->padconf[0x0e] = 0x08080808; - s->padconf[0x0f] = 0x08080808; - s->padconf[0x10] = 0x18181808; /* | 0x07070700 if SBoot3 */ - s->padconf[0x11] = 0x18181818; /* | 0x07070707 if SBoot3 */ - s->padconf[0x12] = 0x18181818; /* | 0x07070707 if SBoot3 */ - s->padconf[0x13] = 0x18181818; /* | 0x07070707 if SBoot3 */ - s->padconf[0x14] = 0x18181818; /* | 0x00070707 if SBoot3 */ - s->padconf[0x15] = 0x18181818; - s->padconf[0x16] = 0x18181818; /* | 0x07000000 if SBoot3 */ - s->padconf[0x17] = 0x1f001f00; - s->padconf[0x18] = 0x1f1f1f1f; - s->padconf[0x19] = 0x00000000; - s->padconf[0x1a] = 0x1f180000; - s->padconf[0x1b] = 0x00001f1f; - s->padconf[0x1c] = 0x1f001f00; - s->padconf[0x1d] = 0x00000000; - s->padconf[0x1e] = 0x00000000; - s->padconf[0x1f] = 0x08000000; - s->padconf[0x20] = 0x08080808; - s->padconf[0x21] = 0x08080808; - s->padconf[0x22] = 0x0f080808; - s->padconf[0x23] = 0x0f0f0f0f; - s->padconf[0x24] = 0x000f0f0f; - s->padconf[0x25] = 0x1f1f1f0f; - s->padconf[0x26] = 0x080f0f1f; - s->padconf[0x27] = 0x070f1808; - s->padconf[0x28] = 0x0f070707; - s->padconf[0x29] = 0x000f0f1f; - s->padconf[0x2a] = 0x0f0f0f1f; - s->padconf[0x2b] = 0x08000000; - s->padconf[0x2c] = 0x0000001f; - s->padconf[0x2d] = 0x0f0f1f00; - s->padconf[0x2e] = 0x1f1f0f0f; - s->padconf[0x2f] = 0x0f1f1f1f; - s->padconf[0x30] = 0x0f0f0f0f; - s->padconf[0x31] = 0x0f1f0f1f; - s->padconf[0x32] = 0x0f0f0f0f; - s->padconf[0x33] = 0x0f1f0f1f; - s->padconf[0x34] = 0x1f1f0f0f; - s->padconf[0x35] = 0x0f0f1f1f; - s->padconf[0x36] = 0x0f0f1f0f; - s->padconf[0x37] = 0x0f0f0f0f; - s->padconf[0x38] = 0x1f18180f; - s->padconf[0x39] = 0x1f1f1f1f; - s->padconf[0x3a] = 0x00001f1f; - s->padconf[0x3b] = 0x00000000; - s->padconf[0x3c] = 0x00000000; - s->padconf[0x3d] = 0x0f0f0f0f; - s->padconf[0x3e] = 0x18000f0f; - s->padconf[0x3f] = 0x00070000; - s->padconf[0x40] = 0x00000707; - s->padconf[0x41] = 0x0f1f0700; - s->padconf[0x42] = 0x1f1f070f; - s->padconf[0x43] = 0x0008081f; - s->padconf[0x44] = 0x00000800; -} - -static struct omap_sysctl_s *omap_sysctl_init(struct omap_target_agent_s *ta, - omap_clk iclk, struct omap_mpu_state_s *mpu) -{ - struct omap_sysctl_s *s = g_new0(struct omap_sysctl_s, 1); - - s->mpu = mpu; - omap_sysctl_reset(s); - - memory_region_init_io(&s->iomem, NULL, &omap_sysctl_ops, s, "omap.sysctl", - omap_l4_region_size(ta, 0)); - omap_l4_attach(ta, 0, &s->iomem); - - return s; -} - -/* General chip reset */ -static void omap2_mpu_reset(void *opaque) -{ - struct omap_mpu_state_s *mpu = opaque; - - omap_dma_reset(mpu->dma); - omap_prcm_reset(mpu->prcm); - omap_sysctl_reset(mpu->sysc); - omap_gp_timer_reset(mpu->gptimer[0]); - omap_gp_timer_reset(mpu->gptimer[1]); - omap_gp_timer_reset(mpu->gptimer[2]); - omap_gp_timer_reset(mpu->gptimer[3]); - omap_gp_timer_reset(mpu->gptimer[4]); - omap_gp_timer_reset(mpu->gptimer[5]); - omap_gp_timer_reset(mpu->gptimer[6]); - omap_gp_timer_reset(mpu->gptimer[7]); - omap_gp_timer_reset(mpu->gptimer[8]); - omap_gp_timer_reset(mpu->gptimer[9]); - omap_gp_timer_reset(mpu->gptimer[10]); - omap_gp_timer_reset(mpu->gptimer[11]); - omap_synctimer_reset(mpu->synctimer); - omap_sdrc_reset(mpu->sdrc); - omap_gpmc_reset(mpu->gpmc); - omap_dss_reset(mpu->dss); - omap_uart_reset(mpu->uart[0]); - omap_uart_reset(mpu->uart[1]); - omap_uart_reset(mpu->uart[2]); - omap_mmc_reset(mpu->mmc); - omap_mcspi_reset(mpu->mcspi[0]); - omap_mcspi_reset(mpu->mcspi[1]); - cpu_reset(CPU(mpu->cpu)); -} - -static int omap2_validate_addr(struct omap_mpu_state_s *s, - hwaddr addr) -{ - return 1; -} - -static const struct dma_irq_map omap2_dma_irq_map[] = { - { 0, OMAP_INT_24XX_SDMA_IRQ0 }, - { 0, OMAP_INT_24XX_SDMA_IRQ1 }, - { 0, OMAP_INT_24XX_SDMA_IRQ2 }, - { 0, OMAP_INT_24XX_SDMA_IRQ3 }, -}; - -struct omap_mpu_state_s *omap2420_mpu_init(MemoryRegion *sdram, - const char *cpu_type) -{ - struct omap_mpu_state_s *s = g_new0(struct omap_mpu_state_s, 1); - qemu_irq dma_irqs[4]; - DriveInfo *dinfo; - int i; - SysBusDevice *busdev; - struct omap_target_agent_s *ta; - MemoryRegion *sysmem = get_system_memory(); - - /* Core */ - s->mpu_model = omap2420; - s->cpu = ARM_CPU(cpu_create(cpu_type)); - s->sram_size = OMAP242X_SRAM_SIZE; - - s->wakeup = qemu_allocate_irq(omap_mpu_wakeup, s, 0); - - /* Clocks */ - omap_clk_init(s); - - /* Memory-mapped stuff */ - memory_region_init_ram(&s->sram, NULL, "omap2.sram", s->sram_size, - &error_fatal); - memory_region_add_subregion(sysmem, OMAP2_SRAM_BASE, &s->sram); - - s->l4 = omap_l4_init(sysmem, OMAP2_L4_BASE, 54); - - /* Actually mapped at any 2K boundary in the ARM11 private-peripheral if */ - s->ih[0] = qdev_new("omap2-intc"); - qdev_prop_set_uint8(s->ih[0], "revision", 0x21); - omap_intc_set_fclk(OMAP_INTC(s->ih[0]), omap_findclk(s, "mpu_intc_fclk")); - omap_intc_set_iclk(OMAP_INTC(s->ih[0]), omap_findclk(s, "mpu_intc_iclk")); - busdev = SYS_BUS_DEVICE(s->ih[0]); - sysbus_realize_and_unref(busdev, &error_fatal); - sysbus_connect_irq(busdev, 0, - qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ)); - sysbus_connect_irq(busdev, 1, - qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_FIQ)); - sysbus_mmio_map(busdev, 0, 0x480fe000); - s->prcm = omap_prcm_init(omap_l4tao(s->l4, 3), - qdev_get_gpio_in(s->ih[0], - OMAP_INT_24XX_PRCM_MPU_IRQ), - NULL, NULL, s); - - s->sysc = omap_sysctl_init(omap_l4tao(s->l4, 1), - omap_findclk(s, "omapctrl_iclk"), s); - - for (i = 0; i < 4; i++) { - dma_irqs[i] = qdev_get_gpio_in(s->ih[omap2_dma_irq_map[i].ih], - omap2_dma_irq_map[i].intr); - } - s->dma = omap_dma4_init(0x48056000, dma_irqs, sysmem, s, 256, 32, - omap_findclk(s, "sdma_iclk"), - omap_findclk(s, "sdma_fclk")); - s->port->addr_valid = omap2_validate_addr; - - /* Register SDRAM and SRAM ports for fast DMA transfers. */ - soc_dma_port_add_mem(s->dma, memory_region_get_ram_ptr(sdram), - OMAP2_Q2_BASE, memory_region_size(sdram)); - soc_dma_port_add_mem(s->dma, memory_region_get_ram_ptr(&s->sram), - OMAP2_SRAM_BASE, s->sram_size); - - s->uart[0] = omap2_uart_init(sysmem, omap_l4ta(s->l4, 19), - qdev_get_gpio_in(s->ih[0], - OMAP_INT_24XX_UART1_IRQ), - omap_findclk(s, "uart1_fclk"), - omap_findclk(s, "uart1_iclk"), - s->drq[OMAP24XX_DMA_UART1_TX], - s->drq[OMAP24XX_DMA_UART1_RX], - "uart1", - serial_hd(0)); - s->uart[1] = omap2_uart_init(sysmem, omap_l4ta(s->l4, 20), - qdev_get_gpio_in(s->ih[0], - OMAP_INT_24XX_UART2_IRQ), - omap_findclk(s, "uart2_fclk"), - omap_findclk(s, "uart2_iclk"), - s->drq[OMAP24XX_DMA_UART2_TX], - s->drq[OMAP24XX_DMA_UART2_RX], - "uart2", - serial_hd(0) ? serial_hd(1) : NULL); - s->uart[2] = omap2_uart_init(sysmem, omap_l4ta(s->l4, 21), - qdev_get_gpio_in(s->ih[0], - OMAP_INT_24XX_UART3_IRQ), - omap_findclk(s, "uart3_fclk"), - omap_findclk(s, "uart3_iclk"), - s->drq[OMAP24XX_DMA_UART3_TX], - s->drq[OMAP24XX_DMA_UART3_RX], - "uart3", - serial_hd(0) && serial_hd(1) ? serial_hd(2) : NULL); - - s->gptimer[0] = omap_gp_timer_init(omap_l4ta(s->l4, 7), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER1), - omap_findclk(s, "wu_gpt1_clk"), - omap_findclk(s, "wu_l4_iclk")); - s->gptimer[1] = omap_gp_timer_init(omap_l4ta(s->l4, 8), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER2), - omap_findclk(s, "core_gpt2_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[2] = omap_gp_timer_init(omap_l4ta(s->l4, 22), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER3), - omap_findclk(s, "core_gpt3_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[3] = omap_gp_timer_init(omap_l4ta(s->l4, 23), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER4), - omap_findclk(s, "core_gpt4_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[4] = omap_gp_timer_init(omap_l4ta(s->l4, 24), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER5), - omap_findclk(s, "core_gpt5_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[5] = omap_gp_timer_init(omap_l4ta(s->l4, 25), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER6), - omap_findclk(s, "core_gpt6_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[6] = omap_gp_timer_init(omap_l4ta(s->l4, 26), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER7), - omap_findclk(s, "core_gpt7_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[7] = omap_gp_timer_init(omap_l4ta(s->l4, 27), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER8), - omap_findclk(s, "core_gpt8_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[8] = omap_gp_timer_init(omap_l4ta(s->l4, 28), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER9), - omap_findclk(s, "core_gpt9_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[9] = omap_gp_timer_init(omap_l4ta(s->l4, 29), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER10), - omap_findclk(s, "core_gpt10_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[10] = omap_gp_timer_init(omap_l4ta(s->l4, 30), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER11), - omap_findclk(s, "core_gpt11_clk"), - omap_findclk(s, "core_l4_iclk")); - s->gptimer[11] = omap_gp_timer_init(omap_l4ta(s->l4, 31), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPTIMER12), - omap_findclk(s, "core_gpt12_clk"), - omap_findclk(s, "core_l4_iclk")); - - omap_tap_init(omap_l4ta(s->l4, 2), s); - - s->synctimer = omap_synctimer_init(omap_l4tao(s->l4, 2), s, - omap_findclk(s, "clk32-kHz"), - omap_findclk(s, "core_l4_iclk")); - - s->i2c[0] = qdev_new("omap_i2c"); - qdev_prop_set_uint8(s->i2c[0], "revision", 0x34); - omap_i2c_set_iclk(OMAP_I2C(s->i2c[0]), omap_findclk(s, "i2c1.iclk")); - omap_i2c_set_fclk(OMAP_I2C(s->i2c[0]), omap_findclk(s, "i2c1.fclk")); - busdev = SYS_BUS_DEVICE(s->i2c[0]); - sysbus_realize_and_unref(busdev, &error_fatal); - sysbus_connect_irq(busdev, 0, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_I2C1_IRQ)); - sysbus_connect_irq(busdev, 1, s->drq[OMAP24XX_DMA_I2C1_TX]); - sysbus_connect_irq(busdev, 2, s->drq[OMAP24XX_DMA_I2C1_RX]); - sysbus_mmio_map(busdev, 0, omap_l4_region_base(omap_l4tao(s->l4, 5), 0)); - - s->i2c[1] = qdev_new("omap_i2c"); - qdev_prop_set_uint8(s->i2c[1], "revision", 0x34); - omap_i2c_set_iclk(OMAP_I2C(s->i2c[1]), omap_findclk(s, "i2c2.iclk")); - omap_i2c_set_fclk(OMAP_I2C(s->i2c[1]), omap_findclk(s, "i2c2.fclk")); - busdev = SYS_BUS_DEVICE(s->i2c[1]); - sysbus_realize_and_unref(busdev, &error_fatal); - sysbus_connect_irq(busdev, 0, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_I2C2_IRQ)); - sysbus_connect_irq(busdev, 1, s->drq[OMAP24XX_DMA_I2C2_TX]); - sysbus_connect_irq(busdev, 2, s->drq[OMAP24XX_DMA_I2C2_RX]); - sysbus_mmio_map(busdev, 0, omap_l4_region_base(omap_l4tao(s->l4, 6), 0)); - - s->gpio = qdev_new("omap2-gpio"); - qdev_prop_set_int32(s->gpio, "mpu_model", s->mpu_model); - omap2_gpio_set_iclk(OMAP2_GPIO(s->gpio), omap_findclk(s, "gpio_iclk")); - omap2_gpio_set_fclk(OMAP2_GPIO(s->gpio), 0, omap_findclk(s, "gpio1_dbclk")); - omap2_gpio_set_fclk(OMAP2_GPIO(s->gpio), 1, omap_findclk(s, "gpio2_dbclk")); - omap2_gpio_set_fclk(OMAP2_GPIO(s->gpio), 2, omap_findclk(s, "gpio3_dbclk")); - omap2_gpio_set_fclk(OMAP2_GPIO(s->gpio), 3, omap_findclk(s, "gpio4_dbclk")); - if (s->mpu_model == omap2430) { - omap2_gpio_set_fclk(OMAP2_GPIO(s->gpio), 4, - omap_findclk(s, "gpio5_dbclk")); - } - busdev = SYS_BUS_DEVICE(s->gpio); - sysbus_realize_and_unref(busdev, &error_fatal); - sysbus_connect_irq(busdev, 0, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPIO_BANK1)); - sysbus_connect_irq(busdev, 3, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPIO_BANK2)); - sysbus_connect_irq(busdev, 6, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPIO_BANK3)); - sysbus_connect_irq(busdev, 9, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPIO_BANK4)); - if (s->mpu_model == omap2430) { - sysbus_connect_irq(busdev, 12, - qdev_get_gpio_in(s->ih[0], - OMAP_INT_243X_GPIO_BANK5)); - } - ta = omap_l4ta(s->l4, 3); - sysbus_mmio_map(busdev, 0, omap_l4_region_base(ta, 1)); - sysbus_mmio_map(busdev, 1, omap_l4_region_base(ta, 0)); - sysbus_mmio_map(busdev, 2, omap_l4_region_base(ta, 2)); - sysbus_mmio_map(busdev, 3, omap_l4_region_base(ta, 4)); - sysbus_mmio_map(busdev, 4, omap_l4_region_base(ta, 5)); - - s->sdrc = omap_sdrc_init(sysmem, 0x68009000); - s->gpmc = omap_gpmc_init(s, 0x6800a000, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_GPMC_IRQ), - s->drq[OMAP24XX_DMA_GPMC]); - - dinfo = drive_get(IF_SD, 0, 0); - if (!dinfo && !qtest_enabled()) { - warn_report("missing SecureDigital device"); - } - s->mmc = omap2_mmc_init(omap_l4tao(s->l4, 9), - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_MMC_IRQ), - &s->drq[OMAP24XX_DMA_MMC1_TX], - omap_findclk(s, "mmc_fclk"), omap_findclk(s, "mmc_iclk")); - - s->mcspi[0] = omap_mcspi_init(omap_l4ta(s->l4, 35), 4, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_MCSPI1_IRQ), - &s->drq[OMAP24XX_DMA_SPI1_TX0], - omap_findclk(s, "spi1_fclk"), - omap_findclk(s, "spi1_iclk")); - s->mcspi[1] = omap_mcspi_init(omap_l4ta(s->l4, 36), 2, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_MCSPI2_IRQ), - &s->drq[OMAP24XX_DMA_SPI2_TX0], - omap_findclk(s, "spi2_fclk"), - omap_findclk(s, "spi2_iclk")); - - s->dss = omap_dss_init(omap_l4ta(s->l4, 10), sysmem, 0x68000800, - /* XXX wire M_IRQ_25, D_L2_IRQ_30 and I_IRQ_13 together */ - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_DSS_IRQ), - s->drq[OMAP24XX_DMA_DSS], - omap_findclk(s, "dss_clk1"), omap_findclk(s, "dss_clk2"), - omap_findclk(s, "dss_54m_clk"), - omap_findclk(s, "dss_l3_iclk"), - omap_findclk(s, "dss_l4_iclk")); - - omap_sti_init(omap_l4ta(s->l4, 18), sysmem, 0x54000000, - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_STI), - omap_findclk(s, "emul_ck"), - serial_hd(0) && serial_hd(1) && serial_hd(2) ? - serial_hd(3) : NULL); - - s->eac = omap_eac_init(omap_l4ta(s->l4, 32), - qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_EAC_IRQ), - /* Ten consecutive lines */ - &s->drq[OMAP24XX_DMA_EAC_AC_RD], - omap_findclk(s, "func_96m_clk"), - omap_findclk(s, "core_l4_iclk")); - - /* All register mappings (including those not currently implemented): - * SystemControlMod 48000000 - 48000fff - * SystemControlL4 48001000 - 48001fff - * 32kHz Timer Mod 48004000 - 48004fff - * 32kHz Timer L4 48005000 - 48005fff - * PRCM ModA 48008000 - 480087ff - * PRCM ModB 48008800 - 48008fff - * PRCM L4 48009000 - 48009fff - * TEST-BCM Mod 48012000 - 48012fff - * TEST-BCM L4 48013000 - 48013fff - * TEST-TAP Mod 48014000 - 48014fff - * TEST-TAP L4 48015000 - 48015fff - * GPIO1 Mod 48018000 - 48018fff - * GPIO Top 48019000 - 48019fff - * GPIO2 Mod 4801a000 - 4801afff - * GPIO L4 4801b000 - 4801bfff - * GPIO3 Mod 4801c000 - 4801cfff - * GPIO4 Mod 4801e000 - 4801efff - * WDTIMER1 Mod 48020000 - 48010fff - * WDTIMER Top 48021000 - 48011fff - * WDTIMER2 Mod 48022000 - 48012fff - * WDTIMER L4 48023000 - 48013fff - * WDTIMER3 Mod 48024000 - 48014fff - * WDTIMER3 L4 48025000 - 48015fff - * WDTIMER4 Mod 48026000 - 48016fff - * WDTIMER4 L4 48027000 - 48017fff - * GPTIMER1 Mod 48028000 - 48018fff - * GPTIMER1 L4 48029000 - 48019fff - * GPTIMER2 Mod 4802a000 - 4801afff - * GPTIMER2 L4 4802b000 - 4801bfff - * L4-Config AP 48040000 - 480407ff - * L4-Config IP 48040800 - 48040fff - * L4-Config LA 48041000 - 48041fff - * ARM11ETB Mod 48048000 - 48049fff - * ARM11ETB L4 4804a000 - 4804afff - * DISPLAY Top 48050000 - 480503ff - * DISPLAY DISPC 48050400 - 480507ff - * DISPLAY RFBI 48050800 - 48050bff - * DISPLAY VENC 48050c00 - 48050fff - * DISPLAY L4 48051000 - 48051fff - * CAMERA Top 48052000 - 480523ff - * CAMERA core 48052400 - 480527ff - * CAMERA DMA 48052800 - 48052bff - * CAMERA MMU 48052c00 - 48052fff - * CAMERA L4 48053000 - 48053fff - * SDMA Mod 48056000 - 48056fff - * SDMA L4 48057000 - 48057fff - * SSI Top 48058000 - 48058fff - * SSI GDD 48059000 - 48059fff - * SSI Port1 4805a000 - 4805afff - * SSI Port2 4805b000 - 4805bfff - * SSI L4 4805c000 - 4805cfff - * USB Mod 4805e000 - 480fefff - * USB L4 4805f000 - 480fffff - * WIN_TRACER1 Mod 48060000 - 48060fff - * WIN_TRACER1 L4 48061000 - 48061fff - * WIN_TRACER2 Mod 48062000 - 48062fff - * WIN_TRACER2 L4 48063000 - 48063fff - * WIN_TRACER3 Mod 48064000 - 48064fff - * WIN_TRACER3 L4 48065000 - 48065fff - * WIN_TRACER4 Top 48066000 - 480660ff - * WIN_TRACER4 ETT 48066100 - 480661ff - * WIN_TRACER4 WT 48066200 - 480662ff - * WIN_TRACER4 L4 48067000 - 48067fff - * XTI Mod 48068000 - 48068fff - * XTI L4 48069000 - 48069fff - * UART1 Mod 4806a000 - 4806afff - * UART1 L4 4806b000 - 4806bfff - * UART2 Mod 4806c000 - 4806cfff - * UART2 L4 4806d000 - 4806dfff - * UART3 Mod 4806e000 - 4806efff - * UART3 L4 4806f000 - 4806ffff - * I2C1 Mod 48070000 - 48070fff - * I2C1 L4 48071000 - 48071fff - * I2C2 Mod 48072000 - 48072fff - * I2C2 L4 48073000 - 48073fff - * McBSP1 Mod 48074000 - 48074fff - * McBSP1 L4 48075000 - 48075fff - * McBSP2 Mod 48076000 - 48076fff - * McBSP2 L4 48077000 - 48077fff - * GPTIMER3 Mod 48078000 - 48078fff - * GPTIMER3 L4 48079000 - 48079fff - * GPTIMER4 Mod 4807a000 - 4807afff - * GPTIMER4 L4 4807b000 - 4807bfff - * GPTIMER5 Mod 4807c000 - 4807cfff - * GPTIMER5 L4 4807d000 - 4807dfff - * GPTIMER6 Mod 4807e000 - 4807efff - * GPTIMER6 L4 4807f000 - 4807ffff - * GPTIMER7 Mod 48080000 - 48080fff - * GPTIMER7 L4 48081000 - 48081fff - * GPTIMER8 Mod 48082000 - 48082fff - * GPTIMER8 L4 48083000 - 48083fff - * GPTIMER9 Mod 48084000 - 48084fff - * GPTIMER9 L4 48085000 - 48085fff - * GPTIMER10 Mod 48086000 - 48086fff - * GPTIMER10 L4 48087000 - 48087fff - * GPTIMER11 Mod 48088000 - 48088fff - * GPTIMER11 L4 48089000 - 48089fff - * GPTIMER12 Mod 4808a000 - 4808afff - * GPTIMER12 L4 4808b000 - 4808bfff - * EAC Mod 48090000 - 48090fff - * EAC L4 48091000 - 48091fff - * FAC Mod 48092000 - 48092fff - * FAC L4 48093000 - 48093fff - * MAILBOX Mod 48094000 - 48094fff - * MAILBOX L4 48095000 - 48095fff - * SPI1 Mod 48098000 - 48098fff - * SPI1 L4 48099000 - 48099fff - * SPI2 Mod 4809a000 - 4809afff - * SPI2 L4 4809b000 - 4809bfff - * MMC/SDIO Mod 4809c000 - 4809cfff - * MMC/SDIO L4 4809d000 - 4809dfff - * MS_PRO Mod 4809e000 - 4809efff - * MS_PRO L4 4809f000 - 4809ffff - * RNG Mod 480a0000 - 480a0fff - * RNG L4 480a1000 - 480a1fff - * DES3DES Mod 480a2000 - 480a2fff - * DES3DES L4 480a3000 - 480a3fff - * SHA1MD5 Mod 480a4000 - 480a4fff - * SHA1MD5 L4 480a5000 - 480a5fff - * AES Mod 480a6000 - 480a6fff - * AES L4 480a7000 - 480a7fff - * PKA Mod 480a8000 - 480a9fff - * PKA L4 480aa000 - 480aafff - * MG Mod 480b0000 - 480b0fff - * MG L4 480b1000 - 480b1fff - * HDQ/1-wire Mod 480b2000 - 480b2fff - * HDQ/1-wire L4 480b3000 - 480b3fff - * MPU interrupt 480fe000 - 480fefff - * STI channel base 54000000 - 5400ffff - * IVA RAM 5c000000 - 5c01ffff - * IVA ROM 5c020000 - 5c027fff - * IMG_BUF_A 5c040000 - 5c040fff - * IMG_BUF_B 5c042000 - 5c042fff - * VLCDS 5c048000 - 5c0487ff - * IMX_COEF 5c049000 - 5c04afff - * IMX_CMD 5c051000 - 5c051fff - * VLCDQ 5c053000 - 5c0533ff - * VLCDH 5c054000 - 5c054fff - * SEQ_CMD 5c055000 - 5c055fff - * IMX_REG 5c056000 - 5c0560ff - * VLCD_REG 5c056100 - 5c0561ff - * SEQ_REG 5c056200 - 5c0562ff - * IMG_BUF_REG 5c056300 - 5c0563ff - * SEQIRQ_REG 5c056400 - 5c0564ff - * OCP_REG 5c060000 - 5c060fff - * SYSC_REG 5c070000 - 5c070fff - * MMU_REG 5d000000 - 5d000fff - * sDMA R 68000400 - 680005ff - * sDMA W 68000600 - 680007ff - * Display Control 68000800 - 680009ff - * DSP subsystem 68000a00 - 68000bff - * MPU subsystem 68000c00 - 68000dff - * IVA subsystem 68001000 - 680011ff - * USB 68001200 - 680013ff - * Camera 68001400 - 680015ff - * VLYNQ (firewall) 68001800 - 68001bff - * VLYNQ 68001e00 - 68001fff - * SSI 68002000 - 680021ff - * L4 68002400 - 680025ff - * DSP (firewall) 68002800 - 68002bff - * DSP subsystem 68002e00 - 68002fff - * IVA (firewall) 68003000 - 680033ff - * IVA 68003600 - 680037ff - * GFX 68003a00 - 68003bff - * CMDWR emulation 68003c00 - 68003dff - * SMS 68004000 - 680041ff - * OCM 68004200 - 680043ff - * GPMC 68004400 - 680045ff - * RAM (firewall) 68005000 - 680053ff - * RAM (err login) 68005400 - 680057ff - * ROM (firewall) 68005800 - 68005bff - * ROM (err login) 68005c00 - 68005fff - * GPMC (firewall) 68006000 - 680063ff - * GPMC (err login) 68006400 - 680067ff - * SMS (err login) 68006c00 - 68006fff - * SMS registers 68008000 - 68008fff - * SDRC registers 68009000 - 68009fff - * GPMC registers 6800a000 6800afff - */ - - qemu_register_reset(omap2_mpu_reset, s); - - return s; -} diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmu-common.c')) system_ss.add(when: 'CONFIG_COLLIE', if_true: files('collie.c')) system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4_boards.c')) system_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) -system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap2.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_peripherals.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2838_peripherals.c')) system_ss.add(when: 'CONFIG_STRONGARM', if_true: files('strongarm.c')) -- 2.34.1 We've removed the OMAP2 SoC, so we can remove the OMAP2 GPIO device. (The source file remains, as it also has the model of the OMAP1 GPIO device.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-39-peter.maydell@linaro.org --- include/hw/arm/omap.h | 8 - hw/gpio/omap_gpio.c | 557 ------------------------------------------ 2 files changed, 565 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ typedef struct Omap1GpioState Omap1GpioState; DECLARE_INSTANCE_CHECKER(Omap1GpioState, OMAP1_GPIO, TYPE_OMAP1_GPIO) -#define TYPE_OMAP2_GPIO "omap2-gpio" -typedef struct Omap2GpioState Omap2GpioState; -DECLARE_INSTANCE_CHECKER(Omap2GpioState, OMAP2_GPIO, - TYPE_OMAP2_GPIO) - /* TODO: clock framework (see above) */ void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); -void omap2_gpio_set_iclk(Omap2GpioState *gpio, omap_clk clk); -void omap2_gpio_set_fclk(Omap2GpioState *gpio, uint8_t i, omap_clk clk); - /* OMAP2 l4 Interconnect */ struct omap_l4_s; struct omap_l4_region_s { diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ static void omap_gpio_reset(struct omap_gpio_s *s) s->pins = ~0; } -struct omap2_gpio_s { - qemu_irq irq[2]; - qemu_irq wkup; - qemu_irq *handler; - MemoryRegion iomem; - - uint8_t revision; - uint8_t config[2]; - uint32_t inputs; - uint32_t outputs; - uint32_t dir; - uint32_t level[2]; - uint32_t edge[2]; - uint32_t mask[2]; - uint32_t wumask; - uint32_t ints[2]; - uint32_t debounce; - uint8_t delay; -}; - -struct Omap2GpioState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - int mpu_model; - void *iclk; - void *fclk[6]; - int modulecount; - struct omap2_gpio_s *modules; - qemu_irq *handler; - int autoidle; - int gpo; -}; - -/* General-Purpose Interface of OMAP2/3 */ -static inline void omap2_gpio_module_int_update(struct omap2_gpio_s *s, - int line) -{ - qemu_set_irq(s->irq[line], s->ints[line] & s->mask[line]); -} - -static void omap2_gpio_module_wake(struct omap2_gpio_s *s, int line) -{ - if (!(s->config[0] & (1 << 2))) /* ENAWAKEUP */ - return; - if (!(s->config[0] & (3 << 3))) /* Force Idle */ - return; - if (!(s->wumask & (1 << line))) - return; - - qemu_irq_raise(s->wkup); -} - -static inline void omap2_gpio_module_out_update(struct omap2_gpio_s *s, - uint32_t diff) -{ - int ln; - - s->outputs ^= diff; - diff &= ~s->dir; - while ((ln = ctz32(diff)) != 32) { - qemu_set_irq(s->handler[ln], (s->outputs >> ln) & 1); - diff &= ~(1 << ln); - } -} - -static void omap2_gpio_module_level_update(struct omap2_gpio_s *s, int line) -{ - s->ints[line] |= s->dir & - ((s->inputs & s->level[1]) | (~s->inputs & s->level[0])); - omap2_gpio_module_int_update(s, line); -} - -static inline void omap2_gpio_module_int(struct omap2_gpio_s *s, int line) -{ - s->ints[0] |= 1 << line; - omap2_gpio_module_int_update(s, 0); - s->ints[1] |= 1 << line; - omap2_gpio_module_int_update(s, 1); - omap2_gpio_module_wake(s, line); -} - -static void omap2_gpio_set(void *opaque, int line, int level) -{ - Omap2GpioState *p = opaque; - struct omap2_gpio_s *s = &p->modules[line >> 5]; - - line &= 31; - if (level) { - if (s->dir & (1 << line) & ((~s->inputs & s->edge[0]) | s->level[1])) - omap2_gpio_module_int(s, line); - s->inputs |= 1 << line; - } else { - if (s->dir & (1 << line) & ((s->inputs & s->edge[1]) | s->level[0])) - omap2_gpio_module_int(s, line); - s->inputs &= ~(1 << line); - } -} - -static void omap2_gpio_module_reset(struct omap2_gpio_s *s) -{ - s->config[0] = 0; - s->config[1] = 2; - s->ints[0] = 0; - s->ints[1] = 0; - s->mask[0] = 0; - s->mask[1] = 0; - s->wumask = 0; - s->dir = ~0; - s->level[0] = 0; - s->level[1] = 0; - s->edge[0] = 0; - s->edge[1] = 0; - s->debounce = 0; - s->delay = 0; -} - -static uint32_t omap2_gpio_module_read(void *opaque, hwaddr addr) -{ - struct omap2_gpio_s *s = opaque; - - switch (addr) { - case 0x00: /* GPIO_REVISION */ - return s->revision; - - case 0x10: /* GPIO_SYSCONFIG */ - return s->config[0]; - - case 0x14: /* GPIO_SYSSTATUS */ - return 0x01; - - case 0x18: /* GPIO_IRQSTATUS1 */ - return s->ints[0]; - - case 0x1c: /* GPIO_IRQENABLE1 */ - case 0x60: /* GPIO_CLEARIRQENABLE1 */ - case 0x64: /* GPIO_SETIRQENABLE1 */ - return s->mask[0]; - - case 0x20: /* GPIO_WAKEUPENABLE */ - case 0x80: /* GPIO_CLEARWKUENA */ - case 0x84: /* GPIO_SETWKUENA */ - return s->wumask; - - case 0x28: /* GPIO_IRQSTATUS2 */ - return s->ints[1]; - - case 0x2c: /* GPIO_IRQENABLE2 */ - case 0x70: /* GPIO_CLEARIRQENABLE2 */ - case 0x74: /* GPIO_SETIREQNEABLE2 */ - return s->mask[1]; - - case 0x30: /* GPIO_CTRL */ - return s->config[1]; - - case 0x34: /* GPIO_OE */ - return s->dir; - - case 0x38: /* GPIO_DATAIN */ - return s->inputs; - - case 0x3c: /* GPIO_DATAOUT */ - case 0x90: /* GPIO_CLEARDATAOUT */ - case 0x94: /* GPIO_SETDATAOUT */ - return s->outputs; - - case 0x40: /* GPIO_LEVELDETECT0 */ - return s->level[0]; - - case 0x44: /* GPIO_LEVELDETECT1 */ - return s->level[1]; - - case 0x48: /* GPIO_RISINGDETECT */ - return s->edge[0]; - - case 0x4c: /* GPIO_FALLINGDETECT */ - return s->edge[1]; - - case 0x50: /* GPIO_DEBOUNCENABLE */ - return s->debounce; - - case 0x54: /* GPIO_DEBOUNCINGTIME */ - return s->delay; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap2_gpio_module_write(void *opaque, hwaddr addr, - uint32_t value) -{ - struct omap2_gpio_s *s = opaque; - uint32_t diff; - int ln; - - switch (addr) { - case 0x00: /* GPIO_REVISION */ - case 0x14: /* GPIO_SYSSTATUS */ - case 0x38: /* GPIO_DATAIN */ - OMAP_RO_REG(addr); - break; - - case 0x10: /* GPIO_SYSCONFIG */ - if (((value >> 3) & 3) == 3) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Illegal IDLEMODE value: 3\n", __func__); - } - if (value & 2) - omap2_gpio_module_reset(s); - s->config[0] = value & 0x1d; - break; - - case 0x18: /* GPIO_IRQSTATUS1 */ - if (s->ints[0] & value) { - s->ints[0] &= ~value; - omap2_gpio_module_level_update(s, 0); - } - break; - - case 0x1c: /* GPIO_IRQENABLE1 */ - s->mask[0] = value; - omap2_gpio_module_int_update(s, 0); - break; - - case 0x20: /* GPIO_WAKEUPENABLE */ - s->wumask = value; - break; - - case 0x28: /* GPIO_IRQSTATUS2 */ - if (s->ints[1] & value) { - s->ints[1] &= ~value; - omap2_gpio_module_level_update(s, 1); - } - break; - - case 0x2c: /* GPIO_IRQENABLE2 */ - s->mask[1] = value; - omap2_gpio_module_int_update(s, 1); - break; - - case 0x30: /* GPIO_CTRL */ - s->config[1] = value & 7; - break; - - case 0x34: /* GPIO_OE */ - diff = s->outputs & (s->dir ^ value); - s->dir = value; - - value = s->outputs & ~s->dir; - while ((ln = ctz32(diff)) != 32) { - diff &= ~(1 << ln); - qemu_set_irq(s->handler[ln], (value >> ln) & 1); - } - - omap2_gpio_module_level_update(s, 0); - omap2_gpio_module_level_update(s, 1); - break; - - case 0x3c: /* GPIO_DATAOUT */ - omap2_gpio_module_out_update(s, s->outputs ^ value); - break; - - case 0x40: /* GPIO_LEVELDETECT0 */ - s->level[0] = value; - omap2_gpio_module_level_update(s, 0); - omap2_gpio_module_level_update(s, 1); - break; - - case 0x44: /* GPIO_LEVELDETECT1 */ - s->level[1] = value; - omap2_gpio_module_level_update(s, 0); - omap2_gpio_module_level_update(s, 1); - break; - - case 0x48: /* GPIO_RISINGDETECT */ - s->edge[0] = value; - break; - - case 0x4c: /* GPIO_FALLINGDETECT */ - s->edge[1] = value; - break; - - case 0x50: /* GPIO_DEBOUNCENABLE */ - s->debounce = value; - break; - - case 0x54: /* GPIO_DEBOUNCINGTIME */ - s->delay = value; - break; - - case 0x60: /* GPIO_CLEARIRQENABLE1 */ - s->mask[0] &= ~value; - omap2_gpio_module_int_update(s, 0); - break; - - case 0x64: /* GPIO_SETIRQENABLE1 */ - s->mask[0] |= value; - omap2_gpio_module_int_update(s, 0); - break; - - case 0x70: /* GPIO_CLEARIRQENABLE2 */ - s->mask[1] &= ~value; - omap2_gpio_module_int_update(s, 1); - break; - - case 0x74: /* GPIO_SETIREQNEABLE2 */ - s->mask[1] |= value; - omap2_gpio_module_int_update(s, 1); - break; - - case 0x80: /* GPIO_CLEARWKUENA */ - s->wumask &= ~value; - break; - - case 0x84: /* GPIO_SETWKUENA */ - s->wumask |= value; - break; - - case 0x90: /* GPIO_CLEARDATAOUT */ - omap2_gpio_module_out_update(s, s->outputs & value); - break; - - case 0x94: /* GPIO_SETDATAOUT */ - omap2_gpio_module_out_update(s, ~s->outputs & value); - break; - - default: - OMAP_BAD_REG(addr); - return; - } -} - -static uint64_t omap2_gpio_module_readp(void *opaque, hwaddr addr, - unsigned size) -{ - return omap2_gpio_module_read(opaque, addr & ~3) >> ((addr & 3) << 3); -} - -static void omap2_gpio_module_writep(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - uint32_t cur = 0; - uint32_t mask = 0xffff; - - if (size == 4) { - omap2_gpio_module_write(opaque, addr, value); - return; - } - - switch (addr & ~3) { - case 0x00: /* GPIO_REVISION */ - case 0x14: /* GPIO_SYSSTATUS */ - case 0x38: /* GPIO_DATAIN */ - OMAP_RO_REG(addr); - break; - - case 0x10: /* GPIO_SYSCONFIG */ - case 0x1c: /* GPIO_IRQENABLE1 */ - case 0x20: /* GPIO_WAKEUPENABLE */ - case 0x2c: /* GPIO_IRQENABLE2 */ - case 0x30: /* GPIO_CTRL */ - case 0x34: /* GPIO_OE */ - case 0x3c: /* GPIO_DATAOUT */ - case 0x40: /* GPIO_LEVELDETECT0 */ - case 0x44: /* GPIO_LEVELDETECT1 */ - case 0x48: /* GPIO_RISINGDETECT */ - case 0x4c: /* GPIO_FALLINGDETECT */ - case 0x50: /* GPIO_DEBOUNCENABLE */ - case 0x54: /* GPIO_DEBOUNCINGTIME */ - cur = omap2_gpio_module_read(opaque, addr & ~3) & - ~(mask << ((addr & 3) << 3)); - - /* Fall through. */ - case 0x18: /* GPIO_IRQSTATUS1 */ - case 0x28: /* GPIO_IRQSTATUS2 */ - case 0x60: /* GPIO_CLEARIRQENABLE1 */ - case 0x64: /* GPIO_SETIRQENABLE1 */ - case 0x70: /* GPIO_CLEARIRQENABLE2 */ - case 0x74: /* GPIO_SETIREQNEABLE2 */ - case 0x80: /* GPIO_CLEARWKUENA */ - case 0x84: /* GPIO_SETWKUENA */ - case 0x90: /* GPIO_CLEARDATAOUT */ - case 0x94: /* GPIO_SETDATAOUT */ - value <<= (addr & 3) << 3; - omap2_gpio_module_write(opaque, addr, cur | value); - break; - - default: - OMAP_BAD_REG(addr); - return; - } -} - -static const MemoryRegionOps omap2_gpio_module_ops = { - .read = omap2_gpio_module_readp, - .write = omap2_gpio_module_writep, - .valid.min_access_size = 1, - .valid.max_access_size = 4, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - static void omap_gpif_reset(DeviceState *dev) { Omap1GpioState *s = OMAP1_GPIO(dev); @@ -XXX,XX +XXX,XX @@ static void omap_gpif_reset(DeviceState *dev) omap_gpio_reset(&s->omap1); } -static void omap2_gpif_reset(DeviceState *dev) -{ - Omap2GpioState *s = OMAP2_GPIO(dev); - int i; - - for (i = 0; i < s->modulecount; i++) { - omap2_gpio_module_reset(&s->modules[i]); - } - s->autoidle = 0; - s->gpo = 0; -} - -static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) -{ - Omap2GpioState *s = opaque; - - switch (addr) { - case 0x00: /* IPGENERICOCPSPL_REVISION */ - return 0x18; - - case 0x10: /* IPGENERICOCPSPL_SYSCONFIG */ - return s->autoidle; - - case 0x14: /* IPGENERICOCPSPL_SYSSTATUS */ - return 0x01; - - case 0x18: /* IPGENERICOCPSPL_IRQSTATUS */ - return 0x00; - - case 0x40: /* IPGENERICOCPSPL_GPO */ - return s->gpo; - - case 0x50: /* IPGENERICOCPSPL_GPI */ - return 0x00; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap2_gpif_top_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - Omap2GpioState *s = opaque; - - switch (addr) { - case 0x00: /* IPGENERICOCPSPL_REVISION */ - case 0x14: /* IPGENERICOCPSPL_SYSSTATUS */ - case 0x18: /* IPGENERICOCPSPL_IRQSTATUS */ - case 0x50: /* IPGENERICOCPSPL_GPI */ - OMAP_RO_REG(addr); - break; - - case 0x10: /* IPGENERICOCPSPL_SYSCONFIG */ - if (value & (1 << 1)) /* SOFTRESET */ - omap2_gpif_reset(DEVICE(s)); - s->autoidle = value & 1; - break; - - case 0x40: /* IPGENERICOCPSPL_GPO */ - s->gpo = value & 1; - break; - - default: - OMAP_BAD_REG(addr); - return; - } -} - -static const MemoryRegionOps omap2_gpif_top_ops = { - .read = omap2_gpif_top_read, - .write = omap2_gpif_top_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - static void omap_gpio_init(Object *obj) { DeviceState *dev = DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void omap_gpio_realize(DeviceState *dev, Error **errp) } } -static void omap2_gpio_realize(DeviceState *dev, Error **errp) -{ - Omap2GpioState *s = OMAP2_GPIO(dev); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - int i; - - if (!s->iclk) { - error_setg(errp, "omap2-gpio: iclk not connected"); - return; - } - - s->modulecount = s->mpu_model < omap2430 ? 4 - : s->mpu_model < omap3430 ? 5 - : 6; - - if (s->mpu_model < omap3430) { - memory_region_init_io(&s->iomem, OBJECT(dev), &omap2_gpif_top_ops, s, - "omap2.gpio", 0x1000); - sysbus_init_mmio(sbd, &s->iomem); - } - - s->modules = g_new0(struct omap2_gpio_s, s->modulecount); - s->handler = g_new0(qemu_irq, s->modulecount * 32); - qdev_init_gpio_in(dev, omap2_gpio_set, s->modulecount * 32); - qdev_init_gpio_out(dev, s->handler, s->modulecount * 32); - - for (i = 0; i < s->modulecount; i++) { - struct omap2_gpio_s *m = &s->modules[i]; - - if (!s->fclk[i]) { - error_setg(errp, "omap2-gpio: fclk%d not connected", i); - return; - } - - m->revision = (s->mpu_model < omap3430) ? 0x18 : 0x25; - m->handler = &s->handler[i * 32]; - sysbus_init_irq(sbd, &m->irq[0]); /* mpu irq */ - sysbus_init_irq(sbd, &m->irq[1]); /* dsp irq */ - sysbus_init_irq(sbd, &m->wkup); - memory_region_init_io(&m->iomem, OBJECT(dev), &omap2_gpio_module_ops, m, - "omap.gpio-module", 0x1000); - sysbus_init_mmio(sbd, &m->iomem); - } -} - void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk) { gpio->clk = clk; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_gpio_info = { .class_init = omap_gpio_class_init, }; -void omap2_gpio_set_iclk(Omap2GpioState *gpio, omap_clk clk) -{ - gpio->iclk = clk; -} - -void omap2_gpio_set_fclk(Omap2GpioState *gpio, uint8_t i, omap_clk clk) -{ - assert(i <= 5); - gpio->fclk[i] = clk; -} - -static Property omap2_gpio_properties[] = { - DEFINE_PROP_INT32("mpu_model", Omap2GpioState, mpu_model, 0), - DEFINE_PROP_END_OF_LIST(), -}; - -static void omap2_gpio_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = omap2_gpio_realize; - device_class_set_legacy_reset(dc, omap2_gpif_reset); - device_class_set_props(dc, omap2_gpio_properties); - /* Reason: pointer properties "iclk", "fclk0", ..., "fclk5" */ - dc->user_creatable = false; -} - -static const TypeInfo omap2_gpio_info = { - .name = TYPE_OMAP2_GPIO, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(Omap2GpioState), - .class_init = omap2_gpio_class_init, -}; - static void omap_gpio_register_types(void) { type_register_static(&omap_gpio_info); - type_register_static(&omap2_gpio_info); } type_init(omap_gpio_register_types) -- 2.34.1 Remove the OMAP2 specific code from omap_uart.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-40-peter.maydell@linaro.org --- include/hw/arm/omap.h | 5 -- hw/char/omap_uart.c | 113 ------------------------------------------ 2 files changed, 118 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ struct omap_uart_s *omap_uart_init(hwaddr base, qemu_irq irq, omap_clk fclk, omap_clk iclk, qemu_irq txdma, qemu_irq rxdma, const char *label, Chardev *chr); -struct omap_uart_s *omap2_uart_init(MemoryRegion *sysmem, - struct omap_target_agent_s *ta, - qemu_irq irq, omap_clk fclk, omap_clk iclk, - qemu_irq txdma, qemu_irq rxdma, - const char *label, Chardev *chr); void omap_uart_reset(struct omap_uart_s *s); struct omap_mpuio_s; diff --git a/hw/char/omap_uart.c b/hw/char/omap_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/omap_uart.c +++ b/hw/char/omap_uart.c @@ -XXX,XX +XXX,XX @@ struct omap_uart_s { MemoryRegion iomem; hwaddr base; SerialMM *serial; /* TODO */ - struct omap_target_agent_s *ta; omap_clk fclk; qemu_irq irq; @@ -XXX,XX +XXX,XX @@ struct omap_uart_s { uint8_t syscontrol; uint8_t wkup; uint8_t cfps; - uint8_t mdr[2]; - uint8_t scr; uint8_t clksel; }; @@ -XXX,XX +XXX,XX @@ struct omap_uart_s *omap_uart_init(hwaddr base, DEVICE_NATIVE_ENDIAN); return s; } - -static uint64_t omap_uart_read(void *opaque, hwaddr addr, unsigned size) -{ - struct omap_uart_s *s = opaque; - - if (size == 4) { - return omap_badwidth_read8(opaque, addr); - } - - switch (addr) { - case 0x20: /* MDR1 */ - return s->mdr[0]; - case 0x24: /* MDR2 */ - return s->mdr[1]; - case 0x40: /* SCR */ - return s->scr; - case 0x44: /* SSR */ - return 0x0; - case 0x48: /* EBLR (OMAP2) */ - return s->eblr; - case 0x4C: /* OSC_12M_SEL (OMAP1) */ - return s->clksel; - case 0x50: /* MVR */ - return 0x30; - case 0x54: /* SYSC (OMAP2) */ - return s->syscontrol; - case 0x58: /* SYSS (OMAP2) */ - return 1; - case 0x5c: /* WER (OMAP2) */ - return s->wkup; - case 0x60: /* CFPS (OMAP2) */ - return s->cfps; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_uart_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_uart_s *s = opaque; - - if (size == 4) { - omap_badwidth_write8(opaque, addr, value); - return; - } - - switch (addr) { - case 0x20: /* MDR1 */ - s->mdr[0] = value & 0x7f; - break; - case 0x24: /* MDR2 */ - s->mdr[1] = value & 0xff; - break; - case 0x40: /* SCR */ - s->scr = value & 0xff; - break; - case 0x48: /* EBLR (OMAP2) */ - s->eblr = value & 0xff; - break; - case 0x4C: /* OSC_12M_SEL (OMAP1) */ - s->clksel = value & 1; - break; - case 0x44: /* SSR */ - case 0x50: /* MVR */ - case 0x58: /* SYSS (OMAP2) */ - OMAP_RO_REG(addr); - break; - case 0x54: /* SYSC (OMAP2) */ - s->syscontrol = value & 0x1d; - if (value & 2) { - omap_uart_reset(s); - } - break; - case 0x5c: /* WER (OMAP2) */ - s->wkup = value & 0x7f; - break; - case 0x60: /* CFPS (OMAP2) */ - s->cfps = value & 0xff; - break; - default: - OMAP_BAD_REG(addr); - } -} - -static const MemoryRegionOps omap_uart_ops = { - .read = omap_uart_read, - .write = omap_uart_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -struct omap_uart_s *omap2_uart_init(MemoryRegion *sysmem, - struct omap_target_agent_s *ta, - qemu_irq irq, omap_clk fclk, omap_clk iclk, - qemu_irq txdma, qemu_irq rxdma, - const char *label, Chardev *chr) -{ - hwaddr base = omap_l4_attach(ta, 0, NULL); - struct omap_uart_s *s = omap_uart_init(base, irq, - fclk, iclk, txdma, rxdma, label, chr); - - memory_region_init_io(&s->iomem, NULL, &omap_uart_ops, s, "omap.uart", 0x100); - - s->ta = ta; - - memory_region_add_subregion(sysmem, base + 0x20, &s->iomem); - - return s; -} -- 2.34.1 Remove the OMAP2 specific code from omap_intc.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-41-peter.maydell@linaro.org --- hw/intc/omap_intc.c | 276 -------------------------------------------- 1 file changed, 276 deletions(-) diff --git a/hw/intc/omap_intc.c b/hw/intc/omap_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/omap_intc.c +++ b/hw/intc/omap_intc.c @@ -XXX,XX +XXX,XX @@ struct OMAPIntcState { int level_only; uint32_t size; - uint8_t revision; - /* state */ uint32_t new_agr[2]; int sir_intr[2]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr(void *opaque, int irq, int req) } } -/* Simplified version with no edge detection */ -static void omap_set_intr_noedge(void *opaque, int irq, int req) -{ - OMAPIntcState *ih = opaque; - uint32_t rise; - - struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; - int n = irq & 31; - - if (req) { - rise = ~bank->inputs & (1 << n); - if (rise) { - bank->irqs |= bank->inputs |= rise; - omap_inth_update(ih, 0); - omap_inth_update(ih, 1); - } - } else - bank->irqs = (bank->inputs &= ~(1 << n)) | bank->swi; -} - static uint64_t omap_inth_read(void *opaque, hwaddr addr, unsigned size) { @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_intc_info = { .class_init = omap_intc_class_init, }; -static uint64_t omap2_inth_read(void *opaque, hwaddr addr, - unsigned size) -{ - OMAPIntcState *s = opaque; - int offset = addr; - int bank_no, line_no; - struct omap_intr_handler_bank_s *bank = NULL; - - if ((offset & 0xf80) == 0x80) { - bank_no = (offset & 0x60) >> 5; - if (bank_no < s->nbanks) { - offset &= ~0x60; - bank = &s->bank[bank_no]; - } else { - OMAP_BAD_REG(addr); - return 0; - } - } - - switch (offset) { - case 0x00: /* INTC_REVISION */ - return s->revision; - - case 0x10: /* INTC_SYSCONFIG */ - return (s->autoidle >> 2) & 1; - - case 0x14: /* INTC_SYSSTATUS */ - return 1; /* RESETDONE */ - - case 0x40: /* INTC_SIR_IRQ */ - return s->sir_intr[0]; - - case 0x44: /* INTC_SIR_FIQ */ - return s->sir_intr[1]; - - case 0x48: /* INTC_CONTROL */ - return (!s->mask) << 2; /* GLOBALMASK */ - - case 0x4c: /* INTC_PROTECTION */ - return 0; - - case 0x50: /* INTC_IDLE */ - return s->autoidle & 3; - - /* Per-bank registers */ - case 0x80: /* INTC_ITR */ - return bank->inputs; - - case 0x84: /* INTC_MIR */ - return bank->mask; - - case 0x88: /* INTC_MIR_CLEAR */ - case 0x8c: /* INTC_MIR_SET */ - return 0; - - case 0x90: /* INTC_ISR_SET */ - return bank->swi; - - case 0x94: /* INTC_ISR_CLEAR */ - return 0; - - case 0x98: /* INTC_PENDING_IRQ */ - return bank->irqs & ~bank->mask & ~bank->fiq; - - case 0x9c: /* INTC_PENDING_FIQ */ - return bank->irqs & ~bank->mask & bank->fiq; - - /* Per-line registers */ - case 0x100 ... 0x300: /* INTC_ILR */ - bank_no = (offset - 0x100) >> 7; - if (bank_no > s->nbanks) - break; - bank = &s->bank[bank_no]; - line_no = (offset & 0x7f) >> 2; - return (bank->priority[line_no] << 2) | - ((bank->fiq >> line_no) & 1); - } - OMAP_BAD_REG(addr); - return 0; -} - -static void omap2_inth_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - OMAPIntcState *s = opaque; - int offset = addr; - int bank_no, line_no; - struct omap_intr_handler_bank_s *bank = NULL; - - if ((offset & 0xf80) == 0x80) { - bank_no = (offset & 0x60) >> 5; - if (bank_no < s->nbanks) { - offset &= ~0x60; - bank = &s->bank[bank_no]; - } else { - OMAP_BAD_REG(addr); - return; - } - } - - switch (offset) { - case 0x10: /* INTC_SYSCONFIG */ - s->autoidle &= 4; - s->autoidle |= (value & 1) << 2; - if (value & 2) { /* SOFTRESET */ - omap_inth_reset(DEVICE(s)); - } - return; - - case 0x48: /* INTC_CONTROL */ - s->mask = (value & 4) ? 0 : ~0; /* GLOBALMASK */ - if (value & 2) { /* NEWFIQAGR */ - qemu_set_irq(s->parent_intr[1], 0); - s->new_agr[1] = ~0; - omap_inth_update(s, 1); - } - if (value & 1) { /* NEWIRQAGR */ - qemu_set_irq(s->parent_intr[0], 0); - s->new_agr[0] = ~0; - omap_inth_update(s, 0); - } - return; - - case 0x4c: /* INTC_PROTECTION */ - /* TODO: Make a bitmap (or sizeof(char)map) of access privileges - * for every register, see Chapter 3 and 4 for privileged mode. */ - if (value & 1) - fprintf(stderr, "%s: protection mode enable attempt\n", - __func__); - return; - - case 0x50: /* INTC_IDLE */ - s->autoidle &= ~3; - s->autoidle |= value & 3; - return; - - /* Per-bank registers */ - case 0x84: /* INTC_MIR */ - bank->mask = value; - omap_inth_update(s, 0); - omap_inth_update(s, 1); - return; - - case 0x88: /* INTC_MIR_CLEAR */ - bank->mask &= ~value; - omap_inth_update(s, 0); - omap_inth_update(s, 1); - return; - - case 0x8c: /* INTC_MIR_SET */ - bank->mask |= value; - return; - - case 0x90: /* INTC_ISR_SET */ - bank->irqs |= bank->swi |= value; - omap_inth_update(s, 0); - omap_inth_update(s, 1); - return; - - case 0x94: /* INTC_ISR_CLEAR */ - bank->swi &= ~value; - bank->irqs = bank->swi & bank->inputs; - return; - - /* Per-line registers */ - case 0x100 ... 0x300: /* INTC_ILR */ - bank_no = (offset - 0x100) >> 7; - if (bank_no > s->nbanks) - break; - bank = &s->bank[bank_no]; - line_no = (offset & 0x7f) >> 2; - bank->priority[line_no] = (value >> 2) & 0x3f; - bank->fiq &= ~(1 << line_no); - bank->fiq |= (value & 1) << line_no; - return; - - case 0x00: /* INTC_REVISION */ - case 0x14: /* INTC_SYSSTATUS */ - case 0x40: /* INTC_SIR_IRQ */ - case 0x44: /* INTC_SIR_FIQ */ - case 0x80: /* INTC_ITR */ - case 0x98: /* INTC_PENDING_IRQ */ - case 0x9c: /* INTC_PENDING_FIQ */ - OMAP_RO_REG(addr); - return; - } - OMAP_BAD_REG(addr); -} - -static const MemoryRegionOps omap2_inth_mem_ops = { - .read = omap2_inth_read, - .write = omap2_inth_write, - .endianness = DEVICE_NATIVE_ENDIAN, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, -}; - -static void omap2_intc_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - OMAPIntcState *s = OMAP_INTC(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - s->level_only = 1; - s->nbanks = 3; - sysbus_init_irq(sbd, &s->parent_intr[0]); - sysbus_init_irq(sbd, &s->parent_intr[1]); - qdev_init_gpio_in(dev, omap_set_intr_noedge, s->nbanks * 32); - memory_region_init_io(&s->mmio, obj, &omap2_inth_mem_ops, s, - "omap2-intc", 0x1000); - sysbus_init_mmio(sbd, &s->mmio); -} - -static void omap2_intc_realize(DeviceState *dev, Error **errp) -{ - OMAPIntcState *s = OMAP_INTC(dev); - - if (!s->iclk) { - error_setg(errp, "omap2-intc: iclk not connected"); - return; - } - if (!s->fclk) { - error_setg(errp, "omap2-intc: fclk not connected"); - return; - } -} - -static Property omap2_intc_properties[] = { - DEFINE_PROP_UINT8("revision", OMAPIntcState, - revision, 0x21), - DEFINE_PROP_END_OF_LIST(), -}; - -static void omap2_intc_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - device_class_set_legacy_reset(dc, omap_inth_reset); - device_class_set_props(dc, omap2_intc_properties); - /* Reason: pointer property "iclk", "fclk" */ - dc->user_creatable = false; - dc->realize = omap2_intc_realize; -} - -static const TypeInfo omap2_intc_info = { - .name = "omap2-intc", - .parent = TYPE_OMAP_INTC, - .instance_init = omap2_intc_init, - .class_init = omap2_intc_class_init, -}; - static const TypeInfo omap_intc_type_info = { .name = TYPE_OMAP_INTC, .parent = TYPE_SYS_BUS_DEVICE, @@ -XXX,XX +XXX,XX @@ static void omap_intc_register_types(void) { type_register_static(&omap_intc_type_info); type_register_static(&omap_intc_info); - type_register_static(&omap2_intc_info); } type_init(omap_intc_register_types) -- 2.34.1 Remove the OMAP2 specific code from omap_mmc.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-42-peter.maydell@linaro.org --- include/hw/arm/omap.h | 5 ---- hw/sd/omap_mmc.c | 63 ------------------------------------------- 2 files changed, 68 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ struct omap_mmc_s *omap_mmc_init(hwaddr base, MemoryRegion *sysmem, BlockBackend *blk, qemu_irq irq, qemu_irq dma[], omap_clk clk); -struct omap_mmc_s *omap2_mmc_init(struct omap_target_agent_s *ta, - BlockBackend *blk, qemu_irq irq, qemu_irq dma[], - omap_clk fclk, omap_clk iclk); void omap_mmc_reset(struct omap_mmc_s *s); -void omap_mmc_handlers(struct omap_mmc_s *s, qemu_irq ro, qemu_irq cover); -void omap_mmc_enable(struct omap_mmc_s *s, int enable); /* omap_i2c.c */ I2CBus *omap_i2c_bus(DeviceState *omap_i2c); diff --git a/hw/sd/omap_mmc.c b/hw/sd/omap_mmc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/omap_mmc.c +++ b/hw/sd/omap_mmc.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_mmc_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static void omap_mmc_cover_cb(void *opaque, int line, int level) -{ - struct omap_mmc_s *host = opaque; - - if (!host->cdet_state && level) { - host->status |= 0x0002; - omap_mmc_interrupts_update(host); - if (host->cdet_wakeup) { - /* TODO: Assert wake-up */ - } - } - - if (host->cdet_state != level) { - qemu_set_irq(host->coverswitch, level); - host->cdet_state = level; - } -} - struct omap_mmc_s *omap_mmc_init(hwaddr base, MemoryRegion *sysmem, BlockBackend *blk, @@ -XXX,XX +XXX,XX @@ struct omap_mmc_s *omap_mmc_init(hwaddr base, return s; } - -struct omap_mmc_s *omap2_mmc_init(struct omap_target_agent_s *ta, - BlockBackend *blk, qemu_irq irq, qemu_irq dma[], - omap_clk fclk, omap_clk iclk) -{ - struct omap_mmc_s *s = g_new0(struct omap_mmc_s, 1); - - s->irq = irq; - s->dma = dma; - s->clk = fclk; - s->lines = 4; - s->rev = 2; - - memory_region_init_io(&s->iomem, NULL, &omap_mmc_ops, s, "omap.mmc", - omap_l4_region_size(ta, 0)); - omap_l4_attach(ta, 0, &s->iomem); - - /* Instantiate the storage */ - s->card = sd_init(blk, false); - if (s->card == NULL) { - exit(1); - } - - s->cdet = qemu_allocate_irq(omap_mmc_cover_cb, s, 0); - sd_set_cb(s->card, NULL, s->cdet); - - omap_mmc_reset(s); - - return s; -} - -void omap_mmc_handlers(struct omap_mmc_s *s, qemu_irq ro, qemu_irq cover) -{ - if (s->cdet) { - sd_set_cb(s->card, ro, s->cdet); - s->coverswitch = cover; - qemu_set_irq(cover, s->cdet_state); - } else - sd_set_cb(s->card, ro, cover); -} - -void omap_mmc_enable(struct omap_mmc_s *s, int enable) -{ - sd_enable(s->card, enable); -} -- 2.34.1 The omap_sdrc device is only in OMAP2, which we are removing. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-43-peter.maydell@linaro.org --- include/hw/arm/omap.h | 7 -- hw/misc/omap_sdrc.c | 167 ------------------------------------------ hw/misc/meson.build | 1 - 3 files changed, 175 deletions(-) delete mode 100644 hw/misc/omap_sdrc.c diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ hwaddr omap_l4_region_base(struct omap_target_agent_s *ta, hwaddr omap_l4_region_size(struct omap_target_agent_s *ta, int region); -/* OMAP2 SDRAM controller */ -struct omap_sdrc_s; -struct omap_sdrc_s *omap_sdrc_init(MemoryRegion *sysmem, - hwaddr base); -void omap_sdrc_reset(struct omap_sdrc_s *s); - /* OMAP2 general purpose memory controller */ struct omap_gpmc_s; struct omap_gpmc_s *omap_gpmc_init(struct omap_mpu_state_s *mpu, @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s { struct omap_gp_timer_s *gptimer[12]; struct omap_synctimer_s *synctimer; - struct omap_sdrc_s *sdrc; struct omap_gpmc_s *gpmc; struct omap_mcspi_s *mcspi[2]; diff --git a/hw/misc/omap_sdrc.c b/hw/misc/omap_sdrc.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/misc/omap_sdrc.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI OMAP SDRAM controller emulation. - * - * Copyright (C) 2007-2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) any later version of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ -#include "qemu/osdep.h" -#include "hw/arm/omap.h" - -/* SDRAM Controller Subsystem */ -struct omap_sdrc_s { - MemoryRegion iomem; - uint8_t config; -}; - -void omap_sdrc_reset(struct omap_sdrc_s *s) -{ - s->config = 0x10; -} - -static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, unsigned size) -{ - struct omap_sdrc_s *s = opaque; - - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x00: /* SDRC_REVISION */ - return 0x20; - - case 0x10: /* SDRC_SYSCONFIG */ - return s->config; - - case 0x14: /* SDRC_SYSSTATUS */ - return 1; /* RESETDONE */ - - case 0x40: /* SDRC_CS_CFG */ - case 0x44: /* SDRC_SHARING */ - case 0x48: /* SDRC_ERR_ADDR */ - case 0x4c: /* SDRC_ERR_TYPE */ - case 0x60: /* SDRC_DLLA_SCTRL */ - case 0x64: /* SDRC_DLLA_STATUS */ - case 0x68: /* SDRC_DLLB_CTRL */ - case 0x6c: /* SDRC_DLLB_STATUS */ - case 0x70: /* SDRC_POWER */ - case 0x80: /* SDRC_MCFG_0 */ - case 0x84: /* SDRC_MR_0 */ - case 0x88: /* SDRC_EMR1_0 */ - case 0x8c: /* SDRC_EMR2_0 */ - case 0x90: /* SDRC_EMR3_0 */ - case 0x94: /* SDRC_DCDL1_CTRL */ - case 0x98: /* SDRC_DCDL2_CTRL */ - case 0x9c: /* SDRC_ACTIM_CTRLA_0 */ - case 0xa0: /* SDRC_ACTIM_CTRLB_0 */ - case 0xa4: /* SDRC_RFR_CTRL_0 */ - case 0xa8: /* SDRC_MANUAL_0 */ - case 0xb0: /* SDRC_MCFG_1 */ - case 0xb4: /* SDRC_MR_1 */ - case 0xb8: /* SDRC_EMR1_1 */ - case 0xbc: /* SDRC_EMR2_1 */ - case 0xc0: /* SDRC_EMR3_1 */ - case 0xc4: /* SDRC_ACTIM_CTRLA_1 */ - case 0xc8: /* SDRC_ACTIM_CTRLB_1 */ - case 0xd4: /* SDRC_RFR_CTRL_1 */ - case 0xd8: /* SDRC_MANUAL_1 */ - return 0x00; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_sdrc_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_sdrc_s *s = opaque; - - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x00: /* SDRC_REVISION */ - case 0x14: /* SDRC_SYSSTATUS */ - case 0x48: /* SDRC_ERR_ADDR */ - case 0x64: /* SDRC_DLLA_STATUS */ - case 0x6c: /* SDRC_DLLB_STATUS */ - OMAP_RO_REG(addr); - return; - - case 0x10: /* SDRC_SYSCONFIG */ - if ((value >> 3) != 0x2) - fprintf(stderr, "%s: bad SDRAM idle mode %i\n", - __func__, (unsigned)value >> 3); - if (value & 2) - omap_sdrc_reset(s); - s->config = value & 0x18; - break; - - case 0x40: /* SDRC_CS_CFG */ - case 0x44: /* SDRC_SHARING */ - case 0x4c: /* SDRC_ERR_TYPE */ - case 0x60: /* SDRC_DLLA_SCTRL */ - case 0x68: /* SDRC_DLLB_CTRL */ - case 0x70: /* SDRC_POWER */ - case 0x80: /* SDRC_MCFG_0 */ - case 0x84: /* SDRC_MR_0 */ - case 0x88: /* SDRC_EMR1_0 */ - case 0x8c: /* SDRC_EMR2_0 */ - case 0x90: /* SDRC_EMR3_0 */ - case 0x94: /* SDRC_DCDL1_CTRL */ - case 0x98: /* SDRC_DCDL2_CTRL */ - case 0x9c: /* SDRC_ACTIM_CTRLA_0 */ - case 0xa0: /* SDRC_ACTIM_CTRLB_0 */ - case 0xa4: /* SDRC_RFR_CTRL_0 */ - case 0xa8: /* SDRC_MANUAL_0 */ - case 0xb0: /* SDRC_MCFG_1 */ - case 0xb4: /* SDRC_MR_1 */ - case 0xb8: /* SDRC_EMR1_1 */ - case 0xbc: /* SDRC_EMR2_1 */ - case 0xc0: /* SDRC_EMR3_1 */ - case 0xc4: /* SDRC_ACTIM_CTRLA_1 */ - case 0xc8: /* SDRC_ACTIM_CTRLB_1 */ - case 0xd4: /* SDRC_RFR_CTRL_1 */ - case 0xd8: /* SDRC_MANUAL_1 */ - break; - - default: - OMAP_BAD_REG(addr); - return; - } -} - -static const MemoryRegionOps omap_sdrc_ops = { - .read = omap_sdrc_read, - .write = omap_sdrc_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -struct omap_sdrc_s *omap_sdrc_init(MemoryRegion *sysmem, - hwaddr base) -{ - struct omap_sdrc_s *s = g_new0(struct omap_sdrc_s, 1); - - omap_sdrc_reset(s); - - memory_region_init_io(&s->iomem, NULL, &omap_sdrc_ops, s, "omap.sdrc", 0x1000); - memory_region_add_subregion(sysmem, base, &s->iomem); - - return s; -} diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_OMAP', if_true: files( 'omap_clk.c', 'omap_gpmc.c', 'omap_l4.c', - 'omap_sdrc.c', 'omap_tap.c', )) system_ss.add(when: 'CONFIG_RASPI', if_true: files( -- 2.34.1 The omap_gpmc device is only in OMAP2, which we are removing. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-44-peter.maydell@linaro.org --- include/hw/arm/omap.h | 11 - hw/misc/omap_gpmc.c | 898 ------------------------------------------ hw/misc/meson.build | 1 - 3 files changed, 910 deletions(-) delete mode 100644 hw/misc/omap_gpmc.c diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ hwaddr omap_l4_region_base(struct omap_target_agent_s *ta, hwaddr omap_l4_region_size(struct omap_target_agent_s *ta, int region); -/* OMAP2 general purpose memory controller */ -struct omap_gpmc_s; -struct omap_gpmc_s *omap_gpmc_init(struct omap_mpu_state_s *mpu, - hwaddr base, - qemu_irq irq, qemu_irq drq); -void omap_gpmc_reset(struct omap_gpmc_s *s); -void omap_gpmc_attach(struct omap_gpmc_s *s, int cs, MemoryRegion *iomem); -void omap_gpmc_attach_nand(struct omap_gpmc_s *s, int cs, DeviceState *nand); - /* * Common IRQ numbers for level 1 interrupt handler * See /usr/include/asm-arm/arch-omap/irqs.h in Linux. @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s { struct omap_gp_timer_s *gptimer[12]; struct omap_synctimer_s *synctimer; - struct omap_gpmc_s *gpmc; - struct omap_mcspi_s *mcspi[2]; struct omap_dss_s *dss; diff --git a/hw/misc/omap_gpmc.c b/hw/misc/omap_gpmc.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/misc/omap_gpmc.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI OMAP general purpose memory controller emulation. - * - * Copyright (C) 2007-2009 Nokia Corporation - * Original code written by Andrzej Zaborowski <andrew@openedhand.com> - * Enhancements for OMAP3 and NAND support written by Juha Riihimäki - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) any later version of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/block/flash.h" -#include "hw/arm/omap.h" -#include "exec/memory.h" -#include "exec/address-spaces.h" - -/* General-Purpose Memory Controller */ -struct omap_gpmc_s { - qemu_irq irq; - qemu_irq drq; - MemoryRegion iomem; - int accept_256; - - uint8_t revision; - uint8_t sysconfig; - uint16_t irqst; - uint16_t irqen; - uint16_t lastirq; - uint16_t timeout; - uint16_t config; - struct omap_gpmc_cs_file_s { - uint32_t config[7]; - MemoryRegion *iomem; - MemoryRegion container; - MemoryRegion nandiomem; - DeviceState *dev; - } cs_file[8]; - int ecc_cs; - int ecc_ptr; - uint32_t ecc_cfg; - ECCState ecc[9]; - struct prefetch { - uint32_t config1; /* GPMC_PREFETCH_CONFIG1 */ - uint32_t transfercount; /* GPMC_PREFETCH_CONFIG2:TRANSFERCOUNT */ - int startengine; /* GPMC_PREFETCH_CONTROL:STARTENGINE */ - int fifopointer; /* GPMC_PREFETCH_STATUS:FIFOPOINTER */ - int count; /* GPMC_PREFETCH_STATUS:COUNTVALUE */ - MemoryRegion iomem; - uint8_t fifo[64]; - } prefetch; -}; - -#define OMAP_GPMC_8BIT 0 -#define OMAP_GPMC_16BIT 1 -#define OMAP_GPMC_NOR 0 -#define OMAP_GPMC_NAND 2 - -static int omap_gpmc_devtype(struct omap_gpmc_cs_file_s *f) -{ - return (f->config[0] >> 10) & 3; -} - -static int omap_gpmc_devsize(struct omap_gpmc_cs_file_s *f) -{ - /* devsize field is really 2 bits but we ignore the high - * bit to ensure consistent behaviour if the guest sets - * it (values 2 and 3 are reserved in the TRM) - */ - return (f->config[0] >> 12) & 1; -} - -/* Extract the chip-select value from the prefetch config1 register */ -static int prefetch_cs(uint32_t config1) -{ - return (config1 >> 24) & 7; -} - -static int prefetch_threshold(uint32_t config1) -{ - return (config1 >> 8) & 0x7f; -} - -static void omap_gpmc_int_update(struct omap_gpmc_s *s) -{ - /* The TRM is a bit unclear, but it seems to say that - * the TERMINALCOUNTSTATUS bit is set only on the - * transition when the prefetch engine goes from - * active to inactive, whereas the FIFOEVENTSTATUS - * bit is held high as long as the fifo has at - * least THRESHOLD bytes available. - * So we do the latter here, but TERMINALCOUNTSTATUS - * is set elsewhere. - */ - if (s->prefetch.fifopointer >= prefetch_threshold(s->prefetch.config1)) { - s->irqst |= 1; - } - if ((s->irqen & s->irqst) != s->lastirq) { - s->lastirq = s->irqen & s->irqst; - qemu_set_irq(s->irq, s->lastirq); - } -} - -static void omap_gpmc_dma_update(struct omap_gpmc_s *s, int value) -{ - if (s->prefetch.config1 & 4) { - qemu_set_irq(s->drq, value); - } -} - -/* Access functions for when a NAND-like device is mapped into memory: - * all addresses in the region behave like accesses to the relevant - * GPMC_NAND_DATA_i register (which is actually implemented to call these) - */ -static uint64_t omap_nand_read(void *opaque, hwaddr addr, - unsigned size) -{ - struct omap_gpmc_cs_file_s *f = opaque; - uint64_t v; - nand_setpins(f->dev, 0, 0, 0, 1, 0); - switch (omap_gpmc_devsize(f)) { - case OMAP_GPMC_8BIT: - v = nand_getio(f->dev); - if (size == 1) { - return v; - } - v |= (nand_getio(f->dev) << 8); - if (size == 2) { - return v; - } - v |= (nand_getio(f->dev) << 16); - v |= (nand_getio(f->dev) << 24); - return v; - case OMAP_GPMC_16BIT: - v = nand_getio(f->dev); - if (size == 1) { - /* 8 bit read from 16 bit device : probably a guest bug */ - return v & 0xff; - } - if (size == 2) { - return v; - } - v |= (nand_getio(f->dev) << 16); - return v; - default: - abort(); - } -} - -static void omap_nand_setio(DeviceState *dev, uint64_t value, - int nandsize, int size) -{ - /* Write the specified value to the NAND device, respecting - * both size of the NAND device and size of the write access. - */ - switch (nandsize) { - case OMAP_GPMC_8BIT: - switch (size) { - case 1: - nand_setio(dev, value & 0xff); - break; - case 2: - nand_setio(dev, value & 0xff); - nand_setio(dev, (value >> 8) & 0xff); - break; - case 4: - default: - nand_setio(dev, value & 0xff); - nand_setio(dev, (value >> 8) & 0xff); - nand_setio(dev, (value >> 16) & 0xff); - nand_setio(dev, (value >> 24) & 0xff); - break; - } - break; - case OMAP_GPMC_16BIT: - switch (size) { - case 1: - /* writing to a 16bit device with 8bit access is probably a guest - * bug; pass the value through anyway. - */ - case 2: - nand_setio(dev, value & 0xffff); - break; - case 4: - default: - nand_setio(dev, value & 0xffff); - nand_setio(dev, (value >> 16) & 0xffff); - break; - } - break; - } -} - -static void omap_nand_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_gpmc_cs_file_s *f = opaque; - nand_setpins(f->dev, 0, 0, 0, 1, 0); - omap_nand_setio(f->dev, value, omap_gpmc_devsize(f), size); -} - -static const MemoryRegionOps omap_nand_ops = { - .read = omap_nand_read, - .write = omap_nand_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void fill_prefetch_fifo(struct omap_gpmc_s *s) -{ - /* Fill the prefetch FIFO by reading data from NAND. - * We do this synchronously, unlike the hardware which - * will do this asynchronously. We refill when the - * FIFO has THRESHOLD bytes free, and we always refill - * as much data as possible starting at the top end - * of the FIFO. - * (We have to refill at THRESHOLD rather than waiting - * for the FIFO to empty to allow for the case where - * the FIFO size isn't an exact multiple of THRESHOLD - * and we're doing DMA transfers.) - * This means we never need to handle wrap-around in - * the fifo-reading code, and the next byte of data - * to read is always fifo[63 - fifopointer]. - */ - int fptr; - int cs = prefetch_cs(s->prefetch.config1); - int is16bit = (((s->cs_file[cs].config[0] >> 12) & 3) != 0); - int bytes; - /* Don't believe the bit of the OMAP TRM that says that COUNTVALUE - * and TRANSFERCOUNT are in units of 16 bit words for 16 bit NAND. - * Instead believe the bit that says it is always a byte count. - */ - bytes = 64 - s->prefetch.fifopointer; - if (bytes > s->prefetch.count) { - bytes = s->prefetch.count; - } - if (is16bit) { - bytes &= ~1; - } - - s->prefetch.count -= bytes; - s->prefetch.fifopointer += bytes; - fptr = 64 - s->prefetch.fifopointer; - /* Move the existing data in the FIFO so it sits just - * before what we're about to read in - */ - while (fptr < (64 - bytes)) { - s->prefetch.fifo[fptr] = s->prefetch.fifo[fptr + bytes]; - fptr++; - } - while (fptr < 64) { - if (is16bit) { - uint32_t v = omap_nand_read(&s->cs_file[cs], 0, 2); - s->prefetch.fifo[fptr++] = v & 0xff; - s->prefetch.fifo[fptr++] = (v >> 8) & 0xff; - } else { - s->prefetch.fifo[fptr++] = omap_nand_read(&s->cs_file[cs], 0, 1); - } - } - if (s->prefetch.startengine && (s->prefetch.count == 0)) { - /* This was the final transfer: raise TERMINALCOUNTSTATUS */ - s->irqst |= 2; - s->prefetch.startengine = 0; - } - /* If there are any bytes in the FIFO at this point then - * we must raise a DMA request (either this is a final part - * transfer, or we filled the FIFO in which case we certainly - * have THRESHOLD bytes available) - */ - if (s->prefetch.fifopointer != 0) { - omap_gpmc_dma_update(s, 1); - } - omap_gpmc_int_update(s); -} - -/* Access functions for a NAND-like device when the prefetch/postwrite - * engine is enabled -- all addresses in the region behave alike: - * data is read or written to the FIFO. - */ -static uint64_t omap_gpmc_prefetch_read(void *opaque, hwaddr addr, - unsigned size) -{ - struct omap_gpmc_s *s = opaque; - uint32_t data; - if (s->prefetch.config1 & 1) { - /* The TRM doesn't define the behaviour if you read from the - * FIFO when the prefetch engine is in write mode. We choose - * to always return zero. - */ - return 0; - } - /* Note that trying to read an empty fifo repeats the last byte */ - if (s->prefetch.fifopointer) { - s->prefetch.fifopointer--; - } - data = s->prefetch.fifo[63 - s->prefetch.fifopointer]; - if (s->prefetch.fifopointer == - (64 - prefetch_threshold(s->prefetch.config1))) { - /* We've drained THRESHOLD bytes now. So deassert the - * DMA request, then refill the FIFO (which will probably - * assert it again.) - */ - omap_gpmc_dma_update(s, 0); - fill_prefetch_fifo(s); - } - omap_gpmc_int_update(s); - return data; -} - -static void omap_gpmc_prefetch_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_gpmc_s *s = opaque; - int cs = prefetch_cs(s->prefetch.config1); - if ((s->prefetch.config1 & 1) == 0) { - /* The TRM doesn't define the behaviour of writing to the - * FIFO when the prefetch engine is in read mode. We - * choose to ignore the write. - */ - return; - } - if (s->prefetch.count == 0) { - /* The TRM doesn't define the behaviour of writing to the - * FIFO if the transfer is complete. We choose to ignore. - */ - return; - } - /* The only reason we do any data buffering in postwrite - * mode is if we are talking to a 16 bit NAND device, in - * which case we need to buffer the first byte of the - * 16 bit word until the other byte arrives. - */ - int is16bit = (((s->cs_file[cs].config[0] >> 12) & 3) != 0); - if (is16bit) { - /* fifopointer alternates between 64 (waiting for first - * byte of word) and 63 (waiting for second byte) - */ - if (s->prefetch.fifopointer == 64) { - s->prefetch.fifo[0] = value; - s->prefetch.fifopointer--; - } else { - value = (value << 8) | s->prefetch.fifo[0]; - omap_nand_write(&s->cs_file[cs], 0, value, 2); - s->prefetch.count--; - s->prefetch.fifopointer = 64; - } - } else { - /* Just write the byte : fifopointer remains 64 at all times */ - omap_nand_write(&s->cs_file[cs], 0, value, 1); - s->prefetch.count--; - } - if (s->prefetch.count == 0) { - /* Final transfer: raise TERMINALCOUNTSTATUS */ - s->irqst |= 2; - s->prefetch.startengine = 0; - } - omap_gpmc_int_update(s); -} - -static const MemoryRegionOps omap_prefetch_ops = { - .read = omap_gpmc_prefetch_read, - .write = omap_gpmc_prefetch_write, - .endianness = DEVICE_NATIVE_ENDIAN, - .impl.min_access_size = 1, - .impl.max_access_size = 1, -}; - -static MemoryRegion *omap_gpmc_cs_memregion(struct omap_gpmc_s *s, int cs) -{ - /* Return the MemoryRegion* to map/unmap for this chipselect */ - struct omap_gpmc_cs_file_s *f = &s->cs_file[cs]; - if (omap_gpmc_devtype(f) == OMAP_GPMC_NOR) { - return f->iomem; - } - if ((s->prefetch.config1 & 0x80) && - (prefetch_cs(s->prefetch.config1) == cs)) { - /* The prefetch engine is enabled for this CS: map the FIFO */ - return &s->prefetch.iomem; - } - return &f->nandiomem; -} - -static void omap_gpmc_cs_map(struct omap_gpmc_s *s, int cs) -{ - struct omap_gpmc_cs_file_s *f = &s->cs_file[cs]; - uint32_t mask = (f->config[6] >> 8) & 0xf; - uint32_t base = f->config[6] & 0x3f; - uint32_t size; - - if (!f->iomem && !f->dev) { - return; - } - - if (!(f->config[6] & (1 << 6))) { - /* Do nothing unless CSVALID */ - return; - } - - /* TODO: check for overlapping regions and report access errors */ - if (mask != 0x8 && mask != 0xc && mask != 0xe && mask != 0xf - && !(s->accept_256 && !mask)) { - fprintf(stderr, "%s: invalid chip-select mask address (0x%x)\n", - __func__, mask); - } - - base <<= 24; - size = (0x0fffffff & ~(mask << 24)) + 1; - /* TODO: rather than setting the size of the mapping (which should be - * constant), the mask should cause wrapping of the address space, so - * that the same memory becomes accessible at every <i>size</i> bytes - * starting from <i>base</i>. */ - memory_region_init(&f->container, NULL, "omap-gpmc-file", size); - memory_region_add_subregion(&f->container, 0, - omap_gpmc_cs_memregion(s, cs)); - memory_region_add_subregion(get_system_memory(), base, - &f->container); -} - -static void omap_gpmc_cs_unmap(struct omap_gpmc_s *s, int cs) -{ - struct omap_gpmc_cs_file_s *f = &s->cs_file[cs]; - if (!(f->config[6] & (1 << 6))) { - /* Do nothing unless CSVALID */ - return; - } - if (!f->iomem && !f->dev) { - return; - } - memory_region_del_subregion(get_system_memory(), &f->container); - memory_region_del_subregion(&f->container, omap_gpmc_cs_memregion(s, cs)); - object_unparent(OBJECT(&f->container)); -} - -void omap_gpmc_reset(struct omap_gpmc_s *s) -{ - int i; - - s->sysconfig = 0; - s->irqst = 0; - s->irqen = 0; - omap_gpmc_int_update(s); - for (i = 0; i < 8; i++) { - /* This has to happen before we change any of the config - * used to determine which memory regions are mapped or unmapped. - */ - omap_gpmc_cs_unmap(s, i); - } - s->timeout = 0; - s->config = 0xa00; - s->prefetch.config1 = 0x00004000; - s->prefetch.transfercount = 0x00000000; - s->prefetch.startengine = 0; - s->prefetch.fifopointer = 0; - s->prefetch.count = 0; - for (i = 0; i < 8; i ++) { - s->cs_file[i].config[1] = 0x101001; - s->cs_file[i].config[2] = 0x020201; - s->cs_file[i].config[3] = 0x10031003; - s->cs_file[i].config[4] = 0x10f1111; - s->cs_file[i].config[5] = 0; - s->cs_file[i].config[6] = 0xf00; - /* In theory we could probe attached devices for some CFG1 - * bits here, but we just retain them across resets as they - * were set initially by omap_gpmc_attach(). - */ - if (i == 0) { - s->cs_file[i].config[0] &= 0x00433e00; - s->cs_file[i].config[6] |= 1 << 6; /* CSVALID */ - omap_gpmc_cs_map(s, i); - } else { - s->cs_file[i].config[0] &= 0x00403c00; - } - } - s->ecc_cs = 0; - s->ecc_ptr = 0; - s->ecc_cfg = 0x3fcff000; - for (i = 0; i < 9; i ++) - ecc_reset(&s->ecc[i]); -} - -static int gpmc_wordaccess_only(hwaddr addr) -{ - /* Return true if the register offset is to a register that - * only permits word width accesses. - * Non-word accesses are only OK for GPMC_NAND_DATA/ADDRESS/COMMAND - * for any chipselect. - */ - if (addr >= 0x60 && addr <= 0x1d4) { - int cs = (addr - 0x60) / 0x30; - addr -= cs * 0x30; - if (addr >= 0x7c && addr < 0x88) { - /* GPMC_NAND_COMMAND, GPMC_NAND_ADDRESS, GPMC_NAND_DATA */ - return 0; - } - } - return 1; -} - -static uint64_t omap_gpmc_read(void *opaque, hwaddr addr, - unsigned size) -{ - struct omap_gpmc_s *s = opaque; - int cs; - struct omap_gpmc_cs_file_s *f; - - if (size != 4 && gpmc_wordaccess_only(addr)) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x000: /* GPMC_REVISION */ - return s->revision; - - case 0x010: /* GPMC_SYSCONFIG */ - return s->sysconfig; - - case 0x014: /* GPMC_SYSSTATUS */ - return 1; /* RESETDONE */ - - case 0x018: /* GPMC_IRQSTATUS */ - return s->irqst; - - case 0x01c: /* GPMC_IRQENABLE */ - return s->irqen; - - case 0x040: /* GPMC_TIMEOUT_CONTROL */ - return s->timeout; - - case 0x044: /* GPMC_ERR_ADDRESS */ - case 0x048: /* GPMC_ERR_TYPE */ - return 0; - - case 0x050: /* GPMC_CONFIG */ - return s->config; - - case 0x054: /* GPMC_STATUS */ - return 0x001; - - case 0x060 ... 0x1d4: - cs = (addr - 0x060) / 0x30; - addr -= cs * 0x30; - f = s->cs_file + cs; - switch (addr) { - case 0x60: /* GPMC_CONFIG1 */ - return f->config[0]; - case 0x64: /* GPMC_CONFIG2 */ - return f->config[1]; - case 0x68: /* GPMC_CONFIG3 */ - return f->config[2]; - case 0x6c: /* GPMC_CONFIG4 */ - return f->config[3]; - case 0x70: /* GPMC_CONFIG5 */ - return f->config[4]; - case 0x74: /* GPMC_CONFIG6 */ - return f->config[5]; - case 0x78: /* GPMC_CONFIG7 */ - return f->config[6]; - case 0x84 ... 0x87: /* GPMC_NAND_DATA */ - if (omap_gpmc_devtype(f) == OMAP_GPMC_NAND) { - return omap_nand_read(f, 0, size); - } - return 0; - } - break; - - case 0x1e0: /* GPMC_PREFETCH_CONFIG1 */ - return s->prefetch.config1; - case 0x1e4: /* GPMC_PREFETCH_CONFIG2 */ - return s->prefetch.transfercount; - case 0x1ec: /* GPMC_PREFETCH_CONTROL */ - return s->prefetch.startengine; - case 0x1f0: /* GPMC_PREFETCH_STATUS */ - /* NB: The OMAP3 TRM is inconsistent about whether the GPMC - * FIFOTHRESHOLDSTATUS bit should be set when - * FIFOPOINTER > FIFOTHRESHOLD or when it is >= FIFOTHRESHOLD. - * Apparently the underlying functional spec from which the TRM was - * created states that the behaviour is ">=", and this also - * makes more conceptual sense. - */ - return (s->prefetch.fifopointer << 24) | - ((s->prefetch.fifopointer >= - ((s->prefetch.config1 >> 8) & 0x7f) ? 1 : 0) << 16) | - s->prefetch.count; - - case 0x1f4: /* GPMC_ECC_CONFIG */ - return s->ecc_cs; - case 0x1f8: /* GPMC_ECC_CONTROL */ - return s->ecc_ptr; - case 0x1fc: /* GPMC_ECC_SIZE_CONFIG */ - return s->ecc_cfg; - case 0x200 ... 0x220: /* GPMC_ECC_RESULT */ - cs = (addr & 0x1f) >> 2; - /* TODO: check correctness */ - return - ((s->ecc[cs].cp & 0x07) << 0) | - ((s->ecc[cs].cp & 0x38) << 13) | - ((s->ecc[cs].lp[0] & 0x1ff) << 3) | - ((s->ecc[cs].lp[1] & 0x1ff) << 19); - - case 0x230: /* GPMC_TESTMODE_CTRL */ - return 0; - case 0x234: /* GPMC_PSA_LSB */ - case 0x238: /* GPMC_PSA_MSB */ - return 0x00000000; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_gpmc_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_gpmc_s *s = opaque; - int cs; - struct omap_gpmc_cs_file_s *f; - - if (size != 4 && gpmc_wordaccess_only(addr)) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x000: /* GPMC_REVISION */ - case 0x014: /* GPMC_SYSSTATUS */ - case 0x054: /* GPMC_STATUS */ - case 0x1f0: /* GPMC_PREFETCH_STATUS */ - case 0x200 ... 0x220: /* GPMC_ECC_RESULT */ - case 0x234: /* GPMC_PSA_LSB */ - case 0x238: /* GPMC_PSA_MSB */ - OMAP_RO_REG(addr); - break; - - case 0x010: /* GPMC_SYSCONFIG */ - if ((value >> 3) == 0x3) - fprintf(stderr, "%s: bad SDRAM idle mode %"PRIi64"\n", - __func__, value >> 3); - if (value & 2) - omap_gpmc_reset(s); - s->sysconfig = value & 0x19; - break; - - case 0x018: /* GPMC_IRQSTATUS */ - s->irqst &= ~value; - omap_gpmc_int_update(s); - break; - - case 0x01c: /* GPMC_IRQENABLE */ - s->irqen = value & 0xf03; - omap_gpmc_int_update(s); - break; - - case 0x040: /* GPMC_TIMEOUT_CONTROL */ - s->timeout = value & 0x1ff1; - break; - - case 0x044: /* GPMC_ERR_ADDRESS */ - case 0x048: /* GPMC_ERR_TYPE */ - break; - - case 0x050: /* GPMC_CONFIG */ - s->config = value & 0xf13; - break; - - case 0x060 ... 0x1d4: - cs = (addr - 0x060) / 0x30; - addr -= cs * 0x30; - f = s->cs_file + cs; - switch (addr) { - case 0x60: /* GPMC_CONFIG1 */ - f->config[0] = value & 0xffef3e13; - break; - case 0x64: /* GPMC_CONFIG2 */ - f->config[1] = value & 0x001f1f8f; - break; - case 0x68: /* GPMC_CONFIG3 */ - f->config[2] = value & 0x001f1f8f; - break; - case 0x6c: /* GPMC_CONFIG4 */ - f->config[3] = value & 0x1f8f1f8f; - break; - case 0x70: /* GPMC_CONFIG5 */ - f->config[4] = value & 0x0f1f1f1f; - break; - case 0x74: /* GPMC_CONFIG6 */ - f->config[5] = value & 0x00000fcf; - break; - case 0x78: /* GPMC_CONFIG7 */ - if ((f->config[6] ^ value) & 0xf7f) { - omap_gpmc_cs_unmap(s, cs); - f->config[6] = value & 0x00000f7f; - omap_gpmc_cs_map(s, cs); - } - break; - case 0x7c ... 0x7f: /* GPMC_NAND_COMMAND */ - if (omap_gpmc_devtype(f) == OMAP_GPMC_NAND) { - nand_setpins(f->dev, 1, 0, 0, 1, 0); /* CLE */ - omap_nand_setio(f->dev, value, omap_gpmc_devsize(f), size); - } - break; - case 0x80 ... 0x83: /* GPMC_NAND_ADDRESS */ - if (omap_gpmc_devtype(f) == OMAP_GPMC_NAND) { - nand_setpins(f->dev, 0, 1, 0, 1, 0); /* ALE */ - omap_nand_setio(f->dev, value, omap_gpmc_devsize(f), size); - } - break; - case 0x84 ... 0x87: /* GPMC_NAND_DATA */ - if (omap_gpmc_devtype(f) == OMAP_GPMC_NAND) { - omap_nand_write(f, 0, value, size); - } - break; - default: - goto bad_reg; - } - break; - - case 0x1e0: /* GPMC_PREFETCH_CONFIG1 */ - if (!s->prefetch.startengine) { - uint32_t newconfig1 = value & 0x7f8f7fbf; - uint32_t changed; - changed = newconfig1 ^ s->prefetch.config1; - if (changed & (0x80 | 0x7000000)) { - /* Turning the engine on or off, or mapping it somewhere else. - * cs_map() and cs_unmap() check the prefetch config and - * overall CSVALID bits, so it is sufficient to unmap-and-map - * both the old cs and the new one. Note that we adhere to - * the "unmap/change config/map" order (and not unmap twice - * if newcs == oldcs), otherwise we'll try to delete the wrong - * memory region. - */ - int oldcs = prefetch_cs(s->prefetch.config1); - int newcs = prefetch_cs(newconfig1); - omap_gpmc_cs_unmap(s, oldcs); - if (oldcs != newcs) { - omap_gpmc_cs_unmap(s, newcs); - } - s->prefetch.config1 = newconfig1; - omap_gpmc_cs_map(s, oldcs); - if (oldcs != newcs) { - omap_gpmc_cs_map(s, newcs); - } - } else { - s->prefetch.config1 = newconfig1; - } - } - break; - - case 0x1e4: /* GPMC_PREFETCH_CONFIG2 */ - if (!s->prefetch.startengine) { - s->prefetch.transfercount = value & 0x3fff; - } - break; - - case 0x1ec: /* GPMC_PREFETCH_CONTROL */ - if (s->prefetch.startengine != (value & 1)) { - s->prefetch.startengine = value & 1; - if (s->prefetch.startengine) { - /* Prefetch engine start */ - s->prefetch.count = s->prefetch.transfercount; - if (s->prefetch.config1 & 1) { - /* Write */ - s->prefetch.fifopointer = 64; - } else { - /* Read */ - s->prefetch.fifopointer = 0; - fill_prefetch_fifo(s); - } - } else { - /* Prefetch engine forcibly stopped. The TRM - * doesn't define the behaviour if you do this. - * We clear the prefetch count, which means that - * we permit no more writes, and don't read any - * more data from NAND. The CPU can still drain - * the FIFO of unread data. - */ - s->prefetch.count = 0; - } - omap_gpmc_int_update(s); - } - break; - - case 0x1f4: /* GPMC_ECC_CONFIG */ - s->ecc_cs = 0x8f; - break; - case 0x1f8: /* GPMC_ECC_CONTROL */ - if (value & (1 << 8)) - for (cs = 0; cs < 9; cs ++) - ecc_reset(&s->ecc[cs]); - s->ecc_ptr = value & 0xf; - if (s->ecc_ptr == 0 || s->ecc_ptr > 9) { - s->ecc_ptr = 0; - s->ecc_cs &= ~1; - } - break; - case 0x1fc: /* GPMC_ECC_SIZE_CONFIG */ - s->ecc_cfg = value & 0x3fcff1ff; - break; - case 0x230: /* GPMC_TESTMODE_CTRL */ - if (value & 7) - fprintf(stderr, "%s: test mode enable attempt\n", __func__); - break; - - default: - bad_reg: - OMAP_BAD_REG(addr); - return; - } -} - -static const MemoryRegionOps omap_gpmc_ops = { - .read = omap_gpmc_read, - .write = omap_gpmc_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -struct omap_gpmc_s *omap_gpmc_init(struct omap_mpu_state_s *mpu, - hwaddr base, - qemu_irq irq, qemu_irq drq) -{ - int cs; - struct omap_gpmc_s *s = g_new0(struct omap_gpmc_s, 1); - - memory_region_init_io(&s->iomem, NULL, &omap_gpmc_ops, s, "omap-gpmc", 0x1000); - memory_region_add_subregion(get_system_memory(), base, &s->iomem); - - s->irq = irq; - s->drq = drq; - s->accept_256 = cpu_is_omap3630(mpu); - s->revision = cpu_class_omap3(mpu) ? 0x50 : 0x20; - s->lastirq = 0; - omap_gpmc_reset(s); - - /* We have to register a different IO memory handler for each - * chip select region in case a NAND device is mapped there. We - * make the region the worst-case size of 256MB and rely on the - * container memory region in cs_map to chop it down to the actual - * guest-requested size. - */ - for (cs = 0; cs < 8; cs++) { - memory_region_init_io(&s->cs_file[cs].nandiomem, NULL, - &omap_nand_ops, - &s->cs_file[cs], - "omap-nand", - 256 * 1024 * 1024); - } - - memory_region_init_io(&s->prefetch.iomem, NULL, &omap_prefetch_ops, s, - "omap-gpmc-prefetch", 256 * 1024 * 1024); - return s; -} - -void omap_gpmc_attach(struct omap_gpmc_s *s, int cs, MemoryRegion *iomem) -{ - struct omap_gpmc_cs_file_s *f; - assert(iomem); - - if (cs < 0 || cs >= 8) { - fprintf(stderr, "%s: bad chip-select %i\n", __func__, cs); - exit(-1); - } - f = &s->cs_file[cs]; - - omap_gpmc_cs_unmap(s, cs); - f->config[0] &= ~(0xf << 10); - f->iomem = iomem; - omap_gpmc_cs_map(s, cs); -} - -void omap_gpmc_attach_nand(struct omap_gpmc_s *s, int cs, DeviceState *nand) -{ - struct omap_gpmc_cs_file_s *f; - assert(nand); - - if (cs < 0 || cs >= 8) { - fprintf(stderr, "%s: bad chip-select %i\n", __func__, cs); - exit(-1); - } - f = &s->cs_file[cs]; - - omap_gpmc_cs_unmap(s, cs); - f->config[0] &= ~(0xf << 10); - f->config[0] |= (OMAP_GPMC_NAND << 10); - f->dev = nand; - if (nand_getbuswidth(f->dev) == 16) { - f->config[0] |= OMAP_GPMC_16BIT << 12; - } - omap_gpmc_cs_map(s, cs); -} diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( )) system_ss.add(when: 'CONFIG_OMAP', if_true: files( 'omap_clk.c', - 'omap_gpmc.c', 'omap_l4.c', 'omap_tap.c', )) -- 2.34.1 The omap_gptimer device is only in the OMAP2 SoC, which we are removing. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-45-peter.maydell@linaro.org --- include/hw/arm/omap.h | 8 - hw/timer/omap_gptimer.c | 512 ---------------------------------------- hw/timer/meson.build | 1 - 3 files changed, 521 deletions(-) delete mode 100644 hw/timer/omap_gptimer.c diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ struct omap_dma_lcd_channel_s { # define OMAP24XX_DMA_MS 63 /* Not in OMAP2420 */ # define OMAP24XX_DMA_EXT_DMAREQ5 64 -/* omap[123].c */ -/* OMAP2 gp timer */ -struct omap_gp_timer_s; -struct omap_gp_timer_s *omap_gp_timer_init(struct omap_target_agent_s *ta, - qemu_irq irq, omap_clk fclk, omap_clk iclk); -void omap_gp_timer_reset(struct omap_gp_timer_s *s); - /* OMAP2 sysctimer */ struct omap_synctimer_s; struct omap_synctimer_s *omap_synctimer_init(struct omap_target_agent_s *ta, @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s { /* OMAP2-only peripherals */ struct omap_l4_s *l4; - struct omap_gp_timer_s *gptimer[12]; struct omap_synctimer_s *synctimer; struct omap_mcspi_s *mcspi[2]; diff --git a/hw/timer/omap_gptimer.c b/hw/timer/omap_gptimer.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/timer/omap_gptimer.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI OMAP2 general purpose timers emulation. - * - * Copyright (C) 2007-2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) any later version of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "qemu/timer.h" -#include "hw/arm/omap.h" - -/* GP timers */ -struct omap_gp_timer_s { - MemoryRegion iomem; - qemu_irq irq; - qemu_irq wkup; - qemu_irq in; - qemu_irq out; - omap_clk clk; - QEMUTimer *timer; - QEMUTimer *match; - struct omap_target_agent_s *ta; - - int in_val; - int out_val; - int64_t time; - int64_t rate; - int64_t ticks_per_sec; - - int16_t config; - int status; - int it_ena; - int wu_ena; - int enable; - int inout; - int capt2; - int pt; - enum { - gpt_trigger_none, gpt_trigger_overflow, gpt_trigger_both - } trigger; - enum { - gpt_capture_none, gpt_capture_rising, - gpt_capture_falling, gpt_capture_both - } capture; - int scpwm; - int ce; - int pre; - int ptv; - int ar; - int st; - int posted; - uint32_t val; - uint32_t load_val; - uint32_t capture_val[2]; - uint32_t match_val; - int capt_num; - - uint16_t writeh; /* LSB */ - uint16_t readh; /* MSB */ -}; - -#define GPT_TCAR_IT (1 << 2) -#define GPT_OVF_IT (1 << 1) -#define GPT_MAT_IT (1 << 0) - -static inline void omap_gp_timer_intr(struct omap_gp_timer_s *timer, int it) -{ - if (timer->it_ena & it) { - if (!timer->status) - qemu_irq_raise(timer->irq); - - timer->status |= it; - /* Or are the status bits set even when masked? - * i.e. is masking applied before or after the status register? */ - } - - if (timer->wu_ena & it) - qemu_irq_pulse(timer->wkup); -} - -static inline void omap_gp_timer_out(struct omap_gp_timer_s *timer, int level) -{ - if (!timer->inout && timer->out_val != level) { - timer->out_val = level; - qemu_set_irq(timer->out, level); - } -} - -static inline uint32_t omap_gp_timer_read(struct omap_gp_timer_s *timer) -{ - uint64_t distance; - - if (timer->st && timer->rate) { - distance = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - timer->time; - distance = muldiv64(distance, timer->rate, timer->ticks_per_sec); - - if (distance >= 0xffffffff - timer->val) - return 0xffffffff; - else - return timer->val + distance; - } else - return timer->val; -} - -static inline void omap_gp_timer_sync(struct omap_gp_timer_s *timer) -{ - if (timer->st) { - timer->val = omap_gp_timer_read(timer); - timer->time = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - } -} - -static inline void omap_gp_timer_update(struct omap_gp_timer_s *timer) -{ - int64_t expires, matches; - - if (timer->st && timer->rate) { - expires = muldiv64(0x100000000ll - timer->val, - timer->ticks_per_sec, timer->rate); - timer_mod(timer->timer, timer->time + expires); - - if (timer->ce && timer->match_val >= timer->val) { - matches = muldiv64(timer->ticks_per_sec, - timer->match_val - timer->val, timer->rate); - timer_mod(timer->match, timer->time + matches); - } else - timer_del(timer->match); - } else { - timer_del(timer->timer); - timer_del(timer->match); - omap_gp_timer_out(timer, timer->scpwm); - } -} - -static inline void omap_gp_timer_trigger(struct omap_gp_timer_s *timer) -{ - if (timer->pt) - /* TODO in overflow-and-match mode if the first event to - * occur is the match, don't toggle. */ - omap_gp_timer_out(timer, !timer->out_val); - else - /* TODO inverted pulse on timer->out_val == 1? */ - qemu_irq_pulse(timer->out); -} - -static void omap_gp_timer_tick(void *opaque) -{ - struct omap_gp_timer_s *timer = opaque; - - if (!timer->ar) { - timer->st = 0; - timer->val = 0; - } else { - timer->val = timer->load_val; - timer->time = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - } - - if (timer->trigger == gpt_trigger_overflow || - timer->trigger == gpt_trigger_both) - omap_gp_timer_trigger(timer); - - omap_gp_timer_intr(timer, GPT_OVF_IT); - omap_gp_timer_update(timer); -} - -static void omap_gp_timer_match(void *opaque) -{ - struct omap_gp_timer_s *timer = opaque; - - if (timer->trigger == gpt_trigger_both) - omap_gp_timer_trigger(timer); - - omap_gp_timer_intr(timer, GPT_MAT_IT); -} - -static void omap_gp_timer_input(void *opaque, int line, int on) -{ - struct omap_gp_timer_s *s = opaque; - int trigger; - - switch (s->capture) { - default: - case gpt_capture_none: - trigger = 0; - break; - case gpt_capture_rising: - trigger = !s->in_val && on; - break; - case gpt_capture_falling: - trigger = s->in_val && !on; - break; - case gpt_capture_both: - trigger = (s->in_val == !on); - break; - } - s->in_val = on; - - if (s->inout && trigger && s->capt_num < 2) { - s->capture_val[s->capt_num] = omap_gp_timer_read(s); - - if (s->capt2 == s->capt_num ++) - omap_gp_timer_intr(s, GPT_TCAR_IT); - } -} - -static void omap_gp_timer_clk_update(void *opaque, int line, int on) -{ - struct omap_gp_timer_s *timer = opaque; - - omap_gp_timer_sync(timer); - timer->rate = on ? omap_clk_getrate(timer->clk) : 0; - omap_gp_timer_update(timer); -} - -static void omap_gp_timer_clk_setup(struct omap_gp_timer_s *timer) -{ - omap_clk_adduser(timer->clk, - qemu_allocate_irq(omap_gp_timer_clk_update, timer, 0)); - timer->rate = omap_clk_getrate(timer->clk); -} - -void omap_gp_timer_reset(struct omap_gp_timer_s *s) -{ - s->config = 0x000; - s->status = 0; - s->it_ena = 0; - s->wu_ena = 0; - s->inout = 0; - s->capt2 = 0; - s->capt_num = 0; - s->pt = 0; - s->trigger = gpt_trigger_none; - s->capture = gpt_capture_none; - s->scpwm = 0; - s->ce = 0; - s->pre = 0; - s->ptv = 0; - s->ar = 0; - s->st = 0; - s->posted = 1; - s->val = 0x00000000; - s->load_val = 0x00000000; - s->capture_val[0] = 0x00000000; - s->capture_val[1] = 0x00000000; - s->match_val = 0x00000000; - omap_gp_timer_update(s); -} - -static uint32_t omap_gp_timer_readw(void *opaque, hwaddr addr) -{ - struct omap_gp_timer_s *s = opaque; - - switch (addr) { - case 0x00: /* TIDR */ - return 0x21; - - case 0x10: /* TIOCP_CFG */ - return s->config; - - case 0x14: /* TISTAT */ - /* ??? When's this bit reset? */ - return 1; /* RESETDONE */ - - case 0x18: /* TISR */ - return s->status; - - case 0x1c: /* TIER */ - return s->it_ena; - - case 0x20: /* TWER */ - return s->wu_ena; - - case 0x24: /* TCLR */ - return (s->inout << 14) | - (s->capt2 << 13) | - (s->pt << 12) | - (s->trigger << 10) | - (s->capture << 8) | - (s->scpwm << 7) | - (s->ce << 6) | - (s->pre << 5) | - (s->ptv << 2) | - (s->ar << 1) | - (s->st << 0); - - case 0x28: /* TCRR */ - return omap_gp_timer_read(s); - - case 0x2c: /* TLDR */ - return s->load_val; - - case 0x30: /* TTGR */ - return 0xffffffff; - - case 0x34: /* TWPS */ - return 0x00000000; /* No posted writes pending. */ - - case 0x38: /* TMAR */ - return s->match_val; - - case 0x3c: /* TCAR1 */ - return s->capture_val[0]; - - case 0x40: /* TSICR */ - return s->posted << 2; - - case 0x44: /* TCAR2 */ - return s->capture_val[1]; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static uint32_t omap_gp_timer_readh(void *opaque, hwaddr addr) -{ - struct omap_gp_timer_s *s = opaque; - uint32_t ret; - - if (addr & 2) - return s->readh; - else { - ret = omap_gp_timer_readw(opaque, addr); - s->readh = ret >> 16; - return ret & 0xffff; - } -} - -static void omap_gp_timer_write(void *opaque, hwaddr addr, uint32_t value) -{ - struct omap_gp_timer_s *s = opaque; - - switch (addr) { - case 0x00: /* TIDR */ - case 0x14: /* TISTAT */ - case 0x34: /* TWPS */ - case 0x3c: /* TCAR1 */ - case 0x44: /* TCAR2 */ - OMAP_RO_REG(addr); - break; - - case 0x10: /* TIOCP_CFG */ - s->config = value & 0x33d; - if (((value >> 3) & 3) == 3) /* IDLEMODE */ - fprintf(stderr, "%s: illegal IDLEMODE value in TIOCP_CFG\n", - __func__); - if (value & 2) /* SOFTRESET */ - omap_gp_timer_reset(s); - break; - - case 0x18: /* TISR */ - if (value & GPT_TCAR_IT) - s->capt_num = 0; - if (s->status && !(s->status &= ~value)) - qemu_irq_lower(s->irq); - break; - - case 0x1c: /* TIER */ - s->it_ena = value & 7; - break; - - case 0x20: /* TWER */ - s->wu_ena = value & 7; - break; - - case 0x24: /* TCLR */ - omap_gp_timer_sync(s); - s->inout = (value >> 14) & 1; - s->capt2 = (value >> 13) & 1; - s->pt = (value >> 12) & 1; - s->trigger = (value >> 10) & 3; - if (s->capture == gpt_capture_none && - ((value >> 8) & 3) != gpt_capture_none) - s->capt_num = 0; - s->capture = (value >> 8) & 3; - s->scpwm = (value >> 7) & 1; - s->ce = (value >> 6) & 1; - s->pre = (value >> 5) & 1; - s->ptv = (value >> 2) & 7; - s->ar = (value >> 1) & 1; - s->st = (value >> 0) & 1; - if (s->inout && s->trigger != gpt_trigger_none) - fprintf(stderr, "%s: GP timer pin must be an output " - "for this trigger mode\n", __func__); - if (!s->inout && s->capture != gpt_capture_none) - fprintf(stderr, "%s: GP timer pin must be an input " - "for this capture mode\n", __func__); - if (s->trigger == gpt_trigger_none) - omap_gp_timer_out(s, s->scpwm); - /* TODO: make sure this doesn't overflow 32-bits */ - s->ticks_per_sec = NANOSECONDS_PER_SECOND << (s->pre ? s->ptv + 1 : 0); - omap_gp_timer_update(s); - break; - - case 0x28: /* TCRR */ - s->time = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - s->val = value; - omap_gp_timer_update(s); - break; - - case 0x2c: /* TLDR */ - s->load_val = value; - break; - - case 0x30: /* TTGR */ - s->time = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - s->val = s->load_val; - omap_gp_timer_update(s); - break; - - case 0x38: /* TMAR */ - omap_gp_timer_sync(s); - s->match_val = value; - omap_gp_timer_update(s); - break; - - case 0x40: /* TSICR */ - s->posted = (value >> 2) & 1; - if (value & 2) /* How much exactly are we supposed to reset? */ - omap_gp_timer_reset(s); - break; - - default: - OMAP_BAD_REG(addr); - } -} - -static void omap_gp_timer_writeh(void *opaque, hwaddr addr, uint32_t value) -{ - struct omap_gp_timer_s *s = opaque; - - if (addr & 2) - omap_gp_timer_write(opaque, addr, (value << 16) | s->writeh); - else - s->writeh = (uint16_t) value; -} - -static uint64_t omap_gp_timer_readfn(void *opaque, hwaddr addr, - unsigned size) -{ - switch (size) { - case 1: - return omap_badwidth_read32(opaque, addr); - case 2: - return omap_gp_timer_readh(opaque, addr); - case 4: - return omap_gp_timer_readw(opaque, addr); - default: - g_assert_not_reached(); - } -} - -static void omap_gp_timer_writefn(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - switch (size) { - case 1: - omap_badwidth_write32(opaque, addr, value); - break; - case 2: - omap_gp_timer_writeh(opaque, addr, value); - break; - case 4: - omap_gp_timer_write(opaque, addr, value); - break; - default: - g_assert_not_reached(); - } -} - -static const MemoryRegionOps omap_gp_timer_ops = { - .read = omap_gp_timer_readfn, - .write = omap_gp_timer_writefn, - .valid.min_access_size = 1, - .valid.max_access_size = 4, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -struct omap_gp_timer_s *omap_gp_timer_init(struct omap_target_agent_s *ta, - qemu_irq irq, omap_clk fclk, omap_clk iclk) -{ - struct omap_gp_timer_s *s = g_new0(struct omap_gp_timer_s, 1); - - s->ta = ta; - s->irq = irq; - s->clk = fclk; - s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, omap_gp_timer_tick, s); - s->match = timer_new_ns(QEMU_CLOCK_VIRTUAL, omap_gp_timer_match, s); - s->in = qemu_allocate_irq(omap_gp_timer_input, s, 0); - omap_gp_timer_reset(s); - omap_gp_timer_clk_setup(s); - - memory_region_init_io(&s->iomem, NULL, &omap_gp_timer_ops, s, "omap.gptimer", - omap_l4_region_size(ta, 0)); - omap_l4_attach(ta, 0, &s->iomem); - - return s; -} diff --git a/hw/timer/meson.build b/hw/timer/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/meson.build +++ b/hw/timer/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('mips_gictimer.c')) system_ss.add(when: 'CONFIG_MSF2', if_true: files('mss-timer.c')) system_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_timer.c')) system_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_timer.c')) -system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_gptimer.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_synctimer.c')) system_ss.add(when: 'CONFIG_PXA2XX_TIMER', if_true: files('pxa2xx_timer.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_systmr.c')) -- 2.34.1 Remove the omap_synctimer device, which is only in the OMAP2 SoC. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-46-peter.maydell@linaro.org --- include/hw/arm/omap.h | 8 --- hw/timer/omap_synctimer.c | 110 -------------------------------------- hw/timer/meson.build | 1 - 3 files changed, 119 deletions(-) delete mode 100644 hw/timer/omap_synctimer.c diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ struct omap_dma_lcd_channel_s { # define OMAP24XX_DMA_MS 63 /* Not in OMAP2420 */ # define OMAP24XX_DMA_EXT_DMAREQ5 64 -/* OMAP2 sysctimer */ -struct omap_synctimer_s; -struct omap_synctimer_s *omap_synctimer_init(struct omap_target_agent_s *ta, - struct omap_mpu_state_s *mpu, omap_clk fclk, omap_clk iclk); -void omap_synctimer_reset(struct omap_synctimer_s *s); - struct omap_uart_s; struct omap_uart_s *omap_uart_init(hwaddr base, qemu_irq irq, omap_clk fclk, omap_clk iclk, @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s { /* OMAP2-only peripherals */ struct omap_l4_s *l4; - struct omap_synctimer_s *synctimer; - struct omap_mcspi_s *mcspi[2]; struct omap_dss_s *dss; diff --git a/hw/timer/omap_synctimer.c b/hw/timer/omap_synctimer.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/timer/omap_synctimer.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI OMAP2 32kHz sync timer emulation. - * - * Copyright (C) 2007-2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) any later version of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ -#include "qemu/osdep.h" -#include "qemu/timer.h" -#include "hw/arm/omap.h" -struct omap_synctimer_s { - MemoryRegion iomem; - uint32_t val; - uint16_t readh; -}; - -/* 32-kHz Sync Timer of the OMAP2 */ -static uint32_t omap_synctimer_read(struct omap_synctimer_s *s) { - return muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), 0x8000, - NANOSECONDS_PER_SECOND); -} - -void omap_synctimer_reset(struct omap_synctimer_s *s) -{ - s->val = omap_synctimer_read(s); -} - -static uint32_t omap_synctimer_readw(void *opaque, hwaddr addr) -{ - struct omap_synctimer_s *s = opaque; - - switch (addr) { - case 0x00: /* 32KSYNCNT_REV */ - return 0x21; - - case 0x10: /* CR */ - return omap_synctimer_read(s) - s->val; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static uint32_t omap_synctimer_readh(void *opaque, hwaddr addr) -{ - struct omap_synctimer_s *s = opaque; - uint32_t ret; - - if (addr & 2) - return s->readh; - else { - ret = omap_synctimer_readw(opaque, addr); - s->readh = ret >> 16; - return ret & 0xffff; - } -} - -static uint64_t omap_synctimer_readfn(void *opaque, hwaddr addr, - unsigned size) -{ - switch (size) { - case 1: - return omap_badwidth_read32(opaque, addr); - case 2: - return omap_synctimer_readh(opaque, addr); - case 4: - return omap_synctimer_readw(opaque, addr); - default: - g_assert_not_reached(); - } -} - -static void omap_synctimer_writefn(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - OMAP_BAD_REG(addr); -} - -static const MemoryRegionOps omap_synctimer_ops = { - .read = omap_synctimer_readfn, - .write = omap_synctimer_writefn, - .valid.min_access_size = 1, - .valid.max_access_size = 4, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -struct omap_synctimer_s *omap_synctimer_init(struct omap_target_agent_s *ta, - struct omap_mpu_state_s *mpu, omap_clk fclk, omap_clk iclk) -{ - struct omap_synctimer_s *s = g_malloc0(sizeof(*s)); - - omap_synctimer_reset(s); - memory_region_init_io(&s->iomem, NULL, &omap_synctimer_ops, s, "omap.synctimer", - omap_l4_region_size(ta, 0)); - omap_l4_attach(ta, 0, &s->iomem); - - return s; -} diff --git a/hw/timer/meson.build b/hw/timer/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/meson.build +++ b/hw/timer/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('mips_gictimer.c')) system_ss.add(when: 'CONFIG_MSF2', if_true: files('mss-timer.c')) system_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_timer.c')) system_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_timer.c')) -system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_synctimer.c')) system_ss.add(when: 'CONFIG_PXA2XX_TIMER', if_true: files('pxa2xx_timer.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_systmr.c')) system_ss.add(when: 'CONFIG_SH_TIMER', if_true: files('sh_timer.c')) -- 2.34.1 The omap_mcspi device is used only in the OMAP2 SoC, which we are removing. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-48-peter.maydell@linaro.org --- include/hw/arm/omap.h | 11 -- hw/ssi/omap_spi.c | 380 ------------------------------------------ hw/ssi/meson.build | 1 - 3 files changed, 392 deletions(-) delete mode 100644 hw/ssi/omap_spi.c diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ struct omap_uwire_s; void omap_uwire_attach(struct omap_uwire_s *s, uWireSlave *slave, int chipselect); -/* OMAP2 spi */ -struct omap_mcspi_s; -struct omap_mcspi_s *omap_mcspi_init(struct omap_target_agent_s *ta, int chnum, - qemu_irq irq, qemu_irq *drq, omap_clk fclk, omap_clk iclk); -void omap_mcspi_attach(struct omap_mcspi_s *s, - uint32_t (*txrx)(void *opaque, uint32_t, int), void *opaque, - int chipselect); -void omap_mcspi_reset(struct omap_mcspi_s *s); - struct I2SCodec { void *opaque; @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s { /* OMAP2-only peripherals */ struct omap_l4_s *l4; - struct omap_mcspi_s *mcspi[2]; - struct omap_dss_s *dss; }; diff --git a/hw/ssi/omap_spi.c b/hw/ssi/omap_spi.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/ssi/omap_spi.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI OMAP processor's Multichannel SPI emulation. - * - * Copyright (C) 2007-2009 Nokia Corporation - * - * Original code for OMAP2 by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) any later version of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include "qemu/osdep.h" -#include "qemu/log.h" -#include "hw/hw.h" -#include "hw/irq.h" -#include "hw/arm/omap.h" - -/* Multichannel SPI */ -struct omap_mcspi_s { - MemoryRegion iomem; - qemu_irq irq; - int chnum; - - uint32_t sysconfig; - uint32_t systest; - uint32_t irqst; - uint32_t irqen; - uint32_t wken; - uint32_t control; - - struct omap_mcspi_ch_s { - qemu_irq txdrq; - qemu_irq rxdrq; - uint32_t (*txrx)(void *opaque, uint32_t, int); - void *opaque; - - uint32_t tx; - uint32_t rx; - - uint32_t config; - uint32_t status; - uint32_t control; - } ch[4]; -}; - -static inline void omap_mcspi_interrupt_update(struct omap_mcspi_s *s) -{ - qemu_set_irq(s->irq, s->irqst & s->irqen); -} - -static inline void omap_mcspi_dmarequest_update(struct omap_mcspi_ch_s *ch) -{ - qemu_set_irq(ch->txdrq, - (ch->control & 1) && /* EN */ - (ch->config & (1 << 14)) && /* DMAW */ - (ch->status & (1 << 1)) && /* TXS */ - ((ch->config >> 12) & 3) != 1); /* TRM */ - qemu_set_irq(ch->rxdrq, - (ch->control & 1) && /* EN */ - (ch->config & (1 << 15)) && /* DMAW */ - (ch->status & (1 << 0)) && /* RXS */ - ((ch->config >> 12) & 3) != 2); /* TRM */ -} - -static void omap_mcspi_transfer_run(struct omap_mcspi_s *s, int chnum) -{ - struct omap_mcspi_ch_s *ch = s->ch + chnum; - - if (!(ch->control & 1)) /* EN */ - return; - if ((ch->status & (1 << 0)) && /* RXS */ - ((ch->config >> 12) & 3) != 2 && /* TRM */ - !(ch->config & (1 << 19))) /* TURBO */ - goto intr_update; - if ((ch->status & (1 << 1)) && /* TXS */ - ((ch->config >> 12) & 3) != 1) /* TRM */ - goto intr_update; - - if (!(s->control & 1) || /* SINGLE */ - (ch->config & (1 << 20))) { /* FORCE */ - if (ch->txrx) - ch->rx = ch->txrx(ch->opaque, ch->tx, /* WL */ - 1 + (0x1f & (ch->config >> 7))); - } - - ch->tx = 0; - ch->status |= 1 << 2; /* EOT */ - ch->status |= 1 << 1; /* TXS */ - if (((ch->config >> 12) & 3) != 2) /* TRM */ - ch->status |= 1 << 0; /* RXS */ - -intr_update: - if ((ch->status & (1 << 0)) && /* RXS */ - ((ch->config >> 12) & 3) != 2 && /* TRM */ - !(ch->config & (1 << 19))) /* TURBO */ - s->irqst |= 1 << (2 + 4 * chnum); /* RX_FULL */ - if ((ch->status & (1 << 1)) && /* TXS */ - ((ch->config >> 12) & 3) != 1) /* TRM */ - s->irqst |= 1 << (0 + 4 * chnum); /* TX_EMPTY */ - omap_mcspi_interrupt_update(s); - omap_mcspi_dmarequest_update(ch); -} - -void omap_mcspi_reset(struct omap_mcspi_s *s) -{ - int ch; - - s->sysconfig = 0; - s->systest = 0; - s->irqst = 0; - s->irqen = 0; - s->wken = 0; - s->control = 4; - - for (ch = 0; ch < 4; ch ++) { - s->ch[ch].config = 0x060000; - s->ch[ch].status = 2; /* TXS */ - s->ch[ch].control = 0; - - omap_mcspi_dmarequest_update(s->ch + ch); - } - - omap_mcspi_interrupt_update(s); -} - -static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, unsigned size) -{ - struct omap_mcspi_s *s = opaque; - int ch = 0; - uint32_t ret; - - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x00: /* MCSPI_REVISION */ - return 0x91; - - case 0x10: /* MCSPI_SYSCONFIG */ - return s->sysconfig; - - case 0x14: /* MCSPI_SYSSTATUS */ - return 1; /* RESETDONE */ - - case 0x18: /* MCSPI_IRQSTATUS */ - return s->irqst; - - case 0x1c: /* MCSPI_IRQENABLE */ - return s->irqen; - - case 0x20: /* MCSPI_WAKEUPENABLE */ - return s->wken; - - case 0x24: /* MCSPI_SYST */ - return s->systest; - - case 0x28: /* MCSPI_MODULCTRL */ - return s->control; - - case 0x68: ch ++; - /* fall through */ - case 0x54: ch ++; - /* fall through */ - case 0x40: ch ++; - /* fall through */ - case 0x2c: /* MCSPI_CHCONF */ - return s->ch[ch].config; - - case 0x6c: ch ++; - /* fall through */ - case 0x58: ch ++; - /* fall through */ - case 0x44: ch ++; - /* fall through */ - case 0x30: /* MCSPI_CHSTAT */ - return s->ch[ch].status; - - case 0x70: ch ++; - /* fall through */ - case 0x5c: ch ++; - /* fall through */ - case 0x48: ch ++; - /* fall through */ - case 0x34: /* MCSPI_CHCTRL */ - return s->ch[ch].control; - - case 0x74: ch ++; - /* fall through */ - case 0x60: ch ++; - /* fall through */ - case 0x4c: ch ++; - /* fall through */ - case 0x38: /* MCSPI_TX */ - return s->ch[ch].tx; - - case 0x78: ch ++; - /* fall through */ - case 0x64: ch ++; - /* fall through */ - case 0x50: ch ++; - /* fall through */ - case 0x3c: /* MCSPI_RX */ - s->ch[ch].status &= ~(1 << 0); /* RXS */ - ret = s->ch[ch].rx; - omap_mcspi_transfer_run(s, ch); - return ret; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_mcspi_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_mcspi_s *s = opaque; - int ch = 0; - - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x00: /* MCSPI_REVISION */ - case 0x14: /* MCSPI_SYSSTATUS */ - case 0x30: /* MCSPI_CHSTAT0 */ - case 0x3c: /* MCSPI_RX0 */ - case 0x44: /* MCSPI_CHSTAT1 */ - case 0x50: /* MCSPI_RX1 */ - case 0x58: /* MCSPI_CHSTAT2 */ - case 0x64: /* MCSPI_RX2 */ - case 0x6c: /* MCSPI_CHSTAT3 */ - case 0x78: /* MCSPI_RX3 */ - OMAP_RO_REG(addr); - return; - - case 0x10: /* MCSPI_SYSCONFIG */ - if (value & (1 << 1)) /* SOFTRESET */ - omap_mcspi_reset(s); - s->sysconfig = value & 0x31d; - break; - - case 0x18: /* MCSPI_IRQSTATUS */ - if (!((s->control & (1 << 3)) && (s->systest & (1 << 11)))) { - s->irqst &= ~value; - omap_mcspi_interrupt_update(s); - } - break; - - case 0x1c: /* MCSPI_IRQENABLE */ - s->irqen = value & 0x1777f; - omap_mcspi_interrupt_update(s); - break; - - case 0x20: /* MCSPI_WAKEUPENABLE */ - s->wken = value & 1; - break; - - case 0x24: /* MCSPI_SYST */ - if (s->control & (1 << 3)) /* SYSTEM_TEST */ - if (value & (1 << 11)) { /* SSB */ - s->irqst |= 0x1777f; - omap_mcspi_interrupt_update(s); - } - s->systest = value & 0xfff; - break; - - case 0x28: /* MCSPI_MODULCTRL */ - if (value & (1 << 3)) /* SYSTEM_TEST */ - if (s->systest & (1 << 11)) { /* SSB */ - s->irqst |= 0x1777f; - omap_mcspi_interrupt_update(s); - } - s->control = value & 0xf; - break; - - case 0x68: ch ++; - /* fall through */ - case 0x54: ch ++; - /* fall through */ - case 0x40: ch ++; - /* fall through */ - case 0x2c: /* MCSPI_CHCONF */ - if ((value ^ s->ch[ch].config) & (3 << 14)) /* DMAR | DMAW */ - omap_mcspi_dmarequest_update(s->ch + ch); - if (((value >> 12) & 3) == 3) { /* TRM */ - qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid TRM value (3)\n", - __func__); - } - if (((value >> 7) & 0x1f) < 3) { /* WL */ - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid WL value (%" PRIx64 ")\n", - __func__, (value >> 7) & 0x1f); - } - s->ch[ch].config = value & 0x7fffff; - break; - - case 0x70: ch ++; - /* fall through */ - case 0x5c: ch ++; - /* fall through */ - case 0x48: ch ++; - /* fall through */ - case 0x34: /* MCSPI_CHCTRL */ - if (value & ~s->ch[ch].control & 1) { /* EN */ - s->ch[ch].control |= 1; - omap_mcspi_transfer_run(s, ch); - } else - s->ch[ch].control = value & 1; - break; - - case 0x74: ch ++; - /* fall through */ - case 0x60: ch ++; - /* fall through */ - case 0x4c: ch ++; - /* fall through */ - case 0x38: /* MCSPI_TX */ - s->ch[ch].tx = value; - s->ch[ch].status &= ~(1 << 1); /* TXS */ - omap_mcspi_transfer_run(s, ch); - break; - - default: - OMAP_BAD_REG(addr); - return; - } -} - -static const MemoryRegionOps omap_mcspi_ops = { - .read = omap_mcspi_read, - .write = omap_mcspi_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -struct omap_mcspi_s *omap_mcspi_init(struct omap_target_agent_s *ta, int chnum, - qemu_irq irq, qemu_irq *drq, omap_clk fclk, omap_clk iclk) -{ - struct omap_mcspi_s *s = g_new0(struct omap_mcspi_s, 1); - struct omap_mcspi_ch_s *ch = s->ch; - - s->irq = irq; - s->chnum = chnum; - while (chnum --) { - ch->txdrq = *drq ++; - ch->rxdrq = *drq ++; - ch ++; - } - omap_mcspi_reset(s); - - memory_region_init_io(&s->iomem, NULL, &omap_mcspi_ops, s, "omap.mcspi", - omap_l4_region_size(ta, 0)); - omap_l4_attach(ta, 0, &s->iomem); - - return s; -} - -void omap_mcspi_attach(struct omap_mcspi_s *s, - uint32_t (*txrx)(void *opaque, uint32_t, int), void *opaque, - int chipselect) -{ - if (chipselect < 0 || chipselect >= s->chnum) - hw_error("%s: Bad chipselect %i\n", __func__, chipselect); - - s->ch[chipselect].txrx = txrx; - s->ch[chipselect].opaque = opaque; -} diff --git a/hw/ssi/meson.build b/hw/ssi/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/meson.build +++ b/hw/ssi/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_XILINX_SPI', if_true: files('xilinx_spi.c')) system_ss.add(when: 'CONFIG_XILINX_SPIPS', if_true: files('xilinx_spips.c')) system_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-ospi.c')) system_ss.add(when: 'CONFIG_IMX', if_true: files('imx_spi.c')) -system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_spi.c')) system_ss.add(when: 'CONFIG_IBEX', if_true: files('ibex_spi_host.c')) system_ss.add(when: 'CONFIG_BCM2835_SPI', if_true: files('bcm2835_spi.c')) system_ss.add(when: 'CONFIG_PNV_SPI', if_true: files('pnv_spi.c')) -- 2.34.1 The omap_tap device is OMAP2 only, and we are removing it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-49-peter.maydell@linaro.org --- include/hw/arm/omap.h | 3 -- hw/misc/omap_tap.c | 117 ------------------------------------------ hw/misc/meson.build | 1 - 3 files changed, 121 deletions(-) delete mode 100644 hw/misc/omap_tap.c diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ struct I2SCodec { struct omap_mcbsp_s; void omap_mcbsp_i2s_attach(struct omap_mcbsp_s *s, I2SCodec *slave); -void omap_tap_init(struct omap_target_agent_s *ta, - struct omap_mpu_state_s *mpu); - /* omap_lcdc.c */ struct omap_lcd_panel_s; void omap_lcdc_reset(struct omap_lcd_panel_s *s); diff --git a/hw/misc/omap_tap.c b/hw/misc/omap_tap.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/misc/omap_tap.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI OMAP TEST-Chip-level TAP emulation. - * - * Copyright (C) 2007-2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) any later version of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "hw/hw.h" -#include "hw/arm/omap.h" - -/* TEST-Chip-level TAP */ -static uint64_t omap_tap_read(void *opaque, hwaddr addr, unsigned size) -{ - struct omap_mpu_state_s *s = opaque; - - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x204: /* IDCODE_reg */ - switch (s->mpu_model) { - case omap2420: - case omap2422: - case omap2423: - return 0x5b5d902f; /* ES 2.2 */ - case omap2430: - return 0x5b68a02f; /* ES 2.2 */ - case omap3430: - return 0x1b7ae02f; /* ES 2 */ - default: - hw_error("%s: Bad mpu model\n", __func__); - } - - case 0x208: /* PRODUCTION_ID_reg for OMAP2 */ - case 0x210: /* PRODUCTION_ID_reg for OMAP3 */ - switch (s->mpu_model) { - case omap2420: - return 0x000254f0; /* POP ESHS2.1.1 in N91/93/95, ES2 in N800 */ - case omap2422: - return 0x000400f0; - case omap2423: - return 0x000800f0; - case omap2430: - return 0x000000f0; - case omap3430: - return 0x000000f0; - default: - hw_error("%s: Bad mpu model\n", __func__); - } - - case 0x20c: - switch (s->mpu_model) { - case omap2420: - case omap2422: - case omap2423: - return 0xcafeb5d9; /* ES 2.2 */ - case omap2430: - return 0xcafeb68a; /* ES 2.2 */ - case omap3430: - return 0xcafeb7ae; /* ES 2 */ - default: - hw_error("%s: Bad mpu model\n", __func__); - } - - case 0x218: /* DIE_ID_reg */ - return ('Q' << 24) | ('E' << 16) | ('M' << 8) | ('U' << 0); - case 0x21c: /* DIE_ID_reg */ - return 0x54 << 24; - case 0x220: /* DIE_ID_reg */ - return ('Q' << 24) | ('E' << 16) | ('M' << 8) | ('U' << 0); - case 0x224: /* DIE_ID_reg */ - return ('Q' << 24) | ('E' << 16) | ('M' << 8) | ('U' << 0); - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_tap_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - OMAP_BAD_REG(addr); -} - -static const MemoryRegionOps omap_tap_ops = { - .read = omap_tap_read, - .write = omap_tap_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -void omap_tap_init(struct omap_target_agent_s *ta, - struct omap_mpu_state_s *mpu) -{ - memory_region_init_io(&mpu->tap_iomem, NULL, &omap_tap_ops, mpu, "omap.tap", - omap_l4_region_size(ta, 0)); - omap_l4_attach(ta, 0, &mpu->tap_iomem); -} diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( system_ss.add(when: 'CONFIG_OMAP', if_true: files( 'omap_clk.c', 'omap_l4.c', - 'omap_tap.c', )) system_ss.add(when: 'CONFIG_RASPI', if_true: files( 'bcm2835_mbox.c', -- 2.34.1 The omap_dss device is OMAP2 only, and we are removing it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-50-peter.maydell@linaro.org --- include/hw/arm/omap.h | 19 - hw/display/omap_dss.c | 1093 ---------------------------------------- hw/display/meson.build | 1 - 3 files changed, 1113 deletions(-) delete mode 100644 hw/display/omap_dss.c diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ struct omap_lcd_panel_s *omap_lcdc_init(MemoryRegion *sysmem, struct omap_dma_lcd_channel_s *dma, omap_clk clk); -/* omap_dss.c */ -struct rfbi_chip_s { - void *opaque; - void (*write)(void *opaque, int dc, uint16_t value); - void (*block)(void *opaque, int dc, void *buf, size_t len, int pitch); - uint16_t (*read)(void *opaque, int dc); -}; -struct omap_dss_s; -void omap_dss_reset(struct omap_dss_s *s); -struct omap_dss_s *omap_dss_init(struct omap_target_agent_s *ta, - MemoryRegion *sysmem, - hwaddr l3_base, - qemu_irq irq, qemu_irq drq, - omap_clk fck1, omap_clk fck2, omap_clk ck54m, - omap_clk ick1, omap_clk ick2); -void omap_rfbi_attach(struct omap_dss_s *s, int cs, struct rfbi_chip_s *chip); - /* omap_mmc.c */ struct omap_mmc_s; struct omap_mmc_s *omap_mmc_init(hwaddr base, @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s { /* OMAP2-only peripherals */ struct omap_l4_s *l4; - - struct omap_dss_s *dss; }; /* omap1.c */ diff --git a/hw/display/omap_dss.c b/hw/display/omap_dss.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/display/omap_dss.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * OMAP2 Display Subsystem. - * - * Copyright (C) 2008 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) version 3 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "qemu/log.h" -#include "hw/hw.h" -#include "hw/irq.h" -#include "ui/console.h" -#include "hw/arm/omap.h" - -struct omap_dss_s { - qemu_irq irq; - qemu_irq drq; - DisplayState *state; - MemoryRegion iomem_diss1, iomem_disc1, iomem_rfbi1, iomem_venc1, iomem_im3; - - int autoidle; - int control; - int enable; - - struct omap_dss_panel_s { - int enable; - int nx; - int ny; - - int x; - int y; - } dig, lcd; - - struct { - uint32_t idlemode; - uint32_t irqst; - uint32_t irqen; - uint32_t control; - uint32_t config; - uint32_t capable; - uint32_t timing[4]; - int line; - uint32_t bg[2]; - uint32_t trans[2]; - - struct omap_dss_plane_s { - int enable; - int bpp; - int posx; - int posy; - int nx; - int ny; - - hwaddr addr[3]; - - uint32_t attr; - uint32_t tresh; - int rowinc; - int colinc; - int wininc; - } l[3]; - - int invalidate; - uint16_t palette[256]; - } dispc; - - struct { - int idlemode; - uint32_t control; - int enable; - int pixels; - int busy; - int skiplines; - uint16_t rxbuf; - uint32_t config[2]; - uint32_t time[4]; - uint32_t data[6]; - uint16_t vsync; - uint16_t hsync; - struct rfbi_chip_s *chip[2]; - } rfbi; -}; - -static void omap_dispc_interrupt_update(struct omap_dss_s *s) -{ - qemu_set_irq(s->irq, s->dispc.irqst & s->dispc.irqen); -} - -static void omap_rfbi_reset(struct omap_dss_s *s) -{ - s->rfbi.idlemode = 0; - s->rfbi.control = 2; - s->rfbi.enable = 0; - s->rfbi.pixels = 0; - s->rfbi.skiplines = 0; - s->rfbi.busy = 0; - s->rfbi.config[0] = 0x00310000; - s->rfbi.config[1] = 0x00310000; - s->rfbi.time[0] = 0; - s->rfbi.time[1] = 0; - s->rfbi.time[2] = 0; - s->rfbi.time[3] = 0; - s->rfbi.data[0] = 0; - s->rfbi.data[1] = 0; - s->rfbi.data[2] = 0; - s->rfbi.data[3] = 0; - s->rfbi.data[4] = 0; - s->rfbi.data[5] = 0; - s->rfbi.vsync = 0; - s->rfbi.hsync = 0; -} - -void omap_dss_reset(struct omap_dss_s *s) -{ - s->autoidle = 0; - s->control = 0; - s->enable = 0; - - s->dig.enable = 0; - s->dig.nx = 1; - s->dig.ny = 1; - - s->lcd.enable = 0; - s->lcd.nx = 1; - s->lcd.ny = 1; - - s->dispc.idlemode = 0; - s->dispc.irqst = 0; - s->dispc.irqen = 0; - s->dispc.control = 0; - s->dispc.config = 0; - s->dispc.capable = 0x161; - s->dispc.timing[0] = 0; - s->dispc.timing[1] = 0; - s->dispc.timing[2] = 0; - s->dispc.timing[3] = 0; - s->dispc.line = 0; - s->dispc.bg[0] = 0; - s->dispc.bg[1] = 0; - s->dispc.trans[0] = 0; - s->dispc.trans[1] = 0; - - s->dispc.l[0].enable = 0; - s->dispc.l[0].bpp = 0; - s->dispc.l[0].addr[0] = 0; - s->dispc.l[0].addr[1] = 0; - s->dispc.l[0].addr[2] = 0; - s->dispc.l[0].posx = 0; - s->dispc.l[0].posy = 0; - s->dispc.l[0].nx = 1; - s->dispc.l[0].ny = 1; - s->dispc.l[0].attr = 0; - s->dispc.l[0].tresh = 0; - s->dispc.l[0].rowinc = 1; - s->dispc.l[0].colinc = 1; - s->dispc.l[0].wininc = 0; - - omap_rfbi_reset(s); - omap_dispc_interrupt_update(s); -} - -static uint64_t omap_diss_read(void *opaque, hwaddr addr, - unsigned size) -{ - struct omap_dss_s *s = opaque; - - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x00: /* DSS_REVISIONNUMBER */ - return 0x20; - - case 0x10: /* DSS_SYSCONFIG */ - return s->autoidle; - - case 0x14: /* DSS_SYSSTATUS */ - return 1; /* RESETDONE */ - - case 0x40: /* DSS_CONTROL */ - return s->control; - - case 0x50: /* DSS_PSA_LCD_REG_1 */ - case 0x54: /* DSS_PSA_LCD_REG_2 */ - case 0x58: /* DSS_PSA_VIDEO_REG */ - /* TODO: fake some values when appropriate s->control bits are set */ - return 0; - - case 0x5c: /* DSS_STATUS */ - return 1 + (s->control & 1); - - default: - break; - } - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_diss_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_dss_s *s = opaque; - - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x00: /* DSS_REVISIONNUMBER */ - case 0x14: /* DSS_SYSSTATUS */ - case 0x50: /* DSS_PSA_LCD_REG_1 */ - case 0x54: /* DSS_PSA_LCD_REG_2 */ - case 0x58: /* DSS_PSA_VIDEO_REG */ - case 0x5c: /* DSS_STATUS */ - OMAP_RO_REG(addr); - break; - - case 0x10: /* DSS_SYSCONFIG */ - if (value & 2) /* SOFTRESET */ - omap_dss_reset(s); - s->autoidle = value & 1; - break; - - case 0x40: /* DSS_CONTROL */ - s->control = value & 0x3dd; - break; - - default: - OMAP_BAD_REG(addr); - } -} - -static const MemoryRegionOps omap_diss_ops = { - .read = omap_diss_read, - .write = omap_diss_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static uint64_t omap_disc_read(void *opaque, hwaddr addr, - unsigned size) -{ - struct omap_dss_s *s = opaque; - - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x000: /* DISPC_REVISION */ - return 0x20; - - case 0x010: /* DISPC_SYSCONFIG */ - return s->dispc.idlemode; - - case 0x014: /* DISPC_SYSSTATUS */ - return 1; /* RESETDONE */ - - case 0x018: /* DISPC_IRQSTATUS */ - return s->dispc.irqst; - - case 0x01c: /* DISPC_IRQENABLE */ - return s->dispc.irqen; - - case 0x040: /* DISPC_CONTROL */ - return s->dispc.control; - - case 0x044: /* DISPC_CONFIG */ - return s->dispc.config; - - case 0x048: /* DISPC_CAPABLE */ - return s->dispc.capable; - - case 0x04c: /* DISPC_DEFAULT_COLOR0 */ - return s->dispc.bg[0]; - case 0x050: /* DISPC_DEFAULT_COLOR1 */ - return s->dispc.bg[1]; - case 0x054: /* DISPC_TRANS_COLOR0 */ - return s->dispc.trans[0]; - case 0x058: /* DISPC_TRANS_COLOR1 */ - return s->dispc.trans[1]; - - case 0x05c: /* DISPC_LINE_STATUS */ - return 0x7ff; - case 0x060: /* DISPC_LINE_NUMBER */ - return s->dispc.line; - - case 0x064: /* DISPC_TIMING_H */ - return s->dispc.timing[0]; - case 0x068: /* DISPC_TIMING_V */ - return s->dispc.timing[1]; - case 0x06c: /* DISPC_POL_FREQ */ - return s->dispc.timing[2]; - case 0x070: /* DISPC_DIVISOR */ - return s->dispc.timing[3]; - - case 0x078: /* DISPC_SIZE_DIG */ - return ((s->dig.ny - 1) << 16) | (s->dig.nx - 1); - case 0x07c: /* DISPC_SIZE_LCD */ - return ((s->lcd.ny - 1) << 16) | (s->lcd.nx - 1); - - case 0x080: /* DISPC_GFX_BA0 */ - return s->dispc.l[0].addr[0]; - case 0x084: /* DISPC_GFX_BA1 */ - return s->dispc.l[0].addr[1]; - case 0x088: /* DISPC_GFX_POSITION */ - return (s->dispc.l[0].posy << 16) | s->dispc.l[0].posx; - case 0x08c: /* DISPC_GFX_SIZE */ - return ((s->dispc.l[0].ny - 1) << 16) | (s->dispc.l[0].nx - 1); - case 0x0a0: /* DISPC_GFX_ATTRIBUTES */ - return s->dispc.l[0].attr; - case 0x0a4: /* DISPC_GFX_FIFO_TRESHOLD */ - return s->dispc.l[0].tresh; - case 0x0a8: /* DISPC_GFX_FIFO_SIZE_STATUS */ - return 256; - case 0x0ac: /* DISPC_GFX_ROW_INC */ - return s->dispc.l[0].rowinc; - case 0x0b0: /* DISPC_GFX_PIXEL_INC */ - return s->dispc.l[0].colinc; - case 0x0b4: /* DISPC_GFX_WINDOW_SKIP */ - return s->dispc.l[0].wininc; - case 0x0b8: /* DISPC_GFX_TABLE_BA */ - return s->dispc.l[0].addr[2]; - - case 0x0bc: /* DISPC_VID1_BA0 */ - case 0x0c0: /* DISPC_VID1_BA1 */ - case 0x0c4: /* DISPC_VID1_POSITION */ - case 0x0c8: /* DISPC_VID1_SIZE */ - case 0x0cc: /* DISPC_VID1_ATTRIBUTES */ - case 0x0d0: /* DISPC_VID1_FIFO_TRESHOLD */ - case 0x0d4: /* DISPC_VID1_FIFO_SIZE_STATUS */ - case 0x0d8: /* DISPC_VID1_ROW_INC */ - case 0x0dc: /* DISPC_VID1_PIXEL_INC */ - case 0x0e0: /* DISPC_VID1_FIR */ - case 0x0e4: /* DISPC_VID1_PICTURE_SIZE */ - case 0x0e8: /* DISPC_VID1_ACCU0 */ - case 0x0ec: /* DISPC_VID1_ACCU1 */ - case 0x0f0 ... 0x140: /* DISPC_VID1_FIR_COEF, DISPC_VID1_CONV_COEF */ - case 0x14c: /* DISPC_VID2_BA0 */ - case 0x150: /* DISPC_VID2_BA1 */ - case 0x154: /* DISPC_VID2_POSITION */ - case 0x158: /* DISPC_VID2_SIZE */ - case 0x15c: /* DISPC_VID2_ATTRIBUTES */ - case 0x160: /* DISPC_VID2_FIFO_TRESHOLD */ - case 0x164: /* DISPC_VID2_FIFO_SIZE_STATUS */ - case 0x168: /* DISPC_VID2_ROW_INC */ - case 0x16c: /* DISPC_VID2_PIXEL_INC */ - case 0x170: /* DISPC_VID2_FIR */ - case 0x174: /* DISPC_VID2_PICTURE_SIZE */ - case 0x178: /* DISPC_VID2_ACCU0 */ - case 0x17c: /* DISPC_VID2_ACCU1 */ - case 0x180 ... 0x1d0: /* DISPC_VID2_FIR_COEF, DISPC_VID2_CONV_COEF */ - case 0x1d4: /* DISPC_DATA_CYCLE1 */ - case 0x1d8: /* DISPC_DATA_CYCLE2 */ - case 0x1dc: /* DISPC_DATA_CYCLE3 */ - return 0; - - default: - break; - } - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_disc_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_dss_s *s = opaque; - - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x010: /* DISPC_SYSCONFIG */ - if (value & 2) /* SOFTRESET */ - omap_dss_reset(s); - s->dispc.idlemode = value & 0x301b; - break; - - case 0x018: /* DISPC_IRQSTATUS */ - s->dispc.irqst &= ~value; - omap_dispc_interrupt_update(s); - break; - - case 0x01c: /* DISPC_IRQENABLE */ - s->dispc.irqen = value & 0xffff; - omap_dispc_interrupt_update(s); - break; - - case 0x040: /* DISPC_CONTROL */ - s->dispc.control = value & 0x07ff9fff; - s->dig.enable = (value >> 1) & 1; - s->lcd.enable = (value >> 0) & 1; - if (value & (1 << 12)) /* OVERLAY_OPTIMIZATION */ - if (!((s->dispc.l[1].attr | s->dispc.l[2].attr) & 1)) { - fprintf(stderr, "%s: Overlay Optimization when no overlay " - "region effectively exists leads to " - "unpredictable behaviour!\n", __func__); - } - if (value & (1 << 6)) { /* GODIGITAL */ - /* XXX: Shadowed fields are: - * s->dispc.config - * s->dispc.capable - * s->dispc.bg[0] - * s->dispc.bg[1] - * s->dispc.trans[0] - * s->dispc.trans[1] - * s->dispc.line - * s->dispc.timing[0] - * s->dispc.timing[1] - * s->dispc.timing[2] - * s->dispc.timing[3] - * s->lcd.nx - * s->lcd.ny - * s->dig.nx - * s->dig.ny - * s->dispc.l[0].addr[0] - * s->dispc.l[0].addr[1] - * s->dispc.l[0].addr[2] - * s->dispc.l[0].posx - * s->dispc.l[0].posy - * s->dispc.l[0].nx - * s->dispc.l[0].ny - * s->dispc.l[0].tresh - * s->dispc.l[0].rowinc - * s->dispc.l[0].colinc - * s->dispc.l[0].wininc - * All they need to be loaded here from their shadow registers. - */ - } - if (value & (1 << 5)) { /* GOLCD */ - /* XXX: Likewise for LCD here. */ - } - s->dispc.invalidate = 1; - break; - - case 0x044: /* DISPC_CONFIG */ - s->dispc.config = value & 0x3fff; - /* XXX: - * bits 2:1 (LOADMODE) reset to 0 after set to 1 and palette loaded - * bits 2:1 (LOADMODE) reset to 2 after set to 3 and palette loaded - */ - s->dispc.invalidate = 1; - break; - - case 0x048: /* DISPC_CAPABLE */ - s->dispc.capable = value & 0x3ff; - break; - - case 0x04c: /* DISPC_DEFAULT_COLOR0 */ - s->dispc.bg[0] = value & 0xffffff; - s->dispc.invalidate = 1; - break; - case 0x050: /* DISPC_DEFAULT_COLOR1 */ - s->dispc.bg[1] = value & 0xffffff; - s->dispc.invalidate = 1; - break; - case 0x054: /* DISPC_TRANS_COLOR0 */ - s->dispc.trans[0] = value & 0xffffff; - s->dispc.invalidate = 1; - break; - case 0x058: /* DISPC_TRANS_COLOR1 */ - s->dispc.trans[1] = value & 0xffffff; - s->dispc.invalidate = 1; - break; - - case 0x060: /* DISPC_LINE_NUMBER */ - s->dispc.line = value & 0x7ff; - break; - - case 0x064: /* DISPC_TIMING_H */ - s->dispc.timing[0] = value & 0x0ff0ff3f; - break; - case 0x068: /* DISPC_TIMING_V */ - s->dispc.timing[1] = value & 0x0ff0ff3f; - break; - case 0x06c: /* DISPC_POL_FREQ */ - s->dispc.timing[2] = value & 0x0003ffff; - break; - case 0x070: /* DISPC_DIVISOR */ - s->dispc.timing[3] = value & 0x00ff00ff; - break; - - case 0x078: /* DISPC_SIZE_DIG */ - s->dig.nx = ((value >> 0) & 0x7ff) + 1; /* PPL */ - s->dig.ny = ((value >> 16) & 0x7ff) + 1; /* LPP */ - s->dispc.invalidate = 1; - break; - case 0x07c: /* DISPC_SIZE_LCD */ - s->lcd.nx = ((value >> 0) & 0x7ff) + 1; /* PPL */ - s->lcd.ny = ((value >> 16) & 0x7ff) + 1; /* LPP */ - s->dispc.invalidate = 1; - break; - case 0x080: /* DISPC_GFX_BA0 */ - s->dispc.l[0].addr[0] = (hwaddr) value; - s->dispc.invalidate = 1; - break; - case 0x084: /* DISPC_GFX_BA1 */ - s->dispc.l[0].addr[1] = (hwaddr) value; - s->dispc.invalidate = 1; - break; - case 0x088: /* DISPC_GFX_POSITION */ - s->dispc.l[0].posx = ((value >> 0) & 0x7ff); /* GFXPOSX */ - s->dispc.l[0].posy = ((value >> 16) & 0x7ff); /* GFXPOSY */ - s->dispc.invalidate = 1; - break; - case 0x08c: /* DISPC_GFX_SIZE */ - s->dispc.l[0].nx = ((value >> 0) & 0x7ff) + 1; /* GFXSIZEX */ - s->dispc.l[0].ny = ((value >> 16) & 0x7ff) + 1; /* GFXSIZEY */ - s->dispc.invalidate = 1; - break; - case 0x0a0: /* DISPC_GFX_ATTRIBUTES */ - s->dispc.l[0].attr = value & 0x7ff; - if (value & (3 << 9)) - fprintf(stderr, "%s: Big-endian pixel format not supported\n", - __func__); - s->dispc.l[0].enable = value & 1; - s->dispc.l[0].bpp = (value >> 1) & 0xf; - s->dispc.invalidate = 1; - break; - case 0x0a4: /* DISPC_GFX_FIFO_TRESHOLD */ - s->dispc.l[0].tresh = value & 0x01ff01ff; - break; - case 0x0ac: /* DISPC_GFX_ROW_INC */ - s->dispc.l[0].rowinc = value; - s->dispc.invalidate = 1; - break; - case 0x0b0: /* DISPC_GFX_PIXEL_INC */ - s->dispc.l[0].colinc = value; - s->dispc.invalidate = 1; - break; - case 0x0b4: /* DISPC_GFX_WINDOW_SKIP */ - s->dispc.l[0].wininc = value; - break; - case 0x0b8: /* DISPC_GFX_TABLE_BA */ - s->dispc.l[0].addr[2] = (hwaddr) value; - s->dispc.invalidate = 1; - break; - - case 0x0bc: /* DISPC_VID1_BA0 */ - case 0x0c0: /* DISPC_VID1_BA1 */ - case 0x0c4: /* DISPC_VID1_POSITION */ - case 0x0c8: /* DISPC_VID1_SIZE */ - case 0x0cc: /* DISPC_VID1_ATTRIBUTES */ - case 0x0d0: /* DISPC_VID1_FIFO_TRESHOLD */ - case 0x0d8: /* DISPC_VID1_ROW_INC */ - case 0x0dc: /* DISPC_VID1_PIXEL_INC */ - case 0x0e0: /* DISPC_VID1_FIR */ - case 0x0e4: /* DISPC_VID1_PICTURE_SIZE */ - case 0x0e8: /* DISPC_VID1_ACCU0 */ - case 0x0ec: /* DISPC_VID1_ACCU1 */ - case 0x0f0 ... 0x140: /* DISPC_VID1_FIR_COEF, DISPC_VID1_CONV_COEF */ - case 0x14c: /* DISPC_VID2_BA0 */ - case 0x150: /* DISPC_VID2_BA1 */ - case 0x154: /* DISPC_VID2_POSITION */ - case 0x158: /* DISPC_VID2_SIZE */ - case 0x15c: /* DISPC_VID2_ATTRIBUTES */ - case 0x160: /* DISPC_VID2_FIFO_TRESHOLD */ - case 0x168: /* DISPC_VID2_ROW_INC */ - case 0x16c: /* DISPC_VID2_PIXEL_INC */ - case 0x170: /* DISPC_VID2_FIR */ - case 0x174: /* DISPC_VID2_PICTURE_SIZE */ - case 0x178: /* DISPC_VID2_ACCU0 */ - case 0x17c: /* DISPC_VID2_ACCU1 */ - case 0x180 ... 0x1d0: /* DISPC_VID2_FIR_COEF, DISPC_VID2_CONV_COEF */ - case 0x1d4: /* DISPC_DATA_CYCLE1 */ - case 0x1d8: /* DISPC_DATA_CYCLE2 */ - case 0x1dc: /* DISPC_DATA_CYCLE3 */ - break; - - default: - OMAP_BAD_REG(addr); - } -} - -static const MemoryRegionOps omap_disc_ops = { - .read = omap_disc_read, - .write = omap_disc_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void omap_rfbi_transfer_stop(struct omap_dss_s *s) -{ - if (!s->rfbi.busy) - return; - - /* TODO: in non-Bypass mode we probably need to just deassert the DRQ. */ - - s->rfbi.busy = 0; -} - -static void omap_rfbi_transfer_start(struct omap_dss_s *s) -{ - void *data; - hwaddr len; - hwaddr data_addr; - int pitch; - static void *bounce_buffer; - static hwaddr bounce_len; - - if (!s->rfbi.enable || s->rfbi.busy) - return; - - if (s->rfbi.control & (1 << 1)) { /* BYPASS */ - /* TODO: in non-Bypass mode we probably need to just assert the - * DRQ and wait for DMA to write the pixels. */ - qemu_log_mask(LOG_UNIMP, "%s: Bypass mode unimplemented\n", __func__); - return; - } - - if (!(s->dispc.control & (1 << 11))) /* RFBIMODE */ - return; - /* TODO: check that LCD output is enabled in DISPC. */ - - s->rfbi.busy = 1; - - len = s->rfbi.pixels * 2; - - data_addr = s->dispc.l[0].addr[0]; - data = cpu_physical_memory_map(data_addr, &len, false); - if (data && len != s->rfbi.pixels * 2) { - cpu_physical_memory_unmap(data, len, 0, 0); - data = NULL; - len = s->rfbi.pixels * 2; - } - if (!data) { - if (len > bounce_len) { - bounce_buffer = g_realloc(bounce_buffer, len); - } - data = bounce_buffer; - cpu_physical_memory_read(data_addr, data, len); - } - - /* TODO bpp */ - s->rfbi.pixels = 0; - - /* TODO: negative values */ - pitch = s->dispc.l[0].nx + (s->dispc.l[0].rowinc - 1) / 2; - - if ((s->rfbi.control & (1 << 2)) && s->rfbi.chip[0]) - s->rfbi.chip[0]->block(s->rfbi.chip[0]->opaque, 1, data, len, pitch); - if ((s->rfbi.control & (1 << 3)) && s->rfbi.chip[1]) - s->rfbi.chip[1]->block(s->rfbi.chip[1]->opaque, 1, data, len, pitch); - - if (data != bounce_buffer) { - cpu_physical_memory_unmap(data, len, 0, len); - } - - omap_rfbi_transfer_stop(s); - - /* TODO */ - s->dispc.irqst |= 1; /* FRAMEDONE */ - omap_dispc_interrupt_update(s); -} - -static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, unsigned size) -{ - struct omap_dss_s *s = opaque; - - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x00: /* RFBI_REVISION */ - return 0x10; - - case 0x10: /* RFBI_SYSCONFIG */ - return s->rfbi.idlemode; - - case 0x14: /* RFBI_SYSSTATUS */ - return 1 | (s->rfbi.busy << 8); /* RESETDONE */ - - case 0x40: /* RFBI_CONTROL */ - return s->rfbi.control; - - case 0x44: /* RFBI_PIXELCNT */ - return s->rfbi.pixels; - - case 0x48: /* RFBI_LINE_NUMBER */ - return s->rfbi.skiplines; - - case 0x58: /* RFBI_READ */ - case 0x5c: /* RFBI_STATUS */ - return s->rfbi.rxbuf; - - case 0x60: /* RFBI_CONFIG0 */ - return s->rfbi.config[0]; - case 0x64: /* RFBI_ONOFF_TIME0 */ - return s->rfbi.time[0]; - case 0x68: /* RFBI_CYCLE_TIME0 */ - return s->rfbi.time[1]; - case 0x6c: /* RFBI_DATA_CYCLE1_0 */ - return s->rfbi.data[0]; - case 0x70: /* RFBI_DATA_CYCLE2_0 */ - return s->rfbi.data[1]; - case 0x74: /* RFBI_DATA_CYCLE3_0 */ - return s->rfbi.data[2]; - - case 0x78: /* RFBI_CONFIG1 */ - return s->rfbi.config[1]; - case 0x7c: /* RFBI_ONOFF_TIME1 */ - return s->rfbi.time[2]; - case 0x80: /* RFBI_CYCLE_TIME1 */ - return s->rfbi.time[3]; - case 0x84: /* RFBI_DATA_CYCLE1_1 */ - return s->rfbi.data[3]; - case 0x88: /* RFBI_DATA_CYCLE2_1 */ - return s->rfbi.data[4]; - case 0x8c: /* RFBI_DATA_CYCLE3_1 */ - return s->rfbi.data[5]; - - case 0x90: /* RFBI_VSYNC_WIDTH */ - return s->rfbi.vsync; - case 0x94: /* RFBI_HSYNC_WIDTH */ - return s->rfbi.hsync; - } - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_rfbi_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_dss_s *s = opaque; - - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x10: /* RFBI_SYSCONFIG */ - if (value & 2) /* SOFTRESET */ - omap_rfbi_reset(s); - s->rfbi.idlemode = value & 0x19; - break; - - case 0x40: /* RFBI_CONTROL */ - s->rfbi.control = value & 0xf; - s->rfbi.enable = value & 1; - if (value & (1 << 4) && /* ITE */ - !(s->rfbi.config[0] & s->rfbi.config[1] & 0xc)) - omap_rfbi_transfer_start(s); - break; - - case 0x44: /* RFBI_PIXELCNT */ - s->rfbi.pixels = value; - break; - - case 0x48: /* RFBI_LINE_NUMBER */ - s->rfbi.skiplines = value & 0x7ff; - break; - - case 0x4c: /* RFBI_CMD */ - if ((s->rfbi.control & (1 << 2)) && s->rfbi.chip[0]) - s->rfbi.chip[0]->write(s->rfbi.chip[0]->opaque, 0, value & 0xffff); - if ((s->rfbi.control & (1 << 3)) && s->rfbi.chip[1]) - s->rfbi.chip[1]->write(s->rfbi.chip[1]->opaque, 0, value & 0xffff); - break; - case 0x50: /* RFBI_PARAM */ - if ((s->rfbi.control & (1 << 2)) && s->rfbi.chip[0]) - s->rfbi.chip[0]->write(s->rfbi.chip[0]->opaque, 1, value & 0xffff); - if ((s->rfbi.control & (1 << 3)) && s->rfbi.chip[1]) - s->rfbi.chip[1]->write(s->rfbi.chip[1]->opaque, 1, value & 0xffff); - break; - case 0x54: /* RFBI_DATA */ - /* TODO: take into account the format set up in s->rfbi.config[?] and - * s->rfbi.data[?], but special-case the most usual scenario so that - * speed doesn't suffer. */ - if ((s->rfbi.control & (1 << 2)) && s->rfbi.chip[0]) { - s->rfbi.chip[0]->write(s->rfbi.chip[0]->opaque, 1, value & 0xffff); - s->rfbi.chip[0]->write(s->rfbi.chip[0]->opaque, 1, value >> 16); - } - if ((s->rfbi.control & (1 << 3)) && s->rfbi.chip[1]) { - s->rfbi.chip[1]->write(s->rfbi.chip[1]->opaque, 1, value & 0xffff); - s->rfbi.chip[1]->write(s->rfbi.chip[1]->opaque, 1, value >> 16); - } - if (!-- s->rfbi.pixels) - omap_rfbi_transfer_stop(s); - break; - case 0x58: /* RFBI_READ */ - if ((s->rfbi.control & (1 << 2)) && s->rfbi.chip[0]) - s->rfbi.rxbuf = s->rfbi.chip[0]->read(s->rfbi.chip[0]->opaque, 1); - else if ((s->rfbi.control & (1 << 3)) && s->rfbi.chip[1]) - s->rfbi.rxbuf = s->rfbi.chip[1]->read(s->rfbi.chip[1]->opaque, 1); - if (!-- s->rfbi.pixels) - omap_rfbi_transfer_stop(s); - break; - - case 0x5c: /* RFBI_STATUS */ - if ((s->rfbi.control & (1 << 2)) && s->rfbi.chip[0]) - s->rfbi.rxbuf = s->rfbi.chip[0]->read(s->rfbi.chip[0]->opaque, 0); - else if ((s->rfbi.control & (1 << 3)) && s->rfbi.chip[1]) - s->rfbi.rxbuf = s->rfbi.chip[1]->read(s->rfbi.chip[1]->opaque, 0); - if (!-- s->rfbi.pixels) - omap_rfbi_transfer_stop(s); - break; - - case 0x60: /* RFBI_CONFIG0 */ - s->rfbi.config[0] = value & 0x003f1fff; - break; - - case 0x64: /* RFBI_ONOFF_TIME0 */ - s->rfbi.time[0] = value & 0x3fffffff; - break; - case 0x68: /* RFBI_CYCLE_TIME0 */ - s->rfbi.time[1] = value & 0x0fffffff; - break; - case 0x6c: /* RFBI_DATA_CYCLE1_0 */ - s->rfbi.data[0] = value & 0x0f1f0f1f; - break; - case 0x70: /* RFBI_DATA_CYCLE2_0 */ - s->rfbi.data[1] = value & 0x0f1f0f1f; - break; - case 0x74: /* RFBI_DATA_CYCLE3_0 */ - s->rfbi.data[2] = value & 0x0f1f0f1f; - break; - case 0x78: /* RFBI_CONFIG1 */ - s->rfbi.config[1] = value & 0x003f1fff; - break; - - case 0x7c: /* RFBI_ONOFF_TIME1 */ - s->rfbi.time[2] = value & 0x3fffffff; - break; - case 0x80: /* RFBI_CYCLE_TIME1 */ - s->rfbi.time[3] = value & 0x0fffffff; - break; - case 0x84: /* RFBI_DATA_CYCLE1_1 */ - s->rfbi.data[3] = value & 0x0f1f0f1f; - break; - case 0x88: /* RFBI_DATA_CYCLE2_1 */ - s->rfbi.data[4] = value & 0x0f1f0f1f; - break; - case 0x8c: /* RFBI_DATA_CYCLE3_1 */ - s->rfbi.data[5] = value & 0x0f1f0f1f; - break; - - case 0x90: /* RFBI_VSYNC_WIDTH */ - s->rfbi.vsync = value & 0xffff; - break; - case 0x94: /* RFBI_HSYNC_WIDTH */ - s->rfbi.hsync = value & 0xffff; - break; - - default: - OMAP_BAD_REG(addr); - } -} - -static const MemoryRegionOps omap_rfbi_ops = { - .read = omap_rfbi_read, - .write = omap_rfbi_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static uint64_t omap_venc_read(void *opaque, hwaddr addr, - unsigned size) -{ - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x00: /* REV_ID */ - case 0x04: /* STATUS */ - case 0x08: /* F_CONTROL */ - case 0x10: /* VIDOUT_CTRL */ - case 0x14: /* SYNC_CTRL */ - case 0x1c: /* LLEN */ - case 0x20: /* FLENS */ - case 0x24: /* HFLTR_CTRL */ - case 0x28: /* CC_CARR_WSS_CARR */ - case 0x2c: /* C_PHASE */ - case 0x30: /* GAIN_U */ - case 0x34: /* GAIN_V */ - case 0x38: /* GAIN_Y */ - case 0x3c: /* BLACK_LEVEL */ - case 0x40: /* BLANK_LEVEL */ - case 0x44: /* X_COLOR */ - case 0x48: /* M_CONTROL */ - case 0x4c: /* BSTAMP_WSS_DATA */ - case 0x50: /* S_CARR */ - case 0x54: /* LINE21 */ - case 0x58: /* LN_SEL */ - case 0x5c: /* L21__WC_CTL */ - case 0x60: /* HTRIGGER_VTRIGGER */ - case 0x64: /* SAVID__EAVID */ - case 0x68: /* FLEN__FAL */ - case 0x6c: /* LAL__PHASE_RESET */ - case 0x70: /* HS_INT_START_STOP_X */ - case 0x74: /* HS_EXT_START_STOP_X */ - case 0x78: /* VS_INT_START_X */ - case 0x7c: /* VS_INT_STOP_X__VS_INT_START_Y */ - case 0x80: /* VS_INT_STOP_Y__VS_INT_START_X */ - case 0x84: /* VS_EXT_STOP_X__VS_EXT_START_Y */ - case 0x88: /* VS_EXT_STOP_Y */ - case 0x90: /* AVID_START_STOP_X */ - case 0x94: /* AVID_START_STOP_Y */ - case 0xa0: /* FID_INT_START_X__FID_INT_START_Y */ - case 0xa4: /* FID_INT_OFFSET_Y__FID_EXT_START_X */ - case 0xa8: /* FID_EXT_START_Y__FID_EXT_OFFSET_Y */ - case 0xb0: /* TVDETGP_INT_START_STOP_X */ - case 0xb4: /* TVDETGP_INT_START_STOP_Y */ - case 0xb8: /* GEN_CTRL */ - case 0xc4: /* DAC_TST__DAC_A */ - case 0xc8: /* DAC_B__DAC_C */ - return 0; - - default: - break; - } - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_venc_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - if (size != 4) { - omap_badwidth_write32(opaque, addr, size); - return; - } - - switch (addr) { - case 0x08: /* F_CONTROL */ - case 0x10: /* VIDOUT_CTRL */ - case 0x14: /* SYNC_CTRL */ - case 0x1c: /* LLEN */ - case 0x20: /* FLENS */ - case 0x24: /* HFLTR_CTRL */ - case 0x28: /* CC_CARR_WSS_CARR */ - case 0x2c: /* C_PHASE */ - case 0x30: /* GAIN_U */ - case 0x34: /* GAIN_V */ - case 0x38: /* GAIN_Y */ - case 0x3c: /* BLACK_LEVEL */ - case 0x40: /* BLANK_LEVEL */ - case 0x44: /* X_COLOR */ - case 0x48: /* M_CONTROL */ - case 0x4c: /* BSTAMP_WSS_DATA */ - case 0x50: /* S_CARR */ - case 0x54: /* LINE21 */ - case 0x58: /* LN_SEL */ - case 0x5c: /* L21__WC_CTL */ - case 0x60: /* HTRIGGER_VTRIGGER */ - case 0x64: /* SAVID__EAVID */ - case 0x68: /* FLEN__FAL */ - case 0x6c: /* LAL__PHASE_RESET */ - case 0x70: /* HS_INT_START_STOP_X */ - case 0x74: /* HS_EXT_START_STOP_X */ - case 0x78: /* VS_INT_START_X */ - case 0x7c: /* VS_INT_STOP_X__VS_INT_START_Y */ - case 0x80: /* VS_INT_STOP_Y__VS_INT_START_X */ - case 0x84: /* VS_EXT_STOP_X__VS_EXT_START_Y */ - case 0x88: /* VS_EXT_STOP_Y */ - case 0x90: /* AVID_START_STOP_X */ - case 0x94: /* AVID_START_STOP_Y */ - case 0xa0: /* FID_INT_START_X__FID_INT_START_Y */ - case 0xa4: /* FID_INT_OFFSET_Y__FID_EXT_START_X */ - case 0xa8: /* FID_EXT_START_Y__FID_EXT_OFFSET_Y */ - case 0xb0: /* TVDETGP_INT_START_STOP_X */ - case 0xb4: /* TVDETGP_INT_START_STOP_Y */ - case 0xb8: /* GEN_CTRL */ - case 0xc4: /* DAC_TST__DAC_A */ - case 0xc8: /* DAC_B__DAC_C */ - break; - - default: - OMAP_BAD_REG(addr); - } -} - -static const MemoryRegionOps omap_venc_ops = { - .read = omap_venc_read, - .write = omap_venc_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static uint64_t omap_im3_read(void *opaque, hwaddr addr, - unsigned size) -{ - if (size != 4) { - return omap_badwidth_read32(opaque, addr); - } - - switch (addr) { - case 0x0a8: /* SBIMERRLOGA */ - case 0x0b0: /* SBIMERRLOG */ - case 0x190: /* SBIMSTATE */ - case 0x198: /* SBTMSTATE_L */ - case 0x19c: /* SBTMSTATE_H */ - case 0x1a8: /* SBIMCONFIG_L */ - case 0x1ac: /* SBIMCONFIG_H */ - case 0x1f8: /* SBID_L */ - case 0x1fc: /* SBID_H */ - return 0; - - default: - break; - } - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_im3_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x0b0: /* SBIMERRLOG */ - case 0x190: /* SBIMSTATE */ - case 0x198: /* SBTMSTATE_L */ - case 0x19c: /* SBTMSTATE_H */ - case 0x1a8: /* SBIMCONFIG_L */ - case 0x1ac: /* SBIMCONFIG_H */ - break; - - default: - OMAP_BAD_REG(addr); - } -} - -static const MemoryRegionOps omap_im3_ops = { - .read = omap_im3_read, - .write = omap_im3_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -struct omap_dss_s *omap_dss_init(struct omap_target_agent_s *ta, - MemoryRegion *sysmem, - hwaddr l3_base, - qemu_irq irq, qemu_irq drq, - omap_clk fck1, omap_clk fck2, omap_clk ck54m, - omap_clk ick1, omap_clk ick2) -{ - struct omap_dss_s *s = g_new0(struct omap_dss_s, 1); - - s->irq = irq; - s->drq = drq; - omap_dss_reset(s); - - memory_region_init_io(&s->iomem_diss1, NULL, &omap_diss_ops, s, "omap.diss1", - omap_l4_region_size(ta, 0)); - memory_region_init_io(&s->iomem_disc1, NULL, &omap_disc_ops, s, "omap.disc1", - omap_l4_region_size(ta, 1)); - memory_region_init_io(&s->iomem_rfbi1, NULL, &omap_rfbi_ops, s, "omap.rfbi1", - omap_l4_region_size(ta, 2)); - memory_region_init_io(&s->iomem_venc1, NULL, &omap_venc_ops, s, "omap.venc1", - omap_l4_region_size(ta, 3)); - memory_region_init_io(&s->iomem_im3, NULL, &omap_im3_ops, s, - "omap.im3", 0x1000); - - omap_l4_attach(ta, 0, &s->iomem_diss1); - omap_l4_attach(ta, 1, &s->iomem_disc1); - omap_l4_attach(ta, 2, &s->iomem_rfbi1); - omap_l4_attach(ta, 3, &s->iomem_venc1); - memory_region_add_subregion(sysmem, l3_base, &s->iomem_im3); - -#if 0 - s->state = graphic_console_init(omap_update_display, - omap_invalidate_display, omap_screen_dump, s); -#endif - - return s; -} - -void omap_rfbi_attach(struct omap_dss_s *s, int cs, struct rfbi_chip_s *chip) -{ - if (cs < 0 || cs > 1) - hw_error("%s: wrong CS %i\n", __func__, cs); - s->rfbi.chip[cs] = chip; -} diff --git a/hw/display/meson.build b/hw/display/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_BOCHS_DISPLAY', if_true: files('bochs-display.c')) system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210_fimd.c')) system_ss.add(when: 'CONFIG_FRAMEBUFFER', if_true: files('framebuffer.c')) -system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_dss.c')) system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_fb.c')) system_ss.add(when: 'CONFIG_SM501', if_true: files('sm501.c')) system_ss.add(when: 'CONFIG_TCX', if_true: files('tcx.c')) -- 2.34.1 The omap_l4 device is OMAP2 only, so we can remove it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-51-peter.maydell@linaro.org --- include/hw/arm/omap.h | 42 ----------- hw/misc/omap_l4.c | 162 ------------------------------------------ hw/misc/meson.build | 1 - 3 files changed, 205 deletions(-) delete mode 100644 hw/misc/omap_l4.c diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ DECLARE_INSTANCE_CHECKER(Omap1GpioState, OMAP1_GPIO, /* TODO: clock framework (see above) */ void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); -/* OMAP2 l4 Interconnect */ -struct omap_l4_s; -struct omap_l4_region_s { - hwaddr offset; - size_t size; - int access; -}; -struct omap_l4_agent_info_s { - int ta; - int region; - int regions; - int ta_region; -}; -struct omap_target_agent_s { - MemoryRegion iomem; - struct omap_l4_s *bus; - int regions; - const struct omap_l4_region_s *start; - hwaddr base; - uint32_t component; - uint32_t control; - uint32_t status; -}; -struct omap_l4_s *omap_l4_init(MemoryRegion *address_space, - hwaddr base, int ta_num); - -struct omap_target_agent_s; -struct omap_target_agent_s *omap_l4ta_get( - struct omap_l4_s *bus, - const struct omap_l4_region_s *regions, - const struct omap_l4_agent_info_s *agents, - int cs); -hwaddr omap_l4_attach(struct omap_target_agent_s *ta, - int region, MemoryRegion *mr); -hwaddr omap_l4_region_base(struct omap_target_agent_s *ta, - int region); -hwaddr omap_l4_region_size(struct omap_target_agent_s *ta, - int region); - /* * Common IRQ numbers for level 1 interrupt handler * See /usr/include/asm-arm/arch-omap/irqs.h in Linux. @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s { uint16_t dsp_idlect2; uint16_t dsp_rstct2; } clkm; - - /* OMAP2-only peripherals */ - struct omap_l4_s *l4; }; /* omap1.c */ diff --git a/hw/misc/omap_l4.c b/hw/misc/omap_l4.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/misc/omap_l4.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * TI OMAP L4 interconnect emulation. - * - * Copyright (C) 2007-2009 Nokia Corporation - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 or - * (at your option) any later version of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ -#include "qemu/osdep.h" -#include "hw/arm/omap.h" - -struct omap_l4_s { - MemoryRegion *address_space; - hwaddr base; - int ta_num; - struct omap_target_agent_s ta[]; -}; - -struct omap_l4_s *omap_l4_init(MemoryRegion *address_space, - hwaddr base, int ta_num) -{ - struct omap_l4_s *bus = g_malloc0( - sizeof(*bus) + ta_num * sizeof(*bus->ta)); - - bus->address_space = address_space; - bus->ta_num = ta_num; - bus->base = base; - - return bus; -} - -hwaddr omap_l4_region_base(struct omap_target_agent_s *ta, - int region) -{ - return ta->bus->base + ta->start[region].offset; -} - -hwaddr omap_l4_region_size(struct omap_target_agent_s *ta, - int region) -{ - return ta->start[region].size; -} - -static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, unsigned size) -{ - struct omap_target_agent_s *s = opaque; - - if (size != 2) { - return omap_badwidth_read16(opaque, addr); - } - - switch (addr) { - case 0x00: /* COMPONENT */ - return s->component; - - case 0x20: /* AGENT_CONTROL */ - return s->control; - - case 0x28: /* AGENT_STATUS */ - return s->status; - } - - OMAP_BAD_REG(addr); - return 0; -} - -static void omap_l4ta_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_target_agent_s *s = opaque; - - if (size != 4) { - omap_badwidth_write32(opaque, addr, value); - return; - } - - switch (addr) { - case 0x00: /* COMPONENT */ - case 0x28: /* AGENT_STATUS */ - OMAP_RO_REG(addr); - break; - - case 0x20: /* AGENT_CONTROL */ - s->control = value & 0x01000700; - if (value & 1) /* OCP_RESET */ - s->status &= ~1; /* REQ_TIMEOUT */ - break; - - default: - OMAP_BAD_REG(addr); - } -} - -static const MemoryRegionOps omap_l4ta_ops = { - .read = omap_l4ta_read, - .write = omap_l4ta_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -struct omap_target_agent_s *omap_l4ta_get(struct omap_l4_s *bus, - const struct omap_l4_region_s *regions, - const struct omap_l4_agent_info_s *agents, - int cs) -{ - int i; - struct omap_target_agent_s *ta = NULL; - const struct omap_l4_agent_info_s *info = NULL; - - for (i = 0; i < bus->ta_num; i ++) - if (agents[i].ta == cs) { - ta = &bus->ta[i]; - info = &agents[i]; - break; - } - if (!ta) { - fprintf(stderr, "%s: bad target agent (%i)\n", __func__, cs); - exit(-1); - } - - ta->bus = bus; - ta->start = &regions[info->region]; - ta->regions = info->regions; - - ta->component = ('Q' << 24) | ('E' << 16) | ('M' << 8) | ('U' << 0); - ta->status = 0x00000000; - ta->control = 0x00000200; /* XXX 01000200 for L4TAO */ - - memory_region_init_io(&ta->iomem, NULL, &omap_l4ta_ops, ta, "omap.l4ta", - omap_l4_region_size(ta, info->ta_region)); - omap_l4_attach(ta, info->ta_region, &ta->iomem); - - return ta; -} - -hwaddr omap_l4_attach(struct omap_target_agent_s *ta, - int region, MemoryRegion *mr) -{ - hwaddr base; - - if (region < 0 || region >= ta->regions) { - fprintf(stderr, "%s: bad io region (%i)\n", __func__, region); - exit(-1); - } - - base = ta->bus->base + ta->start[region].offset; - if (mr) { - memory_region_add_subregion(ta->bus->address_space, base, mr); - } - - return base; -} diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( )) system_ss.add(when: 'CONFIG_OMAP', if_true: files( 'omap_clk.c', - 'omap_l4.c', )) system_ss.add(when: 'CONFIG_RASPI', if_true: files( 'bcm2835_mbox.c', -- 2.34.1 Remove the handling for all non-OMAP1 SoCs. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240903160751.4100218-52-peter.maydell@linaro.org --- hw/misc/omap_clk.c | 527 +-------------------------------------------- 1 file changed, 2 insertions(+), 525 deletions(-) diff --git a/hw/misc/omap_clk.c b/hw/misc/omap_clk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_clk.c +++ b/hw/misc/omap_clk.c @@ -XXX,XX +XXX,XX @@ struct clk { #define CLOCK_IN_OMAP730 (1 << 11) #define CLOCK_IN_OMAP1510 (1 << 12) #define CLOCK_IN_OMAP16XX (1 << 13) -#define CLOCK_IN_OMAP242X (1 << 14) -#define CLOCK_IN_OMAP243X (1 << 15) -#define CLOCK_IN_OMAP343X (1 << 16) uint32_t flags; int id; @@ -XXX,XX +XXX,XX @@ static struct clk xtal_osc12m = { static struct clk xtal_osc32k = { .name = "xtal_osc_32k", .rate = 32768, - .flags = CLOCK_IN_OMAP1510 | CLOCK_IN_OMAP16XX | CLOCK_IN_OMAP310 | - CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, + .flags = CLOCK_IN_OMAP1510 | CLOCK_IN_OMAP16XX | CLOCK_IN_OMAP310, }; static struct clk ck_ref = { @@ -XXX,XX +XXX,XX @@ static struct clk i2c_ick = { static struct clk clk32k = { .name = "clk32-kHz", .flags = CLOCK_IN_OMAP310 | CLOCK_IN_OMAP1510 | CLOCK_IN_OMAP16XX | - CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X | ALWAYS_ENABLED, + ALWAYS_ENABLED, .parent = &xtal_osc32k, }; -static struct clk ref_clk = { - .name = "ref_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X | ALWAYS_ENABLED, - .rate = 12000000, /* 12 MHz or 13 MHz or 19.2 MHz */ - /*.parent = sys.xtalin */ -}; - -static struct clk apll_96m = { - .name = "apll_96m", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X | ALWAYS_ENABLED, - .rate = 96000000, - /*.parent = ref_clk */ -}; - -static struct clk apll_54m = { - .name = "apll_54m", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X | ALWAYS_ENABLED, - .rate = 54000000, - /*.parent = ref_clk */ -}; - -static struct clk sys_clk = { - .name = "sys_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X | ALWAYS_ENABLED, - .rate = 32768, - /*.parent = sys.xtalin */ -}; - -static struct clk sleep_clk = { - .name = "sleep_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X | ALWAYS_ENABLED, - .rate = 32768, - /*.parent = sys.xtalin */ -}; - -static struct clk dpll_ck = { - .name = "dpll", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X | ALWAYS_ENABLED, - .parent = &ref_clk, -}; - -static struct clk dpll_x2_ck = { - .name = "dpll_x2", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X | ALWAYS_ENABLED, - .parent = &ref_clk, -}; - -static struct clk wdt1_sys_clk = { - .name = "wdt1_sys_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X | ALWAYS_ENABLED, - .rate = 32768, - /*.parent = sys.xtalin */ -}; - -static struct clk func_96m_clk = { - .name = "func_96m_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .divisor = 1, - .parent = &apll_96m, -}; - -static struct clk func_48m_clk = { - .name = "func_48m_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .divisor = 2, - .parent = &apll_96m, -}; - -static struct clk func_12m_clk = { - .name = "func_12m_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .divisor = 8, - .parent = &apll_96m, -}; - -static struct clk func_54m_clk = { - .name = "func_54m_clk", - .flags = CLOCK_IN_OMAP242X, - .divisor = 1, - .parent = &apll_54m, -}; - -static struct clk sys_clkout = { - .name = "clkout", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk sys_clkout2 = { - .name = "clkout2", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_clk = { - .name = "core_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &dpll_x2_ck, /* Switchable between dpll_ck and clk32k */ -}; - -static struct clk l3_clk = { - .name = "l3_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_clk, -}; - -static struct clk core_l4_iclk = { - .name = "core_l4_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &l3_clk, -}; - -static struct clk wu_l4_iclk = { - .name = "wu_l4_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &l3_clk, -}; - -static struct clk core_l3_iclk = { - .name = "core_l3_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_clk, -}; - -static struct clk core_l4_usb_clk = { - .name = "core_l4_usb_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &l3_clk, -}; - -static struct clk wu_gpt1_clk = { - .name = "wu_gpt1_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk wu_32k_clk = { - .name = "wu_32k_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk uart1_fclk = { - .name = "uart1_fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &func_48m_clk, -}; - -static struct clk uart1_iclk = { - .name = "uart1_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l4_iclk, -}; - -static struct clk uart2_fclk = { - .name = "uart2_fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &func_48m_clk, -}; - -static struct clk uart2_iclk = { - .name = "uart2_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l4_iclk, -}; - -static struct clk uart3_fclk = { - .name = "uart3_fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &func_48m_clk, -}; - -static struct clk uart3_iclk = { - .name = "uart3_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l4_iclk, -}; - -static struct clk mpu_fclk = { - .name = "mpu_fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_clk, -}; - -static struct clk mpu_iclk = { - .name = "mpu_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_clk, -}; - -static struct clk int_m_fclk = { - .name = "int_m_fclk", - .alias = "mpu_intc_fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_clk, -}; - -static struct clk int_m_iclk = { - .name = "int_m_iclk", - .alias = "mpu_intc_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_clk, -}; - -static struct clk core_gpt2_clk = { - .name = "core_gpt2_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt3_clk = { - .name = "core_gpt3_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt4_clk = { - .name = "core_gpt4_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt5_clk = { - .name = "core_gpt5_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt6_clk = { - .name = "core_gpt6_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt7_clk = { - .name = "core_gpt7_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt8_clk = { - .name = "core_gpt8_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt9_clk = { - .name = "core_gpt9_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt10_clk = { - .name = "core_gpt10_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt11_clk = { - .name = "core_gpt11_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk core_gpt12_clk = { - .name = "core_gpt12_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, -}; - -static struct clk mcbsp1_clk = { - .name = "mcbsp1_cg", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .divisor = 2, - .parent = &func_96m_clk, -}; - -static struct clk mcbsp2_clk = { - .name = "mcbsp2_cg", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .divisor = 2, - .parent = &func_96m_clk, -}; - -static struct clk emul_clk = { - .name = "emul_ck", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &func_54m_clk, -}; - -static struct clk sdma_fclk = { - .name = "sdma_fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &l3_clk, -}; - -static struct clk sdma_iclk = { - .name = "sdma_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l3_iclk, /* core_l4_iclk for the configuration port */ -}; - -static struct clk i2c1_fclk = { - .name = "i2c1.fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &func_12m_clk, - .divisor = 1, -}; - -static struct clk i2c1_iclk = { - .name = "i2c1.iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l4_iclk, -}; - -static struct clk i2c2_fclk = { - .name = "i2c2.fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &func_12m_clk, - .divisor = 1, -}; - -static struct clk i2c2_iclk = { - .name = "i2c2.iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l4_iclk, -}; - -static struct clk gpio_dbclk[5] = { - { - .name = "gpio1_dbclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &wu_32k_clk, - }, { - .name = "gpio2_dbclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &wu_32k_clk, - }, { - .name = "gpio3_dbclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &wu_32k_clk, - }, { - .name = "gpio4_dbclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &wu_32k_clk, - }, { - .name = "gpio5_dbclk", - .flags = CLOCK_IN_OMAP243X, - .parent = &wu_32k_clk, - }, -}; - -static struct clk gpio_iclk = { - .name = "gpio_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &wu_l4_iclk, -}; - -static struct clk mmc_fck = { - .name = "mmc_fclk", - .flags = CLOCK_IN_OMAP242X, - .parent = &func_96m_clk, -}; - -static struct clk mmc_ick = { - .name = "mmc_iclk", - .flags = CLOCK_IN_OMAP242X, - .parent = &core_l4_iclk, -}; - -static struct clk spi_fclk[3] = { - { - .name = "spi1_fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &func_48m_clk, - }, { - .name = "spi2_fclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &func_48m_clk, - }, { - .name = "spi3_fclk", - .flags = CLOCK_IN_OMAP243X, - .parent = &func_48m_clk, - }, -}; - -static struct clk dss_clk[2] = { - { - .name = "dss_clk1", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_clk, - }, { - .name = "dss_clk2", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &sys_clk, - }, -}; - -static struct clk dss_54m_clk = { - .name = "dss_54m_clk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &func_54m_clk, -}; - -static struct clk dss_l3_iclk = { - .name = "dss_l3_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l3_iclk, -}; - -static struct clk dss_l4_iclk = { - .name = "dss_l4_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l4_iclk, -}; - -static struct clk spi_iclk[3] = { - { - .name = "spi1_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l4_iclk, - }, { - .name = "spi2_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - .parent = &core_l4_iclk, - }, { - .name = "spi3_iclk", - .flags = CLOCK_IN_OMAP243X, - .parent = &core_l4_iclk, - }, -}; - -static struct clk omapctrl_clk = { - .name = "omapctrl_iclk", - .flags = CLOCK_IN_OMAP242X | CLOCK_IN_OMAP243X, - /* XXX Should be in WKUP domain */ - .parent = &core_l4_iclk, -}; - static struct clk *onchip_clks[] = { /* OMAP 1 */ @@ -XXX,XX +XXX,XX @@ static struct clk *onchip_clks[] = { &i2c_fck, &i2c_ick, - /* OMAP 2 */ - - &ref_clk, - &apll_96m, - &apll_54m, - &sys_clk, - &sleep_clk, - &dpll_ck, - &dpll_x2_ck, - &wdt1_sys_clk, - &func_96m_clk, - &func_48m_clk, - &func_12m_clk, - &func_54m_clk, - &sys_clkout, - &sys_clkout2, - &core_clk, - &l3_clk, - &core_l4_iclk, - &wu_l4_iclk, - &core_l3_iclk, - &core_l4_usb_clk, - &wu_gpt1_clk, - &wu_32k_clk, - &uart1_fclk, - &uart1_iclk, - &uart2_fclk, - &uart2_iclk, - &uart3_fclk, - &uart3_iclk, - &mpu_fclk, - &mpu_iclk, - &int_m_fclk, - &int_m_iclk, - &core_gpt2_clk, - &core_gpt3_clk, - &core_gpt4_clk, - &core_gpt5_clk, - &core_gpt6_clk, - &core_gpt7_clk, - &core_gpt8_clk, - &core_gpt9_clk, - &core_gpt10_clk, - &core_gpt11_clk, - &core_gpt12_clk, - &mcbsp1_clk, - &mcbsp2_clk, - &emul_clk, - &sdma_fclk, - &sdma_iclk, - &i2c1_fclk, - &i2c1_iclk, - &i2c2_fclk, - &i2c2_iclk, - &gpio_dbclk[0], - &gpio_dbclk[1], - &gpio_dbclk[2], - &gpio_dbclk[3], - &gpio_iclk, - &mmc_fck, - &mmc_ick, - &spi_fclk[0], - &spi_iclk[0], - &spi_fclk[1], - &spi_iclk[1], - &spi_fclk[2], - &spi_iclk[2], - &dss_clk[0], - &dss_clk[1], - &dss_54m_clk, - &dss_l3_iclk, - &dss_l4_iclk, - &omapctrl_clk, - NULL }; @@ -XXX,XX +XXX,XX @@ void omap_clk_init(struct omap_mpu_state_s *mpu) flag = CLOCK_IN_OMAP310; else if (cpu_is_omap1510(mpu)) flag = CLOCK_IN_OMAP1510; - else if (cpu_is_omap2410(mpu) || cpu_is_omap2420(mpu)) - flag = CLOCK_IN_OMAP242X; - else if (cpu_is_omap2430(mpu)) - flag = CLOCK_IN_OMAP243X; - else if (cpu_is_omap3430(mpu)) - flag = CLOCK_IN_OMAP243X; else return; -- 2.34.1 The omap_dma4 device was only used in the OMAP2 SoC, which has been removed. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-53-peter.maydell@linaro.org --- include/hw/arm/omap.h | 1 - hw/dma/omap_dma.c | 451 +----------------------------------------- 2 files changed, 3 insertions(+), 449 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ enum omap_dma_model { omap_dma_3_0, omap_dma_3_1, omap_dma_3_2, - omap_dma_4, }; struct soc_dma_s; diff --git a/hw/dma/omap_dma.c b/hw/dma/omap_dma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/omap_dma.c +++ b/hw/dma/omap_dma.c @@ -XXX,XX +XXX,XX @@ void omap_dma_reset(struct soc_dma_s *dma) struct omap_dma_s *s = dma->opaque; soc_dma_reset(s->dma); - if (s->model < omap_dma_4) - s->gcr = 0x0004; - else - s->gcr = 0x00010010; + s->gcr = 0x0004; s->ocp = 0x00000000; memset(&s->irqstat, 0, sizeof(s->irqstat)); memset(&s->irqen, 0, sizeof(s->irqen)); @@ -XXX,XX +XXX,XX @@ void omap_dma_reset(struct soc_dma_s *dma) s->lcd_ch.condition = 0; s->lcd_ch.interrupts = 0; s->lcd_ch.dual = 0; - if (s->model < omap_dma_4) - omap_dma_enable_3_1_mapping(s); + omap_dma_enable_3_1_mapping(s); for (i = 0; i < s->chans; i ++) { s->ch[i].suspend = 0; s->ch[i].prefetch = 0; @@ -XXX,XX +XXX,XX @@ void omap_dma_reset(struct soc_dma_s *dma) s->ch[i].repeat = 0; s->ch[i].auto_init = 0; s->ch[i].link_enabled = 0; - if (s->model < omap_dma_4) - s->ch[i].interrupts = 0x0003; - else - s->ch[i].interrupts = 0x0000; + s->ch[i].interrupts = 0x0003; s->ch[i].status = 0; s->ch[i].cstatus = 0; s->ch[i].active = 0; @@ -XXX,XX +XXX,XX @@ static void omap_dma_setcaps(struct omap_dma_s *s) case omap_dma_3_1: break; case omap_dma_3_2: - case omap_dma_4: /* XXX Only available for sDMA */ s->caps[0] = (1 << 19) | /* Constant Fill Capability */ @@ -XXX,XX +XXX,XX @@ struct soc_dma_s *omap_dma_init(hwaddr base, qemu_irq *irqs, return s->dma; } -static void omap_dma_interrupts_4_update(struct omap_dma_s *s) -{ - struct omap_dma_channel_s *ch = s->ch; - uint32_t bmp, bit; - - for (bmp = 0, bit = 1; bit; ch ++, bit <<= 1) - if (ch->status) { - bmp |= bit; - ch->cstatus |= ch->status; - ch->status = 0; - } - if ((s->irqstat[0] |= s->irqen[0] & bmp)) - qemu_irq_raise(s->irq[0]); - if ((s->irqstat[1] |= s->irqen[1] & bmp)) - qemu_irq_raise(s->irq[1]); - if ((s->irqstat[2] |= s->irqen[2] & bmp)) - qemu_irq_raise(s->irq[2]); - if ((s->irqstat[3] |= s->irqen[3] & bmp)) - qemu_irq_raise(s->irq[3]); -} - -static uint64_t omap_dma4_read(void *opaque, hwaddr addr, - unsigned size) -{ - struct omap_dma_s *s = opaque; - int irqn = 0, chnum; - struct omap_dma_channel_s *ch; - - if (size == 1) { - return omap_badwidth_read16(opaque, addr); - } - - switch (addr) { - case 0x00: /* DMA4_REVISION */ - return 0x40; - - case 0x14: /* DMA4_IRQSTATUS_L3 */ - irqn ++; - /* fall through */ - case 0x10: /* DMA4_IRQSTATUS_L2 */ - irqn ++; - /* fall through */ - case 0x0c: /* DMA4_IRQSTATUS_L1 */ - irqn ++; - /* fall through */ - case 0x08: /* DMA4_IRQSTATUS_L0 */ - return s->irqstat[irqn]; - - case 0x24: /* DMA4_IRQENABLE_L3 */ - irqn ++; - /* fall through */ - case 0x20: /* DMA4_IRQENABLE_L2 */ - irqn ++; - /* fall through */ - case 0x1c: /* DMA4_IRQENABLE_L1 */ - irqn ++; - /* fall through */ - case 0x18: /* DMA4_IRQENABLE_L0 */ - return s->irqen[irqn]; - - case 0x28: /* DMA4_SYSSTATUS */ - return 1; /* RESETDONE */ - - case 0x2c: /* DMA4_OCP_SYSCONFIG */ - return s->ocp; - - case 0x64: /* DMA4_CAPS_0 */ - return s->caps[0]; - case 0x6c: /* DMA4_CAPS_2 */ - return s->caps[2]; - case 0x70: /* DMA4_CAPS_3 */ - return s->caps[3]; - case 0x74: /* DMA4_CAPS_4 */ - return s->caps[4]; - - case 0x78: /* DMA4_GCR */ - return s->gcr; - - case 0x80 ... 0xfff: - addr -= 0x80; - chnum = addr / 0x60; - ch = s->ch + chnum; - addr -= chnum * 0x60; - break; - - default: - OMAP_BAD_REG(addr); - return 0; - } - - /* Per-channel registers */ - switch (addr) { - case 0x00: /* DMA4_CCR */ - return (ch->buf_disable << 25) | - (ch->src_sync << 24) | - (ch->prefetch << 23) | - ((ch->sync & 0x60) << 14) | - (ch->bs << 18) | - (ch->transparent_copy << 17) | - (ch->constant_fill << 16) | - (ch->mode[1] << 14) | - (ch->mode[0] << 12) | - (0 << 10) | (0 << 9) | - (ch->suspend << 8) | - (ch->enable << 7) | - (ch->priority << 6) | - (ch->fs << 5) | (ch->sync & 0x1f); - - case 0x04: /* DMA4_CLNK_CTRL */ - return (ch->link_enabled << 15) | ch->link_next_ch; - - case 0x08: /* DMA4_CICR */ - return ch->interrupts; - - case 0x0c: /* DMA4_CSR */ - return ch->cstatus; - - case 0x10: /* DMA4_CSDP */ - return (ch->endian[0] << 21) | - (ch->endian_lock[0] << 20) | - (ch->endian[1] << 19) | - (ch->endian_lock[1] << 18) | - (ch->write_mode << 16) | - (ch->burst[1] << 14) | - (ch->pack[1] << 13) | - (ch->translate[1] << 9) | - (ch->burst[0] << 7) | - (ch->pack[0] << 6) | - (ch->translate[0] << 2) | - (ch->data_type >> 1); - - case 0x14: /* DMA4_CEN */ - return ch->elements; - - case 0x18: /* DMA4_CFN */ - return ch->frames; - - case 0x1c: /* DMA4_CSSA */ - return ch->addr[0]; - - case 0x20: /* DMA4_CDSA */ - return ch->addr[1]; - - case 0x24: /* DMA4_CSEI */ - return ch->element_index[0]; - - case 0x28: /* DMA4_CSFI */ - return ch->frame_index[0]; - - case 0x2c: /* DMA4_CDEI */ - return ch->element_index[1]; - - case 0x30: /* DMA4_CDFI */ - return ch->frame_index[1]; - - case 0x34: /* DMA4_CSAC */ - return ch->active_set.src & 0xffff; - - case 0x38: /* DMA4_CDAC */ - return ch->active_set.dest & 0xffff; - - case 0x3c: /* DMA4_CCEN */ - return ch->active_set.element; - - case 0x40: /* DMA4_CCFN */ - return ch->active_set.frame; - - case 0x44: /* DMA4_COLOR */ - /* XXX only in sDMA */ - return ch->color; - - default: - OMAP_BAD_REG(addr); - return 0; - } -} - -static void omap_dma4_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - struct omap_dma_s *s = opaque; - int chnum, irqn = 0; - struct omap_dma_channel_s *ch; - - if (size == 1) { - omap_badwidth_write16(opaque, addr, value); - return; - } - - switch (addr) { - case 0x14: /* DMA4_IRQSTATUS_L3 */ - irqn ++; - /* fall through */ - case 0x10: /* DMA4_IRQSTATUS_L2 */ - irqn ++; - /* fall through */ - case 0x0c: /* DMA4_IRQSTATUS_L1 */ - irqn ++; - /* fall through */ - case 0x08: /* DMA4_IRQSTATUS_L0 */ - s->irqstat[irqn] &= ~value; - if (!s->irqstat[irqn]) - qemu_irq_lower(s->irq[irqn]); - return; - - case 0x24: /* DMA4_IRQENABLE_L3 */ - irqn ++; - /* fall through */ - case 0x20: /* DMA4_IRQENABLE_L2 */ - irqn ++; - /* fall through */ - case 0x1c: /* DMA4_IRQENABLE_L1 */ - irqn ++; - /* fall through */ - case 0x18: /* DMA4_IRQENABLE_L0 */ - s->irqen[irqn] = value; - return; - - case 0x2c: /* DMA4_OCP_SYSCONFIG */ - if (value & 2) /* SOFTRESET */ - omap_dma_reset(s->dma); - s->ocp = value & 0x3321; - if (((s->ocp >> 12) & 3) == 3) { /* MIDLEMODE */ - qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid DMA power mode\n", - __func__); - } - return; - - case 0x78: /* DMA4_GCR */ - s->gcr = value & 0x00ff00ff; - if ((value & 0xff) == 0x00) { /* MAX_CHANNEL_FIFO_DEPTH */ - qemu_log_mask(LOG_GUEST_ERROR, "%s: wrong FIFO depth in GCR\n", - __func__); - } - return; - - case 0x80 ... 0xfff: - addr -= 0x80; - chnum = addr / 0x60; - ch = s->ch + chnum; - addr -= chnum * 0x60; - break; - - case 0x00: /* DMA4_REVISION */ - case 0x28: /* DMA4_SYSSTATUS */ - case 0x64: /* DMA4_CAPS_0 */ - case 0x6c: /* DMA4_CAPS_2 */ - case 0x70: /* DMA4_CAPS_3 */ - case 0x74: /* DMA4_CAPS_4 */ - OMAP_RO_REG(addr); - return; - - default: - OMAP_BAD_REG(addr); - return; - } - - /* Per-channel registers */ - switch (addr) { - case 0x00: /* DMA4_CCR */ - ch->buf_disable = (value >> 25) & 1; - ch->src_sync = (value >> 24) & 1; /* XXX For CamDMA must be 1 */ - if (ch->buf_disable && !ch->src_sync) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Buffering disable is not allowed in " - "destination synchronised mode\n", __func__); - } - ch->prefetch = (value >> 23) & 1; - ch->bs = (value >> 18) & 1; - ch->transparent_copy = (value >> 17) & 1; - ch->constant_fill = (value >> 16) & 1; - ch->mode[1] = (omap_dma_addressing_t) ((value & 0xc000) >> 14); - ch->mode[0] = (omap_dma_addressing_t) ((value & 0x3000) >> 12); - ch->suspend = (value & 0x0100) >> 8; - ch->priority = (value & 0x0040) >> 6; - ch->fs = (value & 0x0020) >> 5; - if (ch->fs && ch->bs && ch->mode[0] && ch->mode[1]) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: For a packet transfer at least one port " - "must be constant-addressed\n", __func__); - } - ch->sync = (value & 0x001f) | ((value >> 14) & 0x0060); - /* XXX must be 0x01 for CamDMA */ - - if (value & 0x0080) - omap_dma_enable_channel(s, ch); - else - omap_dma_disable_channel(s, ch); - - break; - - case 0x04: /* DMA4_CLNK_CTRL */ - ch->link_enabled = (value >> 15) & 0x1; - ch->link_next_ch = value & 0x1f; - break; - - case 0x08: /* DMA4_CICR */ - ch->interrupts = value & 0x09be; - break; - - case 0x0c: /* DMA4_CSR */ - ch->cstatus &= ~value; - break; - - case 0x10: /* DMA4_CSDP */ - ch->endian[0] =(value >> 21) & 1; - ch->endian_lock[0] =(value >> 20) & 1; - ch->endian[1] =(value >> 19) & 1; - ch->endian_lock[1] =(value >> 18) & 1; - if (ch->endian[0] != ch->endian[1]) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: DMA endianness conversion enable attempt\n", - __func__); - } - ch->write_mode = (value >> 16) & 3; - ch->burst[1] = (value & 0xc000) >> 14; - ch->pack[1] = (value & 0x2000) >> 13; - ch->translate[1] = (value & 0x1e00) >> 9; - ch->burst[0] = (value & 0x0180) >> 7; - ch->pack[0] = (value & 0x0040) >> 6; - ch->translate[0] = (value & 0x003c) >> 2; - if (ch->translate[0] | ch->translate[1]) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: bad MReqAddressTranslate sideband signal\n", - __func__); - } - ch->data_type = 1 << (value & 3); - if ((value & 3) == 3) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: bad data_type for DMA channel\n", __func__); - ch->data_type >>= 1; - } - break; - - case 0x14: /* DMA4_CEN */ - ch->set_update = 1; - ch->elements = value & 0xffffff; - break; - - case 0x18: /* DMA4_CFN */ - ch->frames = value & 0xffff; - ch->set_update = 1; - break; - - case 0x1c: /* DMA4_CSSA */ - ch->addr[0] = (hwaddr) (uint32_t) value; - ch->set_update = 1; - break; - - case 0x20: /* DMA4_CDSA */ - ch->addr[1] = (hwaddr) (uint32_t) value; - ch->set_update = 1; - break; - - case 0x24: /* DMA4_CSEI */ - ch->element_index[0] = (int16_t) value; - ch->set_update = 1; - break; - - case 0x28: /* DMA4_CSFI */ - ch->frame_index[0] = (int32_t) value; - ch->set_update = 1; - break; - - case 0x2c: /* DMA4_CDEI */ - ch->element_index[1] = (int16_t) value; - ch->set_update = 1; - break; - - case 0x30: /* DMA4_CDFI */ - ch->frame_index[1] = (int32_t) value; - ch->set_update = 1; - break; - - case 0x44: /* DMA4_COLOR */ - /* XXX only in sDMA */ - ch->color = value; - break; - - case 0x34: /* DMA4_CSAC */ - case 0x38: /* DMA4_CDAC */ - case 0x3c: /* DMA4_CCEN */ - case 0x40: /* DMA4_CCFN */ - OMAP_RO_REG(addr); - break; - - default: - OMAP_BAD_REG(addr); - } -} - -static const MemoryRegionOps omap_dma4_ops = { - .read = omap_dma4_read, - .write = omap_dma4_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -struct soc_dma_s *omap_dma4_init(hwaddr base, qemu_irq *irqs, - MemoryRegion *sysmem, - struct omap_mpu_state_s *mpu, int fifo, - int chans, omap_clk iclk, omap_clk fclk) -{ - int i; - struct omap_dma_s *s = g_new0(struct omap_dma_s, 1); - - s->model = omap_dma_4; - s->chans = chans; - s->mpu = mpu; - s->clk = fclk; - - s->dma = soc_dma_init(s->chans); - s->dma->freq = omap_clk_getrate(fclk); - s->dma->transfer_fn = omap_dma_transfer_generic; - s->dma->setup_fn = omap_dma_transfer_setup; - s->dma->drq = qemu_allocate_irqs(omap_dma_request, s, 64); - s->dma->opaque = s; - for (i = 0; i < s->chans; i ++) { - s->ch[i].dma = &s->dma->ch[i]; - s->dma->ch[i].opaque = &s->ch[i]; - } - - memcpy(&s->irq, irqs, sizeof(s->irq)); - s->intr_update = omap_dma_interrupts_4_update; - - omap_dma_setcaps(s); - omap_clk_adduser(s->clk, qemu_allocate_irq(omap_dma_clk_update, s, 0)); - omap_dma_reset(s->dma); - omap_dma_clk_update(s, 0, !!s->dma->freq); - - memory_region_init_io(&s->iomem, NULL, &omap_dma4_ops, s, "omap.dma4", 0x1000); - memory_region_add_subregion(sysmem, base, &s->iomem); - - mpu->drq = s->dma->drq; - - return s->dma; -} - struct omap_dma_lcd_channel_s *omap_dma_get_lcdch(struct soc_dma_s *dma) { struct omap_dma_s *s = dma->opaque; -- 2.34.1 Remove some defines and enums that are OMAP2 specific and no longer used anywhere. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240903160751.4100218-54-peter.maydell@linaro.org --- include/hw/arm/omap.h | 207 ------------------------------------------ 1 file changed, 207 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" # define OMAP_EMIFS_BASE 0x00000000 -# define OMAP2_Q0_BASE 0x00000000 # define OMAP_CS0_BASE 0x00000000 # define OMAP_CS1_BASE 0x04000000 # define OMAP_CS2_BASE 0x08000000 @@ -XXX,XX +XXX,XX @@ # define OMAP_EMIFF_BASE 0x10000000 # define OMAP_IMIF_BASE 0x20000000 # define OMAP_LOCALBUS_BASE 0x30000000 -# define OMAP2_Q1_BASE 0x40000000 -# define OMAP2_L4_BASE 0x48000000 -# define OMAP2_SRAM_BASE 0x40200000 -# define OMAP2_L3_BASE 0x68000000 -# define OMAP2_Q2_BASE 0x80000000 -# define OMAP2_Q3_BASE 0xc0000000 # define OMAP_MPUI_BASE 0xe1000000 # define OMAP730_SRAM_SIZE 0x00032000 # define OMAP15XX_SRAM_SIZE 0x00030000 # define OMAP16XX_SRAM_SIZE 0x00004000 # define OMAP1611_SRAM_SIZE 0x0003e800 -# define OMAP242X_SRAM_SIZE 0x000a0000 -# define OMAP243X_SRAM_SIZE 0x00010000 # define OMAP_CS0_SIZE 0x04000000 # define OMAP_CS1_SIZE 0x04000000 # define OMAP_CS2_SIZE 0x04000000 @@ -XXX,XX +XXX,XX @@ void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); # define OMAP_INT_730_DMA_CH15 62 # define OMAP_INT_730_NAND 63 -/* - * OMAP-24xx common IRQ numbers - */ -# define OMAP_INT_24XX_STI 4 -# define OMAP_INT_24XX_SYS_NIRQ 7 -# define OMAP_INT_24XX_L3_IRQ 10 -# define OMAP_INT_24XX_PRCM_MPU_IRQ 11 -# define OMAP_INT_24XX_SDMA_IRQ0 12 -# define OMAP_INT_24XX_SDMA_IRQ1 13 -# define OMAP_INT_24XX_SDMA_IRQ2 14 -# define OMAP_INT_24XX_SDMA_IRQ3 15 -# define OMAP_INT_243X_MCBSP2_IRQ 16 -# define OMAP_INT_243X_MCBSP3_IRQ 17 -# define OMAP_INT_243X_MCBSP4_IRQ 18 -# define OMAP_INT_243X_MCBSP5_IRQ 19 -# define OMAP_INT_24XX_GPMC_IRQ 20 -# define OMAP_INT_24XX_GUFFAW_IRQ 21 -# define OMAP_INT_24XX_IVA_IRQ 22 -# define OMAP_INT_24XX_EAC_IRQ 23 -# define OMAP_INT_24XX_CAM_IRQ 24 -# define OMAP_INT_24XX_DSS_IRQ 25 -# define OMAP_INT_24XX_MAIL_U0_MPU 26 -# define OMAP_INT_24XX_DSP_UMA 27 -# define OMAP_INT_24XX_DSP_MMU 28 -# define OMAP_INT_24XX_GPIO_BANK1 29 -# define OMAP_INT_24XX_GPIO_BANK2 30 -# define OMAP_INT_24XX_GPIO_BANK3 31 -# define OMAP_INT_24XX_GPIO_BANK4 32 -# define OMAP_INT_243X_GPIO_BANK5 33 -# define OMAP_INT_24XX_MAIL_U3_MPU 34 -# define OMAP_INT_24XX_WDT3 35 -# define OMAP_INT_24XX_WDT4 36 -# define OMAP_INT_24XX_GPTIMER1 37 -# define OMAP_INT_24XX_GPTIMER2 38 -# define OMAP_INT_24XX_GPTIMER3 39 -# define OMAP_INT_24XX_GPTIMER4 40 -# define OMAP_INT_24XX_GPTIMER5 41 -# define OMAP_INT_24XX_GPTIMER6 42 -# define OMAP_INT_24XX_GPTIMER7 43 -# define OMAP_INT_24XX_GPTIMER8 44 -# define OMAP_INT_24XX_GPTIMER9 45 -# define OMAP_INT_24XX_GPTIMER10 46 -# define OMAP_INT_24XX_GPTIMER11 47 -# define OMAP_INT_24XX_GPTIMER12 48 -# define OMAP_INT_24XX_PKA_IRQ 50 -# define OMAP_INT_24XX_SHA1MD5_IRQ 51 -# define OMAP_INT_24XX_RNG_IRQ 52 -# define OMAP_INT_24XX_MG_IRQ 53 -# define OMAP_INT_24XX_I2C1_IRQ 56 -# define OMAP_INT_24XX_I2C2_IRQ 57 -# define OMAP_INT_24XX_MCBSP1_IRQ_TX 59 -# define OMAP_INT_24XX_MCBSP1_IRQ_RX 60 -# define OMAP_INT_24XX_MCBSP2_IRQ_TX 62 -# define OMAP_INT_24XX_MCBSP2_IRQ_RX 63 -# define OMAP_INT_243X_MCBSP1_IRQ 64 -# define OMAP_INT_24XX_MCSPI1_IRQ 65 -# define OMAP_INT_24XX_MCSPI2_IRQ 66 -# define OMAP_INT_24XX_SSI1_IRQ0 67 -# define OMAP_INT_24XX_SSI1_IRQ1 68 -# define OMAP_INT_24XX_SSI2_IRQ0 69 -# define OMAP_INT_24XX_SSI2_IRQ1 70 -# define OMAP_INT_24XX_SSI_GDD_IRQ 71 -# define OMAP_INT_24XX_UART1_IRQ 72 -# define OMAP_INT_24XX_UART2_IRQ 73 -# define OMAP_INT_24XX_UART3_IRQ 74 -# define OMAP_INT_24XX_USB_IRQ_GEN 75 -# define OMAP_INT_24XX_USB_IRQ_NISO 76 -# define OMAP_INT_24XX_USB_IRQ_ISO 77 -# define OMAP_INT_24XX_USB_IRQ_HGEN 78 -# define OMAP_INT_24XX_USB_IRQ_HSOF 79 -# define OMAP_INT_24XX_USB_IRQ_OTG 80 -# define OMAP_INT_24XX_VLYNQ_IRQ 81 -# define OMAP_INT_24XX_MMC_IRQ 83 -# define OMAP_INT_24XX_MS_IRQ 84 -# define OMAP_INT_24XX_FAC_IRQ 85 -# define OMAP_INT_24XX_MCSPI3_IRQ 91 -# define OMAP_INT_243X_HS_USB_MC 92 -# define OMAP_INT_243X_HS_USB_DMA 93 -# define OMAP_INT_243X_CARKIT 94 -# define OMAP_INT_34XX_GPTIMER12 95 - /* omap_dma.c */ enum omap_dma_model { omap_dma_3_0, @@ -XXX,XX +XXX,XX @@ struct omap_dma_lcd_channel_s { # define OMAP_DMA_MMC2_RX 55 # define OMAP_DMA_CRYPTO_DES_OUT 56 -/* - * DMA request numbers for the OMAP2 - */ -# define OMAP24XX_DMA_NO_DEVICE 0 -# define OMAP24XX_DMA_XTI_DMA 1 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_EXT_DMAREQ0 2 -# define OMAP24XX_DMA_EXT_DMAREQ1 3 -# define OMAP24XX_DMA_GPMC 4 -# define OMAP24XX_DMA_GFX 5 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_DSS 6 -# define OMAP24XX_DMA_VLYNQ_TX 7 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_CWT 8 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_AES_TX 9 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_AES_RX 10 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_DES_TX 11 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_DES_RX 12 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_SHA1MD5_RX 13 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_EXT_DMAREQ2 14 -# define OMAP24XX_DMA_EXT_DMAREQ3 15 -# define OMAP24XX_DMA_EXT_DMAREQ4 16 -# define OMAP24XX_DMA_EAC_AC_RD 17 -# define OMAP24XX_DMA_EAC_AC_WR 18 -# define OMAP24XX_DMA_EAC_MD_UL_RD 19 -# define OMAP24XX_DMA_EAC_MD_UL_WR 20 -# define OMAP24XX_DMA_EAC_MD_DL_RD 21 -# define OMAP24XX_DMA_EAC_MD_DL_WR 22 -# define OMAP24XX_DMA_EAC_BT_UL_RD 23 -# define OMAP24XX_DMA_EAC_BT_UL_WR 24 -# define OMAP24XX_DMA_EAC_BT_DL_RD 25 -# define OMAP24XX_DMA_EAC_BT_DL_WR 26 -# define OMAP24XX_DMA_I2C1_TX 27 -# define OMAP24XX_DMA_I2C1_RX 28 -# define OMAP24XX_DMA_I2C2_TX 29 -# define OMAP24XX_DMA_I2C2_RX 30 -# define OMAP24XX_DMA_MCBSP1_TX 31 -# define OMAP24XX_DMA_MCBSP1_RX 32 -# define OMAP24XX_DMA_MCBSP2_TX 33 -# define OMAP24XX_DMA_MCBSP2_RX 34 -# define OMAP24XX_DMA_SPI1_TX0 35 -# define OMAP24XX_DMA_SPI1_RX0 36 -# define OMAP24XX_DMA_SPI1_TX1 37 -# define OMAP24XX_DMA_SPI1_RX1 38 -# define OMAP24XX_DMA_SPI1_TX2 39 -# define OMAP24XX_DMA_SPI1_RX2 40 -# define OMAP24XX_DMA_SPI1_TX3 41 -# define OMAP24XX_DMA_SPI1_RX3 42 -# define OMAP24XX_DMA_SPI2_TX0 43 -# define OMAP24XX_DMA_SPI2_RX0 44 -# define OMAP24XX_DMA_SPI2_TX1 45 -# define OMAP24XX_DMA_SPI2_RX1 46 - -# define OMAP24XX_DMA_UART1_TX 49 -# define OMAP24XX_DMA_UART1_RX 50 -# define OMAP24XX_DMA_UART2_TX 51 -# define OMAP24XX_DMA_UART2_RX 52 -# define OMAP24XX_DMA_UART3_TX 53 -# define OMAP24XX_DMA_UART3_RX 54 -# define OMAP24XX_DMA_USB_W2FC_TX0 55 -# define OMAP24XX_DMA_USB_W2FC_RX0 56 -# define OMAP24XX_DMA_USB_W2FC_TX1 57 -# define OMAP24XX_DMA_USB_W2FC_RX1 58 -# define OMAP24XX_DMA_USB_W2FC_TX2 59 -# define OMAP24XX_DMA_USB_W2FC_RX2 60 -# define OMAP24XX_DMA_MMC1_TX 61 -# define OMAP24XX_DMA_MMC1_RX 62 -# define OMAP24XX_DMA_MS 63 /* Not in OMAP2420 */ -# define OMAP24XX_DMA_EXT_DMAREQ5 64 - struct omap_uart_s; struct omap_uart_s *omap_uart_init(hwaddr base, qemu_irq irq, omap_clk fclk, omap_clk iclk, @@ -XXX,XX +XXX,XX @@ I2CBus *omap_i2c_bus(DeviceState *omap_i2c); # define cpu_is_omap1510(cpu) (cpu->mpu_model == omap1510) # define cpu_is_omap1610(cpu) (cpu->mpu_model == omap1610) # define cpu_is_omap1710(cpu) (cpu->mpu_model == omap1710) -# define cpu_is_omap2410(cpu) (cpu->mpu_model == omap2410) -# define cpu_is_omap2420(cpu) (cpu->mpu_model == omap2420) -# define cpu_is_omap2430(cpu) (cpu->mpu_model == omap2430) -# define cpu_is_omap3430(cpu) (cpu->mpu_model == omap3430) -# define cpu_is_omap3630(cpu) (cpu->mpu_model == omap3630) # define cpu_is_omap15xx(cpu) \ (cpu_is_omap310(cpu) || cpu_is_omap1510(cpu)) # define cpu_is_omap16xx(cpu) \ (cpu_is_omap1610(cpu) || cpu_is_omap1710(cpu)) -# define cpu_is_omap24xx(cpu) \ - (cpu_is_omap2410(cpu) || cpu_is_omap2420(cpu) || cpu_is_omap2430(cpu)) - -# define cpu_class_omap1(cpu) \ - (cpu_is_omap15xx(cpu) || cpu_is_omap16xx(cpu)) -# define cpu_class_omap2(cpu) cpu_is_omap24xx(cpu) -# define cpu_class_omap3(cpu) \ - (cpu_is_omap3430(cpu) || cpu_is_omap3630(cpu)) struct omap_mpu_state_s { enum omap_mpu_model { @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s { omap1510, omap1610, omap1710, - omap2410, - omap2420, - omap2422, - omap2423, - omap2430, - omap3430, - omap3630, } mpu_model; ARMCPU *cpu; @@ -XXX,XX +XXX,XX @@ void omap_mpu_wakeup(void *opaque, int irq, int req); HWADDR_PRIx "\n", \ __func__, paddr) -/* OMAP-specific Linux bootloader tags for the ATAG_BOARD area - * (Board-specific tags are not here) - */ -#define OMAP_TAG_CLOCK 0x4f01 -#define OMAP_TAG_MMC 0x4f02 -#define OMAP_TAG_SERIAL_CONSOLE 0x4f03 -#define OMAP_TAG_USB 0x4f04 -#define OMAP_TAG_LCD 0x4f05 -#define OMAP_TAG_GPIO_SWITCH 0x4f06 -#define OMAP_TAG_UART 0x4f07 -#define OMAP_TAG_FBMEM 0x4f08 -#define OMAP_TAG_STI_CONSOLE 0x4f09 -#define OMAP_TAG_CAMERA_SENSOR 0x4f0a -#define OMAP_TAG_PARTITION 0x4f0b -#define OMAP_TAG_TEA5761 0x4f10 -#define OMAP_TAG_TMP105 0x4f11 -#define OMAP_TAG_BOOT_REASON 0x4f80 -#define OMAP_TAG_FLASH_PART_STR 0x4f81 -#define OMAP_TAG_VERSION_STR 0x4f82 - -enum { - OMAP_GPIOSW_TYPE_COVER = 0 << 4, - OMAP_GPIOSW_TYPE_CONNECTION = 1 << 4, - OMAP_GPIOSW_TYPE_ACTIVITY = 2 << 4, -}; - -#define OMAP_GPIOSW_INVERTED 0x0001 -#define OMAP_GPIOSW_OUTPUT 0x0002 - # define OMAP_MPUI_REG_MASK 0x000007ff #endif -- 2.34.1 Hi; here's a target-arm pullreq. Apologies for the size: this is because it has all RTH's work to enable emulation of SME2p1 and SVE2p1. thanks -- PMM The following changes since commit c77283dd5d79149f4e7e9edd00f65416c648ee59: Merge tag 'pull-request-2025-07-02' of https://gitlab.com/thuth/qemu into staging (2025-07-03 06:01:41 -0400) are available in the Git repository at: https://gitlab.com/pm215/qemu.git tags/pull-target-arm-20250704 for you to fetch changes up to 083fef73585dfa03f72055ace6de8dec4912d0b0: linux-user/aarch64: Set hwcap bits for SME2p1/SVE2p1 (2025-07-04 15:53:23 +0100) ---------------------------------------------------------------- target-arm queue: * Implement emulation of SME2p1 and SVE2p1 * Correctly enforce alignment checks for v8M loads and stores done via helper functions * Mark the "highbank" and the "midway" machine as deprecated ---------------------------------------------------------------- Peter Maydell (4): target/arm: Rename FMOPA_h to FMOPA_w_h target/arm: Rename BFMOPA to BFMOPA_w target/arm: Implement FMOPA (non-widening) for fp16 target/arm: Implement SME2 BFMOPA (non-widening) Richard Henderson (103): target/arm: Fix SME vs AdvSIMD exception priority target/arm: Fix sve_access_check for SME target/arm: Fix 128-bit element ZIP, UZP, TRN target/arm: Replace @rda_rn_rm_e0 in sve.decode target/arm: Fix FMMLA (64-bit element) for 128-bit VL target/arm: Disable FEAT_F64MM if maximum SVE vector size too small target/arm: Fix PSEL size operands to tcg_gen_gvec_ands target/arm: Fix f16_dotadd vs nan selection target/arm: Fix bfdotadd_ebf vs nan selection target/arm: Remove CPUARMState.vfp.scratch target/arm: Introduce FPST_ZA, FPST_ZA_F16 target/arm: Use FPST_ZA for sme_fmopa_[hsd] target/arm: Rename zarray to za_state.za target/arm: Add isar feature tests for SME2p1, SVE2p1 target/arm: Add ZT0 target/arm: Add zt0_excp_el to DisasContext target/arm: Implement SME2 ZERO ZT0 target/arm: Add alignment argument to gen_sve_{ldr, str} target/arm: Implement SME2 LDR/STR ZT0 target/arm: Implement SME2 MOVT target/arm: Split get_tile_rowcol argument tile_index target/arm: Rename MOVA for translate target/arm: Split out get_zarray target/arm: Introduce ARMCPU.sme_max_vq target/arm: Implement SME2 MOVA to/from tile, multiple registers target/arm: Implement SME2 MOVA to/from array, multiple registers target/arm: Implement SME2 BMOPA target/arm: Implement SME2 SMOPS, UMOPS (2-way) target/arm: Introduce gen_gvec_sve2_sqdmulh target/arm: Implement SME2 Multiple and Single SVE Destructive target/arm: Implement SME2 Multiple Vectors SVE Destructive target/arm: Implement SME2 ADD/SUB (array results, multiple and single vector) target/arm: Implement SME2 ADD/SUB (array results, multiple vectors) target/arm: Pass ZA to helper_sve2_fmlal_zz[zx]w_s target/arm: Add helper_gvec{_ah}_bfmlsl{_nx} target/arm: Implement SME2 FMLAL, BFMLAL target/arm: Implement SME2 FDOT target/arm: Implement SME2 BFDOT target/arm: Implement SME2 FVDOT, BFVDOT target/arm: Rename helper_gvec_*dot_[bh] to *_4[bh] target/arm: Implemement SME2 SDOT, UDOT, USDOT, SUDOT target/arm: Rename SVE SDOT and UDOT patterns target/arm: Tighten USDOT (vectors) decode target/arm: Implement SDOT, UDOT (2-way) for SME2/SVE2p1 target/arm: Implement SME2 SVDOT, UVDOT, SUVDOT, USVDOT target/arm: Implement SME2 SMLAL, SMLSL, UMLAL, UMLSL target/arm: Rename gvec_fml[as]_[hs] with _nf_ infix target/arm: Implement SME2 FMLA, FMLS target/arm: Implement SME2 BFMLA, BFMLS target/arm: Implement SME2 FADD, FSUB, BFADD, BFSUB target/arm: Implement SME2 ADD/SUB (array accumulator) target/arm: Implement SME2 BFCVT, BFCVTN, FCVT, FCVTN target/arm: Implement SME2 FCVT (widening), FCVTL target/arm: Implement SME2 FCVTZS, FCVTZU target/arm: Implement SME2 SCVTF, UCVTF target/arm: Implement SME2 FRINTN, FRINTP, FRINTM, FRINTA target/arm: Introduce do_[us]sat_[bhs] macros target/arm: Use do_[us]sat_[bhs] in sve_helper.c target/arm: Implement SME2 SQCVT, UQCVT, SQCVTU target/arm: Implement SQCVTN, UQCVTN, SQCVTUN for SME2/SVE2p1 target/arm: Implement SME2 SUNPK, UUNPK target/arm: Implement SME2 ZIP, UZP (four registers) target/arm: Move do_urshr, do_srshr to vec_internal.h target/arm: Implement SME2 SQRSHR, UQRSHR, SQRSHRN target/arm: Implement SME2 ZIP, UZP (two registers) target/arm: Implement SME2 FCLAMP, SCLAMP, UCLAMP target/arm: Enable SCLAMP, UCLAMP for SVE2p1 target/arm: Implement FCLAMP for SME2, SVE2p1 target/arm: Implement SME2p1 Multiple Zero target/arm: Introduce pred_count_test target/arm: Fold predtest_ones into helper_sve_brkns target/arm: Expand do_zero inline target/arm: Split out do_whilel from helper_sve_whilel target/arm: Split out do_whileg from helper_sve_whileg target/arm: Move scale by esz into helper_sve_while* target/arm: Split trans_WHILE to lt and gt target/arm: Enable PSEL for SVE2p1 target/arm: Implement SVE2p1 WHILE (predicate pair) target/arm: Implement SVE2p1 WHILE (predicate as counter) target/arm: Implement SVE2p1 PTRUE (predicate as counter) target/arm: Implement {ADD, SMIN, SMAX, UMIN, UMAX}QV for SVE2p1 target/arm: Implement SVE2p1 PEXT target/arm: Implement SME2 SEL target/arm: Implement ANDQV, ORQV, EORQV for SVE2p1 target/arm: Implement FADDQV, F{MIN, MAX}{NM}QV for SVE2p1 target/arm: Implement BFMLSLB{L, T} for SME2/SVE2p1 target/arm: Implement CNTP (predicate as counter) for SME2/SVE2p1 target/arm: Implement DUPQ for SME2p1/SVE2p1 target/arm: Implement EXTQ for SME2p1/SVE2p1 target/arm: Implement PMOV for SME2p1/SVE2p1 target/arm: Implement ZIPQ, UZPQ for SME2p1/SVE2p1 target/arm: Implement TBLQ, TBXQ for SME2p1/SVE2p1 target/arm: Implement SME2 counted predicate register load/store target/arm: Split the ST_zpri and ST_zprr patterns target/arm: Implement {LD1, ST1}{W, D} (128-bit element) for SVE2p1 target/arm: Move ld1qq and st1qq primitives to sve_ldst_internal.h target/arm: Implement {LD, ST}[234]Q for SME2p1/SVE2p1 target/arm: Implement LD1Q, ST1Q for SVE2p1 target/arm: Implement MOVAZ for SME2p1 target/arm: Implement LUTI2, LUTI4 for SME2/SME2p1 target/arm: Support FPCR.AH in SME FMOPS, BFMOPS target/arm: Enable FEAT_SME2p1 on -cpu max linux-user/aarch64: Set hwcap bits for SME2p1/SVE2p1 Thomas Huth (1): hw/arm/highbank: Mark the "highbank" and the "midway" machine as deprecated William Kosasih (11): target/arm: Bring VLSTM/VLLDM helper store/load closer to the ARM pseudocode target/arm: Fix BLXNS helper store alignment checks target/arm: Fix function_return helper load alignment checks target/arm: Fix VLDR helper load alignment checks target/arm: Fix VSTR helper store alignment checks target/arm: Fix VLDR_SG helper load alignment checks target/arm: Fix VSTR_SG helper store alignment checks target/arm: Fix VLD4 helper load alignment checks target/arm: Fix VLD2 helper load alignment checks target/arm: Fix VST4 helper store alignment checks target/arm: Fix VST2 helper store alignment checks docs/about/deprecated.rst | 7 + docs/system/arm/emulation.rst | 6 + target/arm/cpu-features.h | 63 ++ target/arm/cpu.h | 70 +- target/arm/syndrome.h | 1 + target/arm/tcg/helper-sme.h | 215 ++++- target/arm/tcg/helper-sve.h | 212 +++++ target/arm/tcg/helper.h | 91 +- target/arm/tcg/sve_ldst_internal.h | 89 ++ target/arm/tcg/translate-a64.h | 10 +- target/arm/tcg/translate.h | 9 + target/arm/tcg/vec_internal.h | 148 ++++ target/arm/tcg/sme.decode | 937 +++++++++++++++++++- target/arm/tcg/sve.decode | 327 +++++-- hw/arm/highbank.c | 2 + linux-user/aarch64/signal.c | 4 +- linux-user/elfload.c | 8 + target/arm/cpu.c | 11 +- target/arm/cpu64.c | 8 + target/arm/helper.c | 8 +- target/arm/machine.c | 22 +- target/arm/tcg/cpu64.c | 10 +- target/arm/tcg/gengvec64.c | 11 + target/arm/tcg/helper-a64.c | 2 + target/arm/tcg/hflags.c | 34 +- target/arm/tcg/m_helper.c | 33 +- target/arm/tcg/mve_helper.c | 183 ++-- target/arm/tcg/neon_helper.c | 30 + target/arm/tcg/sme_helper.c | 1674 +++++++++++++++++++++++++++++++++--- target/arm/tcg/sve_helper.c | 1201 +++++++++++++++++++++----- target/arm/tcg/translate-a64.c | 45 +- target/arm/tcg/translate-neon.c | 18 +- target/arm/tcg/translate-sme.c | 1480 ++++++++++++++++++++++++++++++- target/arm/tcg/translate-sve.c | 1019 +++++++++++++++++++--- target/arm/tcg/vec_helper.c | 384 +++++++-- target/arm/tcg/vfp_helper.c | 12 +- 36 files changed, 7605 insertions(+), 779 deletions(-) From: Thomas Huth <thuth@redhat.com> We don't have any automatic regression tests for these machines and when asking the usual suspects on the mailing list we came to the conclusion that nobody tests these machines manually, too, so it seems like this is currently just completely unused code. Mark them as depre- cated to see whether anybody still speaks up during the deprecation period, otherwise we can likely remove these two machines in a couple of releases. Signed-off-by: Thomas Huth <thuth@redhat.com> Acked-by: Rob Herring <robh@kernel.org> Acked-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20250702113051.46483-1-thuth@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: tweaked deprecation.rst text] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/about/deprecated.rst | 7 +++++++ hw/arm/highbank.c | 2 ++ 2 files changed, 9 insertions(+) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -XXX,XX +XXX,XX @@ they want to use and avoids confusion. Existing users of the ``spike`` machine must ensure that they're setting the ``spike`` machine in the command line (``-M spike``). +Arm ``highbank`` and ``midway`` machines (since 10.1) +''''''''''''''''''''''''''''''''''''''''''''''''''''' + +There are no known users left for these machines (if you still use it, +please write a mail to the qemu-devel mailing list). If you just want to +boot a Cortex-A15 or Cortex-A9 Linux, use the ``virt`` machine instead. + System emulator binaries ------------------------ diff --git a/hw/arm/highbank.c b/hw/arm/highbank.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/highbank.c +++ b/hw/arm/highbank.c @@ -XXX,XX +XXX,XX @@ static void highbank_class_init(ObjectClass *oc, const void *data) mc->max_cpus = 4; mc->ignore_memory_transaction_failures = true; mc->default_ram_id = "highbank.dram"; + mc->deprecation_reason = "no known users left for this machine"; } static const TypeInfo highbank_type = { @@ -XXX,XX +XXX,XX @@ static void midway_class_init(ObjectClass *oc, const void *data) mc->max_cpus = 4; mc->ignore_memory_transaction_failures = true; mc->default_ram_id = "highbank.dram"; + mc->deprecation_reason = "no known users left for this machine"; } static const TypeInfo midway_type = { -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch brings the VLSTM and VLLDM helper functions closer to the ARM pseudocode by adding MO_ALIGN to the MemOpIdx of the associated store (`cpu_stl_mmu`) operations and load (`cpu_ldl_mmu`) operations. Note that this is not a bug fix: an 8-byte alignment check already exists and remains in place, enforcing stricter alignment than the 4 bytes requirement in the individual loads and stores. This change merely makes the helper implementations closer to the ARM pseudocode. That said, as a side effect, the MMU index is now resolved once instead of on every `cpu_*_data_ra` call, reducing redundant lookups Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-2-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/m_helper.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) bool s = env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_S_MASK; bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK; uintptr_t ra = GETPC(); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + arm_to_core_mmu_idx(mmu_idx)); assert(env->v7m.secure); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) * Note that we do not use v7m_stack_write() here, because the * accesses should not set the FSR bits for stacking errors if they * fail. (In pseudocode terms, they are AccType_NORMAL, not AccType_STACK - * or AccType_LAZYFP). Faults in cpu_stl_data_ra() will throw exceptions + * or AccType_LAZYFP). Faults in cpu_stl_mmu() will throw exceptions * and longjmp out. */ if (!(env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_LSPEN_MASK)) { @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) if (i >= 16) { faddr += 8; /* skip the slot for the FPSCR */ } - cpu_stl_data_ra(env, faddr, slo, ra); - cpu_stl_data_ra(env, faddr + 4, shi, ra); + cpu_stl_mmu(env, faddr, slo, oi, ra); + cpu_stl_mmu(env, faddr + 4, shi, oi, ra); } - cpu_stl_data_ra(env, fptr + 0x40, vfp_get_fpscr(env), ra); + cpu_stl_mmu(env, fptr + 0x40, vfp_get_fpscr(env), oi, ra); if (cpu_isar_feature(aa32_mve, cpu)) { - cpu_stl_data_ra(env, fptr + 0x44, env->v7m.vpr, ra); + cpu_stl_mmu(env, fptr + 0x44, env->v7m.vpr, oi, ra); } /* @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) { ARMCPU *cpu = env_archcpu(env); uintptr_t ra = GETPC(); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + arm_to_core_mmu_idx(mmu_idx)); /* fptr is the value of Rn, the frame pointer we load the FP regs from */ assert(env->v7m.secure); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) faddr += 8; /* skip the slot for the FPSCR and VPR */ } - slo = cpu_ldl_data_ra(env, faddr, ra); - shi = cpu_ldl_data_ra(env, faddr + 4, ra); + slo = cpu_ldl_mmu(env, faddr, oi, ra); + shi = cpu_ldl_mmu(env, faddr + 4, oi, ra); dn = (uint64_t) shi << 32 | slo; *aa32_vfp_dreg(env, i / 2) = dn; } - fpscr = cpu_ldl_data_ra(env, fptr + 0x40, ra); + fpscr = cpu_ldl_mmu(env, fptr + 0x40, oi, ra); vfp_set_fpscr(env, fpscr); if (cpu_isar_feature(aa32_mve, cpu)) { - env->v7m.vpr = cpu_ldl_data_ra(env, fptr + 0x44, ra); + env->v7m.vpr = cpu_ldl_mmu(env, fptr + 0x44, oi, ra); } } -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the store operations (when stacking the return pc and psr) in the BLXNS instruction. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-3-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/m_helper.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) } /* Note that these stores can throw exceptions on MPU faults */ - cpu_stl_data_ra(env, sp, nextinst, GETPC()); - cpu_stl_data_ra(env, sp + 4, saved_psr, GETPC()); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + arm_to_core_mmu_idx(mmu_idx)); + cpu_stl_mmu(env, sp, nextinst, oi, GETPC()); + cpu_stl_mmu(env, sp + 4, saved_psr, oi, GETPC()); env->regs[13] = sp; env->regs[14] = 0xfeffffff; -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the load operations (when unstacking the return pc and psr) in the FunctionReturn pseudocode. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-4-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/m_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ static bool do_v7m_function_return(ARMCPU *cpu) * do them as secure, so work out what MMU index that is. */ mmu_idx = arm_v7m_mmu_idx_for_secstate(env, true); - oi = make_memop_idx(MO_LEUL, arm_to_core_mmu_idx(mmu_idx)); + oi = make_memop_idx(MO_LEUL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); newpc = cpu_ldl_mmu(env, frameptr, oi, 0); newpsr = cpu_ldl_mmu(env, frameptr + 4, oi, 0); -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the load operations in the VLDR instruction. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-5-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) } /* For loads, predicated lanes are zeroed instead of keeping their old values */ -#define DO_VLDR(OP, MSIZE, LDTYPE, ESIZE, TYPE) \ +#define DO_VLDR(OP, MFLAG, MSIZE, MTYPE, LDTYPE, ESIZE, TYPE) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr) \ { \ TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ * beats so we don't care if we update part of the dest and \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ if (eci_mask & (1 << b)) { \ d[H##ESIZE(e)] = (mask & (1 << b)) ? \ - cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + (MTYPE)cpu_##LDTYPE##_mmu(env, addr, oi, GETPC()) : 0;\ } \ addr += MSIZE; \ } \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) mve_advance_vpt(env); \ } -DO_VLDR(vldrb, 1, ldub, 1, uint8_t) -DO_VLDR(vldrh, 2, lduw, 2, uint16_t) -DO_VLDR(vldrw, 4, ldl, 4, uint32_t) +DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t) +DO_VLDR(vldrh, MO_TEUW, 2, uint16_t, ldw, 2, uint16_t) +DO_VLDR(vldrw, MO_TEUL, 4, uint32_t, ldl, 4, uint32_t) DO_VSTR(vstrb, 1, stb, 1, uint8_t) DO_VSTR(vstrh, 2, stw, 2, uint16_t) DO_VSTR(vstrw, 4, stl, 4, uint32_t) -DO_VLDR(vldrb_sh, 1, ldsb, 2, int16_t) -DO_VLDR(vldrb_sw, 1, ldsb, 4, int32_t) -DO_VLDR(vldrb_uh, 1, ldub, 2, uint16_t) -DO_VLDR(vldrb_uw, 1, ldub, 4, uint32_t) -DO_VLDR(vldrh_sw, 2, ldsw, 4, int32_t) -DO_VLDR(vldrh_uw, 2, lduw, 4, uint32_t) +DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t) +DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t) +DO_VLDR(vldrb_uh, MO_UB, 1, uint8_t, ldb, 2, uint16_t) +DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t) +DO_VLDR(vldrh_sw, MO_TESW, 2, int16_t, ldw, 4, int32_t) +DO_VLDR(vldrh_uw, MO_TEUW, 2, uint16_t, ldw, 4, uint32_t) DO_VSTR(vstrb_h, 1, stb, 2, int16_t) DO_VSTR(vstrb_w, 1, stb, 4, int32_t) -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the store operations in the VSTR instruction. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-6-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) mve_advance_vpt(env); \ } -#define DO_VSTR(OP, MSIZE, STTYPE, ESIZE, TYPE) \ +#define DO_VSTR(OP, MFLAG, MSIZE, STTYPE, ESIZE, TYPE) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr) \ { \ TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ unsigned b, e; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ if (mask & (1 << b)) { \ - cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ + cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \ } \ addr += MSIZE; \ } \ @@ -XXX,XX +XXX,XX @@ DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t) DO_VLDR(vldrh, MO_TEUW, 2, uint16_t, ldw, 2, uint16_t) DO_VLDR(vldrw, MO_TEUL, 4, uint32_t, ldl, 4, uint32_t) -DO_VSTR(vstrb, 1, stb, 1, uint8_t) -DO_VSTR(vstrh, 2, stw, 2, uint16_t) -DO_VSTR(vstrw, 4, stl, 4, uint32_t) +DO_VSTR(vstrb, MO_UB, 1, stb, 1, uint8_t) +DO_VSTR(vstrh, MO_TEUW, 2, stw, 2, uint16_t) +DO_VSTR(vstrw, MO_TEUL, 4, stl, 4, uint32_t) DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t) DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t) @@ -XXX,XX +XXX,XX @@ DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t) DO_VLDR(vldrh_sw, MO_TESW, 2, int16_t, ldw, 4, int32_t) DO_VLDR(vldrh_uw, MO_TEUW, 2, uint16_t, ldw, 4, uint32_t) -DO_VSTR(vstrb_h, 1, stb, 2, int16_t) -DO_VSTR(vstrb_w, 1, stb, 4, int32_t) -DO_VSTR(vstrh_w, 2, stw, 4, int32_t) +DO_VSTR(vstrb_h, MO_UB, 1, stb, 2, int16_t) +DO_VSTR(vstrb_w, MO_UB, 1, stb, 4, int32_t) +DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the load operations in the VLDR_SG instructions. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-7-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 42 ++++++++++++++++++++++--------------- 1 file changed, 25 insertions(+), 17 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) * For loads, predicated lanes are zeroed instead of retaining * their previous values. */ -#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB) \ +#define DO_VLDR_SG(OP, MFLAG, MTYPE, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB)\ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ continue; \ } \ addr = ADDRFN(base, m[H##ESIZE(e)]); \ d[H##ESIZE(e)] = (mask & 1) ? \ - cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + (MTYPE)cpu_##LDTYPE##_mmu(env, addr, oi, GETPC()) : 0; \ if (WB) { \ m[H##ESIZE(e)] = addr; \ } \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ } \ addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ - d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + d[H4(e)] = (mask & 1) ? cpu_ldl_mmu(env, addr, oi, GETPC()) : 0; \ if (WB && (e & 1)) { \ m[H4(e & ~1)] = addr - 4; \ } \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) #define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) #define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) -DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, MO_TESW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, MO_TEUW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, MO_TEUW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) +DO_VLDR_SG(vldrh_sg_os_sw, MO_TESW, int16_t, ldw, 4, + int32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uh, MO_TEUW, uint16_t, ldw, 2, + uint16_t, uint16_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uw, MO_TEUW, uint16_t, ldw, 4, + uint32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 4, + uint32_t, uint32_t, ADDR_ADD_OSW, false) DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false) @@ -XXX,XX +XXX,XX @@ DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false) DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false) DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VLDR_SG(vldrw_sg_wb_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the store operations in the VSTR_SG instructions. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-8-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) } /* We know here TYPE is unsigned so always the same as the offset type */ -#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN, WB) \ +#define DO_VSTR_SG(OP, MFLAG, STTYPE, ESIZE, TYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ continue; \ } \ addr = ADDRFN(base, m[H##ESIZE(e)]); \ if (mask & 1) { \ - cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ + cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \ } \ if (WB) { \ m[H##ESIZE(e)] = addr; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ if (mask & 1) { \ - cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ + cpu_stl_mmu(env, addr, d[H4(e)], oi, GETPC()); \ } \ if (WB && (e & 1)) { \ m[H4(e & ~1)] = addr - 4; \ @@ -XXX,XX +XXX,XX @@ DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false) -DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD, false) -DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, false) DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR_SG(vstrh_sg_os_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD_OSW, false) DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) -DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the load operations in the VLD4 instruction. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-9-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint16_t mask = mve_eci_mask(env); \ static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ for (e = 0; e < 4; e++, data >>= 8) { \ uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ qd[H1(off[beat])] = data; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t addr, data; \ int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 8 + (beat & 1) * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ qd[H2(off[beat])] = data; \ data >>= 16; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t addr, data; \ uint32_t *qd; \ int y; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ y = (beat + (O1 & 2)) & 3; \ qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ qd[H4(off[beat] >> 2)] = data; \ -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the load operations in the VLD2 instruction. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-10-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ uint8_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 2; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ for (e = 0; e < 4; e++, data >>= 8) { \ qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ qd[H1(off[beat] + (e >> 1))] = data; \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ int e; \ uint16_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ for (e = 0; e < 2; e++, data >>= 16) { \ qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ qd[H2(off[beat])] = data; \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ uint32_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat]; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ qd[H4(off[beat] >> 3)] = data; \ } \ -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the store operations in the VST4 instruction. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-11-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint16_t mask = mve_eci_mask(env); \ static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ data = (data << 8) | qd[H1(off[beat])]; \ } \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint32_t addr, data; \ int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) data = qd[H2(off[beat])]; \ qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ data |= qd[H2(off[beat])] << 16; \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint32_t addr, data; \ uint32_t *qd; \ int y; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) y = (beat + (O1 & 2)) & 3; \ qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ data = qd[H4(off[beat] >> 2)]; \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } -- 2.43.0 From: William Kosasih <kosasihwilliam4@gmail.com> This patch adds alignment checks in the store operations in the VST2 instruction. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250703085604.154449-12-kosasihwilliam4@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ uint8_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ data = (data << 8) | qd[H1(off[beat] + (e >> 1))]; \ } \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ int e; \ uint16_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ data = (data << 16) | qd[H2(off[beat])]; \ } \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ uint32_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) addr = base + off[beat]; \ qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ data = qd[H4(off[beat] >> 3)]; \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> We failed to raise an exception when sme_excp_el == 0 and fp_excp_el == 1. Cc: qemu-stable@nongnu.org Fixes: 3d74825f4d6 ("target/arm: Add SME enablement checks") Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) 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 @@ bool sme_enabled_check(DisasContext *s) * to be zero when fp_excp_el has priority. This is because we need * sme_excp_el by itself for cpregs access checks. */ - if (!s->fp_excp_el || s->sme_excp_el < s->fp_excp_el) { + if (s->sme_excp_el + && (!s->fp_excp_el || s->sme_excp_el <= s->fp_excp_el)) { bool ret = sme_access_check(s); s->fp_access_checked = (ret ? 1 : -1); return ret; -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Do not assume SME implies SVE. Ensure that the non-streaming check is present along the SME path, since it is not implied by sme_*_enabled_check. Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 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 fp_access_check_only(DisasContext *s) return true; } -static bool fp_access_check(DisasContext *s) +static bool nonstreaming_check(DisasContext *s) { - if (!fp_access_check_only(s)) { - return false; - } if (s->sme_trap_nonstreaming && s->is_nonstreaming) { gen_exception_insn(s, 0, EXCP_UDEF, syn_smetrap(SME_ET_Streaming, false)); @@ -XXX,XX +XXX,XX @@ static bool fp_access_check(DisasContext *s) return true; } +static bool fp_access_check(DisasContext *s) +{ + return fp_access_check_only(s) && nonstreaming_check(s); +} + /* * Return <0 for non-supported element sizes, with MO_16 controlled by * FEAT_FP16; return 0 for fp disabled; otherwise return >0 for success. @@ -XXX,XX +XXX,XX @@ static int fp_access_check_vector_hsd(DisasContext *s, bool is_q, MemOp esz) */ bool sve_access_check(DisasContext *s) { - if (s->pstate_sm || !dc_isar_feature(aa64_sve, s)) { + if (dc_isar_feature(aa64_sme, s)) { bool ret; - assert(dc_isar_feature(aa64_sme, s)); - ret = sme_sm_enabled_check(s); + if (s->pstate_sm) { + ret = sme_enabled_check(s); + } else if (dc_isar_feature(aa64_sve, s)) { + goto continue_sve; + } else { + ret = sme_sm_enabled_check(s); + } + if (ret) { + ret = nonstreaming_check(s); + } s->sve_access_checked = (ret ? 1 : -1); return ret; } + + continue_sve: if (s->sve_excp_el) { /* Assert that we only raise one exception per instruction. */ assert(!s->sve_access_checked); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> We missed the instructions UDEF when the vector size is too small. We missed marking the instructions non-streaming with SME. Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-sve.c | 43 ++++++++++++++++++++++++---------- 1 file changed, 30 insertions(+), 13 deletions(-) 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(PUNPKHI, aa64_sve, do_perm_pred2, a, 1, gen_helper_sve_punpk_p) *** SVE Permute - Interleaving Group */ +static bool do_interleave_q(DisasContext *s, gen_helper_gvec_3 *fn, + arg_rrr_esz *a, int data) +{ + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + if (vsz < 32) { + unallocated_encoding(s); + } else { + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, data, fn); + } + } + return true; +} + static gen_helper_gvec_3 * const zip_fns[4] = { gen_helper_sve_zip_b, gen_helper_sve_zip_h, gen_helper_sve_zip_s, gen_helper_sve_zip_d, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ZIP1_z, aa64_sve, gen_gvec_ool_arg_zzz, TRANS_FEAT(ZIP2_z, aa64_sve, gen_gvec_ool_arg_zzz, zip_fns[a->esz], a, vec_full_reg_size(s) / 2) -TRANS_FEAT(ZIP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_zip_q, a, 0) -TRANS_FEAT(ZIP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_zip_q, a, - QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2) +TRANS_FEAT_NONSTREAMING(ZIP1_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_zip_q, a, 0) +TRANS_FEAT_NONSTREAMING(ZIP2_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_zip_q, a, + QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2) static gen_helper_gvec_3 * const uzp_fns[4] = { gen_helper_sve_uzp_b, gen_helper_sve_uzp_h, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UZP1_z, aa64_sve, gen_gvec_ool_arg_zzz, TRANS_FEAT(UZP2_z, aa64_sve, gen_gvec_ool_arg_zzz, uzp_fns[a->esz], a, 1 << a->esz) -TRANS_FEAT(UZP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_uzp_q, a, 0) -TRANS_FEAT(UZP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_uzp_q, a, 16) +TRANS_FEAT_NONSTREAMING(UZP1_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_uzp_q, a, 0) +TRANS_FEAT_NONSTREAMING(UZP2_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_uzp_q, a, 16) static gen_helper_gvec_3 * const trn_fns[4] = { gen_helper_sve_trn_b, gen_helper_sve_trn_h, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(TRN1_z, aa64_sve, gen_gvec_ool_arg_zzz, TRANS_FEAT(TRN2_z, aa64_sve, gen_gvec_ool_arg_zzz, trn_fns[a->esz], a, 1 << a->esz) -TRANS_FEAT(TRN1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_trn_q, a, 0) -TRANS_FEAT(TRN2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_trn_q, a, 16) +TRANS_FEAT_NONSTREAMING(TRN1_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_trn_q, a, 0) +TRANS_FEAT_NONSTREAMING(TRN2_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_trn_q, a, 16) /* *** SVE Permute Vector - Predicated Group -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Replace @rda_rn_rm_e0 with @rda_rn_rm_ex, and require users to supply an explicit esz. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 48 +++++++++++++++++++-------------------- 1 file changed, 24 insertions(+), 24 deletions(-) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ @rda_rn_rm ........ esz:2 . rm:5 ... ... rn:5 rd:5 \ &rrrr_esz ra=%reg_movprfx -# Four operand with unused vector element size -@rda_rn_rm_e0 ........ ... rm:5 ... ... rn:5 rd:5 \ - &rrrr_esz esz=0 ra=%reg_movprfx -@rdn_ra_rm_e0 ........ ... rm:5 ... ... ra:5 rd:5 \ - &rrrr_esz esz=0 rn=%reg_movprfx +# Four operand with explicit vector element size +@rda_rn_rm_ex ........ ... rm:5 ... ... rn:5 rd:5 \ + &rrrr_esz ra=%reg_movprfx +@rdn_ra_rm_ex ........ ... rm:5 ... ... ra:5 rd:5 \ + &rrrr_esz rn=%reg_movprfx # Three operand with "memory" size, aka immediate left shift @rd_rn_msz_rm ........ ... rm:5 .... imm:2 rn:5 rd:5 &rrri @@ -XXX,XX +XXX,XX @@ XAR 00000100 .. 1 ..... 001 101 rm:5 rd:5 &rrri_esz \ rn=%reg_movprfx esz=%tszimm16_esz imm=%tszimm16_shr # SVE2 bitwise ternary operations -EOR3 00000100 00 1 ..... 001 110 ..... ..... @rdn_ra_rm_e0 -BSL 00000100 00 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 -BCAX 00000100 01 1 ..... 001 110 ..... ..... @rdn_ra_rm_e0 -BSL1N 00000100 01 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 -BSL2N 00000100 10 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 -NBSL 00000100 11 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 +EOR3 00000100 00 1 ..... 001 110 ..... ..... @rdn_ra_rm_ex esz=0 +BSL 00000100 00 1 ..... 001 111 ..... ..... @rdn_ra_rm_ex esz=0 +BCAX 00000100 01 1 ..... 001 110 ..... ..... @rdn_ra_rm_ex esz=0 +BSL1N 00000100 01 1 ..... 001 111 ..... ..... @rdn_ra_rm_ex esz=0 +BSL2N 00000100 10 1 ..... 001 111 ..... ..... @rdn_ra_rm_ex esz=0 +NBSL 00000100 11 1 ..... 001 111 ..... ..... @rdn_ra_rm_ex esz=0 ### SVE Index Generation Group @@ -XXX,XX +XXX,XX @@ EORTB 01000101 .. 0 ..... 10010 1 ..... ..... @rd_rn_rm ## SVE integer matrix multiply accumulate -SMMLA 01000101 00 0 ..... 10011 0 ..... ..... @rda_rn_rm_e0 -USMMLA 01000101 10 0 ..... 10011 0 ..... ..... @rda_rn_rm_e0 -UMMLA 01000101 11 0 ..... 10011 0 ..... ..... @rda_rn_rm_e0 +SMMLA 01000101 00 0 ..... 10011 0 ..... ..... @rda_rn_rm_ex esz=2 +USMMLA 01000101 10 0 ..... 10011 0 ..... ..... @rda_rn_rm_ex esz=2 +UMMLA 01000101 11 0 ..... 10011 0 ..... ..... @rda_rn_rm_ex esz=2 ## SVE2 bitwise permute @@ -XXX,XX +XXX,XX @@ SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx USDOT_zzzz 01000100 .. 0 ..... 011 110 ..... ..... @rda_rn_rm ### SVE2 floating point matrix multiply accumulate -BFMMLA 01100100 01 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 -FMMLA_s 01100100 10 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 -FMMLA_d 01100100 11 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 +BFMMLA 01100100 01 1 ..... 111 001 ..... ..... @rda_rn_rm_ex esz=1 +FMMLA_s 01100100 10 1 ..... 111 001 ..... ..... @rda_rn_rm_ex esz=2 +FMMLA_d 01100100 11 1 ..... 111 001 ..... ..... @rda_rn_rm_ex esz=3 ### SVE2 Memory Gather Load Group @@ -XXX,XX +XXX,XX @@ FCVTLT_sd 01100100 11 0010 11 101 ... ..... ..... @rd_pg_rn_e0 FLOGB 01100101 00 011 esz:2 0101 pg:3 rn:5 rd:5 &rpr_esz ### SVE2 floating-point multiply-add long (vectors) -FMLALB_zzzw 01100100 10 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_e0 -FMLALT_zzzw 01100100 10 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_e0 -FMLSLB_zzzw 01100100 10 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm_e0 -FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_e0 +FMLALB_zzzw 01100100 10 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 +FMLALT_zzzw 01100100 10 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_ex esz=2 +FMLSLB_zzzw 01100100 10 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm_ex esz=2 +FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_ex esz=2 -BFMLALB_zzzw 01100100 11 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_e0 -BFMLALT_zzzw 01100100 11 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_e0 +BFMLALB_zzzw 01100100 11 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 +BFMLALT_zzzw 01100100 11 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_ex esz=2 ### SVE2 floating-point bfloat16 dot-product -BFDOT_zzzz 01100100 01 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_e0 +BFDOT_zzzz 01100100 01 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 ### SVE2 floating-point multiply-add long (indexed) FMLALB_zzxw 01100100 10 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2 -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-sve.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) 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 @@ DO_ZPZZ_FP(FMINNMP, aa64_sve2, sve2_fminnmp_zpzz) DO_ZPZZ_FP(FMAXP, aa64_sve2, sve2_fmaxp_zpzz) DO_ZPZZ_FP(FMINP, aa64_sve2, sve2_fminp_zpzz) +static bool do_fmmla(DisasContext *s, arg_rrrr_esz *a, + gen_helper_gvec_4_ptr *fn) +{ + if (sve_access_check(s)) { + if (vec_full_reg_size(s) < 4 * memop_size(a->esz)) { + unallocated_encoding(s); + } else { + gen_gvec_fpst_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, 0, FPST_A64); + } + } + return true; +} + +TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, do_fmmla, a, gen_helper_fmmla_s) +TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, do_fmmla, a, gen_helper_fmmla_d) + /* * SVE Integer Multiply-Add (unpredicated) */ -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_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_A64) - static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = { NULL, gen_helper_sve2_sqdmlal_zzzw_h, gen_helper_sve2_sqdmlal_zzzw_s, gen_helper_sve2_sqdmlal_zzzw_d, -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> All F64MM instructions operate on a 256-bit vector. If only 128-bit vectors is supported by the cpu, then the cpu cannot enable F64MM. Suggested-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) /* From now on sve_max_vq is the actual maximum supported length. */ cpu->sve_max_vq = max_vq; cpu->sve_vq.map = vq_map; + + /* FEAT_F64MM requires the existence of a 256-bit vector size. */ + if (max_vq < 2) { + uint64_t t = GET_IDREG(&cpu->isar, ID_AA64ZFR0); + t = FIELD_DP64(t, ID_AA64ZFR0, F64MM, 0); + SET_IDREG(&cpu->isar, ID_AA64ZFR0, t); + } } /* -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Gvec only operates on size 8 and multiples of 16. Predicates may be any multiple of 2. Round up the size using the appropriate function. Cc: qemu-stable@nongnu.org Fixes: 598ab0b24c0 ("target/arm: Implement PSEL") Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-sve.c | 1 + 1 file changed, 1 insertion(+) 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 trans_PSEL(DisasContext *s, arg_psel *a) tcg_gen_neg_i64(tmp, tmp); /* Apply to either copy the source, or write zeros. */ + pl = size_for_gvec(pl); tcg_gen_gvec_ands(MO_64, pred_full_reg_offset(s, a->pd), pred_full_reg_offset(s, a->pn), tmp, pl, pl); return true; -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Implement FPProcessNaNs4 within f16_dotadd, rather than simply letting NaNs propagate through the function. Cc: qemu-stable@nongnu.org Fixes: 3916841ac75 ("target/arm: Implement FMOPA, FMOPS (widening)") Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme_helper.c | 62 +++++++++++++++++++++++++++---------- 1 file changed, 46 insertions(+), 16 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 @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, * - we have pre-set-up copy of s_std which is set to round-to-odd, * for the multiply (see below) */ - float64 e1r = float16_to_float64(e1 & 0xffff, true, s_f16); - float64 e1c = float16_to_float64(e1 >> 16, true, s_f16); - float64 e2r = float16_to_float64(e2 & 0xffff, true, s_f16); - float64 e2c = float16_to_float64(e2 >> 16, true, s_f16); - float64 t64; + float16 h1r = e1 & 0xffff; + float16 h1c = e1 >> 16; + float16 h2r = e2 & 0xffff; + float16 h2c = e2 >> 16; float32 t32; - /* - * The ARM pseudocode function FPDot performs both multiplies - * and the add with a single rounding operation. Emulate this - * by performing the first multiply in round-to-odd, then doing - * the second multiply as fused multiply-add, and rounding to - * float32 all in one step. - */ - t64 = float64_mul(e1r, e2r, s_odd); - t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std); + /* C.f. FPProcessNaNs4 */ + if (float16_is_any_nan(h1r) || float16_is_any_nan(h1c) || + float16_is_any_nan(h2r) || float16_is_any_nan(h2c)) { + float16 t16; - /* This conversion is exact, because we've already rounded. */ - t32 = float64_to_float32(t64, s_std); + if (float16_is_signaling_nan(h1r, s_f16)) { + t16 = h1r; + } else if (float16_is_signaling_nan(h1c, s_f16)) { + t16 = h1c; + } else if (float16_is_signaling_nan(h2r, s_f16)) { + t16 = h2r; + } else if (float16_is_signaling_nan(h2c, s_f16)) { + t16 = h2c; + } else if (float16_is_any_nan(h1r)) { + t16 = h1r; + } else if (float16_is_any_nan(h1c)) { + t16 = h1c; + } else if (float16_is_any_nan(h2r)) { + t16 = h2r; + } else { + t16 = h2c; + } + t32 = float16_to_float32(t16, true, s_f16); + } else { + float64 e1r = float16_to_float64(h1r, true, s_f16); + float64 e1c = float16_to_float64(h1c, true, s_f16); + float64 e2r = float16_to_float64(h2r, true, s_f16); + float64 e2c = float16_to_float64(h2c, true, s_f16); + float64 t64; + + /* + * The ARM pseudocode function FPDot performs both multiplies + * and the add with a single rounding operation. Emulate this + * by performing the first multiply in round-to-odd, then doing + * the second multiply as fused multiply-add, and rounding to + * float32 all in one step. + */ + t64 = float64_mul(e1r, e2r, s_odd); + t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std); + + /* This conversion is exact, because we've already rounded. */ + t32 = float64_to_float32(t64, s_std); + } /* The final accumulation step is not fused. */ return float32_add(sum, t32, s_std); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Implement FPProcessNaNs4 within bfdotadd_ebf, rather than simply letting NaNs propagate through the function. Cc: qemu-stable@nongnu.org Fixes: 0e1850182a1 ("target/arm: Implement FPCR.EBF=1 semantics for bfdotadd()") Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250704142112.1018902-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/vec_helper.c | 75 ++++++++++++++++++++++++++----------- 1 file changed, 53 insertions(+), 22 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 @@ float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2, float_status *fpst) float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2, float_status *fpst, float_status *fpst_odd) { - /* - * Compare f16_dotadd() in sme_helper.c, but here we have - * bfloat16 inputs. In particular that means that we do not - * want the FPCR.FZ16 flush semantics, so we use the normal - * float_status for the input handling here. - */ - float64 e1r = float32_to_float64(e1 << 16, fpst); - float64 e1c = float32_to_float64(e1 & 0xffff0000u, fpst); - float64 e2r = float32_to_float64(e2 << 16, fpst); - float64 e2c = float32_to_float64(e2 & 0xffff0000u, fpst); - float64 t64; + float32 s1r = e1 << 16; + float32 s1c = e1 & 0xffff0000u; + float32 s2r = e2 << 16; + float32 s2c = e2 & 0xffff0000u; float32 t32; - /* - * The ARM pseudocode function FPDot performs both multiplies - * and the add with a single rounding operation. Emulate this - * by performing the first multiply in round-to-odd, then doing - * the second multiply as fused multiply-add, and rounding to - * float32 all in one step. - */ - t64 = float64_mul(e1r, e2r, fpst_odd); - t64 = float64r32_muladd(e1c, e2c, t64, 0, fpst); + /* C.f. FPProcessNaNs4 */ + if (float32_is_any_nan(s1r) || float32_is_any_nan(s1c) || + float32_is_any_nan(s2r) || float32_is_any_nan(s2c)) { + if (float32_is_signaling_nan(s1r, fpst)) { + t32 = s1r; + } else if (float32_is_signaling_nan(s1c, fpst)) { + t32 = s1c; + } else if (float32_is_signaling_nan(s2r, fpst)) { + t32 = s2r; + } else if (float32_is_signaling_nan(s2c, fpst)) { + t32 = s2c; + } else if (float32_is_any_nan(s1r)) { + t32 = s1r; + } else if (float32_is_any_nan(s1c)) { + t32 = s1c; + } else if (float32_is_any_nan(s2r)) { + t32 = s2r; + } else { + t32 = s2c; + } + /* + * FPConvertNaN(FPProcessNaN(t32)) will be done as part + * of the final addition below. + */ + } else { + /* + * Compare f16_dotadd() in sme_helper.c, but here we have + * bfloat16 inputs. In particular that means that we do not + * want the FPCR.FZ16 flush semantics, so we use the normal + * float_status for the input handling here. + */ + float64 e1r = float32_to_float64(s1r, fpst); + float64 e1c = float32_to_float64(s1c, fpst); + float64 e2r = float32_to_float64(s2r, fpst); + float64 e2c = float32_to_float64(s2c, fpst); + float64 t64; - /* This conversion is exact, because we've already rounded. */ - t32 = float64_to_float32(t64, fpst); + /* + * The ARM pseudocode function FPDot performs both multiplies + * and the add with a single rounding operation. Emulate this + * by performing the first multiply in round-to-odd, then doing + * the second multiply as fused multiply-add, and rounding to + * float32 all in one step. + */ + t64 = float64_mul(e1r, e2r, fpst_odd); + t64 = float64r32_muladd(e1c, e2c, t64, 0, fpst); + + /* This conversion is exact, because we've already rounded. */ + t32 = float64_to_float32(t64, fpst); + } /* The final accumulation step is not fused. */ return float32_add(sum, t32, fpst); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> The last use of this field was removed in b2fc7be972b9. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { uint32_t xregs[16]; - /* Scratch space for aa32 neon expansion. */ - uint32_t scratch[8]; - /* There are a number of distinct float control structures. */ float_status fp_status[FPST_COUNT]; -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Rather than repeatedly copying FPST_FPCR to locals and setting default nan mode, create dedicated float_status. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 12 +++++++++++- target/arm/cpu.c | 4 ++++ target/arm/tcg/vfp_helper.c | 12 +++++++++++- 3 files changed, 26 insertions(+), 2 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 NVICState NVICState; * when FPCR.AH == 1 (bfloat16 conversions and multiplies, * and the reciprocal and square root estimate/step insns); * for half-precision + * ZA: the "streaming sve" fp status. + * ZA_F16: likewise for half-precision. * * Half-precision operations are governed by a separate * flush-to-zero control bit in FPSCR:FZ16. We pass a separate @@ -XXX,XX +XXX,XX @@ typedef struct NVICState NVICState; * they ignore FPCR.RMode. But they don't ignore FPCR.FZ16, * which means we need an FPST_AH_F16 as well. * + * The "ZA" float_status are for Streaming SVE operations which use + * default-NaN and do not generate fp exceptions, which means that they + * do not accumulate exception bits back into FPCR. + * See e.g. FPAdd vs FPAdd_ZA pseudocode functions, and the setting + * of fpcr.DN and fpexec parameters. + * * To avoid having to transfer exception bits around, we simply * say that the FPSCR cumulative exception flags are the logical * OR of the flags in the four fp statuses. This relies on the @@ -XXX,XX +XXX,XX @@ typedef enum ARMFPStatusFlavour { FPST_A64_F16, FPST_AH, FPST_AH_F16, + FPST_ZA, + FPST_ZA_F16, FPST_STD, FPST_STD_F16, } ARMFPStatusFlavour; -#define FPST_COUNT 8 +#define FPST_COUNT 10 typedef struct CPUArchState { /* Regs for current mode. */ 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.fp_status[FPST_STD]); set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD]); set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD_F16]); + set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA]); + set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA_F16]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32_F16]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD_F16]); arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_AH]); set_flush_to_zero(1, &env->vfp.fp_status[FPST_AH]); diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vfp_helper.c +++ b/target/arm/tcg/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t vfp_get_fpsr_from_host(CPUARMState *env) a64_flags |= (get_float_exception_flags(&env->vfp.fp_status[FPST_A64_F16]) & ~(float_flag_input_denormal_flushed | float_flag_input_denormal_used)); /* - * We do not merge in flags from FPST_AH or FPST_AH_F16, because + * We do not merge in flags from FPST_{AH,ZA} or FPST_{AH,ZA}_F16, because * they are used for insns that must not set the cumulative exception bits. */ @@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64]); set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A32_F16]); set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64_F16]); + set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA]); + set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA_F16]); } if (changed & FPCR_FZ16) { bool ftz_enabled = val & FPCR_FZ16; @@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]); } if (changed & FPCR_FZ) { bool ftz_enabled = val & FPCR_FZ; set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64]); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA]); /* FIZ is A64 only so FZ always makes A32 code flush inputs to zero */ set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]); } @@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) bool fitz_enabled = (val & FPCR_FIZ) || (val & (FPCR_FZ | FPCR_AH)) == FPCR_FZ; set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_A64]); + set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_ZA]); } if (changed & FPCR_DN) { bool dnan_enabled = val & FPCR_DN; @@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) /* Change behaviours for A64 FP operations */ arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64]); arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]); + arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA]); + arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]); } else { arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]); } } /* -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme_helper.c | 37 ++++++++-------------------------- target/arm/tcg/translate-sme.c | 4 ++-- 2 files changed, 10 insertions(+), 31 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_addva_d)(void *vzda, void *vzn, void *vpn, } void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, float_status *fpst_in, uint32_t desc) + void *vpm, float_status *fpst, uint32_t desc) { intptr_t row, col, oprsz = simd_maxsz(desc); uint32_t neg = simd_data(desc) << 31; uint16_t *pn = vpn, *pm = vpm; - float_status fpst; - - /* - * Make a copy of float_status because this operation does not - * update the cumulative fp exception status. It also produces - * default nans. - */ - fpst = *fpst_in; - set_default_nan_mode(true, &fpst); for (row = 0; row < oprsz; ) { uint16_t pa = pn[H2(row >> 4)]; @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, if (pb & 1) { uint32_t *a = vza_row + H1_4(col); uint32_t *m = vzm + H1_4(col); - *a = float32_muladd(n, *m, *a, 0, &fpst); + *a = float32_muladd(n, *m, *a, 0, fpst); } col += 4; pb >>= 4; @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, } void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, float_status *fpst_in, uint32_t desc) + void *vpm, float_status *fpst, uint32_t desc) { intptr_t row, col, oprsz = simd_oprsz(desc) / 8; uint64_t neg = (uint64_t)simd_data(desc) << 63; uint64_t *za = vza, *zn = vzn, *zm = vzm; uint8_t *pn = vpn, *pm = vpm; - float_status fpst = *fpst_in; - - set_default_nan_mode(true, &fpst); for (row = 0; row < oprsz; ++row) { if (pn[H1(row)] & 1) { @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, for (col = 0; col < oprsz; ++col) { if (pm[H1(col)] & 1) { uint64_t *a = &za_row[col]; - *a = float64_muladd(n, zm[col], *a, 0, &fpst); + *a = float64_muladd(n, zm[col], *a, 0, fpst); } } } @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, intptr_t row, col, oprsz = simd_maxsz(desc); uint32_t neg = simd_data(desc) * 0x80008000u; uint16_t *pn = vpn, *pm = vpm; - float_status fpst_odd, fpst_std, fpst_f16; + float_status fpst_odd = env->vfp.fp_status[FPST_ZA]; - /* - * 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[FPST_A64_F16]; - fpst_std = env->vfp.fp_status[FPST_A64]; - set_default_nan_mode(true, &fpst_std); - set_default_nan_mode(true, &fpst_f16); - fpst_odd = fpst_std; set_float_rounding_mode(float_round_to_odd, &fpst_odd); for (row = 0; row < oprsz; ) { @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, m = f16mop_adj_pair(m, pcol, 0); *a = f16_dotadd(*a, n, m, - &fpst_f16, &fpst_std, &fpst_odd); + &env->vfp.fp_status[FPST_ZA_F16], + &env->vfp.fp_status[FPST_ZA], + &fpst_odd); } col += 4; pcol >>= 4; 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_A64, gen_helper_sme_fmopa_s) + MO_32, FPST_ZA, gen_helper_sme_fmopa_s) TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, - MO_64, FPST_A64, gen_helper_sme_fmopa_d) + MO_64, FPST_ZA, gen_helper_sme_fmopa_d) TRANS_FEAT(BFMOPA, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> The whole ZA state will also contain ZT0. Make things easier in aarch64_set_svcr to zero both by wrapping them in a common structure. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 48 +++++++++++++++++++--------------- linux-user/aarch64/signal.c | 4 +-- target/arm/cpu.c | 4 +-- target/arm/helper.c | 2 +- target/arm/machine.c | 2 +- target/arm/tcg/sme_helper.c | 6 ++--- target/arm/tcg/translate-sme.c | 4 +-- 7 files changed, 38 insertions(+), 32 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 { uint64_t scxtnum_el[4]; - /* - * SME ZA storage -- 256 x 256 byte array, with bytes in host word order, - * as we do with vfp.zregs[]. This corresponds to the architectural ZA - * array, where ZA[N] is in the least-significant bytes of env->zarray[N]. - * When SVL is less than the architectural maximum, the accessible - * storage is restricted, such that if the SVL is X bytes the guest can - * see only the bottom X elements of zarray[], and only the least - * significant X bytes of each element of the array. (In other words, - * the observable part is always square.) - * - * The ZA storage can also be considered as a set of square tiles of - * elements of different sizes. The mapping from tiles to the ZA array - * is architecturally defined, such that for tiles of elements of esz - * bytes, the Nth row (or "horizontal slice") of tile T is in - * ZA[T + N * esz]. Note that this means that each tile is not contiguous - * in the ZA storage, because its rows are striped through the ZA array. - * - * Because this is so large, keep this toward the end of the reset area, - * to keep the offsets into the rest of the structure smaller. - */ - ARMVectorReg zarray[ARM_MAX_VQ * 16]; + struct { + /* + * SME ZA storage -- 256 x 256 byte array, with bytes in host + * word order, as we do with vfp.zregs[]. This corresponds to + * the architectural ZA array, where ZA[N] is in the least + * significant bytes of env->za_state.za[N]. + * + * When SVL is less than the architectural maximum, the accessible + * storage is restricted, such that if the SVL is X bytes the guest + * can see only the bottom X elements of zarray[], and only the least + * significant X bytes of each element of the array. (In other words, + * the observable part is always square.) + * + * The ZA storage can also be considered as a set of square tiles of + * elements of different sizes. The mapping from tiles to the ZA array + * is architecturally defined, such that for tiles of elements of esz + * bytes, the Nth row (or "horizontal slice") of tile T is in + * ZA[T + N * esz]. Note that this means that each tile is not + * contiguous in the ZA storage, because its rows are striped through + * the ZA array. + * + * Because this is so large, keep this toward the end of the + * reset area, to keep the offsets into the rest of the structure + * smaller. + */ + ARMVectorReg za[ARM_MAX_VQ * 16]; + } za_state; struct CPUBreakpoint *cpu_breakpoint[16]; struct CPUWatchpoint *cpu_watchpoint[16]; diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static void target_setup_za_record(struct target_za_context *za, for (i = 0; i < vl; ++i) { uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); for (j = 0; j < vq * 2; ++j) { - __put_user_e(env->zarray[i].d[j], z + j, le); + __put_user_e(env->za_state.za[i].d[j], z + j, le); } } } @@ -XXX,XX +XXX,XX @@ static bool target_restore_za_record(CPUARMState *env, for (i = 0; i < vl; ++i) { uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); for (j = 0; j < vq * 2; ++j) { - __get_user_e(env->zarray[i].d[j], z + j, le); + __get_user_e(env->za_state.za[i].d[j], z + j, le); } } return true; 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 aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) qemu_fprintf(f, "ZA[%0*d]=", svl_lg10, i); for (j = zcr_len; j >= 0; --j) { qemu_fprintf(f, "%016" PRIx64 ":%016" PRIx64 "%c", - env->zarray[i].d[2 * j + 1], - env->zarray[i].d[2 * j], + env->za_state.za[i].d[2 * j + 1], + env->za_state.za[i].d[2 * j], j ? ':' : '\n'); } } 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 @@ void aarch64_set_svcr(CPUARMState *env, uint64_t new, uint64_t mask) * when disabled either. */ if (change & new & R_SVCR_ZA_MASK) { - memset(env->zarray, 0, sizeof(env->zarray)); + memset(&env->za_state, 0, sizeof(env->za_state)); } if (tcg_enabled()) { diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_za = { .minimum_version_id = 1, .needed = za_needed, .fields = (const VMStateField[]) { - VMSTATE_STRUCT_ARRAY(env.zarray, ARMCPU, ARM_MAX_VQ * 16, 0, + VMSTATE_STRUCT_ARRAY(env.za_state.za, ARMCPU, ARM_MAX_VQ * 16, 0, vmstate_vreg, ARMVectorReg), VMSTATE_END_OF_LIST() } 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_zero(CPUARMState *env, uint32_t imm, uint32_t svl) uint32_t i; /* - * Special case clearing the entire ZA space. + * Special case clearing the entire ZArray. * This falls into the CONSTRAINED UNPREDICTABLE zeroing of any * parts of the ZA storage outside of SVL. */ if (imm == 0xff) { - memset(env->zarray, 0, sizeof(env->zarray)); + memset(env->za_state.za, 0, sizeof(env->za_state.za)); return; } @@ -XXX,XX +XXX,XX @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl) */ for (i = 0; i < svl; i++) { if (imm & (1 << (i % 8))) { - memset(&env->zarray[i], 0, svl); + memset(&env->za_state.za[i], 0, svl); } } } 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 TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, offset = tile * sizeof(ARMVectorReg); /* Include the byte offset of zarray to make this relative to env. */ - offset += offsetof(CPUARMState, zarray); + offset += offsetof(CPUARMState, za_state.za); tcg_gen_addi_i32(tmp, tmp, offset); /* Add the byte offset to env to produce the final pointer. */ @@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile(DisasContext *s, int esz, int tile) TCGv_ptr addr = tcg_temp_new_ptr(); int offset; - offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, zarray); + offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, za_state.za); tcg_gen_addi_ptr(addr, tcg_env, offset); return addr; -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu-features.h | 63 +++++++++++++++++++++++++++++++++++++++ target/arm/cpu.h | 1 + 2 files changed, 64 insertions(+) diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_rpres(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64ISAR2, RPRES); } +static inline bool isar_feature_aa64_lut(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64ISAR2, LUT); +} + static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) { /* We always set the AdvSIMD and FP fields identically. */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64ZFR0, SVEVER) != 0; } +static inline bool isar_feature_aa64_sve2p1(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64ZFR0, SVEVER) >=2; +} + static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id) { return FIELD_EX64_IDREG(id, ID_AA64ZFR0, AES) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64ZFR0, F64MM) != 0; } +static inline bool isar_feature_aa64_sve_b16b16(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64ZFR0, B16B16); +} + +static inline bool isar_feature_aa64_sme_b16b16(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64SMFR0, B16B16); +} + +static inline bool isar_feature_aa64_sme_f16f16(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F16F16); +} + static inline bool isar_feature_aa64_sme_f64f64(const ARMISARegisters *id) { return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F64F64); @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64SMFR0, FA64); } +static inline bool isar_feature_aa64_sme2(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64SMFR0, SMEVER) != 0; +} + +static inline bool isar_feature_aa64_sme2p1(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64SMFR0, SMEVER) >= 2; +} + +/* + * Combinations of feature tests, for ease of use with TRANS_FEAT. + */ +static inline bool isar_feature_aa64_sme_or_sve2p1(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme(id) || isar_feature_aa64_sve2p1(id); +} + +static inline bool isar_feature_aa64_sme2_or_sve2p1(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme2(id) || isar_feature_aa64_sve2p1(id); +} + +static inline bool isar_feature_aa64_sme2p1_or_sve2p1(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme2p1(id) || isar_feature_aa64_sve2p1(id); +} + +static inline bool isar_feature_aa64_sme2_i16i64(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_i16i64(id); +} + +static inline bool isar_feature_aa64_sme2_f64f64(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_f64f64(id); +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64ISAR2, SYSINSTR_128, 36, 4) FIELD(ID_AA64ISAR2, PRFMSLC, 40, 4) FIELD(ID_AA64ISAR2, RPRFM, 48, 4) FIELD(ID_AA64ISAR2, CSSC, 52, 4) +FIELD(ID_AA64ISAR2, LUT, 56, 4) FIELD(ID_AA64ISAR2, ATS1A, 60, 4) FIELD(ID_AA64PFR0, EL0, 0, 4) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> This is a 512-bit array introduced with SME2. Save it only when ZA is in use. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 3 +++ target/arm/machine.c | 20 ++++++++++++++++++++ 2 files changed, 23 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 { uint64_t scxtnum_el[4]; struct { + /* SME2 ZT0 -- 512 bit array, with data ordered like ARMVectorReg. */ + uint64_t zt0[512 / 64] QEMU_ALIGNED(16); + /* * SME ZA storage -- 256 x 256 byte array, with bytes in host * word order, as we do with vfp.zregs[]. This corresponds to diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_za = { } }; +static bool zt0_needed(void *opaque) +{ + ARMCPU *cpu = opaque; + + return za_needed(cpu) && cpu_isar_feature(aa64_sme2, cpu); +} + +static const VMStateDescription vmstate_zt0 = { + .name = "cpu/zt0", + .version_id = 1, + .minimum_version_id = 1, + .needed = zt0_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64_ARRAY(env.za_state.zt0, ARMCPU, + ARRAY_SIZE(((CPUARMState *)0)->za_state.zt0)), + VMSTATE_END_OF_LIST() + } +}; + static bool serror_needed(void *opaque) { ARMCPU *cpu = opaque; @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_arm_cpu = { &vmstate_m_security, &vmstate_sve, &vmstate_za, + &vmstate_zt0, &vmstate_serror, &vmstate_irq_line_state, &vmstate_wfxt_timer, -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Pipe the value through from SMCR_ELx through hflags and into the disassembly context. Enable EZT0 in smcr_write. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 ++ target/arm/tcg/translate.h | 1 + target/arm/cpu.c | 3 +++ target/arm/helper.c | 6 +++++- target/arm/tcg/hflags.c | 34 +++++++++++++++++++++++++++++++++- target/arm/tcg/translate-a64.c | 1 + 6 files changed, 45 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(SVCR, ZA, 1, 1) /* Fields for SMCR_ELx. */ FIELD(SMCR, LEN, 0, 4) +FIELD(SMCR, EZT0, 30, 1) FIELD(SMCR, FA64, 31, 1) /* Write a new value to v7m.exception, thus transitioning into or out @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, NV2_MEM_E20, 35, 1) FIELD(TBFLAG_A64, NV2_MEM_BE, 36, 1) FIELD(TBFLAG_A64, AH, 37, 1) /* FPCR.AH */ FIELD(TBFLAG_A64, NEP, 38, 1) /* FPCR.NEP */ +FIELD(TBFLAG_A64, ZT0EXC_EL, 39, 2) /* * Helpers for using the above. Note that only the A64 accessors use 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 struct DisasContext { int fp_excp_el; /* FP exception EL or 0 if enabled */ int sve_excp_el; /* SVE exception EL or 0 if enabled */ int sme_excp_el; /* SME exception EL or 0 if enabled */ + int zt0_excp_el; /* ZT0 exception EL or 0 if enabled */ int vl; /* current vector length in bytes */ int svl; /* current streaming vector length in bytes */ bool vfp_enabled; /* FP enabled via FPSCR.EN */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_emulate_firmware_reset(CPUState *cpustate, int target_el) env->cp15.cptr_el[3] |= R_CPTR_EL3_ESM_MASK; env->cp15.scr_el3 |= SCR_ENTP2; env->vfp.smcr_el[3] = 0xf; + if (cpu_isar_feature(aa64_sme2, cpu)) { + env->vfp.smcr_el[3] |= R_SMCR_EZT0_MASK; + } } if (cpu_isar_feature(aa64_hcx, cpu)) { env->cp15.scr_el3 |= SCR_HXEN; 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 smcr_write(CPUARMState *env, const ARMCPRegInfo *ri, { int cur_el = arm_current_el(env); int old_len = sve_vqm1_for_el(env, cur_el); + uint64_t valid_mask = R_SMCR_LEN_MASK | R_SMCR_FA64_MASK; int new_len; QEMU_BUILD_BUG_ON(ARM_MAX_VQ > R_SMCR_LEN_MASK + 1); - value &= R_SMCR_LEN_MASK | R_SMCR_FA64_MASK; + if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) { + valid_mask |= R_SMCR_EZT0_MASK; + } + value &= valid_mask; raw_write(env, ri, value); /* diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/hflags.c +++ b/target/arm/tcg/hflags.c @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } +/* + * Return the exception level to which exceptions should be taken for ZT0. + * C.f. the ARM pseudocode function CheckSMEZT0Enabled, after the ZA check. + */ +static int zt0_exception_el(CPUARMState *env, int el) +{ +#ifndef CONFIG_USER_ONLY + if (el <= 1 + && !el_is_in_host(env, el) + && !FIELD_EX64(env->vfp.smcr_el[1], SMCR, EZT0)) { + return 1; + } + if (el <= 2 + && arm_is_el2_enabled(env) + && !FIELD_EX64(env->vfp.smcr_el[2], SMCR, EZT0)) { + return 2; + } + if (arm_feature(env, ARM_FEATURE_EL3) + && !FIELD_EX64(env->vfp.smcr_el[3], SMCR, EZT0)) { + return 3; + } +#endif + return 0; +} + static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, DP_TBFLAG_A64(flags, PSTATE_SM, 1); DP_TBFLAG_A64(flags, SME_TRAP_NONSTREAMING, !sme_fa64(env, el)); } - DP_TBFLAG_A64(flags, PSTATE_ZA, FIELD_EX64(env->svcr, SVCR, ZA)); + + if (FIELD_EX64(env->svcr, SVCR, ZA)) { + DP_TBFLAG_A64(flags, PSTATE_ZA, 1); + if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) { + int zt0_el = zt0_exception_el(env, el); + DP_TBFLAG_A64(flags, ZT0EXC_EL, zt0_el); + } + } } sctlr = regime_sctlr(env, stage1); 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 aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->trap_eret = EX_TBFLAG_A64(tb_flags, TRAP_ERET); dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL); dc->sme_excp_el = EX_TBFLAG_A64(tb_flags, SMEEXC_EL); + dc->zt0_excp_el = EX_TBFLAG_A64(tb_flags, ZT0EXC_EL); dc->vl = (EX_TBFLAG_A64(tb_flags, VL) + 1) * 16; dc->svl = (EX_TBFLAG_A64(tb_flags, SVL) + 1) * 16; dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 1 + target/arm/tcg/sme.decode | 1 + target/arm/tcg/translate-sme.c | 26 ++++++++++++++++++++++++++ 3 files changed, 28 insertions(+) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ typedef enum { SME_ET_Streaming, SME_ET_NotStreaming, SME_ET_InactiveZA, + SME_ET_InaccessibleZT0, } SMEExceptionType; #define ARM_EL_EC_LENGTH 6 diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ ### SME Misc ZERO 11000000 00 001 00000000000 imm:8 +ZERO_zt0 11000000 01 001 00000000000 00000001 ### SME Move into/from Array 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 @@ #include "decode-sme.c.inc" +static bool sme2_zt0_enabled_check(DisasContext *s) +{ + if (!sme_za_enabled_check(s)) { + return false; + } + if (s->zt0_excp_el) { + gen_exception_insn_el(s, 0, EXCP_UDEF, + syn_smetrap(SME_ET_InaccessibleZT0, false), + s->zt0_excp_el); + return false; + } + return true; +} /* * Resolve tile.size[index] to a host pointer, where tile and index @@ -XXX,XX +XXX,XX @@ static bool trans_ZERO(DisasContext *s, arg_ZERO *a) return true; } +static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a) +{ + if (!dc_isar_feature(aa64_sme2, s)) { + return false; + } + if (sme_enabled_check(s) && sme2_zt0_enabled_check(s)) { + tcg_gen_gvec_dup_imm(MO_64, offsetof(CPUARMState, za_state.zt0), + sizeof_field(CPUARMState, za_state.zt0), + sizeof_field(CPUARMState, za_state.zt0), 0); + } + return true; +} + static bool trans_MOVA(DisasContext *s, arg_MOVA *a) { static gen_helper_gvec_4 * const h_fns[5] = { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Honor AlignmentEnforced() for LDR/STR (vector), (predicate), and (array vector). Within the expansion functions, clear @align when we're done emitting loads at the largest size. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.h | 6 ++-- target/arm/tcg/translate-sme.c | 5 ++-- target/arm/tcg/translate-sve.c | 50 ++++++++++++++++++++++++---------- 3 files changed, 42 insertions(+), 19 deletions(-) diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.h +++ b/target/arm/tcg/translate-a64.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); -void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); -void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); +void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, + int len, int rn, int imm, MemOp align); +void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, + int len, int rn, int imm, MemOp align); #endif /* TARGET_ARM_TRANSLATE_A64_H */ 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 trans_LDST1(DisasContext *s, arg_LDST1 *a) return true; } -typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int); +typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int, MemOp); static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) { @@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) /* ZA[n] equates to ZA0H.B[n]. */ base = get_tile_rowcol(s, MO_8, a->rv, imm, false); - fn(s, base, 0, svl, a->rn, imm * svl); + fn(s, base, 0, svl, a->rn, imm * svl, + s->align_mem ? MO_ALIGN_16 : MO_UNALN); return true; } 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(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, */ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, - int len, int rn, int imm) + int len, int rn, int imm, MemOp align) { int len_align = QEMU_ALIGN_DOWN(len, 16); int len_remain = len % 16; @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, for (i = 0; i < len_align; i += 16) { tcg_gen_qemu_ld_i128(t16, clean_addr, midx, - MO_LE | MO_128 | MO_ATOM_NONE); + MO_LE | MO_128 | MO_ATOM_NONE | align); tcg_gen_extr_i128_i64(t0, t1, t16); tcg_gen_st_i64(t0, base, vofs + i); tcg_gen_st_i64(t1, base, vofs + i + 8); tcg_gen_addi_i64(clean_addr, clean_addr, 16); } + if (len_align) { + align = MO_UNALN; + } } else { TCGLabel *loop = gen_new_label(); TCGv_ptr tp, i = tcg_temp_new_ptr(); @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, t16 = tcg_temp_new_i128(); tcg_gen_qemu_ld_i128(t16, clean_addr, midx, - MO_LE | MO_128 | MO_ATOM_NONE); + MO_LE | MO_128 | MO_ATOM_NONE | align); tcg_gen_addi_i64(clean_addr, clean_addr, 16); tp = tcg_temp_new_ptr(); @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, tcg_gen_st_i64(t1, tp, vofs + 8); tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); + align = MO_UNALN; } /* @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, */ if (len_remain >= 8) { t0 = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE); + tcg_gen_qemu_ld_i64(t0, clean_addr, midx, + MO_LEUQ | MO_ATOM_NONE | align); + align = MO_UNALN; tcg_gen_st_i64(t0, base, vofs + len_align); len_remain -= 8; len_align += 8; @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, case 4: case 8: tcg_gen_qemu_ld_i64(t0, clean_addr, midx, - MO_LE | ctz32(len_remain) | MO_ATOM_NONE); + MO_LE | ctz32(len_remain) + | MO_ATOM_NONE | align); break; case 6: t1 = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE); + tcg_gen_qemu_ld_i64(t0, clean_addr, midx, + MO_LEUL | MO_ATOM_NONE | align); tcg_gen_addi_i64(clean_addr, clean_addr, 4); tcg_gen_qemu_ld_i64(t1, clean_addr, midx, MO_LEUW | MO_ATOM_NONE); tcg_gen_deposit_i64(t0, t0, t1, 32, 32); @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, /* Similarly for stores. */ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, - int len, int rn, int imm) + int len, int rn, int imm, MemOp align) { int len_align = QEMU_ALIGN_DOWN(len, 16); int len_remain = len % 16; @@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, tcg_gen_ld_i64(t1, base, vofs + i + 8); tcg_gen_concat_i64_i128(t16, t0, t1); tcg_gen_qemu_st_i128(t16, clean_addr, midx, - MO_LE | MO_128 | MO_ATOM_NONE); + MO_LE | MO_128 | MO_ATOM_NONE | align); tcg_gen_addi_i64(clean_addr, clean_addr, 16); } + if (len_align) { + align = MO_UNALN; + } } else { TCGLabel *loop = gen_new_label(); TCGv_ptr tp, i = tcg_temp_new_ptr(); @@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, tcg_gen_addi_i64(clean_addr, clean_addr, 16); tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); + align = MO_UNALN; } /* Predicate register stores can be any multiple of 2. */ if (len_remain >= 8) { t0 = tcg_temp_new_i64(); tcg_gen_ld_i64(t0, base, vofs + len_align); - tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE); + tcg_gen_qemu_st_i64(t0, clean_addr, midx, + MO_LEUQ | MO_ATOM_NONE | align); + align = MO_UNALN; len_remain -= 8; len_align += 8; if (len_remain) { @@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, case 4: case 8: tcg_gen_qemu_st_i64(t0, clean_addr, midx, - MO_LE | ctz32(len_remain) | MO_ATOM_NONE); + MO_LE | ctz32(len_remain) + | MO_ATOM_NONE | align); break; case 6: - tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE); + tcg_gen_qemu_st_i64(t0, clean_addr, midx, + MO_LEUL | MO_ATOM_NONE | align); tcg_gen_addi_i64(clean_addr, clean_addr, 4); tcg_gen_shri_i64(t0, t0, 32); tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUW | MO_ATOM_NONE); @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size, + s->align_mem ? MO_ALIGN_16 : MO_UNALN); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size, + s->align_mem ? MO_ALIGN_2 : MO_UNALN); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size); + gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size, + s->align_mem ? MO_ALIGN_16 : MO_UNALN); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size); + gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size, + s->align_mem ? MO_ALIGN_2 : MO_UNALN); } return true; } -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 6 ++++++ target/arm/tcg/translate-sme.c | 13 +++++++++++++ 2 files changed, 19 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ LDR 1110000 100 0 000000 .. 000 ..... 0 .... @ldstr STR 1110000 100 1 000000 .. 000 ..... 0 .... @ldstr +&ldstzt0 rn +@ldstzt0 ....... ... . ...... .. ... rn:5 ..... &ldstzt0 + +LDR_zt0 1110000 100 0 111111 00 000 ..... 00000 @ldstzt0 +STR_zt0 1110000 100 1 111111 00 000 ..... 00000 @ldstzt0 + ### SME Add Vector to Array &adda zad zn pm pn 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_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr) TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str) +static bool do_ldst_zt0(DisasContext *s, arg_ldstzt0 *a, GenLdStR *fn) +{ + if (sme2_zt0_enabled_check(s)) { + fn(s, tcg_env, offsetof(CPUARMState, za_state.zt0), + sizeof_field(CPUARMState, za_state.zt0), a->rn, 0, + s->align_mem ? MO_ALIGN_16 : MO_UNALN); + } + return true; +} + +TRANS_FEAT(LDR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_ldr) +TRANS_FEAT(STR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_str) + static bool do_adda(DisasContext *s, arg_adda *a, MemOp esz, gen_helper_gvec_4 *fn) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 5 +++++ target/arm/tcg/translate-sme.c | 13 +++++++++++++ 2 files changed, 18 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \ MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \ &mova to_vec=1 rs=%mova_rs esz=4 +### SME Move into/from ZT0 + +MOVT_rzt 1100 0000 0100 1100 0 off:3 00 11111 rt:5 +MOVT_ztr 1100 0000 0100 1110 0 off:3 00 11111 rt:5 + ### SME Memory &ldst esz rs pg rn rm za_imm v:bool st:bool 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 trans_MOVA(DisasContext *s, arg_MOVA *a) return true; } +static bool do_movt(DisasContext *s, arg_MOVT_rzt *a, + void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long)) +{ + if (sme2_zt0_enabled_check(s)) { + func(cpu_reg(s, a->rt), tcg_env, + offsetof(CPUARMState, za_state.zt0) + a->off * 8); + } + return true; +} + +TRANS_FEAT(MOVT_rzt, aa64_sme2, do_movt, a, tcg_gen_ld_i64) +TRANS_FEAT(MOVT_ztr, aa64_sme2, do_movt, a, tcg_gen_st_i64) + static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) { typedef void GenLdSt1(TCGv_env, TCGv_ptr, TCGv_ptr, TCGv, TCGv_i32); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Decode tile number and index offset beforehand and separately. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 46 +++++++++++++++++++++++----------- target/arm/tcg/translate-sme.c | 17 +++++-------- 2 files changed, 38 insertions(+), 25 deletions(-) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ ZERO_zt0 11000000 01 001 00000000000 00000001 ### SME Move into/from Array %mova_rs 13:2 !function=plus_12 -&mova esz rs pg zr za_imm v:bool to_vec:bool +&mova esz rs pg zr za off v:bool to_vec:bool -MOVA 11000000 esz:2 00000 0 v:1 .. pg:3 zr:5 0 za_imm:4 \ - &mova to_vec=0 rs=%mova_rs -MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za_imm:4 \ - &mova to_vec=0 rs=%mova_rs esz=4 +MOVA 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \ + &mova to_vec=0 rs=%mova_rs esz=0 za=0 +MOVA 11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3 \ + &mova to_vec=0 rs=%mova_rs esz=1 +MOVA 11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2 \ + &mova to_vec=0 rs=%mova_rs esz=2 +MOVA 11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1 \ + &mova to_vec=0 rs=%mova_rs esz=3 +MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4 \ + &mova to_vec=0 rs=%mova_rs esz=4 off=0 -MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \ - &mova to_vec=1 rs=%mova_rs -MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \ - &mova to_vec=1 rs=%mova_rs esz=4 +MOVA 11000000 00 00001 0 v:1 .. pg:3 0 off:4 zr:5 \ + &mova to_vec=1 rs=%mova_rs esz=0 za=0 +MOVA 11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5 \ + &mova to_vec=1 rs=%mova_rs esz=1 +MOVA 11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5 \ + &mova to_vec=1 rs=%mova_rs esz=2 +MOVA 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \ + &mova to_vec=1 rs=%mova_rs esz=3 +MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \ + &mova to_vec=1 rs=%mova_rs esz=4 off=0 ### SME Move into/from ZT0 @@ -XXX,XX +XXX,XX @@ MOVT_ztr 1100 0000 0100 1110 0 off:3 00 11111 rt:5 ### SME Memory -&ldst esz rs pg rn rm za_imm v:bool st:bool +&ldst esz rs pg rn rm za off v:bool st:bool -LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ - &ldst rs=%mova_rs -LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ - &ldst esz=4 rs=%mova_rs +LDST1 1110000 0 00 st:1 rm:5 v:1 .. pg:3 rn:5 0 off:4 \ + &ldst rs=%mova_rs esz=0 za=0 +LDST1 1110000 0 01 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:1 off:3 \ + &ldst rs=%mova_rs esz=1 +LDST1 1110000 0 10 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:2 off:2 \ + &ldst rs=%mova_rs esz=2 +LDST1 1110000 0 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:3 off:1 \ + &ldst rs=%mova_rs esz=3 +LDST1 1110000 1 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:4 \ + &ldst rs=%mova_rs esz=4 off=0 &ldstr rv rn imm @ldstr ....... ... . ...... .. ... rn:5 . imm:4 \ 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 sme2_zt0_enabled_check(DisasContext *s) return true; } -/* - * Resolve tile.size[index] to a host pointer, where tile and index - * are always decoded together, dependent on the element size. - */ +/* Resolve tile.size[rs+imm] to a host pointer. */ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, - int tile_index, bool vertical) + int tile, int imm, bool vertical) { - int tile = tile_index >> (4 - esz); - int index = esz == MO_128 ? 0 : extract32(tile_index, 0, 4 - esz); int pos, len, offset; TCGv_i32 tmp; TCGv_ptr addr; @@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, /* Compute the final index, which is Rs+imm. */ tmp = tcg_temp_new_i32(); tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs)); - tcg_gen_addi_i32(tmp, tmp, index); + tcg_gen_addi_i32(tmp, tmp, imm); /* Prepare a power-of-two modulo via extraction of @len bits. */ len = ctz32(streaming_vec_reg_size(s)) - esz; @@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) return true; } - t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v); t_zr = vec_full_reg_ptr(s, a->zr); t_pg = pred_full_reg_ptr(s, a->pg); @@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) return true; } - t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v); t_pg = pred_full_reg_ptr(s, a->pg); addr = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) } /* ZA[n] equates to ZA0H.B[n]. */ - base = get_tile_rowcol(s, MO_8, a->rv, imm, false); + base = get_tile_rowcol(s, MO_8, a->rv, 0, imm, false); fn(s, base, 0, svl, a->rn, imm * svl, s->align_mem ? MO_ALIGN_16 : MO_UNALN); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Prepare for more kinds of MOVA from SME2 by renaming the existing SME1 MOVA to indicate tile to/from vector. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 42 +++++++++++++++++----------------- target/arm/tcg/translate-sme.c | 12 +++++----- 2 files changed, 27 insertions(+), 27 deletions(-) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ ZERO_zt0 11000000 01 001 00000000000 00000001 ### SME Move into/from Array %mova_rs 13:2 !function=plus_12 -&mova esz rs pg zr za off v:bool to_vec:bool +&mova_p esz rs pg zr za off v:bool -MOVA 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \ - &mova to_vec=0 rs=%mova_rs esz=0 za=0 -MOVA 11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3 \ - &mova to_vec=0 rs=%mova_rs esz=1 -MOVA 11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2 \ - &mova to_vec=0 rs=%mova_rs esz=2 -MOVA 11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1 \ - &mova to_vec=0 rs=%mova_rs esz=3 -MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4 \ - &mova to_vec=0 rs=%mova_rs esz=4 off=0 +MOVA_tz 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \ + &mova_p rs=%mova_rs esz=0 za=0 +MOVA_tz 11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3 \ + &mova_p rs=%mova_rs esz=1 +MOVA_tz 11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2 \ + &mova_p rs=%mova_rs esz=2 +MOVA_tz 11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1 \ + &mova_p rs=%mova_rs esz=3 +MOVA_tz 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4 \ + &mova_p rs=%mova_rs esz=4 off=0 -MOVA 11000000 00 00001 0 v:1 .. pg:3 0 off:4 zr:5 \ - &mova to_vec=1 rs=%mova_rs esz=0 za=0 -MOVA 11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5 \ - &mova to_vec=1 rs=%mova_rs esz=1 -MOVA 11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5 \ - &mova to_vec=1 rs=%mova_rs esz=2 -MOVA 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \ - &mova to_vec=1 rs=%mova_rs esz=3 -MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \ - &mova to_vec=1 rs=%mova_rs esz=4 off=0 +MOVA_zt 11000000 00 00001 0 v:1 .. pg:3 0 off:4 zr:5 \ + &mova_p rs=%mova_rs esz=0 za=0 +MOVA_zt 11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5 \ + &mova_p rs=%mova_rs esz=1 +MOVA_zt 11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5 \ + &mova_p rs=%mova_rs esz=2 +MOVA_zt 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \ + &mova_p rs=%mova_rs esz=3 +MOVA_zt 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \ + &mova_p rs=%mova_rs esz=4 off=0 ### SME Move into/from ZT0 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 trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a) return true; } -static bool trans_MOVA(DisasContext *s, arg_MOVA *a) +static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec) { static gen_helper_gvec_4 * const h_fns[5] = { gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h, @@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) TCGv_i32 t_desc; int svl; - if (!dc_isar_feature(aa64_sme, s)) { - return false; - } if (!sme_smza_enabled_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) if (a->v) { /* Vertical slice -- use sme mova helpers. */ - if (a->to_vec) { + if (to_vec) { zc_fns[a->esz](t_zr, t_za, t_pg, t_desc); } else { cz_fns[a->esz](t_za, t_zr, t_pg, t_desc); } } else { /* Horizontal slice -- reuse sve sel helpers. */ - if (a->to_vec) { + if (to_vec) { h_fns[a->esz](t_zr, t_za, t_zr, t_pg, t_desc); } else { h_fns[a->esz](t_za, t_zr, t_za, t_pg, t_desc); @@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) return true; } +TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false) +TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true) + static bool do_movt(DisasContext *s, arg_MOVT_rzt *a, void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long)) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Prepare for MOVA array to/from vector with multiple registers by adding a div_len parameter, herein always 1, and a vec_mod parameter, herein always 0. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-sme.c | 47 +++++++++++++++++++++++----------- 1 file changed, 32 insertions(+), 15 deletions(-) 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 sme2_zt0_enabled_check(DisasContext *s) /* Resolve tile.size[rs+imm] to a host pointer. */ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, - int tile, int imm, bool vertical) + int tile, int imm, int div_len, + int vec_mod, bool vertical) { int pos, len, offset; TCGv_i32 tmp; @@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, /* Compute the final index, which is Rs+imm. */ tmp = tcg_temp_new_i32(); tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs)); + /* + * Round the vector index down to a multiple of vec_mod if necessary. + * We do this before adding the offset, to handle cases like + * MOVA (tile to vector, 2 registers) where we want to call this + * several times in a loop with an increasing offset. We rely on + * the instruction encodings always forcing the initial offset in + * [rs + offset] to be a multiple of vec_mod. The pseudocode usually + * does the round-down after adding the offset rather than before, + * but MOVA is an exception. + */ + if (vec_mod > 1) { + tcg_gen_andc_i32(tmp, tmp, tcg_constant_i32(vec_mod - 1)); + } tcg_gen_addi_i32(tmp, tmp, imm); /* Prepare a power-of-two modulo via extraction of @len bits. */ - len = ctz32(streaming_vec_reg_size(s)) - esz; + len = ctz32(streaming_vec_reg_size(s) / div_len) - esz; if (!len) { /* @@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, return addr; } +/* Resolve ZArray[rs+imm] to a host pointer. */ +static TCGv_ptr get_zarray(DisasContext *s, int rs, int imm, + int div_len, int vec_mod) +{ + /* ZA[n] equates to ZA0H.B[n]. */ + return get_tile_rowcol(s, MO_8, rs, 0, imm, div_len, vec_mod, false); +} + /* * Resolve tile.size[0] to a host pointer. * Used by e.g. outer product insns where we require the entire tile. @@ -XXX,XX +XXX,XX @@ static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec) return true; } - t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v); t_zr = vec_full_reg_ptr(s, a->zr); t_pg = pred_full_reg_ptr(s, a->pg); @@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) return true; } - t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v); t_pg = pred_full_reg_ptr(s, a->pg); addr = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int, MemOp); static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) { - int svl = streaming_vec_reg_size(s); - int imm = a->imm; - TCGv_ptr base; + if (sme_za_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int imm = a->imm; + TCGv_ptr base = get_zarray(s, a->rv, imm, 1, 0); - if (!sme_za_enabled_check(s)) { - return true; + fn(s, base, 0, svl, a->rn, imm * svl, + s->align_mem ? MO_ALIGN_16 : MO_UNALN); } - - /* ZA[n] equates to ZA0H.B[n]. */ - base = get_tile_rowcol(s, MO_8, a->rv, 0, imm, false); - - fn(s, base, 0, svl, a->rn, imm * svl, - s->align_mem ? MO_ALIGN_16 : MO_UNALN); return true; } -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 + target/arm/cpu64.c | 1 + 2 files changed, 2 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 ArchCPU { /* Used to set the maximum vector length the cpu will support. */ uint32_t sve_max_vq; + uint32_t sme_max_vq; #ifdef CONFIG_USER_ONLY /* Used to set the default vector length at process start. */ diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp) } cpu->sme_vq.map = vq_map; + cpu->sme_max_vq = 32 - clz32(vq_map); } static bool cpu_arm_get_sme(Object *obj, Error **errp) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 9 +++++ target/arm/tcg/translate.h | 1 + target/arm/tcg/sme.decode | 37 ++++++++++++++++++ target/arm/tcg/sme_helper.c | 64 ++++++++++++++++++++++++++++++ target/arm/tcg/translate-a64.c | 1 + target/arm/tcg/translate-sme.c | 71 ++++++++++++++++++++++++++++++++++ 6 files changed, 183 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_cz_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_cz_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_cz_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_cz_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sme_ld1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_ld1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_ld1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) 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 struct DisasContext { int zt0_excp_el; /* ZT0 exception EL or 0 if enabled */ int vl; /* current vector length in bytes */ int svl; /* current streaming vector length in bytes */ + int max_svl; /* maximum implemented streaming vector length */ bool vfp_enabled; /* FP enabled via FPSCR.EN */ int vec_len; int vec_stride; diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ ZERO_zt0 11000000 01 001 00000000000 00000001 %mova_rs 13:2 !function=plus_12 &mova_p esz rs pg zr za off v:bool +&mova_t esz rs zr za off v:bool MOVA_tz 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \ &mova_p rs=%mova_rs esz=0 za=0 @@ -XXX,XX +XXX,XX @@ MOVA_zt 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \ MOVA_zt 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \ &mova_p rs=%mova_rs esz=4 off=0 +MOVA_tz2 11000000 00 00010 0 v:1 .. 000 zr:4 0 00 off:3 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVA_tz2 11000000 01 00010 0 v:1 .. 000 zr:4 0 00 za:1 off:2 \ + &mova_t rs=%mova_rs esz=1 +MOVA_tz2 11000000 10 00010 0 v:1 .. 000 zr:4 0 00 za:2 off:1 \ + &mova_t rs=%mova_rs esz=2 +MOVA_tz2 11000000 11 00010 0 v:1 .. 000 zr:4 0 00 za:3 \ + &mova_t rs=%mova_rs esz=3 off=0 + +MOVA_zt2 11000000 00 00011 0 v:1 .. 000 00 off:3 zr:4 0 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVA_zt2 11000000 01 00011 0 v:1 .. 000 00 za:1 off:2 zr:4 0 \ + &mova_t rs=%mova_rs esz=1 +MOVA_zt2 11000000 10 00011 0 v:1 .. 000 00 za:2 off:1 zr:4 0 \ + &mova_t rs=%mova_rs esz=2 +MOVA_zt2 11000000 11 00011 0 v:1 .. 000 00 za:3 zr:4 0 \ + &mova_t rs=%mova_rs esz=3 off=0 + +MOVA_tz4 11000000 00 00010 0 v:1 .. 001 zr:3 00 000 off:2 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVA_tz4 11000000 01 00010 0 v:1 .. 001 zr:3 00 000 za:1 off:1 \ + &mova_t rs=%mova_rs esz=1 +MOVA_tz4 11000000 10 00010 0 v:1 .. 001 zr:3 00 000 za:2 \ + &mova_t rs=%mova_rs esz=2 off=0 +MOVA_tz4 11000000 11 00010 0 v:1 .. 001 zr:3 00 00 za:3 \ + &mova_t rs=%mova_rs esz=3 off=0 + +MOVA_zt4 11000000 00 00011 0 v:1 .. 001 000 off:2 zr:3 00 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVA_zt4 11000000 01 00011 0 v:1 .. 001 000 za:1 off:1 zr:3 00 \ + &mova_t rs=%mova_rs esz=1 +MOVA_zt4 11000000 10 00011 0 v:1 .. 001 000 za:2 zr:3 00 \ + &mova_t rs=%mova_rs esz=2 off=0 +MOVA_zt4 11000000 11 00011 0 v:1 .. 001 00 za:3 zr:3 00 \ + &mova_t rs=%mova_rs esz=3 off=0 + ### SME Move into/from ZT0 MOVT_rzt 1100 0000 0100 1100 0 off:3 00 11111 rt:5 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_mova_zc_q)(void *vd, void *za, void *vg, uint32_t desc) #undef DO_MOVA_Z +void HELPER(sme2_mova_zc_b)(void *vdst, void *vsrc, uint32_t desc) +{ + const uint8_t *src = vsrc; + uint8_t *dst = vdst; + size_t i, n = simd_oprsz(desc); + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + } +} + +void HELPER(sme2_mova_zc_h)(void *vdst, void *vsrc, uint32_t desc) +{ + const uint16_t *src = vsrc; + uint16_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 2; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + } +} + +void HELPER(sme2_mova_zc_s)(void *vdst, void *vsrc, uint32_t desc) +{ + const uint32_t *src = vsrc; + uint32_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 4; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + } +} + +void HELPER(sme2_mova_zc_d)(void *vdst, void *vsrc, uint32_t desc) +{ + const uint64_t *src = vsrc; + uint64_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 8; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + } +} + /* * Clear elements in a tile slice comprising len bytes. */ @@ -XXX,XX +XXX,XX @@ static void copy_vertical_q(void *vdst, const void *vsrc, size_t len) } } +void HELPER(sme2_mova_cz_b)(void *vdst, void *vsrc, uint32_t desc) +{ + copy_vertical_b(vdst, vsrc, simd_oprsz(desc)); +} + +void HELPER(sme2_mova_cz_h)(void *vdst, void *vsrc, uint32_t desc) +{ + copy_vertical_h(vdst, vsrc, simd_oprsz(desc)); +} + +void HELPER(sme2_mova_cz_s)(void *vdst, void *vsrc, uint32_t desc) +{ + copy_vertical_s(vdst, vsrc, simd_oprsz(desc)); +} + +void HELPER(sme2_mova_cz_d)(void *vdst, void *vsrc, uint32_t desc) +{ + copy_vertical_d(vdst, vsrc, simd_oprsz(desc)); +} + /* * Host and TLB primitives for vertical tile slice addressing. */ 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 aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->zt0_excp_el = EX_TBFLAG_A64(tb_flags, ZT0EXC_EL); dc->vl = (EX_TBFLAG_A64(tb_flags, VL) + 1) * 16; dc->svl = (EX_TBFLAG_A64(tb_flags, SVL) + 1) * 16; + dc->max_svl = arm_cpu->sme_max_vq * 16; dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE); dc->bt = EX_TBFLAG_A64(tb_flags, BT); dc->btype = EX_TBFLAG_A64(tb_flags, BTYPE); 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_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec) TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false) TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true) +static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec) +{ + static gen_helper_gvec_2 * const cz_fns[] = { + gen_helper_sme2_mova_cz_b, gen_helper_sme2_mova_cz_h, + gen_helper_sme2_mova_cz_s, gen_helper_sme2_mova_cz_d, + }; + static gen_helper_gvec_2 * const zc_fns[] = { + gen_helper_sme2_mova_zc_b, gen_helper_sme2_mova_zc_h, + gen_helper_sme2_mova_zc_s, gen_helper_sme2_mova_zc_d, + }; + TCGv_ptr t_za; + int svl, bytes_per_op = n << a->esz; + + /* + * The MaxImplementedSVL check happens in the decode pseudocode, + * before the SM+ZA enabled check in the operation pseudocode. + * This will (currently) only fail for NREG=4, ESZ=MO_64. + */ + if (s->max_svl < bytes_per_op) { + unallocated_encoding(s); + return true; + } + + if (!sme_smza_enabled_check(s)) { + return true; + } + + svl = streaming_vec_reg_size(s); + + /* + * The CurrentVL check happens in the operation pseudocode, + * after the SM+ZA enabled check. + */ + if (svl < bytes_per_op) { + unallocated_encoding(s); + return true; + } + + if (a->v) { + TCGv_i32 t_desc = tcg_constant_i32(simd_desc(svl, svl, 0)); + + for (int i = 0; i < n; ++i) { + TCGv_ptr t_zr = vec_full_reg_ptr(s, a->zr * n + i); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, + a->off * n + i, 1, n, a->v); + if (to_vec) { + zc_fns[a->esz](t_zr, t_za, t_desc); + } else { + cz_fns[a->esz](t_za, t_zr, t_desc); + } + } + } else { + for (int i = 0; i < n; ++i) { + int o_zr = vec_full_reg_offset(s, a->zr * n + i); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, + a->off * n + i, 1, n, a->v); + if (to_vec) { + tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, 0, svl, svl); + } else { + tcg_gen_gvec_mov_var(MO_8, t_za, 0, tcg_env, o_zr, svl, svl); + } + } + } + return true; +} + +TRANS_FEAT(MOVA_tz2, aa64_sme2, do_mova_tile_n, a, 2, false) +TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false) +TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true) +TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true) + static bool do_movt(DisasContext *s, arg_MOVT_rzt *a, void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long)) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate.h | 5 +++++ target/arm/tcg/sme.decode | 12 ++++++++++++ target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 47 insertions(+) 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 int plus_2(DisasContext *s, int x) return x + 2; } +static inline int plus_8(DisasContext *s, int x) +{ + return x + 8; +} + static inline int plus_12(DisasContext *s, int x) { return x + 12; diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ ZERO_zt0 11000000 01 001 00000000000 00000001 ### SME Move into/from Array %mova_rs 13:2 !function=plus_12 +%mova_rv 13:2 !function=plus_8 +&mova_a rv zr off &mova_p esz rs pg zr za off v:bool &mova_t esz rs zr za off v:bool @@ -XXX,XX +XXX,XX @@ MOVA_zt4 11000000 10 00011 0 v:1 .. 001 000 za:2 zr:3 00 \ MOVA_zt4 11000000 11 00011 0 v:1 .. 001 00 za:3 zr:3 00 \ &mova_t rs=%mova_rs esz=3 off=0 +MOVA_az2 11000000 00 00010 00 .. 010 zr:4 000 off:3 \ + &mova_a rv=%mova_rv +MOVA_az4 11000000 00 00010 00 .. 011 zr:3 0000 off:3 \ + &mova_a rv=%mova_rv + +MOVA_za2 11000000 00 00011 00 .. 010 00 off:3 zr:4 0 \ + &mova_a rv=%mova_rv +MOVA_za4 11000000 00 00011 00 .. 011 00 off:3 zr:3 00 \ + &mova_a rv=%mova_rv + ### SME Move into/from ZT0 MOVT_rzt 1100 0000 0100 1100 0 off:3 00 11111 rt:5 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 @@ TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false) TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true) TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true) +static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec) +{ + TCGv_ptr t_za; + int svl; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + svl = streaming_vec_reg_size(s); + t_za = get_zarray(s, a->rv, a->off, n, 0); + + for (int i = 0; i < n; ++i) { + int o_za = (svl / n * sizeof(ARMVectorReg)) * i; + int o_zr = vec_full_reg_offset(s, a->zr * n + i); + + if (to_vec) { + tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, o_za, svl, svl); + } else { + tcg_gen_gvec_mov_var(MO_8, t_za, o_za, tcg_env, o_zr, svl, svl); + } + } + return true; +} + +TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false) +TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false) +TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true) +TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true) + static bool do_movt(DisasContext *s, arg_MOVT_rzt *a, void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long)) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 3 +++ target/arm/tcg/sme.decode | 2 ++ target/arm/tcg/sme_helper.c | 34 ++++++++++++++++++++++++---------- target/arm/tcg/translate-sme.c | 2 ++ 4 files changed, 31 insertions(+), 10 deletions(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sme_sumopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sme2_bmopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SMOPA_d 1010000 0 11 0 ..... ... ... ..... . 0 ... @op_64 SUMOPA_d 1010000 0 11 1 ..... ... ... ..... . 0 ... @op_64 USMOPA_d 1010000 1 11 0 ..... ... ... ..... . 0 ... @op_64 UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64 + +BMOPA 1000000 0 10 0 ..... ... ... ..... . 10 .. @op_32 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 @@ DEF_IMOP_64(umopa_d, uint16_t, uint16_t) DEF_IMOP_64(sumopa_d, int16_t, uint16_t) DEF_IMOP_64(usmopa_d, uint16_t, int16_t) -#define DEF_IMOPH(NAME, S) \ - void HELPER(sme_##NAME##_##S)(void *vza, void *vzn, void *vzm, \ +#define DEF_IMOPH(P, NAME, S) \ + void HELPER(P##_##NAME##_##S)(void *vza, void *vzn, void *vzm, \ void *vpn, void *vpm, uint32_t desc) \ { do_imopa_##S(vza, vzn, vzm, vpn, vpm, desc, NAME##_##S); } -DEF_IMOPH(smopa, s) -DEF_IMOPH(umopa, s) -DEF_IMOPH(sumopa, s) -DEF_IMOPH(usmopa, s) +DEF_IMOPH(sme, smopa, s) +DEF_IMOPH(sme, umopa, s) +DEF_IMOPH(sme, sumopa, s) +DEF_IMOPH(sme, usmopa, s) -DEF_IMOPH(smopa, d) -DEF_IMOPH(umopa, d) -DEF_IMOPH(sumopa, d) -DEF_IMOPH(usmopa, d) +DEF_IMOPH(sme, smopa, d) +DEF_IMOPH(sme, umopa, d) +DEF_IMOPH(sme, sumopa, d) +DEF_IMOPH(sme, usmopa, d) + +static uint32_t bmopa_s(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) +{ + uint32_t sum = ctpop32(~(n ^ m)); + if (neg) { + sum = -sum; + } + if (!(p & 1)) { + sum = 0; + } + return a + sum; +} + +DEF_IMOPH(sme2, bmopa, s) 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 @@ TRANS_FEAT(SMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_smopa_ TRANS_FEAT(UMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_umopa_d) TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_sumopa_d) TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmopa_d) + +TRANS_FEAT(BMOPA, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_bmopa_s) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 4 ++++ target/arm/tcg/sme.decode | 2 ++ target/arm/tcg/sme_helper.c | 37 +++++++++++++++++++++++++--------- target/arm/tcg/translate-sme.c | 2 ++ 4 files changed, 35 insertions(+), 10 deletions(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(sme2_bmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme2_smopa2_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme2_umopa2_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ USMOPA_d 1010000 1 11 0 ..... ... ... ..... . 0 ... @op_64 UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64 BMOPA 1000000 0 10 0 ..... ... ... ..... . 10 .. @op_32 +SMOPA2_s 1010000 0 10 0 ..... ... ... ..... . 10 .. @op_32 +UMOPA2_s 1010000 1 10 0 ..... ... ... ..... . 10 .. @op_32 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 @@ static inline void do_imopa_d(uint64_t *za, uint64_t *zn, uint64_t *zm, } } -#define DEF_IMOP_32(NAME, NTYPE, MTYPE) \ +#define DEF_IMOP_8x4_32(NAME, NTYPE, MTYPE) \ static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \ { \ uint32_t sum = 0; \ @@ -XXX,XX +XXX,XX @@ static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \ return neg ? a - sum : a + sum; \ } -#define DEF_IMOP_64(NAME, NTYPE, MTYPE) \ +#define DEF_IMOP_16x4_64(NAME, NTYPE, MTYPE) \ static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ { \ uint64_t sum = 0; \ @@ -XXX,XX +XXX,XX @@ static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ return neg ? a - sum : a + sum; \ } -DEF_IMOP_32(smopa_s, int8_t, int8_t) -DEF_IMOP_32(umopa_s, uint8_t, uint8_t) -DEF_IMOP_32(sumopa_s, int8_t, uint8_t) -DEF_IMOP_32(usmopa_s, uint8_t, int8_t) +DEF_IMOP_8x4_32(smopa_s, int8_t, int8_t) +DEF_IMOP_8x4_32(umopa_s, uint8_t, uint8_t) +DEF_IMOP_8x4_32(sumopa_s, int8_t, uint8_t) +DEF_IMOP_8x4_32(usmopa_s, uint8_t, int8_t) -DEF_IMOP_64(smopa_d, int16_t, int16_t) -DEF_IMOP_64(umopa_d, uint16_t, uint16_t) -DEF_IMOP_64(sumopa_d, int16_t, uint16_t) -DEF_IMOP_64(usmopa_d, uint16_t, int16_t) +DEF_IMOP_16x4_64(smopa_d, int16_t, int16_t) +DEF_IMOP_16x4_64(umopa_d, uint16_t, uint16_t) +DEF_IMOP_16x4_64(sumopa_d, int16_t, uint16_t) +DEF_IMOP_16x4_64(usmopa_d, uint16_t, int16_t) #define DEF_IMOPH(P, NAME, S) \ void HELPER(P##_##NAME##_##S)(void *vza, void *vzn, void *vzm, \ @@ -XXX,XX +XXX,XX @@ static uint32_t bmopa_s(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) } DEF_IMOPH(sme2, bmopa, s) + +#define DEF_IMOP_16x2_32(NAME, NTYPE, MTYPE) \ +static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \ +{ \ + uint32_t sum = 0; \ + /* Apply P to N as a mask, making the inactive elements 0. */ \ + n &= expand_pred_h(p); \ + sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \ + sum += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \ + return neg ? a - sum : a + sum; \ +} + +DEF_IMOP_16x2_32(smopa2_s, int16_t, int16_t) +DEF_IMOP_16x2_32(umopa2_s, uint16_t, uint16_t) + +DEF_IMOPH(sme2, smopa2, s) +DEF_IMOPH(sme2, umopa2, s) 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 @@ TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_sumop TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmopa_d) TRANS_FEAT(BMOPA, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_bmopa_s) +TRANS_FEAT(SMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_smopa2_s) +TRANS_FEAT(UMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_umopa2_s) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> To be used by both SVE2 and SME2. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.h | 4 ++++ target/arm/tcg/gengvec64.c | 11 +++++++++++ target/arm/tcg/translate-sve.c | 8 +------- 3 files changed, 16 insertions(+), 7 deletions(-) diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.h +++ b/target/arm/tcg/translate-a64.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sve2_sqdmulh(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz); + void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm, MemOp align); void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, diff --git a/target/arm/tcg/gengvec64.c b/target/arm/tcg/gengvec64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec64.c +++ b/target/arm/tcg/gengvec64.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs, tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } + +void gen_gvec_sve2_sqdmulh(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h, + gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d, + }; + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} 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(MOVPRFX_z, aa64_sve, do_movz_zpz, a->rd, a->rn, a->pg, a->esz, false) */ TRANS_FEAT(MUL_zzz, aa64_sve2, gen_gvec_fn_arg_zzz, tcg_gen_gvec_mul, a) +TRANS_FEAT(SQDMULH_zzz, aa64_sve2, gen_gvec_fn_arg_zzz, gen_gvec_sve2_sqdmulh, a) static gen_helper_gvec_3 * const smulh_zzz_fns[4] = { gen_helper_gvec_smulh_b, gen_helper_gvec_smulh_h, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, TRANS_FEAT(PMUL_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, gen_helper_gvec_pmul_b, a, 0) -static gen_helper_gvec_3 * const sqdmulh_zzz_fns[4] = { - gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h, - gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d, -}; -TRANS_FEAT(SQDMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, - sqdmulh_zzz_fns[a->esz], a, 0) - static gen_helper_gvec_3 * const sqrdmulh_zzz_fns[4] = { gen_helper_sve2_sqrdmulh_b, gen_helper_sve2_sqrdmulh_h, gen_helper_sve2_sqrdmulh_s, gen_helper_sve2_sqrdmulh_d, -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 13 ++++ target/arm/tcg/helper.h | 8 ++ target/arm/tcg/vec_internal.h | 4 + target/arm/tcg/sme.decode | 40 ++++++++++ target/arm/tcg/helper-a64.c | 2 + target/arm/tcg/neon_helper.c | 30 ++++++++ target/arm/tcg/translate-sme.c | 137 +++++++++++++++++++++++++++++++++ target/arm/tcg/vec_helper.c | 7 ++ 8 files changed, 241 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sme2_smopa2_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sme2_umopa2_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmax_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmin_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_ah_fmax_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_ah_fmin_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fminnum_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_urshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_urshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_urshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_srshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_srshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_urshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_urshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_urshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_2(neon_add_u8, i32, i32, i32) DEF_HELPER_2(neon_add_u16, i32, i32, i32) DEF_HELPER_2(neon_sub_u8, i32, i32, i32) diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_internal.h +++ b/target/arm/tcg/vec_internal.h @@ -XXX,XX +XXX,XX @@ static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah) return fpcr_ah && float64_is_any_nan(a) ? a : float64_chs(a); } +/* Not actually called directly as a helper, but uses similar machinery. */ +bfloat16 helper_sme2_ah_fmax_b16(bfloat16 a, bfloat16 b, float_status *fpst); +bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst); + #endif /* TARGET_ARM_VEC_INTERNAL_H */ diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64 BMOPA 1000000 0 10 0 ..... ... ... ..... . 10 .. @op_32 SMOPA2_s 1010000 0 10 0 ..... ... ... ..... . 10 .. @op_32 UMOPA2_s 1010000 1 10 0 ..... ... ... ..... . 10 .. @op_32 + +### SME2 Multi-vector Multiple and Single SVE Destructive + +%zd_ax2 1:4 !function=times_2 +%zd_ax4 2:3 !function=times_4 + +&z2z_en zdn zm esz n +@z2z_2x1 ....... . esz:2 .. zm:4 ....0. ..... .... . \ + &z2z_en n=2 zdn=%zd_ax2 +@z2z_4x1 ....... . esz:2 .. zm:4 ....1. ..... ...0 . \ + &z2z_en n=4 zdn=%zd_ax4 + +SMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 0 @z2z_2x1 +SMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 0 @z2z_4x1 +UMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 1 @z2z_2x1 +UMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 1 @z2z_4x1 +SMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 0 @z2z_2x1 +SMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 0 @z2z_4x1 +UMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 1 @z2z_2x1 +UMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 1 @z2z_4x1 + +FMAX_n1 1100000 1 .. 10 .... 1010.0 01000 .... 0 @z2z_2x1 +FMAX_n1 1100000 1 .. 10 .... 1010.0 01000 .... 0 @z2z_4x1 +FMIN_n1 1100000 1 .. 10 .... 1010.0 01000 .... 1 @z2z_2x1 +FMIN_n1 1100000 1 .. 10 .... 1010.0 01000 .... 1 @z2z_4x1 +FMAXNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 0 @z2z_2x1 +FMAXNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 0 @z2z_4x1 +FMINNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 1 @z2z_2x1 +FMINNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 1 @z2z_4x1 + +SRSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 0 @z2z_2x1 +SRSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 0 @z2z_4x1 +URSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 1 @z2z_2x1 +URSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 1 @z2z_4x1 + +ADD_n1 1100000 1 .. 10 .... 1010.0 11000 .... 0 @z2z_2x1 +ADD_n1 1100000 1 .. 10 .... 1010.0 11000 .... 0 @z2z_4x1 + +SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_2x1 +SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_4x1 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 @@ AH_MINMAX_HELPER(vfp_ah_mind, float64, float64, min) AH_MINMAX_HELPER(vfp_ah_maxh, dh_ctype_f16, float16, max) AH_MINMAX_HELPER(vfp_ah_maxs, float32, float32, max) AH_MINMAX_HELPER(vfp_ah_maxd, float64, float64, max) +AH_MINMAX_HELPER(sme2_ah_fmax_b16, bfloat16, bfloat16, max) +AH_MINMAX_HELPER(sme2_ah_fmin_b16, bfloat16, bfloat16, min) /* 64-bit versions of the CRC helpers. Note that although the operation * (and the prototypes of crc32c() and crc32() mean that only the bottom diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ NEON_VOP(rshl_s16, neon_s16, 2) NEON_GVEC_VOP2(gvec_srshl_h, int16_t) #undef NEON_FN +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, src2, 16, true, NULL)) +NEON_GVEC_VOP2(sme2_srshl_h, int16_t) +#undef NEON_FN + #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, true, NULL)) NEON_GVEC_VOP2(gvec_srshl_s, int32_t) #undef NEON_FN +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, src2, 32, true, NULL)) +NEON_GVEC_VOP2(sme2_srshl_s, int32_t) +#undef NEON_FN + #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_d(src1, (int8_t)src2, true, NULL)) NEON_GVEC_VOP2(gvec_srshl_d, int64_t) #undef NEON_FN +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_d(src1, src2, true, NULL)) +NEON_GVEC_VOP2(sme2_srshl_d, int64_t) +#undef NEON_FN + uint32_t HELPER(neon_rshl_s32)(uint32_t val, uint32_t shift) { return do_sqrshl_bhs(val, (int8_t)shift, 32, true, NULL); @@ -XXX,XX +XXX,XX @@ NEON_VOP(rshl_u16, neon_u16, 2) NEON_GVEC_VOP2(gvec_urshl_h, uint16_t) #undef NEON_FN +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int16_t)src2, 16, true, NULL)) +NEON_GVEC_VOP2(sme2_urshl_h, uint16_t) +#undef NEON_FN + #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, true, NULL)) NEON_GVEC_VOP2(gvec_urshl_s, int32_t) #undef NEON_FN +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, src2, 32, true, NULL)) +NEON_GVEC_VOP2(sme2_urshl_s, int32_t) +#undef NEON_FN + #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_d(src1, (int8_t)src2, true, NULL)) NEON_GVEC_VOP2(gvec_urshl_d, int64_t) #undef NEON_FN +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_d(src1, src2, true, NULL)) +NEON_GVEC_VOP2(sme2_urshl_d, int64_t) +#undef NEON_FN + uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shift) { return do_uqrshl_bhs(val, (int8_t)shift, 32, true, NULL); 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 @@ TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmop TRANS_FEAT(BMOPA, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_bmopa_s) TRANS_FEAT(SMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_smopa2_s) TRANS_FEAT(UMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_umopa2_s) + +static bool do_z2z_n1(DisasContext *s, arg_z2z_en *a, GVecGen3Fn *fn) +{ + int esz, dn, vsz, mofs, n; + bool overlap = false; + + if (!sme_sm_enabled_check(s)) { + return true; + } + + esz = a->esz; + n = a->n; + dn = a->zdn; + mofs = vec_full_reg_offset(s, a->zm); + vsz = streaming_vec_reg_size(s); + + for (int i = 0; i < n; i++) { + int dofs = vec_full_reg_offset(s, dn + i); + if (dofs == mofs) { + overlap = true; + } else { + fn(esz, dofs, dofs, mofs, vsz, vsz); + } + } + if (overlap) { + fn(esz, mofs, mofs, mofs, vsz, vsz); + } + return true; +} + +static void gen_sme2_srshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[] = { + gen_helper_gvec_srshl_b, gen_helper_sme2_srshl_h, + gen_helper_sme2_srshl_s, gen_helper_sme2_srshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} + +static void gen_sme2_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[] = { + gen_helper_gvec_urshl_b, gen_helper_sme2_urshl_h, + gen_helper_sme2_urshl_s, gen_helper_sme2_urshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} + +TRANS_FEAT(ADD_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_add) +TRANS_FEAT(SMAX_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_smax) +TRANS_FEAT(SMIN_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_smin) +TRANS_FEAT(UMAX_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_umax) +TRANS_FEAT(UMIN_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_umin) +TRANS_FEAT(SRSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_srshl) +TRANS_FEAT(URSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_urshl) +TRANS_FEAT(SQDMULH_n1, aa64_sme2, do_z2z_n1, a, gen_gvec_sve2_sqdmulh) + +static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a, + gen_helper_gvec_3_ptr * const fns[4]) +{ + int esz = a->esz, n, dn, vsz, mofs; + bool overlap = false; + gen_helper_gvec_3_ptr *fn; + TCGv_ptr fpst; + + /* These insns use MO_8 to encode BFloat16. */ + if (esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) { + return false; + } + if (!sme_sm_enabled_check(s)) { + return true; + } + + fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64); + fn = fns[esz]; + n = a->n; + dn = a->zdn; + mofs = vec_full_reg_offset(s, a->zm); + vsz = streaming_vec_reg_size(s); + + for (int i = 0; i < n; i++) { + int dofs = vec_full_reg_offset(s, dn + i); + if (dofs == mofs) { + overlap = true; + } else { + tcg_gen_gvec_3_ptr(dofs, dofs, mofs, fpst, vsz, vsz, 0, fn); + } + } + if (overlap) { + tcg_gen_gvec_3_ptr(mofs, mofs, mofs, fpst, vsz, vsz, 0, fn); + } + return true; +} + +static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = { + { gen_helper_gvec_fmax_b16, + gen_helper_gvec_fmax_h, + gen_helper_gvec_fmax_s, + gen_helper_gvec_fmax_d }, + { gen_helper_gvec_ah_fmax_b16, + gen_helper_gvec_ah_fmax_h, + gen_helper_gvec_ah_fmax_s, + gen_helper_gvec_ah_fmax_d }, +}; +TRANS_FEAT(FMAX_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmax[s->fpcr_ah]) + +static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = { + { gen_helper_gvec_fmin_b16, + gen_helper_gvec_fmin_h, + gen_helper_gvec_fmin_s, + gen_helper_gvec_fmin_d }, + { gen_helper_gvec_ah_fmin_b16, + gen_helper_gvec_ah_fmin_h, + gen_helper_gvec_ah_fmin_s, + gen_helper_gvec_ah_fmin_d }, +}; +TRANS_FEAT(FMIN_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmin[s->fpcr_ah]) + +static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = { + gen_helper_gvec_fmaxnum_b16, + gen_helper_gvec_fmaxnum_h, + gen_helper_gvec_fmaxnum_s, + gen_helper_gvec_fmaxnum_d, +}; +TRANS_FEAT(FMAXNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmaxnm) + +static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = { + gen_helper_gvec_fminnum_b16, + gen_helper_gvec_fminnum_h, + gen_helper_gvec_fminnum_s, + gen_helper_gvec_fminnum_d, +}; +TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm) 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 @@ DO_3OP(gvec_ah_fmin_h, helper_vfp_ah_minh, float16) DO_3OP(gvec_ah_fmin_s, helper_vfp_ah_mins, float32) DO_3OP(gvec_ah_fmin_d, helper_vfp_ah_mind, float64) +DO_3OP(gvec_fmax_b16, bfloat16_max, bfloat16) +DO_3OP(gvec_fmin_b16, bfloat16_min, bfloat16) +DO_3OP(gvec_fmaxnum_b16, bfloat16_maxnum, bfloat16) +DO_3OP(gvec_fminnum_b16, bfloat16_minnum, bfloat16) +DO_3OP(gvec_ah_fmax_b16, helper_sme2_ah_fmax_b16, bfloat16) +DO_3OP(gvec_ah_fmin_b16, helper_sme2_ah_fmin_b16, bfloat16) + #endif #undef DO_3OP -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 36 +++++++++++++++++++ target/arm/tcg/translate-sme.c | 65 ++++++++++++++++++++++++++++++++++ 2 files changed, 101 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ ADD_n1 1100000 1 .. 10 .... 1010.0 11000 .... 0 @z2z_4x1 SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_2x1 SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_4x1 + +### SME2 Multi-vector Multiple Vectors SVE Destructive + +%zm_ax2 17:4 !function=times_2 +%zm_ax4 18:3 !function=times_4 + +@z2z_2x2 ....... . esz:2 . ....0 ....0. ..... .... . \ + &z2z_en n=2 zdn=%zd_ax2 zm=%zm_ax2 +@z2z_4x4 ....... . esz:2 . ...00 ....1. ..... ...0 . \ + &z2z_en n=4 zdn=%zd_ax4 zm=%zm_ax4 + +SMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 0 @z2z_2x2 +SMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 0 @z2z_4x4 +UMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 1 @z2z_2x2 +UMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 1 @z2z_4x4 +SMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 0 @z2z_2x2 +SMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 0 @z2z_4x4 +UMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 1 @z2z_2x2 +UMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 1 @z2z_4x4 + +FMAX_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 0 @z2z_2x2 +FMAX_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 0 @z2z_4x4 +FMIN_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 1 @z2z_2x2 +FMIN_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 1 @z2z_4x4 +FMAXNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 0 @z2z_2x2 +FMAXNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 0 @z2z_4x4 +FMINNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 1 @z2z_2x2 +FMINNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 1 @z2z_4x4 + +SRSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 0 @z2z_2x2 +SRSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 0 @z2z_4x4 +URSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 1 @z2z_2x2 +URSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 1 @z2z_4x4 + +SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_2x2 +SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_4x4 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 @@ TRANS_FEAT(SRSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_srshl) TRANS_FEAT(URSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_urshl) TRANS_FEAT(SQDMULH_n1, aa64_sme2, do_z2z_n1, a, gen_gvec_sve2_sqdmulh) +static bool do_z2z_nn(DisasContext *s, arg_z2z_en *a, GVecGen3Fn *fn) +{ + int esz, dn, dm, vsz, n; + + if (!sme_sm_enabled_check(s)) { + return true; + } + + esz = a->esz; + n = a->n; + dn = a->zdn; + dm = a->zm; + vsz = streaming_vec_reg_size(s); + + for (int i = 0; i < n; i++) { + int dofs = vec_full_reg_offset(s, dn + i); + int mofs = vec_full_reg_offset(s, dm + i); + + fn(esz, dofs, dofs, mofs, vsz, vsz); + } + return true; +} + +TRANS_FEAT(SMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smax) +TRANS_FEAT(SMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smin) +TRANS_FEAT(UMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umax) +TRANS_FEAT(UMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umin) +TRANS_FEAT(SRSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_srshl) +TRANS_FEAT(URSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_urshl) +TRANS_FEAT(SQDMULH_nn, aa64_sme2, do_z2z_nn, a, gen_gvec_sve2_sqdmulh) + static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a, gen_helper_gvec_3_ptr * const fns[4]) { @@ -XXX,XX +XXX,XX @@ static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a, return true; } +static bool do_z2z_nn_fpst(DisasContext *s, arg_z2z_en *a, + gen_helper_gvec_3_ptr * const fns[4]) +{ + int esz = a->esz, n, dn, dm, vsz; + gen_helper_gvec_3_ptr *fn; + TCGv_ptr fpst; + + if (esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) { + return false; + } + if (!sme_sm_enabled_check(s)) { + return true; + } + + fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64); + fn = fns[esz]; + n = a->n; + dn = a->zdn; + dm = a->zm; + vsz = streaming_vec_reg_size(s); + + for (int i = 0; i < n; i++) { + int dofs = vec_full_reg_offset(s, dn + i); + int mofs = vec_full_reg_offset(s, dm + i); + + tcg_gen_gvec_3_ptr(dofs, dofs, mofs, fpst, vsz, vsz, 0, fn); + } + return true; +} + static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = { { gen_helper_gvec_fmax_b16, gen_helper_gvec_fmax_h, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = { gen_helper_gvec_ah_fmax_d }, }; TRANS_FEAT(FMAX_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmax[s->fpcr_ah]) +TRANS_FEAT(FMAX_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmax[s->fpcr_ah]) static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = { { gen_helper_gvec_fmin_b16, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = { gen_helper_gvec_ah_fmin_d }, }; TRANS_FEAT(FMIN_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmin[s->fpcr_ah]) +TRANS_FEAT(FMIN_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmin[s->fpcr_ah]) static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = { gen_helper_gvec_fmaxnum_b16, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = { gen_helper_gvec_fmaxnum_d, }; TRANS_FEAT(FMAXNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmaxnm) +TRANS_FEAT(FMAXNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmaxnm) static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = { gen_helper_gvec_fminnum_b16, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = { gen_helper_gvec_fminnum_d, }; TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm) +TRANS_FEAT(FMINNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fminnm) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-33-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate.h | 2 ++ target/arm/tcg/sme.decode | 15 +++++++++++++++ target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 47 insertions(+) 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 void GVecGen3Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t); typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t); +typedef void GVecGen3FnVar(unsigned, TCGv_ptr, uint32_t, TCGv_ptr, uint32_t, + TCGv_ptr, uint32_t, uint32_t, uint32_t); /* Function prototype for gen_ functions for calling Neon helpers */ typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32); diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ URSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 1 @z2z_4x4 SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_2x2 SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_4x4 + +### SME2 Multi-vector Multiple and Single Array Vectors + +&azz_n n off rv zn zm +@azz_nx1_o3 ........ .... zm:4 ...... zn:5 .. off:3 &azz_n rv=%mova_rv + +ADD_azz_n1_s 11000001 0010 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=2 +ADD_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=4 +ADD_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=2 +ADD_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=4 + +SUB_azz_n1_s 11000001 0010 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2 +SUB_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4 +SUB_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2 +SUB_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4 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 gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = { }; TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm) TRANS_FEAT(FMINNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fminnm) + +/* Add/Sub vector Z[m] to each Z[n*N] with result in ZA[d*N]. */ +static bool do_azz_n1(DisasContext *s, arg_azz_n *a, int esz, + GVecGen3FnVar *fn) +{ + TCGv_ptr t_za; + int svl, n, o_zm; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + n = a->n; + t_za = get_zarray(s, a->rv, a->off, n, 0); + o_zm = vec_full_reg_offset(s, a->zm); + svl = streaming_vec_reg_size(s); + + for (int i = 0; i < n; ++i) { + int o_za = (svl / n * sizeof(ARMVectorReg)) * i; + int o_zn = vec_full_reg_offset(s, (a->zn + i) % 32); + + fn(esz, t_za, o_za, tcg_env, o_zn, tcg_env, o_zm, svl, svl); + } + return true; +} + +TRANS_FEAT(ADD_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_sub_var) +TRANS_FEAT(ADD_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_sub_var) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-34-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 20 ++++++++++++++++++++ target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SUB_azz_n1_s 11000001 0010 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2 SUB_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4 SUB_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2 SUB_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4 + +### SME2 Multi-vector Multiple Array Vectors + +%zn_ax2 6:4 !function=times_2 +%zn_ax4 7:3 !function=times_4 + +@azz_2x2_o3 ........ ... ..... . .. ... ..... .. off:3 \ + &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 +@azz_4x4_o3 ........ ... ..... . .. ... ..... .. off:3 \ + &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 + +ADD_azz_nn_s 11000001 101 ....0 0 .. 110 ....0 10 ... @azz_2x2_o3 +ADD_azz_nn_s 11000001 101 ...01 0 .. 110 ...00 10 ... @azz_4x4_o3 +ADD_azz_nn_d 11000001 111 ....0 0 .. 110 ....0 10 ... @azz_2x2_o3 +ADD_azz_nn_d 11000001 111 ...01 0 .. 110 ...00 10 ... @azz_4x4_o3 + +SUB_azz_nn_s 11000001 101 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3 +SUB_azz_nn_s 11000001 101 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3 +SUB_azz_nn_d 11000001 111 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3 +SUB_azz_nn_d 11000001 111 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3 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 @@ TRANS_FEAT(ADD_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_add_var) TRANS_FEAT(SUB_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_sub_var) TRANS_FEAT(ADD_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_add_var) TRANS_FEAT(SUB_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_sub_var) + +/* Add/Sub each vector Z[m*N] to each Z[n*N] with result in ZA[d*N]. */ +static bool do_azz_nn(DisasContext *s, arg_azz_n *a, int esz, + GVecGen3FnVar *fn) +{ + TCGv_ptr t_za; + int svl, n; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + n = a->n; + t_za = get_zarray(s, a->rv, a->off, n, 1); + svl = streaming_vec_reg_size(s); + + for (int i = 0; i < n; ++i) { + int o_za = (svl / n * sizeof(ARMVectorReg)) * i; + int o_zn = vec_full_reg_offset(s, a->zn + i); + int o_zm = vec_full_reg_offset(s, a->zm + i); + + fn(esz, t_za, o_za, tcg_env, o_zn, tcg_env, o_zm, svl, svl); + } + return true; +} + +TRANS_FEAT(ADD_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var) +TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Indicate whether to use FPST_FPCR or FPST_ZA via bit 2 of simd_data(desc). For SVE, this bit remains zero. For do_FMLAL_zzzw, this requires no change. For do_FMLAL_zzxw, move the index up one bit. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-35-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-sve.c | 2 +- target/arm/tcg/vec_helper.c | 8 +++++--- 2 files changed, 6 insertions(+), 4 deletions(-) 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 do_FMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sub, bool sel) { return gen_gvec_ptr_zzzz(s, gen_helper_sve2_fmlal_zzxw_s, a->rd, a->rn, a->rm, a->ra, - (a->index << 2) | (sel << 1) | sub, tcg_env); + (a->index << 3) | (sel << 1) | sub, tcg_env); } TRANS_FEAT(FMLALB_zzxw, aa64_sve2, do_FMLAL_zzxw, a, false, false) 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(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va, intptr_t i, oprsz = simd_oprsz(desc); bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1); intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); - float_status *status = &env->vfp.fp_status[FPST_A64]; + bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64]; bool fz16 = env->vfp.fpcr & FPCR_FZ16; int negx = 0, negf = 0; @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va, intptr_t i, j, oprsz = simd_oprsz(desc); bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1); 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[FPST_A64]; + bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 3, 3) * sizeof(float16); + float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64]; bool fz16 = env->vfp.fpcr & FPCR_FZ16; int negx = 0, negf = 0; -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-36-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper.h | 8 +++++ target/arm/tcg/vec_helper.c | 58 ++++++++++++++++++++++++++++--------- 2 files changed, 53 insertions(+), 13 deletions(-) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_bfmmla, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_bfmlsl, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_ah_bfmlsl, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_bfmlsl_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_ah_bfmlsl_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) 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_bfmmla)(void *vd, void *vn, void *vm, void *va, clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va, - float_status *stat, uint32_t desc) +static void do_bfmlal(float32 *d, bfloat16 *n, bfloat16 *m, float32 *a, + float_status *stat, uint32_t desc, int negx, int negf) { intptr_t i, opr_sz = simd_oprsz(desc); - intptr_t sel = simd_data(desc); - float32 *d = vd, *a = va; - bfloat16 *n = vn, *m = vm; + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1); for (i = 0; i < opr_sz / 4; ++i) { - float32 nn = n[H2(i * 2 + sel)] << 16; + float32 nn = (negx ^ n[H2(i * 2 + sel)]) << 16; float32 mm = m[H2(i * 2 + sel)] << 16; - d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], 0, stat); + d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], negf, stat); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, - void *va, float_status *stat, uint32_t desc) +void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal(vd, vn, vm, va, stat, desc, 0, 0); +} + +void HELPER(gvec_bfmlsl)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal(vd, vn, vm, va, stat, desc, 0x8000, 0); +} + +void HELPER(gvec_ah_bfmlsl)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal(vd, vn, vm, va, stat, desc, 0, float_muladd_negate_product); +} + +static void do_bfmlal_idx(float32 *d, bfloat16 *n, bfloat16 *m, float32 *a, + float_status *stat, uint32_t desc, int negx, int negf) { intptr_t i, j, opr_sz = simd_oprsz(desc); intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1); intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 1, 3); intptr_t elements = opr_sz / 4; intptr_t eltspersegment = MIN(16 / 4, elements); - float32 *d = vd, *a = va; - bfloat16 *n = vn, *m = vm; for (i = 0; i < elements; i += eltspersegment) { float32 m_idx = m[H2(2 * i + index)] << 16; for (j = i; j < i + eltspersegment; j++) { - float32 n_j = n[H2(2 * j + sel)] << 16; - d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], 0, stat); + float32 n_j = (negx ^ n[H2(2 * j + sel)]) << 16; + d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], negf, stat); } } clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0, 0); +} + +void HELPER(gvec_bfmlsl_idx)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0x8000, 0); +} + +void HELPER(gvec_ah_bfmlsl_idx)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0, float_muladd_negate_product); +} + #define DO_CLAMP(NAME, TYPE) \ void HELPER(NAME)(void *d, void *n, void *m, void *a, uint32_t desc) \ { \ -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-37-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 71 ++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 98 ++++++++++++++++++++++++++++++++++ 2 files changed, 169 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SUB_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4 SUB_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2 SUB_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4 +%off3_x2 0:3 !function=times_2 +%off2_x2 0:2 !function=times_2 + +@azz_nx1_o3x2 ........ ... . zm:4 . .. ... zn:5 .. ... \ + &azz_n off=%off3_x2 rv=%mova_rv +@azz_nx1_o2x2 ........ ... . zm:4 . .. ... zn:5 ... .. \ + &azz_n off=%off2_x2 rv=%mova_rv + +FMLAL_n1 11000001 001 0 .... 0 .. 011 ..... 00 ... @azz_nx1_o3x2 n=1 +FMLAL_n1 11000001 001 0 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=2 +FMLAL_n1 11000001 001 1 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=4 + +FMLSL_n1 11000001 001 0 .... 0 .. 011 ..... 01 ... @azz_nx1_o3x2 n=1 +FMLSL_n1 11000001 001 0 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=2 +FMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=4 + +BFMLAL_n1 11000001 001 0 .... 0 .. 011 ..... 10 ... @azz_nx1_o3x2 n=1 +BFMLAL_n1 11000001 001 0 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=2 +BFMLAL_n1 11000001 001 1 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=4 + +BFMLSL_n1 11000001 001 0 .... 0 .. 011 ..... 11 ... @azz_nx1_o3x2 n=1 +BFMLSL_n1 11000001 001 0 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=2 +BFMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4 + ### SME2 Multi-vector Multiple Array Vectors %zn_ax2 6:4 !function=times_2 @@ -XXX,XX +XXX,XX @@ SUB_azz_nn_s 11000001 101 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3 SUB_azz_nn_s 11000001 101 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3 SUB_azz_nn_d 11000001 111 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3 SUB_azz_nn_d 11000001 111 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3 + +@azz_2x2_o2x2 ........ ... ..... . .. ... ..... ... .. \ + &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off2_x2 +@azz_4x4_o2x2 ........ ... ..... . .. ... ..... ... .. \ + &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off2_x2 + +FMLAL_nn 11000001 101 ....0 0 .. 010 ....0 000 .. @azz_2x2_o2x2 +FMLAL_nn 11000001 101 ...01 0 .. 010 ...00 000 .. @azz_4x4_o2x2 + +FMLSL_nn 11000001 101 ....0 0 .. 010 ....0 010 .. @azz_2x2_o2x2 +FMLSL_nn 11000001 101 ...01 0 .. 010 ...00 010 .. @azz_4x4_o2x2 + +BFMLAL_nn 11000001 101 ....0 0 .. 010 ....0 100 .. @azz_2x2_o2x2 +BFMLAL_nn 11000001 101 ...01 0 .. 010 ...00 100 .. @azz_4x4_o2x2 + +BFMLSL_nn 11000001 101 ....0 0 .. 010 ....0 110 .. @azz_2x2_o2x2 +BFMLSL_nn 11000001 101 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2 + +### SME2 Multi-vector Indexed + +&azx_n n off rv zn zm idx + +%idx3_15_10 15:1 10:2 +%idx2_10_2 10:2 2:1 + +@azx_1x1_o3x2 ........ .... zm:4 . .. . .. zn:5 .. ... \ + &azx_n n=1 rv=%mova_rv off=%off3_x2 idx=%idx3_15_10 +@azx_2x1_o2x2 ........ .... zm:4 . .. . .. ..... .. ... \ + &azx_n n=2 rv=%mova_rv off=%off2_x2 zn=%zn_ax2 idx=%idx2_10_2 +@azx_4x1_o2x2 ........ .... zm:4 . .. . .. ..... .. ... \ + &azx_n n=4 rv=%mova_rv off=%off2_x2 zn=%zn_ax4 idx=%idx2_10_2 + +FMLAL_nx 11000001 1000 .... . .. 1 .. ..... 00 ... @azx_1x1_o3x2 +FMLAL_nx 11000001 1001 .... 0 .. 1 .. ....0 00 ... @azx_2x1_o2x2 +FMLAL_nx 11000001 1001 .... 1 .. 1 .. ...00 00 ... @azx_4x1_o2x2 + +FMLSL_nx 11000001 1000 .... . .. 1 .. ..... 01 ... @azx_1x1_o3x2 +FMLSL_nx 11000001 1001 .... 0 .. 1 .. ....0 01 ... @azx_2x1_o2x2 +FMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 01 ... @azx_4x1_o2x2 + +BFMLAL_nx 11000001 1000 .... . .. 1 .. ..... 10 ... @azx_1x1_o3x2 +BFMLAL_nx 11000001 1001 .... 0 .. 1 .. ....0 10 ... @azx_2x1_o2x2 +BFMLAL_nx 11000001 1001 .... 1 .. 1 .. ...00 10 ... @azx_4x1_o2x2 + +BFMLSL_nx 11000001 1000 .... . .. 1 .. ..... 11 ... @azx_1x1_o3x2 +BFMLSL_nx 11000001 1001 .... 0 .. 1 .. ....0 11 ... @azx_2x1_o2x2 +BFMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2 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 @@ TRANS_FEAT(ADD_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_add_var) TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var) TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var) TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var) + +/* + * Expand array multi-vector single (n1), array multi-vector (nn), + * and array multi-vector indexed (nx), for floating-point accumulate. + * multi: true for nn, false for n1. + * fpst: >= 0 to set ptr argument for FPST_*, < 0 for ENV. + * data: stuff for simd_data, including any index. + */ +#define FPST_ENV -1 + +static bool do_azz_acc_fp(DisasContext *s, int nreg, int nsel, + int rv, int off, int zn, int zm, + int data, int shsel, bool multi, int fpst, + gen_helper_gvec_4_ptr *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / nreg; + TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel); + TCGv_ptr t, ptr; + + if (fpst >= 0) { + ptr = fpstatus_ptr(fpst); + } else { + ptr = tcg_env; + } + t = tcg_temp_new_ptr(); + + for (int r = 0; r < nreg; ++r) { + TCGv_ptr t_zn = vec_full_reg_ptr(s, zn); + TCGv_ptr t_zm = vec_full_reg_ptr(s, zm); + + for (int i = 0; i < nsel; ++i) { + int o_za = (r * vstride + i) * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, data | (i << shsel)); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t_zn, t_zm, t, ptr, tcg_constant_i32(desc)); + } + + /* + * For multiple-and-single vectors, Zn may wrap. + * For multiple vectors, both Zn and Zm are aligned. + */ + zn = (zn + 1) % 32; + zm += multi; + } + } + return true; +} + +static bool do_fmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi) +{ + return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + (1 << 2) | sub, 1, + multi, FPST_ENV, gen_helper_sve2_fmlal_zzzw_s); +} + +TRANS_FEAT(FMLAL_n1, aa64_sme2, do_fmlal, a, false, false) +TRANS_FEAT(FMLSL_n1, aa64_sme2, do_fmlal, a, true, false) +TRANS_FEAT(FMLAL_nn, aa64_sme2, do_fmlal, a, false, true) +TRANS_FEAT(FMLSL_nn, aa64_sme2, do_fmlal, a, true, true) + +static bool do_fmlal_nx(DisasContext *s, arg_azx_n *a, bool sub) +{ + return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + (a->idx << 3) | (1 << 2) | sub, 1, + false, FPST_ENV, gen_helper_sve2_fmlal_zzxw_s); +} + +TRANS_FEAT(FMLAL_nx, aa64_sme2, do_fmlal_nx, a, false) +TRANS_FEAT(FMLSL_nx, aa64_sme2, do_fmlal_nx, a, true) + +static bool do_bfmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi) +{ + return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, FPST_ZA, + (!sub ? gen_helper_gvec_bfmlal + : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl + : gen_helper_gvec_bfmlsl)); +} + +TRANS_FEAT(BFMLAL_n1, aa64_sme2, do_bfmlal, a, false, false) +TRANS_FEAT(BFMLSL_n1, aa64_sme2, do_bfmlal, a, true, false) +TRANS_FEAT(BFMLAL_nn, aa64_sme2, do_bfmlal, a, false, true) +TRANS_FEAT(BFMLSL_nn, aa64_sme2, do_bfmlal, a, true, true) + +static bool do_bfmlal_nx(DisasContext *s, arg_azx_n *a, bool sub) +{ + return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + a->idx << 1, 0, false, FPST_ZA, + !sub ? gen_helper_gvec_bfmlal_idx + : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl_idx + : gen_helper_gvec_bfmlsl_idx); +} + +TRANS_FEAT(BFMLAL_nx, aa64_sme2, do_bfmlal_nx, a, false) +TRANS_FEAT(BFMLSL_nx, aa64_sme2, do_bfmlal_nx, a, true) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-38-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 5 ++++ target/arm/tcg/sme.decode | 14 +++++++++++ target/arm/tcg/sve.decode | 7 ++++-- target/arm/tcg/sme_helper.c | 44 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 18 ++++++++++++++ target/arm/tcg/translate-sve.c | 5 ++++ 6 files changed, 91 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmaxnum_b16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fminnum_b16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_6(sme2_fdot_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_6(sme2_fdot_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, env, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ BFMLSL_n1 11000001 001 0 .... 0 .. 011 ..... 11 ... @azz_nx1_o3x2 n=1 BFMLSL_n1 11000001 001 0 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=2 BFMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4 +FDOT_n1 11000001 001 0 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=2 +FDOT_n1 11000001 001 1 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=4 + ### SME2 Multi-vector Multiple Array Vectors %zn_ax2 6:4 !function=times_2 @@ -XXX,XX +XXX,XX @@ BFMLAL_nn 11000001 101 ...01 0 .. 010 ...00 100 .. @azz_4x4_o2x2 BFMLSL_nn 11000001 101 ....0 0 .. 010 ....0 110 .. @azz_2x2_o2x2 BFMLSL_nn 11000001 101 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2 +FDOT_nn 11000001 101 ....0 0 .. 100 ....0 00 ... @azz_2x2_o3 +FDOT_nn 11000001 101 ...01 0 .. 100 ...00 00 ... @azz_4x4_o3 + ### SME2 Multi-vector Indexed &azx_n n off rv zn zm idx @@ -XXX,XX +XXX,XX @@ BFMLAL_nx 11000001 1001 .... 1 .. 1 .. ...00 10 ... @azx_4x1_o2x2 BFMLSL_nx 11000001 1000 .... . .. 1 .. ..... 11 ... @azx_1x1_o3x2 BFMLSL_nx 11000001 1001 .... 0 .. 1 .. ....0 11 ... @azx_2x1_o2x2 BFMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2 + +@azx_2x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \ + &azx_n n=2 rv=%mova_rv zn=%zn_ax2 +@azx_4x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \ + &azx_n n=2 rv=%mova_rv zn=%zn_ax4 + +FDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_i2_o3 +FDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_i2_o3 diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_ex esz=2 BFMLALB_zzzw 01100100 11 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 BFMLALT_zzzw 01100100 11 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_ex esz=2 -### SVE2 floating-point bfloat16 dot-product +### SVE2 floating-point dot-product +FDOT_zzzz 01100100 00 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 BFDOT_zzzz 01100100 01 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 ### SVE2 floating-point multiply-add long (indexed) @@ -XXX,XX +XXX,XX @@ FMLSLT_zzxw 01100100 10 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2 BFMLALB_zzxw 01100100 11 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2 BFMLALT_zzxw 01100100 11 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 -### SVE2 floating-point bfloat16 dot-product (indexed) +### SVE2 floating-point dot-product (indexed) + +FDOT_zzxz 01100100 00 1 ..... 010000 ..... ..... @rrxr_2 esz=2 BFDOT_zzxz 01100100 01 1 ..... 010000 ..... ..... @rrxr_2 esz=2 ### SVE broadcast predicate element 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, } } +void HELPER(sme2_fdot_h)(void *vd, void *vn, void *vm, void *va, + CPUARMState *env, uint32_t desc) +{ + intptr_t i, oprsz = simd_maxsz(desc); + bool za = extract32(desc, SIMD_DATA_SHIFT, 1); + float_status *fpst_std = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64]; + float_status *fpst_f16 = &env->vfp.fp_status[za ? FPST_ZA_F16 : FPST_A64_F16]; + float_status fpst_odd = *fpst_std; + float32 *d = vd, *a = va; + uint32_t *n = vn, *m = vm; + + set_float_rounding_mode(float_round_to_odd, &fpst_odd); + + for (i = 0; i < oprsz / sizeof(float32); ++i) { + d[H4(i)] = f16_dotadd(a[H4(i)], n[H4(i)], m[H4(i)], + fpst_f16, fpst_std, &fpst_odd); + } +} + +void HELPER(sme2_fdot_idx_h)(void *vd, void *vn, void *vm, void *va, + CPUARMState *env, uint32_t desc) +{ + intptr_t i, j, oprsz = simd_maxsz(desc); + intptr_t elements = oprsz / sizeof(float32); + intptr_t eltspersegment = MIN(4, elements); + int idx = extract32(desc, SIMD_DATA_SHIFT, 2); + bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + float_status *fpst_std = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64]; + float_status *fpst_f16 = &env->vfp.fp_status[za ? FPST_ZA_F16 : FPST_A64_F16]; + float_status fpst_odd = *fpst_std; + float32 *d = vd, *a = va; + uint32_t *n = vn, *m = (uint32_t *)vm + H4(idx); + + set_float_rounding_mode(float_round_to_odd, &fpst_odd); + + for (i = 0; i < elements; i += eltspersegment) { + uint32_t mm = m[i]; + for (j = 0; j < eltspersegment; ++j) { + d[H4(i + j)] = f16_dotadd(a[H4(i + j)], n[H4(i + j)], mm, + fpst_f16, fpst_std, &fpst_odd); + } + } +} + void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, void *vpm, CPUARMState *env, uint32_t desc) { 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_bfmlal_nx(DisasContext *s, arg_azx_n *a, bool sub) TRANS_FEAT(BFMLAL_nx, aa64_sme2, do_bfmlal_nx, a, false) TRANS_FEAT(BFMLSL_nx, aa64_sme2, do_bfmlal_nx, a, true) + +static bool do_fdot(DisasContext *s, arg_azz_n *a, bool multi) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, 1, 0, + multi, FPST_ENV, gen_helper_sme2_fdot_h); +} + +TRANS_FEAT(FDOT_n1, aa64_sme2, do_fdot, a, false) +TRANS_FEAT(FDOT_nn, aa64_sme2, do_fdot, a, true) + +static bool do_fdot_nx(DisasContext *s, arg_azx_n *a) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + a->idx | (1 << 2), 0, false, FPST_ENV, + gen_helper_sme2_fdot_idx_h); +} + +TRANS_FEAT(FDOT_nx, aa64_sme2, do_fdot_nx, a) 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_NONSTREAMING(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, TRANS_FEAT_NONSTREAMING(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, gen_helper_gvec_ummla_b, a, 0) +TRANS_FEAT(FDOT_zzzz, aa64_sme2_or_sve2p1, gen_gvec_env_arg_zzzz, + gen_helper_sme2_fdot_h, a, 0) +TRANS_FEAT(FDOT_zzxz, aa64_sme2_or_sve2p1, gen_gvec_env_arg_zzxz, + gen_helper_sme2_fdot_idx_h, a) + TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_env_arg_zzzz, gen_helper_gvec_bfdot, a, 0) TRANS_FEAT(BFDOT_zzxz, aa64_sve_bf16, gen_gvec_env_arg_zzxz, -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-39-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 9 +++++++++ target/arm/tcg/translate-sme.c | 17 +++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ BFMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4 FDOT_n1 11000001 001 0 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=2 FDOT_n1 11000001 001 1 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=4 +BFDOT_n1 11000001 001 0 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=2 +BFDOT_n1 11000001 001 1 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=4 + ### SME2 Multi-vector Multiple Array Vectors %zn_ax2 6:4 !function=times_2 @@ -XXX,XX +XXX,XX @@ BFMLSL_nn 11000001 101 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2 FDOT_nn 11000001 101 ....0 0 .. 100 ....0 00 ... @azz_2x2_o3 FDOT_nn 11000001 101 ...01 0 .. 100 ...00 00 ... @azz_4x4_o3 +BFDOT_nn 11000001 101 ....0 0 .. 100 ....0 10 ... @azz_2x2_o3 +BFDOT_nn 11000001 101 ...01 0 .. 100 ...00 10 ... @azz_4x4_o3 + ### SME2 Multi-vector Indexed &azx_n n off rv zn zm idx @@ -XXX,XX +XXX,XX @@ BFMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2 FDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_i2_o3 FDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_i2_o3 + +BFDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 11 ... @azx_2x1_i2_o3 +BFDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_i2_o3 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_fdot_nx(DisasContext *s, arg_azx_n *a) } TRANS_FEAT(FDOT_nx, aa64_sme2, do_fdot_nx, a) + +static bool do_bfdot(DisasContext *s, arg_azz_n *a, bool multi) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, 0, 0, + multi, FPST_ENV, gen_helper_gvec_bfdot); +} + +TRANS_FEAT(BFDOT_n1, aa64_sme2, do_bfdot, a, false) +TRANS_FEAT(BFDOT_nn, aa64_sme2, do_bfdot, a, true) + +static bool do_bfdot_nx(DisasContext *s, arg_azx_n *a) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, a->idx, 0, + false, FPST_ENV, gen_helper_gvec_bfdot_idx); +} + +TRANS_FEAT(BFDOT_nx, aa64_sme2, do_bfdot_nx, a) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-40-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 2 ++ target/arm/tcg/helper.h | 2 ++ target/arm/tcg/sme.decode | 3 +++ target/arm/tcg/sme_helper.c | 30 ++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 24 +++++++++++++++++++++ target/arm/tcg/vec_helper.c | 39 ++++++++++++++++++++++++++++++++++ 6 files changed, 100 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sme2_fdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(sme2_fdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_6(sme2_fvdot_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, env, i32) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_bfdot, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(gvec_bfdot_idx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_6(sme2_bfvdot_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(gvec_bfmmla, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ FDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_i2_o3 BFDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 11 ... @azx_2x1_i2_o3 BFDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_i2_o3 + +FVDOT 11000001 0101 .... 0 .. 0 .. ....0 01 ... @azx_2x1_i2_o3 +BFVDOT 11000001 0101 .... 0 .. 0 .. ....0 11 ... @azx_2x1_i2_o3 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(sme2_fdot_idx_h)(void *vd, void *vn, void *vm, void *va, } } +void HELPER(sme2_fvdot_idx_h)(void *vd, void *vn, void *vm, void *va, + CPUARMState *env, uint32_t desc) +{ + intptr_t i, j, oprsz = simd_maxsz(desc); + intptr_t elements = oprsz / sizeof(float32); + intptr_t eltspersegment = MIN(4, elements); + int idx = extract32(desc, SIMD_DATA_SHIFT, 2); + int sel = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + float_status fpst_odd, *fpst_std, *fpst_f16; + float32 *d = vd, *a = va; + uint16_t *n0 = vn; + uint16_t *n1 = vn + sizeof(ARMVectorReg); + uint32_t *m = (uint32_t *)vm + H4(idx); + + fpst_std = &env->vfp.fp_status[FPST_ZA]; + fpst_f16 = &env->vfp.fp_status[FPST_ZA_F16]; + fpst_odd = *fpst_std; + set_float_rounding_mode(float_round_to_odd, &fpst_odd); + + for (i = 0; i < elements; i += eltspersegment) { + uint32_t mm = m[i]; + for (j = 0; j < eltspersegment; ++j) { + uint32_t nn = (n0[H2(2 * (i + j) + sel)]) + | (n1[H2(2 * (i + j) + sel)] << 16); + d[i + H4(j)] = f16_dotadd(a[i + H4(j)], nn, mm, + fpst_f16, fpst_std, &fpst_odd); + } + } +} + void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, void *vpm, CPUARMState *env, uint32_t desc) { 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_bfdot_nx(DisasContext *s, arg_azx_n *a) } TRANS_FEAT(BFDOT_nx, aa64_sme2, do_bfdot_nx, a) + +static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / 2; + TCGv_ptr t_za = get_zarray(s, a->rv, a->off, 2, 1); + TCGv_ptr t_zn = vec_full_reg_ptr(s, a->zn); + TCGv_ptr t_zm = vec_full_reg_ptr(s, a->zm); + TCGv_ptr t = tcg_temp_new_ptr(); + + for (int i = 0; i < 2; ++i) { + int o_za = i * vstride * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, a->idx | (i << 2)); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t_zn, t_zm, t, tcg_env, tcg_constant_i32(desc)); + } + } + return true; +} + +TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h) +TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx) 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_bfdot_idx)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(sme2_bfvdot_idx)(void *vd, void *vn, void *vm, + void *va, CPUARMState *env, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT, 2); + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + intptr_t elements = opr_sz / 4; + intptr_t eltspersegment = MIN(16 / 4, elements); + float32 *d = vd, *a = va; + uint16_t *n0 = vn; + uint16_t *n1 = vn + sizeof(ARMVectorReg); + uint32_t *m = vm; + float_status fpst, fpst_odd; + + if (is_ebf(env, &fpst, &fpst_odd)) { + for (i = 0; i < elements; i += eltspersegment) { + uint32_t m_idx = m[i + H4(idx)]; + + for (j = 0; j < eltspersegment; j++) { + uint32_t nn = (n0[H2(2 * (i + j) + sel)]) + | (n1[H2(2 * (i + j) + sel)] << 16); + d[i + H4(j)] = bfdotadd_ebf(a[i + H4(j)], nn, m_idx, + &fpst, &fpst_odd); + } + } + } else { + for (i = 0; i < elements; i += eltspersegment) { + uint32_t m_idx = m[i + H4(idx)]; + + for (j = 0; j < eltspersegment; j++) { + uint32_t nn = (n0[H2(2 * (i + j) + sel)]) + | (n1[H2(2 * (i + j) + sel)] << 16); + d[i + H4(j)] = bfdotadd(a[i + H4(j)], nn, m_idx, &fpst); + } + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va, CPUARMState *env, uint32_t desc) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Emphasize that these are 4-way dot products. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-41-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper.h | 22 +++++++++++----------- target/arm/tcg/translate-a64.c | 14 +++++++------- target/arm/tcg/translate-neon.c | 14 +++++++------- target/arm/tcg/translate-sve.c | 18 +++++++++--------- target/arm/tcg/vec_helper.c | 22 +++++++++++----------- 5 files changed, 45 insertions(+), 45 deletions(-) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_sdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_udot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_sdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_udot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_sudot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_usdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool do_dot_vector_env(DisasContext *s, arg_qrrr_e *a, return true; } -TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b) -TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b) -TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b) +TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_4b) +TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_4b) +TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_4b) TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfdot) TRANS_FEAT(BFMMLA, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfmmla) TRANS_FEAT(SMMLA, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_smmla_b) @@ -XXX,XX +XXX,XX @@ static bool do_dot_vector_idx_env(DisasContext *s, arg_qrrx_e *a, return true; } -TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_b) -TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_b) +TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_4b) +TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_4b) TRANS_FEAT(SUDOT_vi, aa64_i8mm, do_dot_vector_idx, a, - gen_helper_gvec_sudot_idx_b) + gen_helper_gvec_sudot_idx_4b) TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a, - gen_helper_gvec_usdot_idx_b) + gen_helper_gvec_usdot_idx_4b) TRANS_FEAT(BFDOT_vi, aa64_bf16, do_dot_vector_idx_env, a, gen_helper_gvec_bfdot_idx) diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSDOT(DisasContext *s, arg_VSDOT *a) return false; } return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, - gen_helper_gvec_sdot_b); + gen_helper_gvec_sdot_4b); } static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a) @@ -XXX,XX +XXX,XX @@ static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a) return false; } return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, - gen_helper_gvec_udot_b); + gen_helper_gvec_udot_4b); } static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a) @@ -XXX,XX +XXX,XX @@ static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a) return false; } return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, - gen_helper_gvec_usdot_b); + gen_helper_gvec_usdot_4b); } static bool trans_VDOT_b16(DisasContext *s, arg_VDOT_b16 *a) @@ -XXX,XX +XXX,XX @@ static bool trans_VSDOT_scalar(DisasContext *s, arg_VSDOT_scalar *a) return false; } return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, - gen_helper_gvec_sdot_idx_b); + gen_helper_gvec_sdot_idx_4b); } static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a) @@ -XXX,XX +XXX,XX @@ static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a) return false; } return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, - gen_helper_gvec_udot_idx_b); + gen_helper_gvec_udot_idx_4b); } static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a) @@ -XXX,XX +XXX,XX @@ static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a) return false; } return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, - gen_helper_gvec_usdot_idx_b); + gen_helper_gvec_usdot_idx_4b); } static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a) @@ -XXX,XX +XXX,XX @@ static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a) return false; } return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, - gen_helper_gvec_sudot_idx_b); + gen_helper_gvec_sudot_idx_4b); } static bool trans_VDOT_b16_scal(DisasContext *s, arg_VDOT_b16_scal *a) 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 @@ DO_ZZI(UMIN, umin) #undef DO_ZZI static gen_helper_gvec_4 * const dot_fns[2][2] = { - { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h }, - { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h } + { gen_helper_gvec_sdot_4b, gen_helper_gvec_sdot_4h }, + { gen_helper_gvec_udot_4b, gen_helper_gvec_udot_4h } }; TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz, dot_fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz, */ TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_sdot_idx_b, a) + gen_helper_gvec_sdot_idx_4b, a) TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_sdot_idx_h, a) + gen_helper_gvec_sdot_idx_4h, a) TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_udot_idx_b, a) + gen_helper_gvec_udot_idx_4b, a) TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_udot_idx_h, a) + gen_helper_gvec_udot_idx_4h, a) TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_sudot_idx_b, a) + gen_helper_gvec_sudot_idx_4b, a) TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_usdot_idx_b, a) + gen_helper_gvec_usdot_idx_4b, a) #define DO_SVE2_RRX(NAME, FUNC) \ TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC, \ @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot) TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - a->esz == 2 ? gen_helper_gvec_usdot_b : NULL, a, 0) + a->esz == 2 ? gen_helper_gvec_usdot_4b : NULL, a, 0) TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, gen_helper_crypto_aesmc, a->rd, a->rd, 0) 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(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ clear_tail(d, opr_sz, simd_maxsz(desc)); \ } -DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t) -DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t) -DO_DOT(gvec_usdot_b, uint32_t, uint8_t, int8_t) -DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t) -DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t) +DO_DOT(gvec_sdot_4b, int32_t, int8_t, int8_t) +DO_DOT(gvec_udot_4b, uint32_t, uint8_t, uint8_t) +DO_DOT(gvec_usdot_4b, uint32_t, uint8_t, int8_t) +DO_DOT(gvec_sdot_4h, int64_t, int16_t, int16_t) +DO_DOT(gvec_udot_4h, uint64_t, uint16_t, uint16_t) #define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ clear_tail(d, opr_sz, simd_maxsz(desc)); \ } -DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4) -DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4) -DO_DOT_IDX(gvec_sudot_idx_b, int32_t, int8_t, uint8_t, H4) -DO_DOT_IDX(gvec_usdot_idx_b, int32_t, uint8_t, int8_t, H4) -DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, H8) -DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, H8) +DO_DOT_IDX(gvec_sdot_idx_4b, int32_t, int8_t, int8_t, H4) +DO_DOT_IDX(gvec_udot_idx_4b, uint32_t, uint8_t, uint8_t, H4) +DO_DOT_IDX(gvec_sudot_idx_4b, int32_t, int8_t, uint8_t, H4) +DO_DOT_IDX(gvec_usdot_idx_4b, int32_t, uint8_t, int8_t, H4) +DO_DOT_IDX(gvec_sdot_idx_4h, int64_t, int16_t, int16_t, H8) +DO_DOT_IDX(gvec_udot_idx_4h, uint64_t, uint16_t, uint16_t, H8) void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm, float_status *fpst, uint32_t desc) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250704142112.1018902-42-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper.h | 8 ++++ target/arm/tcg/sme.decode | 63 ++++++++++++++++++++++++- target/arm/tcg/translate-sme.c | 85 ++++++++++++++++++++++++++++++++++ target/arm/tcg/vec_helper.c | 51 ++++++++++++++++++++ 4 files changed, 206 insertions(+), 1 deletion(-) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_sdot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_udot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_usdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_sdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_udot_idx_4b, TCG_CALL_NO_RWG, @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_sudot_idx_4b, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_usdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_idx_2h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_idx_2h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG, diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ FDOT_n1 11000001 001 1 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=4 BFDOT_n1 11000001 001 0 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=2 BFDOT_n1 11000001 001 1 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=4 +USDOT_n1 11000001 001 0 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=2 +USDOT_n1 11000001 001 1 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=4 + +SUDOT_n1 11000001 001 0 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=2 +SUDOT_n1 11000001 001 1 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=4 + +SDOT_n1_4b 11000001 001 0 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=2 +SDOT_n1_4b 11000001 001 1 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=4 +SDOT_n1_4h 11000001 011 0 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=2 +SDOT_n1_4h 11000001 011 1 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=4 +SDOT_n1_2h 11000001 011 0 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=2 +SDOT_n1_2h 11000001 011 1 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=4 + +UDOT_n1_4b 11000001 001 0 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=2 +UDOT_n1_4b 11000001 001 1 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=4 +UDOT_n1_4h 11000001 011 0 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=2 +UDOT_n1_4h 11000001 011 1 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=4 +UDOT_n1_2h 11000001 011 0 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=2 +UDOT_n1_2h 11000001 011 1 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=4 + ### SME2 Multi-vector Multiple Array Vectors %zn_ax2 6:4 !function=times_2 @@ -XXX,XX +XXX,XX @@ FDOT_nn 11000001 101 ...01 0 .. 100 ...00 00 ... @azz_4x4_o3 BFDOT_nn 11000001 101 ....0 0 .. 100 ....0 10 ... @azz_2x2_o3 BFDOT_nn 11000001 101 ...01 0 .. 100 ...00 10 ... @azz_4x4_o3 +USDOT_nn 11000001 101 ....0 0 .. 101 ....0 01 ... @azz_2x2_o3 +USDOT_nn 11000001 101 ...01 0 .. 101 ...00 01 ... @azz_4x4_o3 + +SDOT_nn_4b 11000001 101 ....0 0 .. 101 ....0 00 ... @azz_2x2_o3 +SDOT_nn_4b 11000001 101 ...01 0 .. 101 ...00 00 ... @azz_4x4_o3 +SDOT_nn_4h 11000001 111 ....0 0 .. 101 ....0 00 ... @azz_2x2_o3 +SDOT_nn_4h 11000001 111 ...01 0 .. 101 ...00 00 ... @azz_4x4_o3 +SDOT_nn_2h 11000001 111 ....0 0 .. 101 ....0 01 ... @azz_2x2_o3 +SDOT_nn_2h 11000001 111 ...01 0 .. 101 ...00 01 ... @azz_4x4_o3 + +UDOT_nn_4b 11000001 101 ....0 0 .. 101 ....0 10 ... @azz_2x2_o3 +UDOT_nn_4b 11000001 101 ...01 0 .. 101 ...00 10 ... @azz_4x4_o3 +UDOT_nn_4h 11000001 111 ....0 0 .. 101 ....0 10 ... @azz_2x2_o3 +UDOT_nn_4h 11000001 111 ...01 0 .. 101 ...00 10 ... @azz_4x4_o3 +UDOT_nn_2h 11000001 111 ....0 0 .. 101 ....0 11 ... @azz_2x2_o3 +UDOT_nn_2h 11000001 111 ...01 0 .. 101 ...00 11 ... @azz_4x4_o3 + ### SME2 Multi-vector Indexed &azx_n n off rv zn zm idx @@ -XXX,XX +XXX,XX @@ BFMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2 @azx_2x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \ &azx_n n=2 rv=%mova_rv zn=%zn_ax2 @azx_4x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \ - &azx_n n=2 rv=%mova_rv zn=%zn_ax4 + &azx_n n=4 rv=%mova_rv zn=%zn_ax4 +@azx_2x1_i1_o3 ........ .... zm:4 . .. .. idx:1 .... ... off:3 \ + &azx_n n=2 rv=%mova_rv zn=%zn_ax2 +@azx_4x1_i1_o3 ........ .... zm:4 . .. .. idx:1 .... ... off:3 \ + &azx_n n=4 rv=%mova_rv zn=%zn_ax4 FDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_i2_o3 FDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_i2_o3 @@ -XXX,XX +XXX,XX @@ BFDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_i2_o3 FVDOT 11000001 0101 .... 0 .. 0 .. ....0 01 ... @azx_2x1_i2_o3 BFVDOT 11000001 0101 .... 0 .. 0 .. ....0 11 ... @azx_2x1_i2_o3 + +SDOT_nx_2h 11000001 0101 .... 0 .. 1 .. ....0 00 ... @azx_2x1_i2_o3 +SDOT_nx_2h 11000001 0101 .... 1 .. 1 .. ...00 00 ... @azx_4x1_i2_o3 +SDOT_nx_4b 11000001 0101 .... 0 .. 1 .. ....1 00 ... @azx_2x1_i2_o3 +SDOT_nx_4b 11000001 0101 .... 1 .. 1 .. ...01 00 ... @azx_4x1_i2_o3 +SDOT_nx_4h 11000001 1101 .... 0 .. 00 . ....0 01 ... @azx_2x1_i1_o3 +SDOT_nx_4h 11000001 1101 .... 1 .. 00 . ...00 01 ... @azx_4x1_i1_o3 + +UDOT_nx_2h 11000001 0101 .... 0 .. 1 .. ....0 10 ... @azx_2x1_i2_o3 +UDOT_nx_2h 11000001 0101 .... 1 .. 1 .. ...00 10 ... @azx_4x1_i2_o3 +UDOT_nx_4b 11000001 0101 .... 0 .. 1 .. ....1 10 ... @azx_2x1_i2_o3 +UDOT_nx_4b 11000001 0101 .... 1 .. 1 .. ...01 10 ... @azx_4x1_i2_o3 +UDOT_nx_4h 11000001 1101 .... 0 .. 00 . ....0 11 ... @azx_2x1_i1_o3 +UDOT_nx_4h 11000001 1101 .... 1 .. 00 . ...00 11 ... @azx_4x1_i1_o3 + +USDOT_nx 11000001 0101 .... 0 .. 1 .. ....1 01 ... @azx_2x1_i2_o3 +USDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 01 ... @azx_4x1_i2_o3 + +SUDOT_nx 11000001 0101 .... 0 .. 1 .. ....1 11 ... @azx_2x1_i2_o3 +SUDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 11 ... @azx_4x1_i2_o3 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_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn) TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h) TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx) + +/* + * Expand array multi-vector single (n1), array multi-vector (nn), + * and array multi-vector indexed (nx), for integer accumulate. + * multi: true for nn, false for n1. + * data: stuff for simd_data, including any index. + */ +static bool do_azz_acc(DisasContext *s, int nreg, int nsel, + int rv, int off, int zn, int zm, + int data, int shsel, bool multi, + gen_helper_gvec_4 *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / nreg; + TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel); + TCGv_ptr t = tcg_temp_new_ptr(); + + for (int r = 0; r < nreg; ++r) { + TCGv_ptr t_zn = vec_full_reg_ptr(s, zn); + TCGv_ptr t_zm = vec_full_reg_ptr(s, zm); + + for (int i = 0; i < nsel; ++i) { + int o_za = (r * vstride + i) * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, data | (i << shsel)); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t_zn, t_zm, t, tcg_constant_i32(desc)); + } + + /* + * For multiple-and-single vectors, Zn may wrap. + * For multiple vectors, both Zn and Zm are aligned. + */ + zn = (zn + 1) % 32; + zm += multi; + } + } + return true; +} + +static bool do_dot(DisasContext *s, arg_azz_n *a, bool multi, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, fn); +} + +static void gen_helper_gvec_sudot_4b(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m, + TCGv_ptr a, TCGv_i32 desc) +{ + gen_helper_gvec_usdot_4b(d, m, n, a, desc); +} + +TRANS_FEAT(USDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_usdot_4b) +TRANS_FEAT(SUDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_sudot_4b) +TRANS_FEAT(SDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_2h) +TRANS_FEAT(UDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_2h) +TRANS_FEAT(SDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_4b) +TRANS_FEAT(UDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_4b) +TRANS_FEAT(SDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_sdot_4h) +TRANS_FEAT(UDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_udot_4h) + +TRANS_FEAT(USDOT_nn, aa64_sme2, do_dot, a, true, gen_helper_gvec_usdot_4b) +TRANS_FEAT(SDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_2h) +TRANS_FEAT(UDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_2h) +TRANS_FEAT(SDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_4b) +TRANS_FEAT(UDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_4b) +TRANS_FEAT(SDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_sdot_4h) +TRANS_FEAT(UDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_udot_4h) + +static bool do_dot_nx(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + a->idx, 0, false, fn); +} + +TRANS_FEAT(USDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_usdot_idx_4b) +TRANS_FEAT(SUDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sudot_idx_4b) +TRANS_FEAT(SDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_2h) +TRANS_FEAT(UDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_2h) +TRANS_FEAT(SDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_4b) +TRANS_FEAT(UDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_4b) +TRANS_FEAT(SDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_sdot_idx_4h) +TRANS_FEAT(UDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_udot_idx_4h) 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 @@ DO_DOT_IDX(gvec_usdot_idx_4b, int32_t, uint8_t, int8_t, H4) DO_DOT_IDX(gvec_sdot_idx_4h, int64_t, int16_t, int16_t, H8) DO_DOT_IDX(gvec_udot_idx_4h, uint64_t, uint16_t, uint16_t, H8) +#undef DO_DOT +#undef DO_DOT_IDX + +/* Similar for 2-way dot product */ +#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + TYPED *d = vd, *a = va; \ + TYPEN *n = vn; \ + TYPEM *m = vm; \ + for (i = 0; i < opr_sz / sizeof(TYPED); ++i) { \ + d[i] = (a[i] + \ + (TYPED)n[i * 2 + 0] * m[i * 2 + 0] + \ + (TYPED)n[i * 2 + 1] * m[i * 2 + 1]); \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i = 0, opr_sz = simd_oprsz(desc); \ + intptr_t opr_sz_n = opr_sz / sizeof(TYPED); \ + intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n); \ + intptr_t index = simd_data(desc); \ + TYPED *d = vd, *a = va; \ + TYPEN *n = vn; \ + TYPEM *m_indexed = (TYPEM *)vm + HD(index) * 2; \ + do { \ + TYPED m0 = m_indexed[i * 2 + 0]; \ + TYPED m1 = m_indexed[i * 2 + 1]; \ + do { \ + d[i] = (a[i] + \ + n[i * 2 + 0] * m0 + \ + n[i * 2 + 1] * m1); \ + } while (++i < segend); \ + segend = i + (16 / sizeof(TYPED)); \ + } while (i < opr_sz_n); \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_DOT(gvec_sdot_2h, int32_t, int16_t, int16_t) +DO_DOT(gvec_udot_2h, uint32_t, uint16_t, uint16_t) + +DO_DOT_IDX(gvec_sdot_idx_2h, int32_t, int16_t, int16_t, H4) +DO_DOT_IDX(gvec_udot_idx_2h, uint32_t, uint16_t, uint16_t, H4) + +#undef DO_DOT +#undef DO_DOT_IDX + void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm, float_status *fpst, uint32_t desc) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Emphasize the 4-way nature of these dot products. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-43-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 12 ++++++------ target/arm/tcg/translate-sve.c | 12 ++++++------ 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ CDOT_zzzz 01000100 esz:2 0 rm:5 0001 rot:2 rn:5 rd:5 ra=%reg_movprfx #### SVE Multiply - Indexed # SVE integer dot product (indexed) -SDOT_zzxw_s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2 -SDOT_zzxw_d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 -UDOT_zzxw_s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 -UDOT_zzxw_d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 +SDOT_zzxw_4s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2 +SDOT_zzxw_4d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 +UDOT_zzxw_4s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 +UDOT_zzxw_4d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 # SVE2 integer multiply-add (indexed) MLA_zzxz_h 01000100 0. 1 ..... 000010 ..... ..... @rrxr_3 esz=1 @@ -XXX,XX +XXX,XX @@ SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... ..... @rrxr_2 esz=2 SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... ..... @rrxr_1 esz=3 # SVE mixed sign dot product (indexed) -USDOT_zzxw_s 01000100 10 1 ..... 000110 ..... ..... @rrxr_2 esz=2 -SUDOT_zzxw_s 01000100 10 1 ..... 000111 ..... ..... @rrxr_2 esz=2 +USDOT_zzxw_4s 01000100 10 1 ..... 000110 ..... ..... @rrxr_2 esz=2 +SUDOT_zzxw_4s 01000100 10 1 ..... 000111 ..... ..... @rrxr_2 esz=2 # SVE2 saturating multiply-add (indexed) SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... ..... @rrxr_3a esz=2 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(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz, * SVE Multiply - Indexed */ -TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz, +TRANS_FEAT(SDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz, gen_helper_gvec_sdot_idx_4b, a) -TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz, +TRANS_FEAT(SDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz, gen_helper_gvec_sdot_idx_4h, a) -TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz, +TRANS_FEAT(UDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz, gen_helper_gvec_udot_idx_4b, a) -TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz, +TRANS_FEAT(UDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz, gen_helper_gvec_udot_idx_4h, a) -TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, +TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, gen_helper_gvec_sudot_idx_4b, a) -TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, +TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, gen_helper_gvec_usdot_idx_4b, a) #define DO_SVE2_RRX(NAME, FUNC) \ -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Rename to USDOT_zzzz_4s and force size=2 during decode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-44-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 2 +- target/arm/tcg/translate-sve.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx ## SVE mixed sign dot product -USDOT_zzzz 01000100 .. 0 ..... 011 110 ..... ..... @rda_rn_rm +USDOT_zzzz_4s 01000100 10 0 ..... 011 110 ..... ..... @rda_rn_rm_ex esz=2 ### SVE2 floating point matrix multiply accumulate BFMMLA 01100100 01 1 ..... 111 001 ..... ..... @rda_rn_rm_ex esz=1 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 gen_helper_gvec_4 * const sqrdcmlah_fns[] = { TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot) -TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - a->esz == 2 ? gen_helper_gvec_usdot_4b : NULL, a, 0) +TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_usdot_4b, a, 0) TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, gen_helper_crypto_aesmc, a->rd, a->rd, 0) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-45-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 8 +++++++- target/arm/tcg/translate-sve.c | 10 ++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ SDOT_zzxw_4d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 UDOT_zzxw_4s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 UDOT_zzxw_4d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 +SDOT_zzxw_2s 01000100 10 0 ..... 110010 ..... ..... @rrxr_2 esz=2 +UDOT_zzxw_2s 01000100 10 0 ..... 110011 ..... ..... @rrxr_2 esz=2 + # SVE2 integer multiply-add (indexed) MLA_zzxz_h 01000100 0. 1 ..... 000010 ..... ..... @rrxr_3 esz=1 MLA_zzxz_s 01000100 10 1 ..... 000010 ..... ..... @rrxr_2 esz=2 @@ -XXX,XX +XXX,XX @@ UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx -## SVE mixed sign dot product +## SVE dot product + +SDOT_zzzz_2s 01000100 00 0 ..... 110 010 ..... ..... @rda_rn_rm_ex esz=2 +UDOT_zzzz_2s 01000100 00 0 ..... 110 011 ..... ..... @rda_rn_rm_ex esz=2 USDOT_zzzz_4s 01000100 10 0 ..... 011 110 ..... ..... @rda_rn_rm_ex esz=2 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(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, gen_helper_gvec_usdot_idx_4b, a) +TRANS_FEAT(SDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_sdot_idx_2h, a) +TRANS_FEAT(UDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_udot_idx_2h, a) + #define DO_SVE2_RRX(NAME, FUNC) \ TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC, \ a->rd, a->rn, a->rm, a->index) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, gen_helper_gvec_usdot_4b, a, 0) +TRANS_FEAT(SDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_sdot_2h, a, 0) +TRANS_FEAT(UDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_udot_2h, a, 0) + TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, gen_helper_crypto_aesmc, a->rd, a->rd, 0) TRANS_FEAT_NONSTREAMING(AESIMC, aa64_sve2_aes, gen_gvec_ool_zz, -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-46-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 11 +++++++++ target/arm/tcg/sme.decode | 11 +++++++++ target/arm/tcg/sme_helper.c | 42 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 23 +++++++++++++++++++ 4 files changed, 87 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sme2_fdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(sme2_fvdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_svdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_suvdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_usvdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_svdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_svdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uvdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ USDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 01 ... @azx_4x1_i2_o3 SUDOT_nx 11000001 0101 .... 0 .. 1 .. ....1 11 ... @azx_2x1_i2_o3 SUDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 11 ... @azx_4x1_i2_o3 + +SVDOT_nx_2h 11000001 0101 .... 0 .. 0 .. ....1 00 ... @azx_2x1_i2_o3 +SVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 00 ... @azx_4x1_i2_o3 +SVDOT_nx_4h 11000001 1101 .... 1 .. 01 . ...00 01 ... @azx_4x1_i1_o3 + +UVDOT_nx_2h 11000001 0101 .... 0 .. 0 .. ....1 10 ... @azx_2x1_i2_o3 +UVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 10 ... @azx_4x1_i2_o3 +UVDOT_nx_4h 11000001 1101 .... 1 .. 01 . ...00 11 ... @azx_4x1_i1_o3 + +SUVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 11 ... @azx_4x1_i2_o3 +USVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 01 ... @azx_4x1_i2_o3 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 @@ DEF_IMOP_16x2_32(umopa2_s, uint16_t, uint16_t) DEF_IMOPH(sme2, smopa2, s) DEF_IMOPH(sme2, umopa2, s) + +#define DO_VDOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD, HN) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t svl = simd_oprsz(desc); \ + intptr_t elements = svl / sizeof(TYPED); \ + intptr_t eltperseg = 16 / sizeof(TYPED); \ + intptr_t nreg = sizeof(TYPED) / sizeof(TYPEN); \ + intptr_t vstride = (svl / nreg) * sizeof(ARMVectorReg); \ + intptr_t zstride = sizeof(ARMVectorReg) / sizeof(TYPEN); \ + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT, 2); \ + TYPEN *n = vn; \ + TYPEM *m = vm; \ + for (intptr_t r = 0; r < nreg; r++) { \ + TYPED *d = vd + r * vstride; \ + for (intptr_t seg = 0; seg < elements; seg += eltperseg) { \ + intptr_t s = seg + idx; \ + for (intptr_t e = seg; e < seg + eltperseg; e++) { \ + TYPED sum = d[HD(e)]; \ + for (intptr_t i = 0; i < nreg; i++) { \ + TYPED nn = n[i * zstride + HN(nreg * e + r)]; \ + TYPED mm = m[HN(nreg * s + i)]; \ + sum += nn * mm; \ + } \ + d[HD(e)] = sum; \ + } \ + } \ + } \ +} + +DO_VDOT_IDX(sme2_svdot_idx_4b, int32_t, int8_t, int8_t, H4, H1) +DO_VDOT_IDX(sme2_uvdot_idx_4b, uint32_t, uint8_t, uint8_t, H4, H1) +DO_VDOT_IDX(sme2_suvdot_idx_4b, int32_t, int8_t, uint8_t, H4, H1) +DO_VDOT_IDX(sme2_usvdot_idx_4b, int32_t, uint8_t, int8_t, H4, H1) + +DO_VDOT_IDX(sme2_svdot_idx_4h, int64_t, int16_t, int16_t, H8, H2) +DO_VDOT_IDX(sme2_uvdot_idx_4h, uint64_t, uint16_t, uint16_t, H8, H2) + +DO_VDOT_IDX(sme2_svdot_idx_2h, int32_t, int16_t, int16_t, H4, H2) +DO_VDOT_IDX(sme2_uvdot_idx_2h, uint32_t, uint16_t, uint16_t, H4, H2) + +#undef DO_VDOT_IDX 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 @@ TRANS_FEAT(SDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_4b) TRANS_FEAT(UDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_4b) TRANS_FEAT(SDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_sdot_idx_4h) TRANS_FEAT(UDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_udot_idx_4h) + +static bool do_vdot_nx(DisasContext *s, arg_azx_n *a, gen_helper_gvec_3 *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + fn(get_zarray(s, a->rv, a->off, a->n, 0), + vec_full_reg_ptr(s, a->zn), + vec_full_reg_ptr(s, a->zm), + tcg_constant_i32(simd_desc(svl, svl, a->idx))); + } + return true; +} + +TRANS_FEAT(SVDOT_nx_2h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_svdot_idx_2h) +TRANS_FEAT(SVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_svdot_idx_4b) +TRANS_FEAT(SVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_svdot_idx_4h) + +TRANS_FEAT(UVDOT_nx_2h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_2h) +TRANS_FEAT(UVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4b) +TRANS_FEAT(UVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4h) + +TRANS_FEAT(SUVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_suvdot_idx_4b) +TRANS_FEAT(USVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_usvdot_idx_4b) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-47-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 21 +++++ target/arm/tcg/sme.decode | 168 +++++++++++++++++++++++++++++++++ target/arm/tcg/sme_helper.c | 59 ++++++++++++ target/arm/tcg/translate-sme.c | 84 +++++++++++++++++ 4 files changed, 332 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme2_svdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme2_uvdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sme2_smlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_usmlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sme2_smlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_usmlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_sumlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ UDOT_n1_4h 11000001 011 1 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=4 UDOT_n1_2h 11000001 011 0 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=2 UDOT_n1_2h 11000001 011 1 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=4 +SMLAL_n1 11000001 011 0 .... 0 .. 011 ..... 00 ... @azz_nx1_o3x2 n=1 +SMLAL_n1 11000001 011 0 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=2 +SMLAL_n1 11000001 011 1 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=4 + +SMLSL_n1 11000001 011 0 .... 0 .. 011 ..... 01 ... @azz_nx1_o3x2 n=1 +SMLSL_n1 11000001 011 0 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=2 +SMLSL_n1 11000001 011 1 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=4 + +UMLAL_n1 11000001 011 0 .... 0 .. 011 ..... 10 ... @azz_nx1_o3x2 n=1 +UMLAL_n1 11000001 011 0 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=2 +UMLAL_n1 11000001 011 1 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=4 + +UMLSL_n1 11000001 011 0 .... 0 .. 011 ..... 11 ... @azz_nx1_o3x2 n=1 +UMLSL_n1 11000001 011 0 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=2 +UMLSL_n1 11000001 011 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4 + +%off2_x4 0:2 !function=times_4 +%off1_x4 0:1 !function=times_4 + +@azz_nx1_o2x4 ........ ... . zm:4 . .. ... zn:5 ... .. \ + &azz_n off=%off2_x4 rv=%mova_rv +@azz_nx1_o1x4 ........ ... . zm:4 . .. ... zn:5 .... . \ + &azz_n off=%off1_x4 rv=%mova_rv + +SMLALL_n1_s 11000001 001 0 .... 0 .. 001 ..... 000 .. @azz_nx1_o2x4 n=1 +SMLALL_n1_d 11000001 011 0 .... 0 .. 001 ..... 000 .. @azz_nx1_o2x4 n=1 +SMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=2 +SMLALL_n1_d 11000001 011 0 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=2 +SMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=4 +SMLALL_n1_d 11000001 011 1 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=4 + +SMLSLL_n1_s 11000001 001 0 .... 0 .. 001 ..... 010 .. @azz_nx1_o2x4 n=1 +SMLSLL_n1_d 11000001 011 0 .... 0 .. 001 ..... 010 .. @azz_nx1_o2x4 n=1 +SMLSLL_n1_s 11000001 001 0 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=2 +SMLSLL_n1_d 11000001 011 0 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=2 +SMLSLL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=4 +SMLSLL_n1_d 11000001 011 1 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=4 + +UMLALL_n1_s 11000001 001 0 .... 0 .. 001 ..... 100 .. @azz_nx1_o2x4 n=1 +UMLALL_n1_d 11000001 011 0 .... 0 .. 001 ..... 100 .. @azz_nx1_o2x4 n=1 +UMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=2 +UMLALL_n1_d 11000001 011 0 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=2 +UMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=4 +UMLALL_n1_d 11000001 011 1 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=4 + +UMLSLL_n1_s 11000001 001 0 .... 0 .. 001 ..... 110 .. @azz_nx1_o2x4 n=1 +UMLSLL_n1_d 11000001 011 0 .... 0 .. 001 ..... 110 .. @azz_nx1_o2x4 n=1 +UMLSLL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=2 +UMLSLL_n1_d 11000001 011 0 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=2 +UMLSLL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=4 +UMLSLL_n1_d 11000001 011 1 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=4 + +USMLALL_n1_s 11000001 001 0 .... 0 .. 001 ..... 001 .. @azz_nx1_o2x4 n=1 +USMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=2 +USMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=4 + +SUMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=2 +SUMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=4 + ### SME2 Multi-vector Multiple Array Vectors %zn_ax2 6:4 !function=times_2 @@ -XXX,XX +XXX,XX @@ UDOT_nn_4h 11000001 111 ...01 0 .. 101 ...00 10 ... @azz_4x4_o3 UDOT_nn_2h 11000001 111 ....0 0 .. 101 ....0 11 ... @azz_2x2_o3 UDOT_nn_2h 11000001 111 ...01 0 .. 101 ...00 11 ... @azz_4x4_o3 +SMLAL_nn 11000001 111 ....0 0 .. 010 ....0 000 .. @azz_2x2_o2x2 +SMLAL_nn 11000001 111 ...01 0 .. 010 ...00 000 .. @azz_4x4_o2x2 + +SMLSL_nn 11000001 111 ....0 0 .. 010 ....0 010 .. @azz_2x2_o2x2 +SMLSL_nn 11000001 111 ...01 0 .. 010 ...00 010 .. @azz_4x4_o2x2 + +UMLAL_nn 11000001 111 ....0 0 .. 010 ....0 100 .. @azz_2x2_o2x2 +UMLAL_nn 11000001 111 ...01 0 .. 010 ...00 100 .. @azz_4x4_o2x2 + +UMLSL_nn 11000001 111 ....0 0 .. 010 ....0 110 .. @azz_2x2_o2x2 +UMLSL_nn 11000001 111 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2 + +@azz_2x2_o1x4 ........ ... ..... . .. ... ..... ... .. \ + &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off1_x4 +@azz_4x4_o1x4 ........ ... ..... . .. ... ..... ... .. \ + &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off1_x4 + +SMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0000 . @azz_2x2_o1x4 +SMLALL_nn_d 11000001 111 ....0 0 .. 000 ....0 0000 . @azz_2x2_o1x4 +SMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0000 . @azz_4x4_o1x4 +SMLALL_nn_d 11000001 111 ...01 0 .. 000 ...00 0000 . @azz_4x4_o1x4 + +SMLSLL_nn_s 11000001 101 ....0 0 .. 000 ....0 0100 . @azz_2x2_o1x4 +SMLSLL_nn_d 11000001 111 ....0 0 .. 000 ....0 0100 . @azz_2x2_o1x4 +SMLSLL_nn_s 11000001 101 ...01 0 .. 000 ...00 0100 . @azz_4x4_o1x4 +SMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 0100 . @azz_4x4_o1x4 + +UMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 1000 . @azz_2x2_o1x4 +UMLALL_nn_d 11000001 111 ....0 0 .. 000 ....0 1000 . @azz_2x2_o1x4 +UMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 1000 . @azz_4x4_o1x4 +UMLALL_nn_d 11000001 111 ...01 0 .. 000 ...00 1000 . @azz_4x4_o1x4 + +UMLSLL_nn_s 11000001 101 ....0 0 .. 000 ....0 1100 . @azz_2x2_o1x4 +UMLSLL_nn_d 11000001 111 ....0 0 .. 000 ....0 1100 . @azz_2x2_o1x4 +UMLSLL_nn_s 11000001 101 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4 +UMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4 + +USMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0010 . @azz_2x2_o1x4 +USMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0010 . @azz_4x4_o1x4 + ### SME2 Multi-vector Indexed &azx_n n off rv zn zm idx @@ -XXX,XX +XXX,XX @@ UVDOT_nx_4h 11000001 1101 .... 1 .. 01 . ...00 11 ... @azx_4x1_i1_o3 SUVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 11 ... @azx_4x1_i2_o3 USVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 01 ... @azx_4x1_i2_o3 + +SMLAL_nx 11000001 1100 .... . .. 1 .. ..... 00 ... @azx_1x1_o3x2 +SMLAL_nx 11000001 1101 .... 0 .. 1 .. ....0 00 ... @azx_2x1_o2x2 +SMLAL_nx 11000001 1101 .... 1 .. 1 .. ...00 00 ... @azx_4x1_o2x2 + +SMLSL_nx 11000001 1100 .... . .. 1 .. ..... 01 ... @azx_1x1_o3x2 +SMLSL_nx 11000001 1101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_o2x2 +SMLSL_nx 11000001 1101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_o2x2 + +UMLAL_nx 11000001 1100 .... . .. 1 .. ..... 10 ... @azx_1x1_o3x2 +UMLAL_nx 11000001 1101 .... 0 .. 1 .. ....0 10 ... @azx_2x1_o2x2 +UMLAL_nx 11000001 1101 .... 1 .. 1 .. ...00 10 ... @azx_4x1_o2x2 + +UMLSL_nx 11000001 1100 .... . .. 1 .. ..... 11 ... @azx_1x1_o3x2 +UMLSL_nx 11000001 1101 .... 0 .. 1 .. ....0 11 ... @azx_2x1_o2x2 +UMLSL_nx 11000001 1101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2 + +%idx4_15_10 15:1 10:3 +%idx4_10_1 10:2 1:2 +%idx3_10_1 10:1 1:2 + +@azx_1x1_i4_o2 ........ .... zm:4 . .. ... zn:5 ... .. \ + &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx4_15_10 +@azx_1x1_i3_o2 ........ .... zm:4 . .. ... zn:5 ... .. \ + &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx3_15_10 +@azx_2x1_i4_o1 ........ .... zm:4 . .. ... ..... ... .. \ + &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx4_10_1 +@azx_2x1_i3_o1 ........ .... zm:4 . .. ... ..... ... .. \ + &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx3_10_1 +@azx_4x1_i4_o1 ........ .... zm:4 . .. ... ..... ... .. \ + &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx4_10_1 +@azx_4x1_i3_o1 ........ .... zm:4 . .. ... ..... ... .. \ + &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx3_10_1 + +SMLALL_nx_s 11000001 0000 .... . .. ... ..... 000 .. @azx_1x1_i4_o2 +SMLALL_nx_d 11000001 1000 .... . .. 0.. ..... 000 .. @azx_1x1_i3_o2 +SMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....0 00 ... @azx_2x1_i4_o1 +SMLALL_nx_d 11000001 1001 .... 0 .. 00. ....0 00 ... @azx_2x1_i3_o1 +SMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...00 00 ... @azx_4x1_i4_o1 +SMLALL_nx_d 11000001 1001 .... 1 .. 00. ...00 00 ... @azx_4x1_i3_o1 + +SMLSLL_nx_s 11000001 0000 .... . .. ... ..... 010 .. @azx_1x1_i4_o2 +SMLSLL_nx_d 11000001 1000 .... . .. 0.. ..... 010 .. @azx_1x1_i3_o2 +SMLSLL_nx_s 11000001 0001 .... 0 .. 0.. ....0 01 ... @azx_2x1_i4_o1 +SMLSLL_nx_d 11000001 1001 .... 0 .. 00. ....0 01 ... @azx_2x1_i3_o1 +SMLSLL_nx_s 11000001 0001 .... 1 .. 0.. ...00 01 ... @azx_4x1_i4_o1 +SMLSLL_nx_d 11000001 1001 .... 1 .. 00. ...00 01 ... @azx_4x1_i3_o1 + +UMLALL_nx_s 11000001 0000 .... . .. ... ..... 100 .. @azx_1x1_i4_o2 +UMLALL_nx_d 11000001 1000 .... . .. 0.. ..... 100 .. @azx_1x1_i3_o2 +UMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....0 10 ... @azx_2x1_i4_o1 +UMLALL_nx_d 11000001 1001 .... 0 .. 00. ....0 10 ... @azx_2x1_i3_o1 +UMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...00 10 ... @azx_4x1_i4_o1 +UMLALL_nx_d 11000001 1001 .... 1 .. 00. ...00 10 ... @azx_4x1_i3_o1 + +UMLSLL_nx_s 11000001 0000 .... . .. ... ..... 110 .. @azx_1x1_i4_o2 +UMLSLL_nx_d 11000001 1000 .... . .. 0.. ..... 110 .. @azx_1x1_i3_o2 +UMLSLL_nx_s 11000001 0001 .... 0 .. 0.. ....0 11 ... @azx_2x1_i4_o1 +UMLSLL_nx_d 11000001 1001 .... 0 .. 00. ....0 11 ... @azx_2x1_i3_o1 +UMLSLL_nx_s 11000001 0001 .... 1 .. 0.. ...00 11 ... @azx_4x1_i4_o1 +UMLSLL_nx_d 11000001 1001 .... 1 .. 00. ...00 11 ... @azx_4x1_i3_o1 + +USMLALL_nx_s 11000001 0000 .... . .. ... ..... 001 .. @azx_1x1_i4_o2 +USMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....1 00 ... @azx_2x1_i4_o1 +USMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 00 ... @azx_4x1_i4_o1 + +SUMLALL_nx_s 11000001 0000 .... . .. ... ..... 101 .. @azx_1x1_i4_o2 +SUMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....1 10 ... @azx_2x1_i4_o1 +SUMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 10 ... @azx_4x1_i4_o1 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 @@ DO_VDOT_IDX(sme2_svdot_idx_2h, int32_t, int16_t, int16_t, H4, H2) DO_VDOT_IDX(sme2_uvdot_idx_2h, uint32_t, uint16_t, uint16_t, H4, H2) #undef DO_VDOT_IDX + +#define DO_MLALL(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW); \ + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2); \ + TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm; \ + for (intptr_t i = 0; i < elements; ++i) { \ + TYPEW nn = n[HN(i * 4 + sel)]; \ + TYPEM mm = m[HN(i * 4 + sel)]; \ + d[HW(i)] = a[HW(i)] OP (nn * mm); \ + } \ +} + +DO_MLALL(sme2_smlall_s, int32_t, int8_t, int8_t, H4, H1, +) +DO_MLALL(sme2_smlall_d, int64_t, int16_t, int16_t, H8, H2, +) +DO_MLALL(sme2_smlsll_s, int32_t, int8_t, int8_t, H4, H1, -) +DO_MLALL(sme2_smlsll_d, int64_t, int16_t, int16_t, H8, H2, -) + +DO_MLALL(sme2_umlall_s, uint32_t, uint8_t, uint8_t, H4, H1, +) +DO_MLALL(sme2_umlall_d, uint64_t, uint16_t, uint16_t, H8, H2, +) +DO_MLALL(sme2_umlsll_s, uint32_t, uint8_t, uint8_t, H4, H1, -) +DO_MLALL(sme2_umlsll_d, uint64_t, uint16_t, uint16_t, H8, H2, -) + +DO_MLALL(sme2_usmlall_s, uint32_t, uint8_t, int8_t, H4, H1, +) + +#undef DO_MLALL + +#define DO_MLALL_IDX(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW); \ + intptr_t eltspersegment = 16 / sizeof(TYPEW); \ + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2); \ + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 4); \ + TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm; \ + for (intptr_t i = 0; i < elements; i += eltspersegment) { \ + TYPEW mm = m[HN(i * 4 + idx)]; \ + for (intptr_t j = 0; j < eltspersegment; ++j) { \ + TYPEN nn = n[HN((i + j) * 4 + sel)]; \ + d[HW(i + j)] = a[HW(i + j)] OP (nn * mm); \ + } \ + } \ +} + +DO_MLALL_IDX(sme2_smlall_idx_s, int32_t, int8_t, int8_t, H4, H1, +) +DO_MLALL_IDX(sme2_smlall_idx_d, int64_t, int16_t, int16_t, H8, H2, +) +DO_MLALL_IDX(sme2_smlsll_idx_s, int32_t, int8_t, int8_t, H4, H1, -) +DO_MLALL_IDX(sme2_smlsll_idx_d, int64_t, int16_t, int16_t, H8, H2, -) + +DO_MLALL_IDX(sme2_umlall_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, +) +DO_MLALL_IDX(sme2_umlall_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, +) +DO_MLALL_IDX(sme2_umlsll_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, -) +DO_MLALL_IDX(sme2_umlsll_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, -) + +DO_MLALL_IDX(sme2_usmlall_idx_s, uint32_t, uint8_t, int8_t, H4, H1, +) +DO_MLALL_IDX(sme2_sumlall_idx_s, uint32_t, int8_t, uint8_t, H4, H1, +) + +#undef DO_MLALL_IDX 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 @@ TRANS_FEAT(UVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4h) TRANS_FEAT(SUVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_suvdot_idx_4b) TRANS_FEAT(USVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_usvdot_idx_4b) + +static bool do_smlal(DisasContext *s, arg_azz_n *a, bool multi, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, fn); +} + +TRANS_FEAT(SMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlal_zzzw_s) +TRANS_FEAT(SMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlsl_zzzw_s) +TRANS_FEAT(UMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlal_zzzw_s) +TRANS_FEAT(UMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlsl_zzzw_s) + +TRANS_FEAT(SMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlal_zzzw_s) +TRANS_FEAT(SMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlsl_zzzw_s) +TRANS_FEAT(UMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlal_zzzw_s) +TRANS_FEAT(UMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlsl_zzzw_s) + +static bool do_smlal_nx(DisasContext *s, arg_azx_n *a, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + a->idx << 1, 0, false, fn); +} + +TRANS_FEAT(SMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlal_idx_s) +TRANS_FEAT(SMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlsl_idx_s) +TRANS_FEAT(UMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlal_idx_s) +TRANS_FEAT(UMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlsl_idx_s) + +static bool do_smlall(DisasContext *s, arg_azz_n *a, bool multi, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, fn); +} + +static void gen_helper_sme2_sumlall_s(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m, + TCGv_ptr a, TCGv_i32 desc) +{ + gen_helper_sme2_usmlall_s(d, m, n, a, desc); +} + +TRANS_FEAT(SMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlall_s) +TRANS_FEAT(SMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlsll_s) +TRANS_FEAT(UMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlall_s) +TRANS_FEAT(UMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlsll_s) +TRANS_FEAT(USMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_usmlall_s) +TRANS_FEAT(SUMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_sumlall_s) + +TRANS_FEAT(SMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlall_d) +TRANS_FEAT(SMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlsll_d) +TRANS_FEAT(UMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlall_d) +TRANS_FEAT(UMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlsll_d) + +TRANS_FEAT(SMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlall_s) +TRANS_FEAT(SMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlsll_s) +TRANS_FEAT(UMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlall_s) +TRANS_FEAT(UMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlsll_s) +TRANS_FEAT(USMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_usmlall_s) + +TRANS_FEAT(SMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlall_d) +TRANS_FEAT(SMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlsll_d) +TRANS_FEAT(UMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlall_d) +TRANS_FEAT(UMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlsll_d) + +static bool do_smlall_nx(DisasContext *s, arg_azx_n *a, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm, + a->idx << 2, 0, false, fn); +} + +TRANS_FEAT(SMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlall_idx_s) +TRANS_FEAT(SMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_s) +TRANS_FEAT(UMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlall_idx_s) +TRANS_FEAT(UMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_s) +TRANS_FEAT(USMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_usmlall_idx_s) +TRANS_FEAT(SUMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_sumlall_idx_s) + +TRANS_FEAT(SMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlall_idx_d) +TRANS_FEAT(SMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_d) +TRANS_FEAT(UMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlall_idx_d) +TRANS_FEAT(UMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_d) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Emphasize the non-fused nature of these multiply-add. Matches other helpers such as gvec_rsqrts_nf_[hs]. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-48-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper.h | 8 ++++---- target/arm/tcg/translate-neon.c | 4 ++-- target/arm/tcg/vec_helper.c | 8 ++++---- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h) DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h) DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h) -DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h) -DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) +DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_nf_s, gen_helper_gvec_fmla_nf_h) +DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_nf_s, gen_helper_gvec_fmls_nf_h) DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h) DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h) DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_h) 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(NAME)(void *vd, void *vn, void *vm, \ clear_tail(d, oprsz, simd_maxsz(desc)); \ } -DO_MULADD(gvec_fmla_h, float16_muladd_nf, float16) -DO_MULADD(gvec_fmla_s, float32_muladd_nf, float32) +DO_MULADD(gvec_fmla_nf_h, float16_muladd_nf, float16) +DO_MULADD(gvec_fmla_nf_s, float32_muladd_nf, float32) -DO_MULADD(gvec_fmls_h, float16_mulsub_nf, float16) -DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32) +DO_MULADD(gvec_fmls_nf_h, float16_mulsub_nf, float16) +DO_MULADD(gvec_fmls_nf_s, float32_mulsub_nf, float32) DO_MULADD(gvec_vfma_h, float16_muladd_f, float16) DO_MULADD(gvec_vfma_s, float32_muladd_f, float32) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-49-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 48 +++++++++++++++++ target/arm/tcg/translate-sme.c | 95 ++++++++++++++++++++++++++++++++++ 2 files changed, 143 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ USMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=4 SUMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=2 SUMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=4 +FMLA_n1_h 11000001 001 0 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=2 +FMLA_n1_s 11000001 001 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2 +FMLA_n1_d 11000001 011 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2 +FMLA_n1_h 11000001 001 1 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=4 +FMLA_n1_s 11000001 001 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4 +FMLA_n1_d 11000001 011 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4 + +FMLS_n1_h 11000001 001 0 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=2 +FMLS_n1_s 11000001 001 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2 +FMLS_n1_d 11000001 011 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2 +FMLS_n1_h 11000001 001 1 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=4 +FMLS_n1_s 11000001 001 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4 +FMLS_n1_d 11000001 011 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4 + ### SME2 Multi-vector Multiple Array Vectors %zn_ax2 6:4 !function=times_2 @@ -XXX,XX +XXX,XX @@ UMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4 USMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0010 . @azz_2x2_o1x4 USMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0010 . @azz_4x4_o1x4 +FMLA_nn_h 11000001 101 ....0 0 .. 100 ....0 01 ... @azz_2x2_o3 +FMLA_nn_s 11000001 101 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3 +FMLA_nn_d 11000001 111 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3 +FMLA_nn_h 11000001 101 ...01 0 .. 100 ...00 01 ... @azz_4x4_o3 +FMLA_nn_s 11000001 101 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3 +FMLA_nn_d 11000001 111 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3 + +FMLS_nn_h 11000001 101 ....0 0 .. 100 ....0 11 ... @azz_2x2_o3 +FMLS_nn_s 11000001 101 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3 +FMLS_nn_d 11000001 111 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3 +FMLS_nn_h 11000001 101 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3 +FMLS_nn_s 11000001 101 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3 +FMLS_nn_d 11000001 111 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3 + ### SME2 Multi-vector Indexed &azx_n n off rv zn zm idx @@ -XXX,XX +XXX,XX @@ USMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 00 ... @azx_4x1_i4_o1 SUMLALL_nx_s 11000001 0000 .... . .. ... ..... 101 .. @azx_1x1_i4_o2 SUMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....1 10 ... @azx_2x1_i4_o1 SUMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 10 ... @azx_4x1_i4_o1 + +%idx3_10_3 10:2 3:1 +@azx_2x1_i3_o3 ........ .... zm:4 . .. ... ..... .. off:3 \ + &azx_n n=2 rv=%mova_rv zn=%zn_ax2 idx=%idx3_10_3 +@azx_4x1_i3_o3 ........ .... zm:4 . .. ... ..... .. off:3 \ + &azx_n n=4 rv=%mova_rv zn=%zn_ax4 idx=%idx3_10_3 + +FMLA_nx_h 11000001 0001 .... 0 .. 1.. ....0 0 .... @azx_2x1_i3_o3 +FMLA_nx_s 11000001 0101 .... 0 .. 0.. ....0 00 ... @azx_2x1_i2_o3 +FMLA_nx_d 11000001 1101 .... 0 .. 00. ....0 00 ... @azx_2x1_i1_o3 +FMLA_nx_h 11000001 0001 .... 1 .. 1.. ...00 0 .... @azx_4x1_i3_o3 +FMLA_nx_s 11000001 0101 .... 1 .. 0.. ...00 00 ... @azx_4x1_i2_o3 +FMLA_nx_d 11000001 1101 .... 1 .. 00. ...00 00 ... @azx_4x1_i1_o3 + +FMLS_nx_h 11000001 0001 .... 0 .. 1.. ....0 1 .... @azx_2x1_i3_o3 +FMLS_nx_s 11000001 0101 .... 0 .. 0.. ....0 10 ... @azx_2x1_i2_o3 +FMLS_nx_d 11000001 1101 .... 0 .. 00. ....0 10 ... @azx_2x1_i1_o3 +FMLS_nx_h 11000001 0001 .... 1 .. 1.. ...00 1 .... @azx_4x1_i3_o3 +FMLS_nx_s 11000001 0101 .... 1 .. 0.. ...00 10 ... @azx_4x1_i2_o3 +FMLS_nx_d 11000001 1101 .... 1 .. 00. ...00 10 ... @azx_4x1_i1_o3 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 @@ TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub */ #define FPST_ENV -1 +static bool do_azz_fp(DisasContext *s, int nreg, int nsel, + int rv, int off, int zn, int zm, + int data, int shsel, bool multi, int fpst, + gen_helper_gvec_3_ptr *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / nreg; + TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel); + TCGv_ptr t, ptr; + + if (fpst >= 0) { + ptr = fpstatus_ptr(fpst); + } else { + ptr = tcg_env; + } + t = tcg_temp_new_ptr(); + + for (int r = 0; r < nreg; ++r) { + TCGv_ptr t_zn = vec_full_reg_ptr(s, zn); + TCGv_ptr t_zm = vec_full_reg_ptr(s, zm); + + for (int i = 0; i < nsel; ++i) { + int o_za = (r * vstride + i) * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, data | (i << shsel)); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t_zn, t_zm, ptr, tcg_constant_i32(desc)); + } + + /* + * For multiple-and-single vectors, Zn may wrap. + * For multiple vectors, both Zn and Zm are aligned. + */ + zn = (zn + 1) % 32; + zm += multi; + } + } + return true; +} + static bool do_azz_acc_fp(DisasContext *s, int nreg, int nsel, int rv, int off, int zn, int zm, int data, int shsel, bool multi, int fpst, @@ -XXX,XX +XXX,XX @@ static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn) TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h) TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx) +static bool do_fmla(DisasContext *s, arg_azz_n *a, bool multi, + ARMFPStatusFlavour fpst, gen_helper_gvec_3_ptr *fn) +{ + return do_azz_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, fpst, fn); +} + +TRANS_FEAT(FMLA_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16, + gen_helper_gvec_vfma_h) +TRANS_FEAT(FMLS_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h) +TRANS_FEAT(FMLA_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16, + gen_helper_gvec_vfma_h) +TRANS_FEAT(FMLS_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h) + +TRANS_FEAT(FMLA_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA, + gen_helper_gvec_vfma_s) +TRANS_FEAT(FMLS_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s) +TRANS_FEAT(FMLA_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA, + gen_helper_gvec_vfma_s) +TRANS_FEAT(FMLS_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s) + +TRANS_FEAT(FMLA_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA, + gen_helper_gvec_vfma_d) +TRANS_FEAT(FMLS_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d) +TRANS_FEAT(FMLA_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA, + gen_helper_gvec_vfma_d) +TRANS_FEAT(FMLS_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d) + +static bool do_fmla_nx(DisasContext *s, arg_azx_n *a, + ARMFPStatusFlavour fpst, gen_helper_gvec_4_ptr *fn) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + a->idx, 0, false, fpst, fn); +} + +TRANS_FEAT(FMLA_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16, + gen_helper_gvec_fmla_idx_h) +TRANS_FEAT(FMLS_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16, + s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_h : gen_helper_gvec_fmls_idx_h) +TRANS_FEAT(FMLA_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA, + gen_helper_gvec_fmla_idx_s) +TRANS_FEAT(FMLS_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_s : gen_helper_gvec_fmls_idx_s) +TRANS_FEAT(FMLA_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA, + gen_helper_gvec_fmla_idx_d) +TRANS_FEAT(FMLS_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_d : gen_helper_gvec_fmls_idx_d) + /* * Expand array multi-vector single (n1), array multi-vector (nn), * and array multi-vector indexed (nx), for integer accumulate. -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-50-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper.h | 9 +++++++++ target/arm/tcg/sme.decode | 18 ++++++++++++++++++ target/arm/tcg/translate-sme.c | 14 ++++++++++++++ target/arm/tcg/vec_helper.c | 26 ++++++++++++++++++++++++++ 4 files changed, 67 insertions(+) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmls_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfma_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_bfmla, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ah_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ah_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ah_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_ah_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_bfmla_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fmls_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_fmls_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fmls_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_bfmls_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_ah_bfmls_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ USMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=4 SUMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=2 SUMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=4 +BFMLA_n1 11000001 011 0 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=2 FMLA_n1_h 11000001 001 0 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=2 FMLA_n1_s 11000001 001 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2 FMLA_n1_d 11000001 011 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2 + +BFMLA_n1 11000001 011 1 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=4 FMLA_n1_h 11000001 001 1 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=4 FMLA_n1_s 11000001 001 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4 FMLA_n1_d 11000001 011 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4 +BFMLS_n1 11000001 011 0 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=2 FMLS_n1_h 11000001 001 0 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=2 FMLS_n1_s 11000001 001 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2 FMLS_n1_d 11000001 011 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2 + +BFMLS_n1 11000001 011 1 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=4 FMLS_n1_h 11000001 001 1 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=4 FMLS_n1_s 11000001 001 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4 FMLS_n1_d 11000001 011 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4 @@ -XXX,XX +XXX,XX @@ UMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4 USMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0010 . @azz_2x2_o1x4 USMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0010 . @azz_4x4_o1x4 +BFMLA_nn 11000001 111 ....0 0 .. 100 ....0 01 ... @azz_2x2_o3 FMLA_nn_h 11000001 101 ....0 0 .. 100 ....0 01 ... @azz_2x2_o3 FMLA_nn_s 11000001 101 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3 FMLA_nn_d 11000001 111 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3 + +BFMLA_nn 11000001 111 ...01 0 .. 100 ...00 01 ... @azz_4x4_o3 FMLA_nn_h 11000001 101 ...01 0 .. 100 ...00 01 ... @azz_4x4_o3 FMLA_nn_s 11000001 101 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3 FMLA_nn_d 11000001 111 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3 +BFMLS_nn 11000001 111 ....0 0 .. 100 ....0 11 ... @azz_2x2_o3 FMLS_nn_h 11000001 101 ....0 0 .. 100 ....0 11 ... @azz_2x2_o3 FMLS_nn_s 11000001 101 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3 FMLS_nn_d 11000001 111 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3 + +BFMLS_nn 11000001 111 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3 FMLS_nn_h 11000001 101 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3 FMLS_nn_s 11000001 101 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3 FMLS_nn_d 11000001 111 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3 @@ -XXX,XX +XXX,XX @@ SUMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 10 ... @azx_4x1_i4_o1 @azx_4x1_i3_o3 ........ .... zm:4 . .. ... ..... .. off:3 \ &azx_n n=4 rv=%mova_rv zn=%zn_ax4 idx=%idx3_10_3 +BFMLA_nx 11000001 0001 .... 0 .. 1.. ....1 0 .... @azx_2x1_i3_o3 FMLA_nx_h 11000001 0001 .... 0 .. 1.. ....0 0 .... @azx_2x1_i3_o3 FMLA_nx_s 11000001 0101 .... 0 .. 0.. ....0 00 ... @azx_2x1_i2_o3 FMLA_nx_d 11000001 1101 .... 0 .. 00. ....0 00 ... @azx_2x1_i1_o3 + +BFMLA_nx 11000001 0001 .... 1 .. 1.. ...01 0 .... @azx_4x1_i3_o3 FMLA_nx_h 11000001 0001 .... 1 .. 1.. ...00 0 .... @azx_4x1_i3_o3 FMLA_nx_s 11000001 0101 .... 1 .. 0.. ...00 00 ... @azx_4x1_i2_o3 FMLA_nx_d 11000001 1101 .... 1 .. 00. ...00 00 ... @azx_4x1_i1_o3 +BFMLS_nx 11000001 0001 .... 0 .. 1.. ....1 1 .... @azx_2x1_i3_o3 FMLS_nx_h 11000001 0001 .... 0 .. 1.. ....0 1 .... @azx_2x1_i3_o3 FMLS_nx_s 11000001 0101 .... 0 .. 0.. ....0 10 ... @azx_2x1_i2_o3 FMLS_nx_d 11000001 1101 .... 0 .. 00. ....0 10 ... @azx_2x1_i1_o3 + +BFMLS_nx 11000001 0001 .... 1 .. 1.. ...01 1 .... @azx_4x1_i3_o3 FMLS_nx_h 11000001 0001 .... 1 .. 1.. ...00 1 .... @azx_4x1_i3_o3 FMLS_nx_s 11000001 0101 .... 1 .. 0.. ...00 10 ... @azx_4x1_i2_o3 FMLS_nx_d 11000001 1101 .... 1 .. 00. ...00 10 ... @azx_4x1_i1_o3 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 @@ TRANS_FEAT(FMLA_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA, TRANS_FEAT(FMLS_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA, s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d) +TRANS_FEAT(BFMLA_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA, + gen_helper_gvec_bfmla) +TRANS_FEAT(BFMLS_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls) +TRANS_FEAT(BFMLA_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA, + gen_helper_gvec_bfmla) +TRANS_FEAT(BFMLS_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls) + static bool do_fmla_nx(DisasContext *s, arg_azx_n *a, ARMFPStatusFlavour fpst, gen_helper_gvec_4_ptr *fn) { @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMLA_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA, TRANS_FEAT(FMLS_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA, s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_d : gen_helper_gvec_fmls_idx_d) +TRANS_FEAT(BFMLA_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA, + gen_helper_gvec_bfmla_idx) +TRANS_FEAT(BFMLS_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_bfmls_idx : gen_helper_gvec_bfmls_idx) + /* * Expand array multi-vector single (n1), array multi-vector (nn), * and array multi-vector indexed (nx), for integer accumulate. 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 @@ static float16 float16_muladd_f(float16 dest, float16 op1, float16 op2, return float16_muladd(op1, op2, dest, 0, stat); } +static bfloat16 bfloat16_muladd_f(bfloat16 dest, bfloat16 op1, bfloat16 op2, + float_status *stat) +{ + return bfloat16_muladd(op1, op2, dest, 0, stat); +} + static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2, float_status *stat) { @@ -XXX,XX +XXX,XX @@ static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2, return float16_muladd(float16_chs(op1), op2, dest, 0, stat); } +static bfloat16 bfloat16_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2, + float_status *stat) +{ + return bfloat16_muladd(bfloat16_chs(op1), op2, dest, 0, stat); +} + static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2, float_status *stat) { @@ -XXX,XX +XXX,XX @@ static float16 float16_ah_mulsub_f(float16 dest, float16 op1, float16 op2, return float16_muladd(op1, op2, dest, float_muladd_negate_product, stat); } +static bfloat16 bfloat16_ah_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2, + float_status *stat) +{ + return bfloat16_muladd(op1, op2, dest, float_muladd_negate_product, stat); +} + static float32 float32_ah_mulsub_f(float32 dest, float32 op1, float32 op2, float_status *stat) { @@ -XXX,XX +XXX,XX @@ DO_MULADD(gvec_fmls_nf_s, float32_mulsub_nf, float32) DO_MULADD(gvec_vfma_h, float16_muladd_f, float16) DO_MULADD(gvec_vfma_s, float32_muladd_f, float32) DO_MULADD(gvec_vfma_d, float64_muladd_f, float64) +DO_MULADD(gvec_bfmla, bfloat16_muladd_f, bfloat16) DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16) DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32) DO_MULADD(gvec_vfms_d, float64_mulsub_f, float64) +DO_MULADD(gvec_bfmls, bfloat16_mulsub_f, bfloat16) DO_MULADD(gvec_ah_vfms_h, float16_ah_mulsub_f, float16) DO_MULADD(gvec_ah_vfms_s, float32_ah_mulsub_f, float32) DO_MULADD(gvec_ah_vfms_d, float64_ah_mulsub_f, float64) +DO_MULADD(gvec_ah_bfmls, bfloat16_ah_mulsub_f, bfloat16) + +#undef DO_MULADD /* For the indexed ops, SVE applies the index per 128-bit vector segment. * For AdvSIMD, there is of course only one such vector segment. @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \ DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2, 0, 0) DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4, 0, 0) DO_FMLA_IDX(gvec_fmla_idx_d, float64, H8, 0, 0) +DO_FMLA_IDX(gvec_bfmla_idx, bfloat16, H2, 0, 0) DO_FMLA_IDX(gvec_fmls_idx_h, float16, H2, INT16_MIN, 0) DO_FMLA_IDX(gvec_fmls_idx_s, float32, H4, INT32_MIN, 0) DO_FMLA_IDX(gvec_fmls_idx_d, float64, H8, INT64_MIN, 0) +DO_FMLA_IDX(gvec_bfmls_idx, bfloat16, H2, INT16_MIN, 0) DO_FMLA_IDX(gvec_ah_fmls_idx_h, float16, H2, 0, float_muladd_negate_product) DO_FMLA_IDX(gvec_ah_fmls_idx_s, float32, H4, 0, float_muladd_negate_product) DO_FMLA_IDX(gvec_ah_fmls_idx_d, float64, H8, 0, float_muladd_negate_product) +DO_FMLA_IDX(gvec_ah_bfmls_idx, bfloat16, H2, 0, float_muladd_negate_product) #undef DO_FMLA_IDX -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-51-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper.h | 2 ++ target/arm/tcg/sme.decode | 25 +++++++++++++++++++ target/arm/tcg/translate-sme.c | 44 ++++++++++++++++++++++++++++++++++ target/arm/tcg/vec_helper.c | 2 ++ 4 files changed, 73 insertions(+) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_fclt0_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_bfadd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_bfsub, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ FMLS_nn_h 11000001 101 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3 FMLS_nn_s 11000001 101 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3 FMLS_nn_d 11000001 111 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3 +&az_n n off rv zm +@az_2x2_o3 ........ ... ..... . .. ... ..... .. off:3 \ + &az_n n=2 rv=%mova_rv zm=%zn_ax2 +@az_4x4_o3 ........ ... ..... . .. ... ..... .. off:3 \ + &az_n n=4 rv=%mova_rv zm=%zn_ax4 + +FADD_nn_h 11000001 101 00100 0 .. 111 ....0 00 ... @az_2x2_o3 +FADD_nn_s 11000001 101 00000 0 .. 111 ....0 00 ... @az_2x2_o3 +FADD_nn_d 11000001 111 00000 0 .. 111 ....0 00 ... @az_2x2_o3 +FADD_nn_h 11000001 101 00101 0 .. 111 ...00 00 ... @az_4x4_o3 +FADD_nn_s 11000001 101 00001 0 .. 111 ...00 00 ... @az_4x4_o3 +FADD_nn_d 11000001 111 00001 0 .. 111 ...00 00 ... @az_4x4_o3 + +FSUB_nn_h 11000001 101 00100 0 .. 111 ....0 01 ... @az_2x2_o3 +FSUB_nn_s 11000001 101 00000 0 .. 111 ....0 01 ... @az_2x2_o3 +FSUB_nn_d 11000001 111 00000 0 .. 111 ....0 01 ... @az_2x2_o3 +FSUB_nn_h 11000001 101 00101 0 .. 111 ...00 01 ... @az_4x4_o3 +FSUB_nn_s 11000001 101 00001 0 .. 111 ...00 01 ... @az_4x4_o3 +FSUB_nn_d 11000001 111 00001 0 .. 111 ...00 01 ... @az_4x4_o3 + +BFADD_nn 11000001 111 00100 0 .. 111 ....0 00 ... @az_2x2_o3 +BFADD_nn 11000001 111 00101 0 .. 111 ...00 00 ... @az_4x4_o3 +BFSUB_nn 11000001 111 00100 0 .. 111 ....0 01 ... @az_2x2_o3 +BFSUB_nn 11000001 111 00101 0 .. 111 ...00 01 ... @az_4x4_o3 + ### SME2 Multi-vector Indexed &azx_n n off rv zn zm idx 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 @@ TRANS_FEAT(BFMLA_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA, TRANS_FEAT(BFMLS_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA, s->fpcr_ah ? gen_helper_gvec_ah_bfmls_idx : gen_helper_gvec_bfmls_idx) +static bool do_faddsub(DisasContext *s, arg_az_n *a, ARMFPStatusFlavour fpst, + gen_helper_gvec_3_ptr *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int n = a->n; + int zm = a->zm; + int vstride = svl / n; + TCGv_ptr t_za = get_zarray(s, a->rv, a->off, n, 0); + TCGv_ptr ptr = fpstatus_ptr(fpst); + TCGv_ptr t = tcg_temp_new_ptr(); + + for (int r = 0; r < n; ++r) { + TCGv_ptr t_zm = vec_full_reg_ptr(s, zm + r); + int o_za = r * vstride * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, 0); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t, t_zm, ptr, tcg_constant_i32(desc)); + } + } + return true; +} + +TRANS_FEAT(FADD_nn_h, aa64_sme_f16f16, do_faddsub, a, + FPST_ZA_F16, gen_helper_gvec_fadd_h) +TRANS_FEAT(FSUB_nn_h, aa64_sme_f16f16, do_faddsub, a, + FPST_ZA_F16, gen_helper_gvec_fsub_h) + +TRANS_FEAT(FADD_nn_s, aa64_sme2, do_faddsub, a, + FPST_ZA, gen_helper_gvec_fadd_s) +TRANS_FEAT(FSUB_nn_s, aa64_sme2, do_faddsub, a, + FPST_ZA, gen_helper_gvec_fsub_s) + +TRANS_FEAT(FADD_nn_d, aa64_sme2_f64f64, do_faddsub, a, + FPST_ZA, gen_helper_gvec_fadd_d) +TRANS_FEAT(FSUB_nn_d, aa64_sme2_f64f64, do_faddsub, a, + FPST_ZA, gen_helper_gvec_fsub_d) + +TRANS_FEAT(BFADD_nn, aa64_sme_b16b16, do_faddsub, a, + FPST_ZA, gen_helper_gvec_bfadd) +TRANS_FEAT(BFSUB_nn, aa64_sme_b16b16, do_faddsub, a, + FPST_ZA, gen_helper_gvec_bfsub) + /* * Expand array multi-vector single (n1), array multi-vector (nn), * and array multi-vector indexed (nx), for integer accumulate. 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(NAME)(void *vd, void *vn, void *vm, \ DO_3OP(gvec_fadd_h, float16_add, float16) DO_3OP(gvec_fadd_s, float32_add, float32) DO_3OP(gvec_fadd_d, float64_add, float64) +DO_3OP(gvec_bfadd, bfloat16_add, bfloat16) DO_3OP(gvec_fsub_h, float16_sub, float16) DO_3OP(gvec_fsub_s, float32_sub, float32) DO_3OP(gvec_fsub_d, float64_sub, float64) +DO_3OP(gvec_bfsub, bfloat16_sub, bfloat16) DO_3OP(gvec_fmul_h, float16_mul, float16) DO_3OP(gvec_fmul_s, float32_mul, float32) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-52-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 12 ++++++++++++ target/arm/tcg/translate-sme.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ BFMLS_nx 11000001 0001 .... 1 .. 1.. ...01 1 .... @azx_4x1_i3_o3 FMLS_nx_h 11000001 0001 .... 1 .. 1.. ...00 1 .... @azx_4x1_i3_o3 FMLS_nx_s 11000001 0101 .... 1 .. 0.. ...00 10 ... @azx_4x1_i2_o3 FMLS_nx_d 11000001 1101 .... 1 .. 00. ...00 10 ... @azx_4x1_i1_o3 + +### SME2 Add / Sub array accumulators + +ADD_aaz_s 11000001 101 000000 .. 111 ....0 10 ... @az_2x2_o3 +ADD_aaz_s 11000001 101 000010 .. 111 ...00 10 ... @az_4x4_o3 +ADD_aaz_d 11000001 111 000000 .. 111 ....0 10 ... @az_2x2_o3 +ADD_aaz_d 11000001 111 000010 .. 111 ...00 10 ... @az_4x4_o3 + +SUB_aaz_s 11000001 101 000000 .. 111 ....0 11 ... @az_2x2_o3 +SUB_aaz_s 11000001 101 000010 .. 111 ...00 11 ... @az_4x4_o3 +SUB_aaz_d 11000001 111 000000 .. 111 ....0 11 ... @az_2x2_o3 +SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3 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 @@ TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var) TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var) TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var) +/* Add/Sub each ZA[d*N] += Z[m*N] */ +static bool do_aaz(DisasContext *s, arg_az_n *a, int esz, GVecGen3FnVar *fn) +{ + TCGv_ptr t_za; + int svl, n; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + n = a->n; + t_za = get_zarray(s, a->rv, a->off, n, 0); + svl = streaming_vec_reg_size(s); + + for (int i = 0; i < n; ++i) { + int o_za = (svl / n * sizeof(ARMVectorReg)) * i; + int o_zm = vec_full_reg_offset(s, a->zm + i); + + fn(esz, t_za, o_za, t_za, o_za, tcg_env, o_zm, svl, svl); + } + return true; +} + +TRANS_FEAT(ADD_aaz_s, aa64_sme2, do_aaz, a, MO_32, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_aaz_s, aa64_sme2, do_aaz, a, MO_32, tcg_gen_gvec_sub_var) +TRANS_FEAT(ADD_aaz_d, aa64_sme2_i16i64, do_aaz, a, MO_64, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_aaz_d, aa64_sme2_i16i64, do_aaz, a, MO_64, tcg_gen_gvec_sub_var) + /* * Expand array multi-vector single (n1), array multi-vector (nn), * and array multi-vector indexed (nx), for floating-point accumulate. -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-53-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 5 +++ target/arm/tcg/vec_internal.h | 2 + target/arm/tcg/sme.decode | 12 ++++++ target/arm/tcg/sme_helper.c | 74 ++++++++++++++++++++++++++++++++++ target/arm/tcg/sve_helper.c | 2 +- target/arm/tcg/translate-sme.c | 25 ++++++++++++ 6 files changed, 119 insertions(+), 1 deletion(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme2_umlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, DEF_HELPER_FLAGS_5(sme2_umlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme2_usmlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme2_sumlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_bfcvt, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_bfcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_fcvt_n, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_fcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_internal.h +++ b/target/arm/tcg/vec_internal.h @@ -XXX,XX +XXX,XX @@ static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah) bfloat16 helper_sme2_ah_fmax_b16(bfloat16 a, bfloat16 b, float_status *fpst); bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst); +float16 sve_f32_to_f16(float32 f, float_status *fpst); + #endif /* TARGET_ARM_VEC_INTERNAL_H */ diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SUB_aaz_s 11000001 101 000000 .. 111 ....0 11 ... @az_2x2_o3 SUB_aaz_s 11000001 101 000010 .. 111 ...00 11 ... @az_4x4_o3 SUB_aaz_d 11000001 111 000000 .. 111 ....0 11 ... @az_2x2_o3 SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3 + +### SME2 Multi-vector SVE Constructive Unary + +&zz_n zd zn n +@zz_1x2 ........ ... ..... ...... ..... zd:5 \ + &zz_n n=1 zn=%zn_ax2 + +BFCVT 11000001 011 00000 111000 ....0 ..... @zz_1x2 +BFCVTN 11000001 011 00000 111000 ....1 ..... @zz_1x2 + +FCVT_n 11000001 001 00000 111000 ....0 ..... @zz_1x2 +FCVTN 11000001 001 00000 111000 ....1 ..... @zz_1x2 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 @@ DO_MLALL_IDX(sme2_usmlall_idx_s, uint32_t, uint8_t, int8_t, H4, H1, +) DO_MLALL_IDX(sme2_sumlall_idx_s, uint32_t, int8_t, uint8_t, H4, H1, +) #undef DO_MLALL_IDX + +/* Convert and compress */ +void HELPER(sme2_bfcvt)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + ARMVectorReg scratch; + size_t oprsz = simd_oprsz(desc); + size_t i, n = oprsz / 4; + float32 *s0 = vs; + float32 *s1 = vs + sizeof(ARMVectorReg); + bfloat16 *d = vd; + + if (vd == s1) { + s1 = memcpy(&scratch, s1, oprsz); + } + + for (i = 0; i < n; ++i) { + d[H2(i)] = float32_to_bfloat16(s0[H4(i)], fpst); + } + for (i = 0; i < n; ++i) { + d[H2(i) + n] = float32_to_bfloat16(s1[H4(i)], fpst); + } +} + +void HELPER(sme2_fcvt_n)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + ARMVectorReg scratch; + size_t oprsz = simd_oprsz(desc); + size_t i, n = oprsz / 4; + float32 *s0 = vs; + float32 *s1 = vs + sizeof(ARMVectorReg); + float16 *d = vd; + + if (vd == s1) { + s1 = memcpy(&scratch, s1, oprsz); + } + + for (i = 0; i < n; ++i) { + d[H2(i)] = sve_f32_to_f16(s0[H4(i)], fpst); + } + for (i = 0; i < n; ++i) { + d[H2(i) + n] = sve_f32_to_f16(s1[H4(i)], fpst); + } +} + +/* Convert and interleave */ +void HELPER(sme2_bfcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + float32 *s0 = vs; + float32 *s1 = vs + sizeof(ARMVectorReg); + bfloat16 *d = vd; + + for (i = 0; i < n; ++i) { + bfloat16 d0 = float32_to_bfloat16(s0[H4(i)], fpst); + bfloat16 d1 = float32_to_bfloat16(s1[H4(i)], fpst); + d[H2(i * 2 + 0)] = d0; + d[H2(i * 2 + 1)] = d1; + } +} + +void HELPER(sme2_fcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + float32 *s0 = vs; + float32 *s1 = vs + sizeof(ARMVectorReg); + bfloat16 *d = vd; + + for (i = 0; i < n; ++i) { + bfloat16 d0 = sve_f32_to_f16(s0[H4(i)], fpst); + bfloat16 d1 = sve_f32_to_f16(s1[H4(i)], fpst); + d[H2(i * 2 + 0)] = d0; + d[H2(i * 2 + 1)] = d1; + } +} 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 inline float64 sve_f16_to_f64(float16 f, float_status *fpst) return ret; } -static inline float16 sve_f32_to_f16(float32 f, float_status *fpst) +float16 sve_f32_to_f16(float32 f, float_status *fpst) { bool save = get_flush_to_zero(fpst); float16 ret; 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 @@ TRANS_FEAT(SMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlal TRANS_FEAT(SMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_d) TRANS_FEAT(UMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlall_idx_d) TRANS_FEAT(UMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_d) + +static bool do_zz_fpst(DisasContext *s, arg_zz_n *a, int data, + ARMFPStatusFlavour type, gen_helper_gvec_2_ptr *fn) +{ + if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + TCGv_ptr fpst = fpstatus_ptr(type); + + for (int i = 0, n = a->n; i < n; ++i) { + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd + i), + vec_full_reg_offset(s, a->zn + i), + fpst, svl, svl, data, fn); + } + } + return true; +} + +TRANS_FEAT(BFCVT, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_bfcvt) +TRANS_FEAT(BFCVTN, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_bfcvtn) +TRANS_FEAT(FCVT_n, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_fcvt_n) +TRANS_FEAT(FCVTN, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_fcvtn) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-54-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 2 ++ target/arm/tcg/vec_internal.h | 1 + target/arm/tcg/sme.decode | 5 ++++ target/arm/tcg/sme_helper.c | 45 ++++++++++++++++++++++++++++++++++ target/arm/tcg/sve_helper.c | 2 +- target/arm/tcg/translate-sme.c | 5 ++++ 6 files changed, 59 insertions(+), 1 deletion(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme2_bfcvt, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sme2_bfcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sme2_fcvt_n, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sme2_fcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_fcvt_w, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_fcvtl, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_internal.h +++ b/target/arm/tcg/vec_internal.h @@ -XXX,XX +XXX,XX @@ static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah) bfloat16 helper_sme2_ah_fmax_b16(bfloat16 a, bfloat16 b, float_status *fpst); bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst); +float32 sve_f16_to_f32(float16 f, float_status *fpst); float16 sve_f32_to_f16(float32 f, float_status *fpst); #endif /* TARGET_ARM_VEC_INTERNAL_H */ diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3 &zz_n zd zn n @zz_1x2 ........ ... ..... ...... ..... zd:5 \ &zz_n n=1 zn=%zn_ax2 +@zz_2x1 ........ ... ..... ...... zn:5 ..... \ + &zz_n n=1 zd=%zd_ax2 BFCVT 11000001 011 00000 111000 ....0 ..... @zz_1x2 BFCVTN 11000001 011 00000 111000 ....1 ..... @zz_1x2 FCVT_n 11000001 001 00000 111000 ....0 ..... @zz_1x2 FCVTN 11000001 001 00000 111000 ....1 ..... @zz_1x2 + +FCVT_w 11000001 101 00000 111000 ..... ....0 @zz_2x1 +FCVTL 11000001 101 00000 111000 ..... ....1 @zz_2x1 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 @@ #include "vec_internal.h" #include "sve_ldst_internal.h" + +static bool vectors_overlap(ARMVectorReg *x, unsigned nx, + ARMVectorReg *y, unsigned ny) +{ + return !(x + nx <= y || y + ny <= x); +} + void helper_set_svcr(CPUARMState *env, uint32_t val, uint32_t mask) { aarch64_set_svcr(env, val, mask); @@ -XXX,XX +XXX,XX @@ void HELPER(sme2_fcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc) d[H2(i * 2 + 1)] = d1; } } + +/* Expand and convert */ +void HELPER(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + ARMVectorReg scratch; + size_t oprsz = simd_oprsz(desc); + size_t i, n = oprsz / 4; + float16 *s = vs; + float32 *d0 = vd; + float32 *d1 = vd + sizeof(ARMVectorReg); + + if (vectors_overlap(vd, 1, vs, 2)) { + s = memcpy(&scratch, s, oprsz); + } + + for (i = 0; i < n; ++i) { + d0[H4(i)] = sve_f16_to_f32(s[H2(i)], fpst); + } + for (i = 0; i < n; ++i) { + d1[H4(i)] = sve_f16_to_f32(s[H2(n + i)], fpst); + } +} + +/* Deinterleave and convert. */ +void HELPER(sme2_fcvtl)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + float16 *s = vs; + float32 *d0 = vd; + float32 *d1 = vd + sizeof(ARMVectorReg); + + for (i = 0; i < n; ++i) { + float32 v0 = sve_f16_to_f32(s[H2(i * 2 + 0)], fpst); + float32 v1 = sve_f16_to_f32(s[H2(i * 2 + 1)], fpst); + d0[H4(i)] = v0; + d1[H4(i)] = v1; + } +} 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 @@ void HELPER(NAME)(void *vd, void *vn, void *vg, \ * FZ16. When converting from fp16, this affects flushing input denormals; * when converting to fp16, this affects flushing output denormals. */ -static inline float32 sve_f16_to_f32(float16 f, float_status *fpst) +float32 sve_f16_to_f32(float16 f, float_status *fpst) { bool save = get_flush_inputs_to_zero(fpst); float32 ret; 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 @@ TRANS_FEAT(FCVT_n, aa64_sme2, do_zz_fpst, a, 0, FPST_A64, gen_helper_sme2_fcvt_n) TRANS_FEAT(FCVTN, aa64_sme2, do_zz_fpst, a, 0, FPST_A64, gen_helper_sme2_fcvtn) + +TRANS_FEAT(FCVT_w, aa64_sme_f16f16, do_zz_fpst, a, 0, + FPST_A64_F16, gen_helper_sme2_fcvt_w) +TRANS_FEAT(FCVTL, aa64_sme_f16f16, do_zz_fpst, a, 0, + FPST_A64_F16, gen_helper_sme2_fcvtl) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-55-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 9 +++++++++ target/arm/tcg/translate-sme.c | 5 +++++ 2 files changed, 14 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3 &zz_n n=1 zn=%zn_ax2 @zz_2x1 ........ ... ..... ...... zn:5 ..... \ &zz_n n=1 zd=%zd_ax2 +@zz_2x2 ........ ... ..... ...... .... . ..... \ + &zz_n n=2 zd=%zd_ax2 zn=%zn_ax2 +@zz_4x4 ........ ... ..... ...... .... . ..... \ + &zz_n n=4 zd=%zd_ax4 zn=%zn_ax4 BFCVT 11000001 011 00000 111000 ....0 ..... @zz_1x2 BFCVTN 11000001 011 00000 111000 ....1 ..... @zz_1x2 @@ -XXX,XX +XXX,XX @@ FCVTN 11000001 001 00000 111000 ....1 ..... @zz_1x2 FCVT_w 11000001 101 00000 111000 ..... ....0 @zz_2x1 FCVTL 11000001 101 00000 111000 ..... ....1 @zz_2x1 + +FCVTZS 11000001 001 00001 111000 ....0 ....0 @zz_2x2 +FCVTZS 11000001 001 10001 111000 ...00 ...00 @zz_4x4 +FCVTZU 11000001 001 00001 111000 ....1 ....0 @zz_2x2 +FCVTZU 11000001 001 10001 111000 ...01 ...00 @zz_4x4 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 @@ TRANS_FEAT(FCVT_w, aa64_sme_f16f16, do_zz_fpst, a, 0, FPST_A64_F16, gen_helper_sme2_fcvt_w) TRANS_FEAT(FCVTL, aa64_sme_f16f16, do_zz_fpst, a, 0, FPST_A64_F16, gen_helper_sme2_fcvtl) + +TRANS_FEAT(FCVTZS, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_gvec_vcvt_rz_fs) +TRANS_FEAT(FCVTZU, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_gvec_vcvt_rz_fu) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-56-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 2 ++ target/arm/tcg/sme.decode | 5 +++++ target/arm/tcg/sme_helper.c | 22 ++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 5 +++++ 4 files changed, 34 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme2_fcvt_n, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sme2_fcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sme2_fcvt_w, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sme2_fcvtl, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_scvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_ucvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ FCVTZS 11000001 001 00001 111000 ....0 ....0 @zz_2x2 FCVTZS 11000001 001 10001 111000 ...00 ...00 @zz_4x4 FCVTZU 11000001 001 00001 111000 ....1 ....0 @zz_2x2 FCVTZU 11000001 001 10001 111000 ...01 ...00 @zz_4x4 + +SCVTF 11000001 001 00010 111000 ....0 ....0 @zz_2x2 +SCVTF 11000001 001 10010 111000 ...00 ...00 @zz_4x4 +UCVTF 11000001 001 00010 111000 ....1 ....0 @zz_2x2 +UCVTF 11000001 001 10010 111000 ...01 ...00 @zz_4x4 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(sme2_fcvtl)(void *vd, void *vs, float_status *fpst, uint32_t desc) d1[H4(i)] = v1; } } + +void HELPER(sme2_scvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + int32_t *d = vd; + float32 *s = vs; + + for (i = 0; i < n; ++i) { + d[i] = int32_to_float32(s[i], fpst); + } +} + +void HELPER(sme2_ucvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + uint32_t *d = vd; + float32 *s = vs; + + for (i = 0; i < n; ++i) { + d[i] = uint32_to_float32(s[i], fpst); + } +} 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 @@ TRANS_FEAT(FCVTZS, aa64_sme2, do_zz_fpst, a, 0, FPST_A64, gen_helper_gvec_vcvt_rz_fs) TRANS_FEAT(FCVTZU, aa64_sme2, do_zz_fpst, a, 0, FPST_A64, gen_helper_gvec_vcvt_rz_fu) + +TRANS_FEAT(SCVTF, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_scvtf) +TRANS_FEAT(UCVTF, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_ucvtf) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-57-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 9 +++++++++ target/arm/tcg/translate-sme.c | 9 +++++++++ 2 files changed, 18 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SCVTF 11000001 001 00010 111000 ....0 ....0 @zz_2x2 SCVTF 11000001 001 10010 111000 ...00 ...00 @zz_4x4 UCVTF 11000001 001 00010 111000 ....1 ....0 @zz_2x2 UCVTF 11000001 001 10010 111000 ...01 ...00 @zz_4x4 + +FRINTN 11000001 101 01000 111000 ....0 ....0 @zz_2x2 +FRINTN 11000001 101 11000 111000 ...00 ...00 @zz_4x4 +FRINTP 11000001 101 01001 111000 ....0 ....0 @zz_2x2 +FRINTP 11000001 101 11001 111000 ...00 ...00 @zz_4x4 +FRINTM 11000001 101 01010 111000 ....0 ....0 @zz_2x2 +FRINTM 11000001 101 11010 111000 ...00 ...00 @zz_4x4 +FRINTA 11000001 101 01100 111000 ....0 ....0 @zz_2x2 +FRINTA 11000001 101 11100 111000 ...00 ...00 @zz_4x4 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 @@ TRANS_FEAT(SCVTF, aa64_sme2, do_zz_fpst, a, 0, FPST_A64, gen_helper_sme2_scvtf) TRANS_FEAT(UCVTF, aa64_sme2, do_zz_fpst, a, 0, FPST_A64, gen_helper_sme2_ucvtf) + +TRANS_FEAT(FRINTN, aa64_sme2, do_zz_fpst, a, float_round_nearest_even, + FPST_A64, gen_helper_gvec_vrint_rm_s) +TRANS_FEAT(FRINTP, aa64_sme2, do_zz_fpst, a, float_round_up, + FPST_A64, gen_helper_gvec_vrint_rm_s) +TRANS_FEAT(FRINTM, aa64_sme2, do_zz_fpst, a, float_round_down, + FPST_A64, gen_helper_gvec_vrint_rm_s) +TRANS_FEAT(FRINTA, aa64_sme2, do_zz_fpst, a, float_round_ties_away, + FPST_A64, gen_helper_gvec_vrint_rm_s) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Inputs are a wider type of indeterminate sign. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-58-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/vec_internal.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_internal.h +++ b/target/arm/tcg/vec_internal.h @@ -XXX,XX +XXX,XX @@ int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *); int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *); int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool); +#define do_ssat_b(val) MIN(MAX(val, INT8_MIN), INT8_MAX) +#define do_ssat_h(val) MIN(MAX(val, INT16_MIN), INT16_MAX) +#define do_ssat_s(val) MIN(MAX(val, INT32_MIN), INT32_MAX) +#define do_usat_b(val) MIN(MAX(val, 0), UINT8_MAX) +#define do_usat_h(val) MIN(MAX(val, 0), UINT16_MAX) +#define do_usat_s(val) MIN(MAX(val, 0), UINT32_MAX) + /** * bfdotadd: * @sum: addend -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Replace and remove do_sat_bhs. This avoids multiple repetitions of INT*_MIN/MAX. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-59-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve_helper.c | 116 +++++++++++++++--------------------- 1 file changed, 48 insertions(+), 68 deletions(-) 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 @@ DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS) DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS) DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D) -static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max) -{ - return val >= max ? max : val <= min ? min : val; -} - -#define DO_SQADD_B(n, m) do_sat_bhs((int64_t)n + m, INT8_MIN, INT8_MAX) -#define DO_SQADD_H(n, m) do_sat_bhs((int64_t)n + m, INT16_MIN, INT16_MAX) -#define DO_SQADD_S(n, m) do_sat_bhs((int64_t)n + m, INT32_MIN, INT32_MAX) +#define DO_SQADD_B(n, m) do_ssat_b((int64_t)n + m) +#define DO_SQADD_H(n, m) do_ssat_h((int64_t)n + m) +#define DO_SQADD_S(n, m) do_ssat_s((int64_t)n + m) static inline int64_t do_sqadd_d(int64_t n, int64_t m) { @@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_sqadd_zpzz_h, int16_t, H1_2, DO_SQADD_H) DO_ZPZZ(sve2_sqadd_zpzz_s, int32_t, H1_4, DO_SQADD_S) DO_ZPZZ_D(sve2_sqadd_zpzz_d, int64_t, do_sqadd_d) -#define DO_UQADD_B(n, m) do_sat_bhs((int64_t)n + m, 0, UINT8_MAX) -#define DO_UQADD_H(n, m) do_sat_bhs((int64_t)n + m, 0, UINT16_MAX) -#define DO_UQADD_S(n, m) do_sat_bhs((int64_t)n + m, 0, UINT32_MAX) +#define DO_UQADD_B(n, m) do_usat_b((int64_t)n + m) +#define DO_UQADD_H(n, m) do_usat_h((int64_t)n + m) +#define DO_UQADD_S(n, m) do_usat_s((int64_t)n + m) static inline uint64_t do_uqadd_d(uint64_t n, uint64_t m) { @@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uqadd_zpzz_h, uint16_t, H1_2, DO_UQADD_H) DO_ZPZZ(sve2_uqadd_zpzz_s, uint32_t, H1_4, DO_UQADD_S) DO_ZPZZ_D(sve2_uqadd_zpzz_d, uint64_t, do_uqadd_d) -#define DO_SQSUB_B(n, m) do_sat_bhs((int64_t)n - m, INT8_MIN, INT8_MAX) -#define DO_SQSUB_H(n, m) do_sat_bhs((int64_t)n - m, INT16_MIN, INT16_MAX) -#define DO_SQSUB_S(n, m) do_sat_bhs((int64_t)n - m, INT32_MIN, INT32_MAX) +#define DO_SQSUB_B(n, m) do_ssat_b((int64_t)n - m) +#define DO_SQSUB_H(n, m) do_ssat_h((int64_t)n - m) +#define DO_SQSUB_S(n, m) do_ssat_s((int64_t)n - m) static inline int64_t do_sqsub_d(int64_t n, int64_t m) { @@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_sqsub_zpzz_h, int16_t, H1_2, DO_SQSUB_H) DO_ZPZZ(sve2_sqsub_zpzz_s, int32_t, H1_4, DO_SQSUB_S) DO_ZPZZ_D(sve2_sqsub_zpzz_d, int64_t, do_sqsub_d) -#define DO_UQSUB_B(n, m) do_sat_bhs((int64_t)n - m, 0, UINT8_MAX) -#define DO_UQSUB_H(n, m) do_sat_bhs((int64_t)n - m, 0, UINT16_MAX) -#define DO_UQSUB_S(n, m) do_sat_bhs((int64_t)n - m, 0, UINT32_MAX) +#define DO_UQSUB_B(n, m) do_usat_b((int64_t)n - m) +#define DO_UQSUB_H(n, m) do_usat_h((int64_t)n - m) +#define DO_UQSUB_S(n, m) do_usat_s((int64_t)n - m) static inline uint64_t do_uqsub_d(uint64_t n, uint64_t m) { @@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uqsub_zpzz_h, uint16_t, H1_2, DO_UQSUB_H) DO_ZPZZ(sve2_uqsub_zpzz_s, uint32_t, H1_4, DO_UQSUB_S) DO_ZPZZ_D(sve2_uqsub_zpzz_d, uint64_t, do_uqsub_d) -#define DO_SUQADD_B(n, m) \ - do_sat_bhs((int64_t)(int8_t)n + m, INT8_MIN, INT8_MAX) -#define DO_SUQADD_H(n, m) \ - do_sat_bhs((int64_t)(int16_t)n + m, INT16_MIN, INT16_MAX) -#define DO_SUQADD_S(n, m) \ - do_sat_bhs((int64_t)(int32_t)n + m, INT32_MIN, INT32_MAX) +#define DO_SUQADD_B(n, m) do_ssat_b((int64_t)(int8_t)n + m) +#define DO_SUQADD_H(n, m) do_ssat_h((int64_t)(int16_t)n + m) +#define DO_SUQADD_S(n, m) do_ssat_s((int64_t)(int32_t)n + m) static inline int64_t do_suqadd_d(int64_t n, uint64_t m) { @@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_suqadd_zpzz_h, uint16_t, H1_2, DO_SUQADD_H) DO_ZPZZ(sve2_suqadd_zpzz_s, uint32_t, H1_4, DO_SUQADD_S) DO_ZPZZ_D(sve2_suqadd_zpzz_d, uint64_t, do_suqadd_d) -#define DO_USQADD_B(n, m) \ - do_sat_bhs((int64_t)n + (int8_t)m, 0, UINT8_MAX) -#define DO_USQADD_H(n, m) \ - do_sat_bhs((int64_t)n + (int16_t)m, 0, UINT16_MAX) -#define DO_USQADD_S(n, m) \ - do_sat_bhs((int64_t)n + (int32_t)m, 0, UINT32_MAX) +#define DO_USQADD_B(n, m) do_usat_b((int64_t)n + (int8_t)m) +#define DO_USQADD_H(n, m) do_usat_h((int64_t)n + (int16_t)m) +#define DO_USQADD_S(n, m) do_usat_s((int64_t)n + (int32_t)m) static inline uint64_t do_usqadd_d(uint64_t n, int64_t m) { @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ } \ } -#define DO_SQXTN_H(n) do_sat_bhs(n, INT8_MIN, INT8_MAX) -#define DO_SQXTN_S(n) do_sat_bhs(n, INT16_MIN, INT16_MAX) -#define DO_SQXTN_D(n) do_sat_bhs(n, INT32_MIN, INT32_MAX) +DO_XTNB(sve2_sqxtnb_h, int16_t, do_ssat_b) +DO_XTNB(sve2_sqxtnb_s, int32_t, do_ssat_h) +DO_XTNB(sve2_sqxtnb_d, int64_t, do_ssat_s) -DO_XTNB(sve2_sqxtnb_h, int16_t, DO_SQXTN_H) -DO_XTNB(sve2_sqxtnb_s, int32_t, DO_SQXTN_S) -DO_XTNB(sve2_sqxtnb_d, int64_t, DO_SQXTN_D) +DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, do_ssat_b) +DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, do_ssat_h) +DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, do_ssat_s) -DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, DO_SQXTN_H) -DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, DO_SQXTN_S) -DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, DO_SQXTN_D) +DO_XTNB(sve2_uqxtnb_h, uint16_t, do_usat_b) +DO_XTNB(sve2_uqxtnb_s, uint32_t, do_usat_h) +DO_XTNB(sve2_uqxtnb_d, uint64_t, do_usat_s) -#define DO_UQXTN_H(n) do_sat_bhs(n, 0, UINT8_MAX) -#define DO_UQXTN_S(n) do_sat_bhs(n, 0, UINT16_MAX) -#define DO_UQXTN_D(n) do_sat_bhs(n, 0, UINT32_MAX) +DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, do_usat_b) +DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, do_usat_h) +DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, do_usat_s) -DO_XTNB(sve2_uqxtnb_h, uint16_t, DO_UQXTN_H) -DO_XTNB(sve2_uqxtnb_s, uint32_t, DO_UQXTN_S) -DO_XTNB(sve2_uqxtnb_d, uint64_t, DO_UQXTN_D) +DO_XTNB(sve2_sqxtunb_h, int16_t, do_usat_b) +DO_XTNB(sve2_sqxtunb_s, int32_t, do_usat_h) +DO_XTNB(sve2_sqxtunb_d, int64_t, do_usat_s) -DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, DO_UQXTN_H) -DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, DO_UQXTN_S) -DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, DO_UQXTN_D) - -DO_XTNB(sve2_sqxtunb_h, int16_t, DO_UQXTN_H) -DO_XTNB(sve2_sqxtunb_s, int32_t, DO_UQXTN_S) -DO_XTNB(sve2_sqxtunb_d, int64_t, DO_UQXTN_D) - -DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, DO_UQXTN_H) -DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, DO_UQXTN_S) -DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, DO_UQXTN_D) +DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, do_usat_b) +DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, do_usat_h) +DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, do_usat_s) #undef DO_XTNB #undef DO_XTNT @@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, do_urshr) DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, do_urshr) DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t, H1_8, H1_4, do_urshr) -#define DO_SQSHRUN_H(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT8_MAX) -#define DO_SQSHRUN_S(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT16_MAX) -#define DO_SQSHRUN_D(x, sh) \ - do_sat_bhs((int64_t)(x) >> (sh < 64 ? sh : 63), 0, UINT32_MAX) +#define DO_SQSHRUN_H(x, sh) do_usat_b((int64_t)(x) >> sh) +#define DO_SQSHRUN_S(x, sh) do_usat_h((int64_t)(x) >> sh) +#define DO_SQSHRUN_D(x, sh) do_usat_s((int64_t)(x) >> (sh < 64 ? sh : 63)) DO_SHRNB(sve2_sqshrunb_h, int16_t, uint8_t, DO_SQSHRUN_H) DO_SHRNB(sve2_sqshrunb_s, int32_t, uint16_t, DO_SQSHRUN_S) @@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRUN_H) DO_SHRNT(sve2_sqshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRUN_S) DO_SHRNT(sve2_sqshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRUN_D) -#define DO_SQRSHRUN_H(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT8_MAX) -#define DO_SQRSHRUN_S(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT16_MAX) -#define DO_SQRSHRUN_D(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT32_MAX) +#define DO_SQRSHRUN_H(x, sh) do_usat_b(do_srshr(x, sh)) +#define DO_SQRSHRUN_S(x, sh) do_usat_h(do_srshr(x, sh)) +#define DO_SQRSHRUN_D(x, sh) do_usat_s(do_srshr(x, sh)) DO_SHRNB(sve2_sqrshrunb_h, int16_t, uint8_t, DO_SQRSHRUN_H) DO_SHRNB(sve2_sqrshrunb_s, int32_t, uint16_t, DO_SQRSHRUN_S) @@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H) DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S) DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQRSHRUN_D) -#define DO_SQSHRN_H(x, sh) do_sat_bhs(x >> sh, INT8_MIN, INT8_MAX) -#define DO_SQSHRN_S(x, sh) do_sat_bhs(x >> sh, INT16_MIN, INT16_MAX) -#define DO_SQSHRN_D(x, sh) do_sat_bhs(x >> sh, INT32_MIN, INT32_MAX) +#define DO_SQSHRN_H(x, sh) do_ssat_b(x >> sh) +#define DO_SQSHRN_S(x, sh) do_ssat_h(x >> sh) +#define DO_SQSHRN_D(x, sh) do_ssat_s(x >> sh) DO_SHRNB(sve2_sqshrnb_h, int16_t, uint8_t, DO_SQSHRN_H) DO_SHRNB(sve2_sqshrnb_s, int32_t, uint16_t, DO_SQSHRN_S) @@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRN_H) DO_SHRNT(sve2_sqshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRN_S) DO_SHRNT(sve2_sqshrnt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRN_D) -#define DO_SQRSHRN_H(x, sh) do_sat_bhs(do_srshr(x, sh), INT8_MIN, INT8_MAX) -#define DO_SQRSHRN_S(x, sh) do_sat_bhs(do_srshr(x, sh), INT16_MIN, INT16_MAX) -#define DO_SQRSHRN_D(x, sh) do_sat_bhs(do_srshr(x, sh), INT32_MIN, INT32_MAX) +#define DO_SQRSHRN_H(x, sh) do_ssat_b(do_srshr(x, sh)) +#define DO_SQRSHRN_S(x, sh) do_ssat_h(do_srshr(x, sh)) +#define DO_SQRSHRN_D(x, sh) do_ssat_s(do_srshr(x, sh)) DO_SHRNB(sve2_sqrshrnb_h, int16_t, uint8_t, DO_SQRSHRN_H) DO_SHRNB(sve2_sqrshrnb_s, int32_t, uint16_t, DO_SQRSHRN_S) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250704142112.1018902-60-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 20 ++++++ target/arm/tcg/sme.decode | 22 +++++++ target/arm/tcg/sme_helper.c | 116 +++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 35 ++++++++++ 4 files changed, 193 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme2_fcvt_w, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sme2_fcvtl, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sme2_scvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sme2_ucvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_3(sme2_sqcvt_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvt_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtu_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtu_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvt_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvt_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtu_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_sqcvtn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvtn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtun_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvtn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtun_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3 &zz_n zd zn n @zz_1x2 ........ ... ..... ...... ..... zd:5 \ &zz_n n=1 zn=%zn_ax2 +@zz_1x4 ........ ... ..... ...... ..... zd:5 \ + &zz_n n=1 zn=%zn_ax4 @zz_2x1 ........ ... ..... ...... zn:5 ..... \ &zz_n n=1 zd=%zd_ax2 @zz_2x2 ........ ... ..... ...... .... . ..... \ @@ -XXX,XX +XXX,XX @@ FRINTM 11000001 101 01010 111000 ....0 ....0 @zz_2x2 FRINTM 11000001 101 11010 111000 ...00 ...00 @zz_4x4 FRINTA 11000001 101 01100 111000 ....0 ....0 @zz_2x2 FRINTA 11000001 101 11100 111000 ...00 ...00 @zz_4x4 + +SQCVT_sh 11000001 001 00011 111000 ....0 ..... @zz_1x2 +UQCVT_sh 11000001 001 00011 111000 ....1 ..... @zz_1x2 +SQCVTU_sh 11000001 011 00011 111000 ....0 ..... @zz_1x2 + +SQCVT_sb 11000001 001 10011 111000 ...00 ..... @zz_1x4 +UQCVT_sb 11000001 001 10011 111000 ...01 ..... @zz_1x4 +SQCVTU_sb 11000001 011 10011 111000 ...00 ..... @zz_1x4 + +SQCVT_dh 11000001 101 10011 111000 ...00 ..... @zz_1x4 +UQCVT_dh 11000001 101 10011 111000 ...01 ..... @zz_1x4 +SQCVTU_dh 11000001 111 10011 111000 ...00 ..... @zz_1x4 + +SQCVTN_sb 11000001 001 10011 111000 ...10 ..... @zz_1x4 +UQCVTN_sb 11000001 001 10011 111000 ...11 ..... @zz_1x4 +SQCVTUN_sb 11000001 011 10011 111000 ...10 ..... @zz_1x4 + +SQCVTN_dh 11000001 101 10011 111000 ...10 ..... @zz_1x4 +UQCVTN_dh 11000001 101 10011 111000 ...11 ..... @zz_1x4 +SQCVTUN_dh 11000001 111 10011 111000 ...10 ..... @zz_1x4 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(sme2_fcvt_n)(void *vd, void *vs, float_status *fpst, uint32_t desc) } } +#define SQCVT2(NAME, TW, TN, HW, HN, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 2)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(i)] = SAT(s0[HW(i)]); \ + d[HN(i + n)] = SAT(s1[HW(i)]); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQCVT2(sme2_sqcvt_sh, int32_t, int16_t, H4, H2, do_ssat_h) +SQCVT2(sme2_uqcvt_sh, uint32_t, uint16_t, H4, H2, do_usat_h) +SQCVT2(sme2_sqcvtu_sh, int32_t, uint16_t, H4, H2, do_usat_h) + +#undef SQCVT2 + +#define SQCVT4(NAME, TW, TN, HW, HN, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TW *s2 = vs + 2 * sizeof(ARMVectorReg); \ + TW *s3 = vs + 3 * sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 4)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(i)] = SAT(s0[HW(i)]); \ + d[HN(i + n)] = SAT(s1[HW(i)]); \ + d[HN(i + 2 * n)] = SAT(s2[HW(i)]); \ + d[HN(i + 3 * n)] = SAT(s3[HW(i)]); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQCVT4(sme2_sqcvt_sb, int32_t, int8_t, H4, H2, do_ssat_b) +SQCVT4(sme2_uqcvt_sb, uint32_t, uint8_t, H4, H2, do_usat_b) +SQCVT4(sme2_sqcvtu_sb, int32_t, uint8_t, H4, H2, do_usat_b) + +SQCVT4(sme2_sqcvt_dh, int64_t, int16_t, H8, H2, do_ssat_h) +SQCVT4(sme2_uqcvt_dh, uint64_t, uint16_t, H8, H2, do_usat_h) +SQCVT4(sme2_sqcvtu_dh, int64_t, uint16_t, H8, H2, do_usat_h) + +#undef SQCVT4 + /* Convert and interleave */ void HELPER(sme2_bfcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc) { @@ -XXX,XX +XXX,XX @@ void HELPER(sme2_fcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc) } } +#define SQCVTN2(NAME, TW, TN, HW, HN, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 2)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(2 * i + 0)] = SAT(s0[HW(i)]); \ + d[HN(2 * i + 1)] = SAT(s1[HW(i)]); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQCVTN2(sme2_sqcvtn_sh, int32_t, int16_t, H4, H2, do_ssat_h) +SQCVTN2(sme2_uqcvtn_sh, uint32_t, uint16_t, H4, H2, do_usat_h) +SQCVTN2(sme2_sqcvtun_sh, int32_t, uint16_t, H4, H2, do_usat_h) + +#undef SQCVTN2 + +#define SQCVTN4(NAME, TW, TN, HW, HN, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TW *s2 = vs + 2 * sizeof(ARMVectorReg); \ + TW *s3 = vs + 3 * sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 4)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(4 * i + 0)] = SAT(s0[HW(i)]); \ + d[HN(4 * i + 1)] = SAT(s1[HW(i)]); \ + d[HN(4 * i + 2)] = SAT(s2[HW(i)]); \ + d[HN(4 * i + 3)] = SAT(s3[HW(i)]); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQCVTN4(sme2_sqcvtn_sb, int32_t, int8_t, H4, H1, do_ssat_b) +SQCVTN4(sme2_uqcvtn_sb, uint32_t, uint8_t, H4, H1, do_usat_b) +SQCVTN4(sme2_sqcvtun_sb, int32_t, uint8_t, H4, H1, do_usat_b) + +SQCVTN4(sme2_sqcvtn_dh, int64_t, int16_t, H8, H2, do_ssat_h) +SQCVTN4(sme2_uqcvtn_dh, uint64_t, uint16_t, H8, H2, do_usat_h) +SQCVTN4(sme2_sqcvtun_dh, int64_t, uint16_t, H8, H2, do_usat_h) + +#undef SQCVTN4 + /* Expand and convert */ void HELPER(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc) { 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 @@ TRANS_FEAT(FRINTM, aa64_sme2, do_zz_fpst, a, float_round_down, FPST_A64, gen_helper_gvec_vrint_rm_s) TRANS_FEAT(FRINTA, aa64_sme2, do_zz_fpst, a, float_round_ties_away, FPST_A64, gen_helper_gvec_vrint_rm_s) + +static bool do_zz(DisasContext *s, arg_zz_n *a, int data, + gen_helper_gvec_2 *fn) +{ + if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + + for (int i = 0, n = a->n; i < n; ++i) { + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->zd + i), + vec_full_reg_offset(s, a->zn + i), + svl, svl, data, fn); + } + } + return true; +} + +TRANS_FEAT(SQCVT_sh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvt_sh) +TRANS_FEAT(UQCVT_sh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvt_sh) +TRANS_FEAT(SQCVTU_sh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtu_sh) + +TRANS_FEAT(SQCVT_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvt_sb) +TRANS_FEAT(UQCVT_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvt_sb) +TRANS_FEAT(SQCVTU_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtu_sb) + +TRANS_FEAT(SQCVT_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvt_dh) +TRANS_FEAT(UQCVT_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvt_dh) +TRANS_FEAT(SQCVTU_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtu_dh) + +TRANS_FEAT(SQCVTN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtn_sb) +TRANS_FEAT(UQCVTN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvtn_sb) +TRANS_FEAT(SQCVTUN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_sb) + +TRANS_FEAT(SQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtn_dh) +TRANS_FEAT(UQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvtn_dh) +TRANS_FEAT(SQCVTUN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_dh) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-61-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 20 ++++++++++++++++---- target/arm/tcg/translate-sve.c | 7 +++++++ 2 files changed, 23 insertions(+), 4 deletions(-) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ # as propagated via the MOVPRFX instruction. %reg_movprfx 0:5 +%rn_ax2 6:4 !function=times_2 + ########################################################################### # Named attribute sets. These are used to make nice(er) names # when creating helpers common to those for the individual @@ -XXX,XX +XXX,XX @@ # Two operand @pd_pn ........ esz:2 .. .... ....... rn:4 . rd:4 &rr_esz @rd_rn ........ esz:2 ...... ...... rn:5 rd:5 &rr_esz +@rd_rnx2 ........ ... ..... ...... ..... rd:5 &rr_esz rn=%rn_ax2 # Two operand with governing predicate, flags setting @pd_pg_pn_s ........ . s:1 ...... .. pg:4 . rn:4 . rd:4 &rpr_s @@ -XXX,XX +XXX,XX @@ UABA 01000101 .. 0 ..... 11111 1 ..... ..... @rd_rn_rm #### SVE2 Narrowing ## SVE2 saturating extract narrow - # Bits 23, 18-16 are zero, limited in the translator via esz < 3 & imm == 0. -SQXTNB 01000101 .. 1 ..... 010 000 ..... ..... @rd_rn_tszimm_shl + +{ + SQCVTN_sh 01000101 00 1 10001 010 000 ....0 ..... @rd_rnx2 esz=1 + SQXTNB 01000101 .. 1 ..... 010 000 ..... ..... @rd_rn_tszimm_shl +} SQXTNT 01000101 .. 1 ..... 010 001 ..... ..... @rd_rn_tszimm_shl -UQXTNB 01000101 .. 1 ..... 010 010 ..... ..... @rd_rn_tszimm_shl +{ + UQCVTN_sh 01000101 00 1 10001 010 010 ....0 ..... @rd_rnx2 esz=1 + UQXTNB 01000101 .. 1 ..... 010 010 ..... ..... @rd_rn_tszimm_shl +} UQXTNT 01000101 .. 1 ..... 010 011 ..... ..... @rd_rn_tszimm_shl -SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl +{ + SQCVTUN_sh 01000101 00 1 10001 010 100 ....0 ..... @rd_rnx2 esz=1 + SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl +} SQXTUNT 01000101 .. 1 ..... 010 101 ..... ..... @rd_rn_tszimm_shl ## SVE2 bitwise shift right narrow 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 void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, } TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a) + +TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, + gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0) +TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, + gen_helper_sme2_uqcvtn_sh, a->rd, a->rn, 0) +TRANS_FEAT(SQCVTUN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, + gen_helper_sme2_sqcvtun_sh, a->rd, a->rn, 0) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250704142112.1018902-62-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 13 ++++++++++++ target/arm/tcg/sme.decode | 18 ++++++++++++++++ target/arm/tcg/sme_helper.c | 38 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 16 ++++++++++++++ 4 files changed, 85 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sme2_sqcvtun_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_sqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_sqcvtun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_sunpk2_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk2_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk2_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk2_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3 &zz_n n=2 zd=%zd_ax2 zn=%zn_ax2 @zz_4x4 ........ ... ..... ...... .... . ..... \ &zz_n n=4 zd=%zd_ax4 zn=%zn_ax4 +@zz_4x2_n1 ........ ... ..... ...... .... . ..... \ + &zz_n n=1 zd=%zd_ax4 zn=%zn_ax2 BFCVT 11000001 011 00000 111000 ....0 ..... @zz_1x2 BFCVTN 11000001 011 00000 111000 ....1 ..... @zz_1x2 @@ -XXX,XX +XXX,XX @@ SQCVTUN_sb 11000001 011 10011 111000 ...10 ..... @zz_1x4 SQCVTN_dh 11000001 101 10011 111000 ...10 ..... @zz_1x4 UQCVTN_dh 11000001 101 10011 111000 ...11 ..... @zz_1x4 SQCVTUN_dh 11000001 111 10011 111000 ...10 ..... @zz_1x4 + +SUNPK_2bh 11000001 011 00101 111000 ..... ....0 @zz_2x1 +SUNPK_2hs 11000001 101 00101 111000 ..... ....0 @zz_2x1 +SUNPK_2sd 11000001 111 00101 111000 ..... ....0 @zz_2x1 + +UUNPK_2bh 11000001 011 00101 111000 ..... ....1 @zz_2x1 +UUNPK_2hs 11000001 101 00101 111000 ..... ....1 @zz_2x1 +UUNPK_2sd 11000001 111 00101 111000 ..... ....1 @zz_2x1 + +SUNPK_4bh 11000001 011 10101 111000 ....0 ...00 @zz_4x2_n1 +SUNPK_4hs 11000001 101 10101 111000 ....0 ...00 @zz_4x2_n1 +SUNPK_4sd 11000001 111 10101 111000 ....0 ...00 @zz_4x2_n1 + +UUNPK_4bh 11000001 011 10101 111000 ....0 ...01 @zz_4x2_n1 +UUNPK_4hs 11000001 101 10101 111000 ....0 ...01 @zz_4x2_n1 +UUNPK_4sd 11000001 111 10101 111000 ....0 ...01 @zz_4x2_n1 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(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc) } } +#define UNPK(NAME, SREG, TW, TN, HW, HN) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch[SREG]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t n = oprsz / sizeof(TW); \ + if (vectors_overlap(vd, 2 * SREG, vs, SREG)) { \ + vs = memcpy(scratch, vs, sizeof(scratch)); \ + } \ + for (size_t r = 0; r < SREG; ++r) { \ + TN *s = vs + r * sizeof(ARMVectorReg); \ + for (size_t i = 0; i < 2; ++i) { \ + TW *d = vd + (2 * r + i) * sizeof(ARMVectorReg); \ + for (size_t e = 0; e < n; ++e) { \ + d[HW(e)] = s[HN(i * n + e)]; \ + } \ + } \ + } \ +} + +UNPK(sme2_sunpk2_bh, 1, int16_t, int8_t, H2, H1) +UNPK(sme2_sunpk2_hs, 1, int32_t, int16_t, H4, H2) +UNPK(sme2_sunpk2_sd, 1, int64_t, int32_t, H8, H4) + +UNPK(sme2_sunpk4_bh, 2, int16_t, int8_t, H2, H1) +UNPK(sme2_sunpk4_hs, 2, int32_t, int16_t, H4, H2) +UNPK(sme2_sunpk4_sd, 2, int64_t, int32_t, H8, H4) + +UNPK(sme2_uunpk2_bh, 1, uint16_t, uint8_t, H2, H1) +UNPK(sme2_uunpk2_hs, 1, uint32_t, uint16_t, H4, H2) +UNPK(sme2_uunpk2_sd, 1, uint64_t, uint32_t, H8, H4) + +UNPK(sme2_uunpk4_bh, 2, uint16_t, uint8_t, H2, H1) +UNPK(sme2_uunpk4_hs, 2, uint32_t, uint16_t, H4, H2) +UNPK(sme2_uunpk4_sd, 2, uint64_t, uint32_t, H8, H4) + +#undef UNPK + /* Deinterleave and convert. */ void HELPER(sme2_fcvtl)(void *vd, void *vs, float_status *fpst, uint32_t desc) { 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 @@ TRANS_FEAT(SQCVTUN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_sb) TRANS_FEAT(SQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtn_dh) TRANS_FEAT(UQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvtn_dh) TRANS_FEAT(SQCVTUN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_dh) + +TRANS_FEAT(SUNPK_2bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_bh) +TRANS_FEAT(SUNPK_2hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_hs) +TRANS_FEAT(SUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_sd) + +TRANS_FEAT(SUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_bh) +TRANS_FEAT(SUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_hs) +TRANS_FEAT(SUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_sd) + +TRANS_FEAT(UUNPK_2bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_bh) +TRANS_FEAT(UUNPK_2hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_hs) +TRANS_FEAT(UUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_sd) + +TRANS_FEAT(UUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_bh) +TRANS_FEAT(UUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_hs) +TRANS_FEAT(UUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_sd) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-63-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 12 ++++++ target/arm/tcg/sme.decode | 11 ++++++ target/arm/tcg/sme_helper.c | 68 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 39 +++++++++++++++++++ 4 files changed, 130 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sme2_uunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_zip4_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_zip4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_zip4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_zip4_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_zip4_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_uzp4_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uzp4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uzp4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uzp4_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uzp4_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3 ### SME2 Multi-vector SVE Constructive Unary +&zz_e zd zn esz &zz_n zd zn n @zz_1x2 ........ ... ..... ...... ..... zd:5 \ &zz_n n=1 zn=%zn_ax2 @@ -XXX,XX +XXX,XX @@ SUNPK_4sd 11000001 111 10101 111000 ....0 ...00 @zz_4x2_n1 UUNPK_4bh 11000001 011 10101 111000 ....0 ...01 @zz_4x2_n1 UUNPK_4hs 11000001 101 10101 111000 ....0 ...01 @zz_4x2_n1 UUNPK_4sd 11000001 111 10101 111000 ....0 ...01 @zz_4x2_n1 + +ZIP_4 11000001 esz:2 1 10110 111000 ...00 ... 00 \ + &zz_e zd=%zd_ax4 zn=%zn_ax4 +ZIP_4 11000001 001 10111 111000 ...00 ... 00 \ + &zz_e esz=4 zd=%zd_ax4 zn=%zn_ax4 + +UZP_4 11000001 esz:2 1 10110 111000 ...00 ... 10 \ + &zz_e zd=%zd_ax4 zn=%zn_ax4 +UZP_4 11000001 001 10111 111000 ...00 ... 10 \ + &zz_e esz=4 zd=%zd_ax4 zn=%zn_ax4 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(sme2_ucvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc) d[i] = uint32_to_float32(s[i], fpst); } } + +#define ZIP4(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch[4]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t quads = oprsz / (sizeof(TYPE) * 4); \ + TYPE *s0, *s1, *s2, *s3; \ + if (vs == vd) { \ + vs = memcpy(scratch, vs, sizeof(scratch)); \ + } \ + s0 = vs; \ + s1 = vs + sizeof(ARMVectorReg); \ + s2 = vs + 2 * sizeof(ARMVectorReg); \ + s3 = vs + 3 * sizeof(ARMVectorReg); \ + for (size_t r = 0; r < 4; ++r) { \ + TYPE *d = vd + r * sizeof(ARMVectorReg); \ + size_t base = r * quads; \ + for (size_t q = 0; q < quads; ++q) { \ + d[H(4 * q + 0)] = s0[base + H(q)]; \ + d[H(4 * q + 1)] = s1[base + H(q)]; \ + d[H(4 * q + 2)] = s2[base + H(q)]; \ + d[H(4 * q + 3)] = s3[base + H(q)]; \ + } \ + } \ +} + +ZIP4(sme2_zip4_b, uint8_t, H1) +ZIP4(sme2_zip4_h, uint16_t, H2) +ZIP4(sme2_zip4_s, uint32_t, H4) +ZIP4(sme2_zip4_d, uint64_t, ) +ZIP4(sme2_zip4_q, Int128, ) + +#undef ZIP4 + +#define UZP4(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch[4]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t quads = oprsz / (sizeof(TYPE) * 4); \ + TYPE *d0, *d1, *d2, *d3; \ + if (vs == vd) { \ + vs = memcpy(scratch, vs, sizeof(scratch)); \ + } \ + d0 = vd; \ + d1 = vd + sizeof(ARMVectorReg); \ + d2 = vd + 2 * sizeof(ARMVectorReg); \ + d3 = vd + 3 * sizeof(ARMVectorReg); \ + for (size_t r = 0; r < 4; ++r) { \ + TYPE *s = vs + r * sizeof(ARMVectorReg); \ + size_t base = r * quads; \ + for (size_t q = 0; q < quads; ++q) { \ + d0[base + H(q)] = s[H(4 * q + 0)]; \ + d1[base + H(q)] = s[H(4 * q + 1)]; \ + d2[base + H(q)] = s[H(4 * q + 2)]; \ + d3[base + H(q)] = s[H(4 * q + 3)]; \ + } \ + } \ +} + +UZP4(sme2_uzp4_b, uint8_t, H1) +UZP4(sme2_uzp4_h, uint16_t, H2) +UZP4(sme2_uzp4_s, uint32_t, H4) +UZP4(sme2_uzp4_d, uint64_t, ) +UZP4(sme2_uzp4_q, Int128, ) + +#undef UZP4 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 @@ TRANS_FEAT(UUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_sd) TRANS_FEAT(UUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_bh) TRANS_FEAT(UUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_hs) TRANS_FEAT(UUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_sd) + +static bool do_zipuzp_4(DisasContext *s, arg_zz_e *a, + gen_helper_gvec_2 * const fn[5]) +{ + int bytes_per_op = 4 << a->esz; + + /* Both MO_64 and MO_128 can fail the size test. */ + if (s->max_svl < bytes_per_op) { + unallocated_encoding(s); + } else if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + if (svl < bytes_per_op) { + unallocated_encoding(s); + } else { + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + svl, svl, 0, fn[a->esz]); + } + } + return true; +} + +static gen_helper_gvec_2 * const zip4_fns[] = { + gen_helper_sme2_zip4_b, + gen_helper_sme2_zip4_h, + gen_helper_sme2_zip4_s, + gen_helper_sme2_zip4_d, + gen_helper_sme2_zip4_q, +}; +TRANS_FEAT(ZIP_4, aa64_sme2, do_zipuzp_4, a, zip4_fns) + +static gen_helper_gvec_2 * const uzp4_fns[] = { + gen_helper_sme2_uzp4_b, + gen_helper_sme2_uzp4_h, + gen_helper_sme2_uzp4_s, + gen_helper_sme2_uzp4_d, + gen_helper_sme2_uzp4_q, +}; +TRANS_FEAT(UZP_4, aa64_sme2, do_zipuzp_4, a, uzp4_fns) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Unify two copies of these inline functions. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-64-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/vec_internal.h | 21 +++++++++++++++++++++ target/arm/tcg/mve_helper.c | 21 --------------------- target/arm/tcg/sve_helper.c | 21 --------------------- 3 files changed, 21 insertions(+), 42 deletions(-) diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_internal.h +++ b/target/arm/tcg/vec_internal.h @@ -XXX,XX +XXX,XX @@ int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool); #define do_usat_h(val) MIN(MAX(val, 0), UINT16_MAX) #define do_usat_s(val) MIN(MAX(val, 0), UINT32_MAX) +static inline uint64_t do_urshr(uint64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else if (sh == 64) { + return x >> 63; + } else { + return 0; + } +} + +static inline int64_t do_srshr(int64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else { + /* Rounding the sign bit always produces 0. */ + return 0; + } +} + /** * bfdotadd: * @sum: addend diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHLL_ALL(vshllt, true) DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN) \ DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN) -static inline uint64_t do_urshr(uint64_t x, unsigned sh) -{ - if (likely(sh < 64)) { - return (x >> sh) + ((x >> (sh - 1)) & 1); - } else if (sh == 64) { - return x >> 63; - } else { - return 0; - } -} - -static inline int64_t do_srshr(int64_t x, unsigned sh) -{ - if (likely(sh < 64)) { - return (x >> sh) + ((x >> (sh - 1)) & 1); - } else { - /* Rounding the sign bit always produces 0. */ - return 0; - } -} - DO_VSHRN_ALL(vshrn, DO_SHR) DO_VSHRN_ALL(vrshrn, do_urshr) 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 @@ void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \ when N is negative, add 2**M-1. */ #define DO_ASRD(N, M) ((N + (N < 0 ? ((__typeof(N))1 << M) - 1 : 0)) >> M) -static inline uint64_t do_urshr(uint64_t x, unsigned sh) -{ - if (likely(sh < 64)) { - return (x >> sh) + ((x >> (sh - 1)) & 1); - } else if (sh == 64) { - return x >> 63; - } else { - return 0; - } -} - -static inline int64_t do_srshr(int64_t x, unsigned sh) -{ - if (likely(sh < 64)) { - return (x >> sh) + ((x >> (sh - 1)) & 1); - } else { - /* Rounding the sign bit always produces 0. */ - return 0; - } -} - DO_ZPZI(sve_asr_zpzi_b, int8_t, H1, DO_SHR) DO_ZPZI(sve_asr_zpzi_h, int16_t, H1_2, DO_SHR) DO_ZPZI(sve_asr_zpzi_s, int32_t, H1_4, DO_SHR) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250704142112.1018902-65-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 20 ++++++ target/arm/tcg/sme.decode | 37 ++++++++++ target/arm/tcg/sme_helper.c | 120 +++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 33 +++++++++ 4 files changed, 210 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sme2_uzp4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uzp4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uzp4_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uzp4_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_sqrshr_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshr_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshru_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshr_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshr_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshru_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshr_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshr_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshru_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_sqrshrn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshrn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrun_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshrn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrun_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ UZP_4 11000001 esz:2 1 10110 111000 ...00 ... 10 \ &zz_e zd=%zd_ax4 zn=%zn_ax4 UZP_4 11000001 001 10111 111000 ...00 ... 10 \ &zz_e esz=4 zd=%zd_ax4 zn=%zn_ax4 + +### SME2 Multi-vector SVE Constructive Binary + +&rshr zd zn shift + +%rshr_sh_shift 16:4 !function=rsub_16 +%rshr_sb_shift 16:5 !function=rsub_32 +%rshr_dh_shift 22:1 16:5 !function=rsub_64 + +@rshr_sh ........ .... .... ...... ..... zd:5 \ + &rshr zn=%zn_ax2 shift=%rshr_sh_shift +@rshr_sb ........ ... ..... ...... ..... zd:5 \ + &rshr zn=%zn_ax4 shift=%rshr_sb_shift +@rshr_dh ........ ... ..... ...... ..... zd:5 \ + &rshr zn=%zn_ax4 shift=%rshr_dh_shift + +SQRSHR_sh 11000001 1110 .... 110101 ....0 ..... @rshr_sh +UQRSHR_sh 11000001 1110 .... 110101 ....1 ..... @rshr_sh +SQRSHRU_sh 11000001 1111 .... 110101 ....0 ..... @rshr_sh + +SQRSHR_sb 11000001 011 ..... 110110 ...00 ..... @rshr_sb +SQRSHR_dh 11000001 1.1 ..... 110110 ...00 ..... @rshr_dh +UQRSHR_sb 11000001 011 ..... 110110 ...01 ..... @rshr_sb +UQRSHR_dh 11000001 1.1 ..... 110110 ...01 ..... @rshr_dh +SQRSHRU_sb 11000001 011 ..... 110110 ...10 ..... @rshr_sb +SQRSHRU_dh 11000001 1.1 ..... 110110 ...10 ..... @rshr_dh + +SQRSHRN_sh 01000101 1011 .... 001010 ....0 ..... @rshr_sh +UQRSHRN_sh 01000101 1011 .... 001110 ....0 ..... @rshr_sh +SQRSHRUN_sh 01000101 1011 .... 000010 ....0 ..... @rshr_sh + +SQRSHRN_sb 11000001 011 ..... 110111 ...00 ..... @rshr_sb +SQRSHRN_dh 11000001 1.1 ..... 110111 ...00 ..... @rshr_dh +UQRSHRN_sb 11000001 011 ..... 110111 ...01 ..... @rshr_sb +UQRSHRN_dh 11000001 1.1 ..... 110111 ...01 ..... @rshr_dh +SQRSHRUN_sb 11000001 011 ..... 110111 ...10 ..... @rshr_sb +SQRSHRUN_dh 11000001 1.1 ..... 110111 ...10 ..... @rshr_dh 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 @@ SQCVT4(sme2_sqcvtu_dh, int64_t, uint16_t, H8, H2, do_usat_h) #undef SQCVT4 +#define SQRSHR2(NAME, TW, TN, HW, HN, RSHR, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + int shift = simd_data(desc); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 2)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(i)] = SAT(RSHR(s0[HW(i)], shift)); \ + d[HN(i + n)] = SAT(RSHR(s1[HW(i)], shift)); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQRSHR2(sme2_sqrshr_sh, int32_t, int16_t, H4, H2, do_srshr, do_ssat_h) +SQRSHR2(sme2_uqrshr_sh, uint32_t, uint16_t, H4, H2, do_urshr, do_usat_h) +SQRSHR2(sme2_sqrshru_sh, int32_t, uint16_t, H4, H2, do_srshr, do_usat_h) + +#undef SQRSHR2 + +#define SQRSHR4(NAME, TW, TN, HW, HN, RSHR, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + int shift = simd_data(desc); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TW *s2 = vs + 2 * sizeof(ARMVectorReg); \ + TW *s3 = vs + 3 * sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 4)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(i)] = SAT(RSHR(s0[HW(i)], shift)); \ + d[HN(i + n)] = SAT(RSHR(s1[HW(i)], shift)); \ + d[HN(i + 2 * n)] = SAT(RSHR(s2[HW(i)], shift)); \ + d[HN(i + 3 * n)] = SAT(RSHR(s3[HW(i)], shift)); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQRSHR4(sme2_sqrshr_sb, int32_t, int8_t, H4, H2, do_srshr, do_ssat_b) +SQRSHR4(sme2_uqrshr_sb, uint32_t, uint8_t, H4, H2, do_urshr, do_usat_b) +SQRSHR4(sme2_sqrshru_sb, int32_t, uint8_t, H4, H2, do_srshr, do_usat_b) + +SQRSHR4(sme2_sqrshr_dh, int64_t, int16_t, H8, H2, do_srshr, do_ssat_h) +SQRSHR4(sme2_uqrshr_dh, uint64_t, uint16_t, H8, H2, do_urshr, do_usat_h) +SQRSHR4(sme2_sqrshru_dh, int64_t, uint16_t, H8, H2, do_srshr, do_usat_h) + +#undef SQRSHR4 + /* Convert and interleave */ void HELPER(sme2_bfcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc) { @@ -XXX,XX +XXX,XX @@ SQCVTN4(sme2_sqcvtun_dh, int64_t, uint16_t, H8, H2, do_usat_h) #undef SQCVTN4 +#define SQRSHRN2(NAME, TW, TN, HW, HN, RSHR, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + int shift = simd_data(desc); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 2)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(2 * i + 0)] = SAT(RSHR(s0[HW(i)], shift)); \ + d[HN(2 * i + 1)] = SAT(RSHR(s1[HW(i)], shift)); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQRSHRN2(sme2_sqrshrn_sh, int32_t, int16_t, H4, H2, do_srshr, do_ssat_h) +SQRSHRN2(sme2_uqrshrn_sh, uint32_t, uint16_t, H4, H2, do_urshr, do_usat_h) +SQRSHRN2(sme2_sqrshrun_sh, int32_t, uint16_t, H4, H2, do_srshr, do_usat_h) + +#undef SQRSHRN2 + +#define SQRSHRN4(NAME, TW, TN, HW, HN, RSHR, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + int shift = simd_data(desc); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TW *s2 = vs + 2 * sizeof(ARMVectorReg); \ + TW *s3 = vs + 3 * sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 4)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(4 * i + 0)] = SAT(RSHR(s0[HW(i)], shift)); \ + d[HN(4 * i + 1)] = SAT(RSHR(s1[HW(i)], shift)); \ + d[HN(4 * i + 2)] = SAT(RSHR(s2[HW(i)], shift)); \ + d[HN(4 * i + 3)] = SAT(RSHR(s3[HW(i)], shift)); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQRSHRN4(sme2_sqrshrn_sb, int32_t, int8_t, H4, H1, do_srshr, do_ssat_b) +SQRSHRN4(sme2_uqrshrn_sb, uint32_t, uint8_t, H4, H1, do_urshr, do_usat_b) +SQRSHRN4(sme2_sqrshrun_sb, int32_t, uint8_t, H4, H1, do_srshr, do_usat_b) + +SQRSHRN4(sme2_sqrshrn_dh, int64_t, int16_t, H8, H2, do_srshr, do_ssat_h) +SQRSHRN4(sme2_uqrshrn_dh, uint64_t, uint16_t, H8, H2, do_urshr, do_usat_h) +SQRSHRN4(sme2_sqrshrun_dh, int64_t, uint16_t, H8, H2, do_srshr, do_usat_h) + +#undef SQRSHRN4 + /* Expand and convert */ void HELPER(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc) { 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 gen_helper_gvec_2 * const uzp4_fns[] = { gen_helper_sme2_uzp4_q, }; TRANS_FEAT(UZP_4, aa64_sme2, do_zipuzp_4, a, uzp4_fns) + +static bool do_zz_rshr(DisasContext *s, arg_rshr *a, gen_helper_gvec_2 *fn) +{ + if (sve_access_check(s)) { + int vl = vec_full_reg_size(s); + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + vl, vl, a->shift, fn); + } + return true; +} + +TRANS_FEAT(SQRSHR_sh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshr_sh) +TRANS_FEAT(UQRSHR_sh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshr_sh) +TRANS_FEAT(SQRSHRU_sh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshru_sh) + +TRANS_FEAT(SQRSHR_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshr_sb) +TRANS_FEAT(SQRSHR_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshr_dh) +TRANS_FEAT(UQRSHR_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshr_sb) +TRANS_FEAT(UQRSHR_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshr_dh) +TRANS_FEAT(SQRSHRU_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshru_sb) +TRANS_FEAT(SQRSHRU_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshru_dh) + +TRANS_FEAT(SQRSHRN_sh, aa64_sme2_or_sve2p1, do_zz_rshr, a, gen_helper_sme2_sqrshrn_sh) +TRANS_FEAT(UQRSHRN_sh, aa64_sme2_or_sve2p1, do_zz_rshr, a, gen_helper_sme2_uqrshrn_sh) +TRANS_FEAT(SQRSHRUN_sh, aa64_sme2_or_sve2p1, do_zz_rshr, a, gen_helper_sme2_sqrshrun_sh) + +TRANS_FEAT(SQRSHRN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrn_sb) +TRANS_FEAT(SQRSHRN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrn_dh) +TRANS_FEAT(UQRSHRN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_sb) +TRANS_FEAT(UQRSHRN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_dh) +TRANS_FEAT(SQRSHRUN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_sb) +TRANS_FEAT(SQRSHRUN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_dh) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-66-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 12 +++++++ target/arm/tcg/sme.decode | 12 +++++++ target/arm/tcg/sme_helper.c | 62 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 40 ++++++++++++++++++++++ 4 files changed, 126 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sme2_uunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_zip2_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_zip2_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_zip2_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_zip2_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_zip2_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_uzp2_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uzp2_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uzp2_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uzp2_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uzp2_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(sme2_zip4_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_zip4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_zip4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ UQRSHRN_sb 11000001 011 ..... 110111 ...01 ..... @rshr_sb UQRSHRN_dh 11000001 1.1 ..... 110111 ...01 ..... @rshr_dh SQRSHRUN_sb 11000001 011 ..... 110111 ...10 ..... @rshr_sb SQRSHRUN_dh 11000001 1.1 ..... 110111 ...10 ..... @rshr_dh + +&zzz_e zd zn zm esz + +ZIP_2 11000001 esz:2 1 zm:5 110100 zn:5 .... 0 \ + &zzz_e zd=%zd_ax2 +ZIP_2 11000001 00 1 zm:5 110101 zn:5 .... 0 \ + &zzz_e zd=%zd_ax2 esz=4 + +UZP_2 11000001 esz:2 1 zm:5 110100 zn:5 .... 1 \ + &zzz_e zd=%zd_ax2 +UZP_2 11000001 00 1 zm:5 110101 zn:5 .... 1 \ + &zzz_e zd=%zd_ax2 esz=4 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(sme2_ucvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc) } } +#define ZIP2(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + ARMVectorReg scratch[2]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t pairs = oprsz / (sizeof(TYPE) * 2); \ + TYPE *n = vn, *m = vm; \ + if (vectors_overlap(vd, 2, vn, 1)) { \ + n = memcpy(&scratch[0], vn, oprsz); \ + } \ + if (vectors_overlap(vd, 2, vm, 1)) { \ + m = memcpy(&scratch[1], vm, oprsz); \ + } \ + for (size_t r = 0; r < 2; ++r) { \ + TYPE *d = vd + r * sizeof(ARMVectorReg); \ + size_t base = r * pairs; \ + for (size_t p = 0; p < pairs; ++p) { \ + d[H(2 * p + 0)] = n[base + H(p)]; \ + d[H(2 * p + 1)] = m[base + H(p)]; \ + } \ + } \ +} + +ZIP2(sme2_zip2_b, uint8_t, H1) +ZIP2(sme2_zip2_h, uint16_t, H2) +ZIP2(sme2_zip2_s, uint32_t, H4) +ZIP2(sme2_zip2_d, uint64_t, ) +ZIP2(sme2_zip2_q, Int128, ) + +#undef ZIP2 + #define ZIP4(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ ZIP4(sme2_zip4_q, Int128, ) #undef ZIP4 +#define UZP2(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + ARMVectorReg scratch[2]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t pairs = oprsz / (sizeof(TYPE) * 2); \ + TYPE *d0 = vd, *d1 = vd + sizeof(ARMVectorReg); \ + if (vectors_overlap(vd, 2, vn, 1)) { \ + vn = memcpy(&scratch[0], vn, oprsz); \ + } \ + if (vectors_overlap(vd, 2, vm, 1)) { \ + vm = memcpy(&scratch[1], vm, oprsz); \ + } \ + for (size_t r = 0; r < 2; ++r) { \ + TYPE *s = r ? vm : vn; \ + size_t base = r * pairs; \ + for (size_t p = 0; p < pairs; ++p) { \ + d0[base + H(p)] = s[H(2 * p + 0)]; \ + d1[base + H(p)] = s[H(2 * p + 1)]; \ + } \ + } \ +} + +UZP2(sme2_uzp2_b, uint8_t, H1) +UZP2(sme2_uzp2_h, uint16_t, H2) +UZP2(sme2_uzp2_s, uint32_t, H4) +UZP2(sme2_uzp2_d, uint64_t, ) +UZP2(sme2_uzp2_q, Int128, ) + +#undef UZP2 + #define UZP4(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ { \ 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 @@ TRANS_FEAT(UQRSHRN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_sb) TRANS_FEAT(UQRSHRN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_dh) TRANS_FEAT(SQRSHRUN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_sb) TRANS_FEAT(SQRSHRUN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_dh) + +static bool do_zipuzp_2(DisasContext *s, arg_zzz_e *a, + gen_helper_gvec_3 * const fn[5]) +{ + int bytes_per_op = 2 << a->esz; + + /* MO_128 can fail the size test. */ + if (s->max_svl < bytes_per_op) { + unallocated_encoding(s); + } else if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + if (svl < bytes_per_op) { + unallocated_encoding(s); + } else { + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + vec_full_reg_offset(s, a->zm), + svl, svl, 0, fn[a->esz]); + } + } + return true; +} + +static gen_helper_gvec_3 * const zip2_fns[] = { + gen_helper_sme2_zip2_b, + gen_helper_sme2_zip2_h, + gen_helper_sme2_zip2_s, + gen_helper_sme2_zip2_d, + gen_helper_sme2_zip2_q, +}; +TRANS_FEAT(ZIP_2, aa64_sme2, do_zipuzp_2, a, zip2_fns) + +static gen_helper_gvec_3 * const uzp2_fns[] = { + gen_helper_sme2_uzp2_b, + gen_helper_sme2_uzp2_h, + gen_helper_sme2_uzp2_s, + gen_helper_sme2_uzp2_d, + gen_helper_sme2_uzp2_q, +}; +TRANS_FEAT(UZP_2, aa64_sme2, do_zipuzp_2, a, uzp2_fns) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-67-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 15 +++++++ target/arm/tcg/sme.decode | 17 ++++++++ target/arm/tcg/sme_helper.c | 56 +++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 75 ++++++++++++++++++++++++++++++++++ 4 files changed, 163 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sme2_sqrshrun_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_sqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_uqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_sqrshrun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_sclamp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_sclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_sclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_sclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_uclamp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sme2_fclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sme2_fclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sme2_fclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sme2_bfclamp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ UZP_2 11000001 esz:2 1 zm:5 110100 zn:5 .... 1 \ &zzz_e zd=%zd_ax2 UZP_2 11000001 00 1 zm:5 110101 zn:5 .... 1 \ &zzz_e zd=%zd_ax2 esz=4 + +&zzz_en zd zn zm esz n + +FCLAMP 11000001 esz:2 1 zm:5 110000 zn:5 .... 0 \ + &zzz_en zd=%zd_ax2 n=2 +FCLAMP 11000001 esz:2 1 zm:5 110010 zn:5 ...0 0 \ + &zzz_en zd=%zd_ax4 n=4 + +SCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 0 \ + &zzz_en zd=%zd_ax2 n=2 +SCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 0 \ + &zzz_en zd=%zd_ax4 n=4 + +UCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 1 \ + &zzz_en zd=%zd_ax2 n=2 +UCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 1 \ + &zzz_en zd=%zd_ax4 n=4 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 @@ UZP4(sme2_uzp4_d, uint64_t, ) UZP4(sme2_uzp4_q, Int128, ) #undef UZP4 + +#define ICLAMP(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + size_t stride = sizeof(ARMVectorReg) / sizeof(TYPE); \ + size_t elements = simd_oprsz(desc) / sizeof(TYPE); \ + size_t nreg = simd_data(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + for (size_t e = 0; e < elements; e++) { \ + TYPE nn = n[H(e)], mm = m[H(e)]; \ + for (size_t r = 0; r < nreg; r++) { \ + TYPE *dd = &d[r * stride + H(e)]; \ + *dd = MIN(MAX(*dd, nn), mm); \ + } \ + } \ +} + +ICLAMP(sme2_sclamp_b, int8_t, H1) +ICLAMP(sme2_sclamp_h, int16_t, H2) +ICLAMP(sme2_sclamp_s, int32_t, H4) +ICLAMP(sme2_sclamp_d, int64_t, H8) + +ICLAMP(sme2_uclamp_b, uint8_t, H1) +ICLAMP(sme2_uclamp_h, uint16_t, H2) +ICLAMP(sme2_uclamp_s, uint32_t, H4) +ICLAMP(sme2_uclamp_d, uint64_t, H8) + +#undef ICLAMP + +/* + * Note the argument ordering to minnum and maxnum must match + * the ARM pseudocode so that NaNs are propagated properly. + */ +#define FCLAMP(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, \ + float_status *fpst, uint32_t desc) \ +{ \ + size_t stride = sizeof(ARMVectorReg) / sizeof(TYPE); \ + size_t elements = simd_oprsz(desc) / sizeof(TYPE); \ + size_t nreg = simd_data(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + for (size_t e = 0; e < elements; e++) { \ + TYPE nn = n[H(e)], mm = m[H(e)]; \ + for (size_t r = 0; r < nreg; r++) { \ + TYPE *dd = &d[r * stride + H(e)]; \ + *dd = TYPE##_minnum(TYPE##_maxnum(nn, *dd, fpst), mm, fpst); \ + } \ + } \ +} + +FCLAMP(sme2_fclamp_h, float16, H2) +FCLAMP(sme2_fclamp_s, float32, H4) +FCLAMP(sme2_fclamp_d, float64, H8) +FCLAMP(sme2_bfclamp, bfloat16, H2) + +#undef FCLAMP 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 gen_helper_gvec_3 * const uzp2_fns[] = { gen_helper_sme2_uzp2_q, }; TRANS_FEAT(UZP_2, aa64_sme2, do_zipuzp_2, a, uzp2_fns) + +static bool trans_FCLAMP(DisasContext *s, arg_zzz_en *a) +{ + static gen_helper_gvec_3_ptr * const fn[] = { + gen_helper_sme2_bfclamp, + gen_helper_sme2_fclamp_h, + gen_helper_sme2_fclamp_s, + gen_helper_sme2_fclamp_d, + }; + TCGv_ptr fpst; + int vl; + + if (!dc_isar_feature(aa64_sme2, s)) { + return false; + } + /* This insn uses MO_8 to encode BFloat16. */ + if (a->esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) { + return false; + } + if (!sme_sm_enabled_check(s)) { + return true; + } + + fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); + vl = vec_full_reg_size(s); + + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + vec_full_reg_offset(s, a->zm), + fpst, vl, vl, a->n, fn[a->esz]); + return true; +} + +static bool do_clamp(DisasContext *s, arg_zzz_en *a, + gen_helper_gvec_3 * const fn[4]) +{ + int vl; + + if (!dc_isar_feature(aa64_sme2, s)) { + return false; + } + if (!sme_sm_enabled_check(s)) { + return true; + } + + /* + * Clamp is just a min+max, easily supported by most host + * vector operations -- we already have such an expansion in + * translate-sve.c for a single output. + * TODO: Add support in gvec for multiple simultaneous output, + * and/or copy to temporary upon overlap. + */ + vl = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + vec_full_reg_offset(s, a->zm), + vl, vl, a->n, fn[a->esz]); + return true; +} + +static gen_helper_gvec_3 * const sclamp_fns[] = { + gen_helper_sme2_sclamp_b, + gen_helper_sme2_sclamp_h, + gen_helper_sme2_sclamp_s, + gen_helper_sme2_sclamp_d, +}; +TRANS(SCLAMP, do_clamp, a, sclamp_fns) + +static gen_helper_gvec_3 * const uclamp_fns[] = { + gen_helper_sme2_uclamp_b, + gen_helper_sme2_uclamp_h, + gen_helper_sme2_uclamp_s, + gen_helper_sme2_uclamp_d, +}; +TRANS(UCLAMP, do_clamp, a, uclamp_fns) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> These instructions are present in both SME(1) and SVE2.1 extensions. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-68-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-sve.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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 void gen_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); } -TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a) +TRANS_FEAT(SCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_sclamp, a) static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a) { @@ -XXX,XX +XXX,XX @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); } -TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a) +TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a) TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> This is the single vector version within SVE decode space. Tested-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-69-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 2 ++ target/arm/tcg/translate-sve.c | 22 ++++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \ SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm + +FCLAMP 01100100 .. 1 ..... 001001 ..... ..... @rda_rn_rm 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 void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a) +static bool trans_FCLAMP(DisasContext *s, arg_FCLAMP *a) +{ + static gen_helper_gvec_3_ptr * const fn[] = { + gen_helper_sme2_bfclamp, + gen_helper_sme2_fclamp_h, + gen_helper_sme2_fclamp_s, + gen_helper_sme2_fclamp_d, + }; + + /* This insn uses MO_8 to encode BFloat16. */ + if (a->esz == MO_8 + ? !dc_isar_feature(aa64_sve_b16b16, s) + : !dc_isar_feature(aa64_sme2_or_sve2p1, s)) { + return false; + } + + /* So far we never optimize rda with MOVPRFX */ + assert(a->rd == a->ra); + return gen_gvec_fpst_zzz(s, fn[a->esz], a->rd, a->rn, a->rm, 1, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); +} + TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0) TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-70-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sme.decode | 23 +++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 20 ++++++++++++++++++++ 2 files changed, 43 insertions(+) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ UCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 1 \ &zzz_en zd=%zd_ax2 n=2 UCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 1 \ &zzz_en zd=%zd_ax4 n=4 + +### SME Multiple Zero + +&zero_za rv off ngrp nvec + +ZERO_za 11000000 000011 000 .. 0000000000 off:3 \ + &zero_za ngrp=2 nvec=1 rv=%mova_rv +ZERO_za 11000000 000011 100 .. 0000000000 off:3 \ + &zero_za ngrp=4 nvec=1 rv=%mova_rv + +ZERO_za 11000000 000011 001 .. 0000000000 ... \ + &zero_za ngrp=1 nvec=2 rv=%mova_rv off=%off3_x2 +ZERO_za 11000000 000011 010 .. 0000000000 0.. \ + &zero_za ngrp=2 nvec=2 rv=%mova_rv off=%off2_x2 +ZERO_za 11000000 000011 011 .. 0000000000 0.. \ + &zero_za ngrp=4 nvec=2 rv=%mova_rv off=%off2_x2 + +ZERO_za 11000000 000011 101 .. 0000000000 0.. \ + &zero_za ngrp=1 nvec=4 rv=%mova_rv off=%off2_x4 +ZERO_za 11000000 000011 110 .. 0000000000 00. \ + &zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4 +ZERO_za 11000000 000011 111 .. 0000000000 00. \ + &zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4 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 trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a) return true; } +static bool trans_ZERO_za(DisasContext *s, arg_ZERO_za *a) +{ + if (!dc_isar_feature(aa64_sme2p1, s)) { + return false; + } + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / a->ngrp; + TCGv_ptr t_za = get_zarray(s, a->rv, a->off, a->ngrp, a->nvec); + + for (int r = 0; r < a->ngrp; ++r) { + for (int i = 0; i < a->nvec; ++i) { + int o_za = (r * vstride + i) * sizeof(ARMVectorReg); + tcg_gen_gvec_dup_imm_var(MO_64, t_za, o_za, svl, svl, 0); + } + } + } + return true; +} + static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec) { static gen_helper_gvec_4 * const h_fns[5] = { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> For WHILE, we have the count of enabled predicates, so we don't need to search to compute the PredTest result. Reuse the logic that will shortly be required for counted predicates. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250704142112.1018902-71-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve_helper.c | 81 +++++++++++++++++++++---------------- 1 file changed, 46 insertions(+), 35 deletions(-) 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 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) return sum; } +/* C.f. Arm pseudocode PredCountTest */ +static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert) +{ + uint32_t flags; + + if (count == 0) { + flags = 1; /* !N, Z, C */ + } else if (!invert) { + flags = (1u << 31) | 2; /* N, !Z */ + flags |= count != elements; /* C */ + } else { + flags = 2; /* !Z, !C */ + flags |= (count == elements) << 31; /* N */ + } + return flags; +} + uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) { intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); uint64_t esz_mask = pred_esz_masks[esz]; ARMPredicateReg *d = vd; - uint32_t flags; - intptr_t i; + intptr_t i, oprbits = oprsz * 8; + + tcg_debug_assert(count <= oprbits); /* Begin with a zero predicate register. */ - flags = do_zero(d, oprsz); - if (count == 0) { - return flags; + do_zero(d, oprsz); + if (count) { + /* Set all of the requested bits. */ + for (i = 0; i < count / 64; ++i) { + d->p[i] = esz_mask; + } + if (count & 63) { + d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask; + } } - /* Set all of the requested bits. */ - for (i = 0; i < count / 64; ++i) { - d->p[i] = esz_mask; - } - if (count & 63) { - d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask; - } - - return predtest_ones(d, oprsz, esz_mask); + return pred_count_test(oprbits, count, false); } uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); uint64_t esz_mask = pred_esz_masks[esz]; ARMPredicateReg *d = vd; - intptr_t i, invcount, oprbits; + intptr_t i, invcount, oprbits = oprsz * 8; uint64_t bits; - if (count == 0) { - return do_zero(d, oprsz); - } - - oprbits = oprsz * 8; tcg_debug_assert(count <= oprbits); - bits = esz_mask; - if (oprbits & 63) { - bits &= MAKE_64BIT_MASK(0, oprbits & 63); - } - - invcount = oprbits - count; - for (i = (oprsz - 1) / 8; i > invcount / 64; --i) { - d->p[i] = bits; + /* Begin with a zero predicate register. */ + do_zero(d, oprsz); + if (count) { + /* Set all of the requested bits. */ bits = esz_mask; + if (oprbits & 63) { + bits &= MAKE_64BIT_MASK(0, oprbits & 63); + } + + invcount = oprbits - count; + for (i = (oprsz - 1) / 8; i > invcount / 64; --i) { + d->p[i] = bits; + bits = esz_mask; + } + d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64); } - d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64); - - while (--i >= 0) { - d->p[i] = 0; - } - - return predtest_ones(d, oprsz, esz_mask); + return pred_count_test(oprbits, count, true); } /* Recursive reduction on a function; -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Merge predtest_ones into its only caller. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-72-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve_helper.c | 34 ++++++++++++++-------------------- 1 file changed, 14 insertions(+), 20 deletions(-) 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 @@ void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc) } } -/* As if PredTest(Ones(PL), D, esz). */ -static uint32_t predtest_ones(ARMPredicateReg *d, intptr_t oprsz, - uint64_t esz_mask) -{ - uint32_t flags = PREDTEST_INIT; - intptr_t i; - - for (i = 0; i < oprsz / 8; i++) { - flags = iter_predtest_fwd(d->p[i], esz_mask, flags); - } - if (oprsz & 7) { - uint64_t mask = ~(-1ULL << (8 * (oprsz & 7))); - flags = iter_predtest_fwd(d->p[i], esz_mask & mask, flags); - } - return flags; -} - uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc) { intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (last_active_pred(vn, vg, oprsz)) { - return predtest_ones(vd, oprsz, -1); - } else { - return do_zero(vd, oprsz); + ARMPredicateReg *d = vd; + uint32_t flags = PREDTEST_INIT; + intptr_t i; + + /* As if PredTest(Ones(PL), D, MO_8). */ + for (i = 0; i < oprsz / 8; i++) { + flags = iter_predtest_fwd(d->p[i], -1, flags); + } + if (oprsz & 7) { + uint64_t mask = ~(-1ULL << (8 * (oprsz & 7))); + flags = iter_predtest_fwd(d->p[i], mask, flags); + } + return flags; } + return do_zero(vd, oprsz); } uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Expand to memset plus the return value, when used. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250704142112.1018902-73-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve_helper.c | 28 +++++++++++----------------- 1 file changed, 11 insertions(+), 17 deletions(-) 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 uint32_t compute_brks_m(uint64_t *d, uint64_t *n, uint64_t *g, return flags; } -static uint32_t do_zero(ARMPredicateReg *d, intptr_t oprsz) -{ - /* It is quicker to zero the whole predicate than loop on OPRSZ. - * The compiler should turn this into 4 64-bit integer stores. - */ - memset(d, 0, sizeof(ARMPredicateReg)); - return PREDTEST_INIT; -} - void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg, uint32_t pred_desc) { @@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg, if (last_active_pred(vn, vg, oprsz)) { compute_brk_z(vd, vm, vg, oprsz, true); } else { - do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); } } @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkpas)(void *vd, void *vn, void *vm, void *vg, if (last_active_pred(vn, vg, oprsz)) { return compute_brks_z(vd, vm, vg, oprsz, true); } else { - return do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); + return PREDTEST_INIT; } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkpb)(void *vd, void *vn, void *vm, void *vg, if (last_active_pred(vn, vg, oprsz)) { compute_brk_z(vd, vm, vg, oprsz, false); } else { - do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); } } @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkpbs)(void *vd, void *vn, void *vm, void *vg, if (last_active_pred(vn, vg, oprsz)) { return compute_brks_z(vd, vm, vg, oprsz, false); } else { - return do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); + return PREDTEST_INIT; } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc) { intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (!last_active_pred(vn, vg, oprsz)) { - do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); } } @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc) } return flags; } - return do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); + return PREDTEST_INIT; } uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) tcg_debug_assert(count <= oprbits); /* Begin with a zero predicate register. */ - do_zero(d, oprsz); + memset(d, 0, sizeof(*d)); if (count) { /* Set all of the requested bits. */ for (i = 0; i < count / 64; ++i) { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) tcg_debug_assert(count <= oprbits); /* Begin with a zero predicate register. */ - do_zero(d, oprsz); + memset(d, 0, sizeof(*d)); if (count) { /* Set all of the requested bits. */ bits = esz_mask; -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-74-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve_helper.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) 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 uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert) return flags; } -uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) +/* D must be cleared on entry. */ +static void do_whilel(ARMPredicateReg *d, uint64_t esz_mask, + uint32_t count, uint32_t oprbits) { - intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); - intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); - uint64_t esz_mask = pred_esz_masks[esz]; - ARMPredicateReg *d = vd; - intptr_t i, oprbits = oprsz * 8; - tcg_debug_assert(count <= oprbits); - - /* Begin with a zero predicate register. */ - memset(d, 0, sizeof(*d)); if (count) { + uint32_t i; + /* Set all of the requested bits. */ for (i = 0; i < count / 64; ++i) { d->p[i] = esz_mask; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask; } } +} +uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t oprbits = oprsz * 8; + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; + + memset(d, 0, sizeof(*d)); + do_whilel(d, esz_mask, count, oprbits); return pred_count_test(oprbits, count, false); } -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250704142112.1018902-75-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve_helper.c | 39 +++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 19 deletions(-) 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 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) return pred_count_test(oprbits, count, false); } -uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) +/* D must be cleared on entry. */ +static void do_whileg(ARMPredicateReg *d, uint64_t esz_mask, + uint32_t count, uint32_t oprbits) { - intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); - intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); - uint64_t esz_mask = pred_esz_masks[esz]; - ARMPredicateReg *d = vd; - intptr_t i, invcount, oprbits = oprsz * 8; - uint64_t bits; - tcg_debug_assert(count <= oprbits); - - /* Begin with a zero predicate register. */ - memset(d, 0, sizeof(*d)); if (count) { - /* Set all of the requested bits. */ - bits = esz_mask; - if (oprbits & 63) { - bits &= MAKE_64BIT_MASK(0, oprbits & 63); - } + uint32_t i, invcount = oprbits - count; + uint64_t bits = esz_mask & MAKE_64BIT_MASK(invcount & 63, 64); - invcount = oprbits - count; - for (i = (oprsz - 1) / 8; i > invcount / 64; --i) { + for (i = invcount / 64; i < oprbits / 64; ++i) { d->p[i] = bits; bits = esz_mask; } - d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64); + if (oprbits & 63) { + d->p[i] = bits & MAKE_64BIT_MASK(0, oprbits & 63); + } } +} +uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t oprbits = oprsz * 8; + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; + + memset(d, 0, sizeof(*d)); + do_whileg(d, esz_mask, count, oprbits); return pred_count_test(oprbits, count, true); } -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Change the API to pass element count rather than bit count. This will be helpful later for predicate as counter. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-76-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve_helper.c | 2 ++ target/arm/tcg/translate-sve.c | 13 +++++-------- 2 files changed, 7 insertions(+), 8 deletions(-) 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 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) uint64_t esz_mask = pred_esz_masks[esz]; ARMPredicateReg *d = vd; + count <<= esz; memset(d, 0, sizeof(*d)); do_whilel(d, esz_mask, count, oprbits); return pred_count_test(oprbits, count, false); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) uint64_t esz_mask = pred_esz_masks[esz]; ARMPredicateReg *d = vd; + count <<= esz; memset(d, 0, sizeof(*d)); do_whileg(d, esz_mask, count, oprbits); return pred_count_test(oprbits, count, true); 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 trans_WHILE(DisasContext *s, arg_WHILE *a) t2 = tcg_temp_new_i32(); tcg_gen_extrl_i64_i32(t2, t0); - /* Scale elements to bits. */ - tcg_gen_shli_i32(t2, t2, a->esz); - desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8); desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) op0 = read_cpu_reg(s, a->rn, 1); op1 = read_cpu_reg(s, a->rm, 1); - tmax = tcg_constant_i64(vsz); + tmax = tcg_constant_i64(vsz >> a->esz); diff = tcg_temp_new_i64(); if (a->rw) { @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) tcg_gen_sub_i64(diff, op0, op1); tcg_gen_sub_i64(t1, op1, op0); tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, diff, t1); - /* Round down to a multiple of ESIZE. */ - tcg_gen_andi_i64(diff, diff, -1 << a->esz); + /* Divide, rounding down, by ESIZE. */ + tcg_gen_shri_i64(diff, diff, a->esz); /* If op1 == op0, diff == 0, and the condition is always true. */ tcg_gen_movcond_i64(TCG_COND_EQ, diff, op0, op1, tmax, diff); } else { /* WHILEWR */ tcg_gen_sub_i64(diff, op1, op0); - /* Round down to a multiple of ESIZE. */ - tcg_gen_andi_i64(diff, diff, -1 << a->esz); + /* Divide, rounding down, by ESIZE. */ + tcg_gen_shri_i64(diff, diff, a->esz); /* If op0 >= op1, diff <= 0, the condition is always true. */ tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, tmax, diff); } -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Use TRANS_FEAT to select the correct predicate. Pass the helper and a boolean to do_WHILE. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-77-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 4 +++- target/arm/tcg/translate-sve.c | 23 +++++++++-------------- 2 files changed, 12 insertions(+), 15 deletions(-) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000 # SVE integer compare scalar count and limit -WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4 +&while esz rd rn rm sf u eq +WHILE_lt 00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4 &while +WHILE_gt 00100101 esz:2 1 rm:5 000 sf:1 u:1 0 rn:5 eq:1 rd:4 &while # SVE2 pointer conflict compare WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4 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 trans_CTERM(DisasContext *s, arg_CTERM *a) return true; } -static bool trans_WHILE(DisasContext *s, arg_WHILE *a) +typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); +static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn) { TCGv_i64 op0, op1, t0, t1, tmax; TCGv_i32 t2; @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) TCGCond cond; uint64_t maxval; /* Note that GE/HS has a->eq == 0 and GT/HI has a->eq == 1. */ - bool eq = a->eq == a->lt; + bool eq = a->eq == lt; - /* The greater-than conditions are all SVE2. */ - if (a->lt - ? !dc_isar_feature(aa64_sve, s) - : !dc_isar_feature(aa64_sve2, s)) { - return false; - } if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) t0 = tcg_temp_new_i64(); t1 = tcg_temp_new_i64(); - if (a->lt) { + if (lt) { tcg_gen_sub_i64(t0, op1, op0); if (a->u) { maxval = a->sf ? UINT64_MAX : UINT32_MAX; @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) ptr = tcg_temp_new_ptr(); tcg_gen_addi_ptr(ptr, tcg_env, pred_full_reg_offset(s, a->rd)); - if (a->lt) { - gen_helper_sve_whilel(t2, ptr, t2, tcg_constant_i32(desc)); - } else { - gen_helper_sve_whileg(t2, ptr, t2, tcg_constant_i32(desc)); - } + fn(t2, ptr, t2, tcg_constant_i32(desc)); + do_pred_flags(t2); return true; } +TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, gen_helper_sve_whilel) +TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, gen_helper_sve_whileg) + static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) { TCGv_i64 op0, op1, diff, t1, tmax; -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-78-richard.henderson@linaro.org This instruction is present in both SME(1) and SVE2.1 extensions. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-sve.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 trans_PSEL(DisasContext *s, arg_psel *a) TCGv_i64 tmp, didx, dbit; TCGv_ptr ptr; - if (!dc_isar_feature(aa64_sme, s)) { + if (!dc_isar_feature(aa64_sme_or_sve2p1, s)) { return false; } if (!sve_access_check(s)) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-79-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 3 +++ target/arm/tcg/sve.decode | 8 +++++++ target/arm/tcg/sve_helper.c | 40 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sve.c | 14 ++++++++---- 4 files changed, 61 insertions(+), 4 deletions(-) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_while2l, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_while2g, TCG_CALL_NO_RWG, i32, ptr, i32, i32) + DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ WHILE_gt 00100101 esz:2 1 rm:5 000 sf:1 u:1 0 rn:5 eq:1 rd:4 &while # SVE2 pointer conflict compare WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4 +# SVE2.1 predicate pair +%pd_pair 1:3 !function=times_2 +@while_pair ........ esz:2 . rm:5 .... u:1 . rn:5 . ... eq:1 \ + &while rd=%pd_pair sf=1 + +WHILE_lt_pair 00100101 .. 1 ..... 0101 . 1 ..... 1 ... . @while_pair +WHILE_gt_pair 00100101 .. 1 ..... 0101 . 0 ..... 1 ... . @while_pair + ### SVE Integer Wide Immediate - Unpredicated Group # SVE broadcast floating-point immediate (unpredicated) 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 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) return pred_count_test(oprbits, count, false); } +uint32_t HELPER(sve_while2l)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t oprbits = oprsz * 8; + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; + + count <<= esz; + memset(d, 0, 2 * sizeof(*d)); + if (count <= oprbits) { + do_whilel(&d[0], esz_mask, count, oprbits); + } else { + do_whilel(&d[0], esz_mask, oprbits, oprbits); + do_whilel(&d[1], esz_mask, count - oprbits, oprbits); + } + + return pred_count_test(2 * oprbits, count, false); +} + /* D must be cleared on entry. */ static void do_whileg(ARMPredicateReg *d, uint64_t esz_mask, uint32_t count, uint32_t oprbits) @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) return pred_count_test(oprbits, count, true); } +uint32_t HELPER(sve_while2g)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t oprbits = oprsz * 8; + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; + + count <<= esz; + memset(d, 0, 2 * sizeof(*d)); + if (count <= oprbits) { + do_whileg(&d[1], esz_mask, count, oprbits); + } else { + do_whilel(&d[1], esz_mask, oprbits, oprbits); + do_whileg(&d[0], esz_mask, count - oprbits, oprbits); + } + + return pred_count_test(2 * oprbits, count, true); +} + /* Recursive reduction on a function; * C.f. the ARM ARM function ReducePredicated. * 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 trans_CTERM(DisasContext *s, arg_CTERM *a) } typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); -static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn) +static bool do_WHILE(DisasContext *s, arg_while *a, + bool lt, int scale, gen_while_fn *fn) { TCGv_i64 op0, op1, t0, t1, tmax; TCGv_i32 t2; @@ -XXX,XX +XXX,XX @@ static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn) } } - tmax = tcg_constant_i64(vsz >> a->esz); + tmax = tcg_constant_i64((vsz << scale) >> a->esz); if (eq) { /* Equality means one more iteration. */ tcg_gen_addi_i64(t0, t0, 1); @@ -XXX,XX +XXX,XX @@ static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn) return true; } -TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, gen_helper_sve_whilel) -TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, gen_helper_sve_whileg) +TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, 0, gen_helper_sve_whilel) +TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, 0, gen_helper_sve_whileg) + +TRANS_FEAT(WHILE_lt_pair, aa64_sme2_or_sve2p1, do_WHILE, + a, true, 1, gen_helper_sve_while2l) +TRANS_FEAT(WHILE_gt_pair, aa64_sme2_or_sve2p1, do_WHILE, + a, false, 1, gen_helper_sve_while2g) static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-80-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 3 ++ target/arm/tcg/sve.decode | 11 +++++++ target/arm/tcg/sve_helper.c | 53 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sve.c | 22 ++++++++++---- 4 files changed, 84 insertions(+), 5 deletions(-) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_3(sve_while2l, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_3(sve_while2g, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whilecl, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whilecg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) + DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ %rn_ax2 6:4 !function=times_2 +%pnd 0:3 !function=plus_8 + ########################################################################### # Named attribute sets. These are used to make nice(er) names # when creating helpers common to those for the individual @@ -XXX,XX +XXX,XX @@ WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4 WHILE_lt_pair 00100101 .. 1 ..... 0101 . 1 ..... 1 ... . @while_pair WHILE_gt_pair 00100101 .. 1 ..... 0101 . 0 ..... 1 ... . @while_pair +# SVE2.1 predicate as count +@while_cnt ........ esz:2 . rm:5 .... u:1 . rn:5 . eq:1 ... \ + &while rd=%pnd sf=1 + +WHILE_lt_cnt2 00100101 .. 1 ..... 0100 . 1 ..... 1 . ... @while_cnt +WHILE_lt_cnt4 00100101 .. 1 ..... 0110 . 1 ..... 1 . ... @while_cnt +WHILE_gt_cnt2 00100101 .. 1 ..... 0100 . 0 ..... 1 . ... @while_cnt +WHILE_gt_cnt4 00100101 .. 1 ..... 0110 . 0 ..... 1 . ... @while_cnt + ### SVE Integer Wide Immediate - Unpredicated Group # SVE broadcast floating-point immediate (unpredicated) 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 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) return sum; } +/* C.f. Arm pseudocode EncodePredCount */ +static uint64_t encode_pred_count(uint32_t elements, uint32_t count, + uint32_t esz, bool invert) +{ + uint32_t pred; + + if (count == 0) { + return 0; + } + if (invert) { + count = elements - count; + } else if (count == elements) { + count = 0; + invert = true; + } + + pred = (count << 1) | 1; + pred <<= esz; + pred |= invert << 15; + + return pred; +} + /* C.f. Arm pseudocode PredCountTest */ static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert) { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_while2l)(void *vd, uint32_t count, uint32_t pred_desc) return pred_count_test(2 * oprbits, count, false); } +uint32_t HELPER(sve_whilecl)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t pl = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t scale = FIELD_EX32(pred_desc, PREDDESC, DATA); + uint32_t vl = pl * 8; + uint32_t elements = (vl >> esz) << scale; + ARMPredicateReg *d = vd; + + *d = (ARMPredicateReg) { + .p[0] = encode_pred_count(elements, count, esz, false) + }; + return pred_count_test(elements, count, false); +} + /* D must be cleared on entry. */ static void do_whileg(ARMPredicateReg *d, uint64_t esz_mask, uint32_t count, uint32_t oprbits) @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_while2g)(void *vd, uint32_t count, uint32_t pred_desc) return pred_count_test(2 * oprbits, count, true); } +uint32_t HELPER(sve_whilecg)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t pl = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t scale = FIELD_EX32(pred_desc, PREDDESC, DATA); + uint32_t vl = pl * 8; + uint32_t elements = (vl >> esz) << scale; + ARMPredicateReg *d = vd; + + *d = (ARMPredicateReg) { + .p[0] = encode_pred_count(elements, count, esz, true) + }; + return pred_count_test(elements, count, true); +} + /* Recursive reduction on a function; * C.f. the ARM ARM function ReducePredicated. * 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 trans_CTERM(DisasContext *s, arg_CTERM *a) typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); static bool do_WHILE(DisasContext *s, arg_while *a, - bool lt, int scale, gen_while_fn *fn) + bool lt, int scale, int data, gen_while_fn *fn) { TCGv_i64 op0, op1, t0, t1, tmax; TCGv_i32 t2; @@ -XXX,XX +XXX,XX @@ static bool do_WHILE(DisasContext *s, arg_while *a, desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8); desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); + desc = FIELD_DP32(desc, PREDDESC, DATA, data); ptr = tcg_temp_new_ptr(); tcg_gen_addi_ptr(ptr, tcg_env, pred_full_reg_offset(s, a->rd)); @@ -XXX,XX +XXX,XX @@ static bool do_WHILE(DisasContext *s, arg_while *a, return true; } -TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, 0, gen_helper_sve_whilel) -TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, 0, gen_helper_sve_whileg) +TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, + a, true, 0, 0, gen_helper_sve_whilel) +TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, + a, false, 0, 0, gen_helper_sve_whileg) TRANS_FEAT(WHILE_lt_pair, aa64_sme2_or_sve2p1, do_WHILE, - a, true, 1, gen_helper_sve_while2l) + a, true, 1, 0, gen_helper_sve_while2l) TRANS_FEAT(WHILE_gt_pair, aa64_sme2_or_sve2p1, do_WHILE, - a, false, 1, gen_helper_sve_while2g) + a, false, 1, 0, gen_helper_sve_while2g) + +TRANS_FEAT(WHILE_lt_cnt2, aa64_sme2_or_sve2p1, do_WHILE, + a, true, 1, 1, gen_helper_sve_whilecl) +TRANS_FEAT(WHILE_lt_cnt4, aa64_sme2_or_sve2p1, do_WHILE, + a, true, 2, 2, gen_helper_sve_whilecl) +TRANS_FEAT(WHILE_gt_cnt2, aa64_sme2_or_sve2p1, do_WHILE, + a, false, 1, 1, gen_helper_sve_whilecg) +TRANS_FEAT(WHILE_gt_cnt4, aa64_sme2_or_sve2p1, do_WHILE, + a, false, 2, 2, gen_helper_sve_whilecg) static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-81-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 1 + target/arm/tcg/translate-sve.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ PTEST 00100101 01 010000 11 pg:4 0 rn:4 0 0000 # SVE predicate initialize PTRUE 00100101 esz:2 01100 s:1 111000 pat:5 0 rd:4 +PTRUE_cnt 00100101 esz:2 1000000111100000010 ... rd=%pnd # SVE initialize FFR SETFFR 00100101 0010 1100 1001 0000 0000 0000 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 do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag) TRANS_FEAT(PTRUE, aa64_sve, do_predset, a->esz, a->rd, a->pat, a->s) +static bool trans_PTRUE_cnt(DisasContext *s, arg_PTRUE_cnt *a) +{ + if (!dc_isar_feature(aa64_sme2_or_sve2p1, s)) { + return false; + } + if (sve_access_check(s)) { + /* Canonical TRUE is 0 count, invert bit, plus element size. */ + int val = (1 << 15) | (1 << a->esz); + + /* Write val to the first uint64_t; clear all of the rest. */ + tcg_gen_gvec_dup_imm(MO_64, pred_full_reg_offset(s, a->rd), + 8, size_for_gvec(pred_full_reg_size(s)), val); + } + return true; +} + /* Note pat == 31 is #all, to set all elements. */ TRANS_FEAT_NONSTREAMING(SETFFR, aa64_sve, do_predset, 0, FFR_PRED_NUM, 31, false) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-82-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 25 ++++++++++++++++++ target/arm/tcg/sve.decode | 7 ++++++ target/arm/tcg/sve_helper.c | 46 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sve.c | 35 ++++++++++++++++++++++++++ 4 files changed, 113 insertions(+) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_sqshlu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqshlu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqshlu_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqshlu_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_addqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_addqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_addqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_addqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_smaxqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_smaxqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_smaxqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_smaxqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_sminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_sminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_sminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_sminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_umaxqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_umaxqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_umaxqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_umaxqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_uminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ UMAXV 00000100 .. 001 001 001 ... ..... ..... @rd_pg_rn SMINV 00000100 .. 001 010 001 ... ..... ..... @rd_pg_rn UMINV 00000100 .. 001 011 001 ... ..... ..... @rd_pg_rn +# SVE2.1 segment reduction +ADDQV 00000100 .. 000 101 001 ... ..... ..... @rd_pg_rn +SMAXQV 00000100 .. 001 100 001 ... ..... ..... @rd_pg_rn +SMINQV 00000100 .. 001 110 001 ... ..... ..... @rd_pg_rn +UMAXQV 00000100 .. 001 101 001 ... ..... ..... @rd_pg_rn +UMINQV 00000100 .. 001 111 001 ... ..... ..... @rd_pg_rn + ### SVE Shift by Immediate - Predicated Group # SVE bitwise shift by immediate (predicated) 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 @@ DO_VPZ_D(sve_uminv_d, uint64_t, uint64_t, -1, DO_MIN) #undef DO_VPZ #undef DO_VPZ_D +#define DO_VPQ(NAME, TYPE, H, INIT, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \ +{ \ + TYPE tmp[16 / sizeof(TYPE)] = { [0 ... 16 / sizeof(TYPE) - 1] = INIT }; \ + TYPE *n = vn; uint16_t *g = vg; \ + uintptr_t oprsz = simd_oprsz(desc); \ + uintptr_t nseg = oprsz / 16, nsegelt = 16 / sizeof(TYPE); \ + for (uintptr_t s = 0; s < nseg; s++) { \ + uint16_t pg = g[H2(s)]; \ + for (uintptr_t e = 0; e < nsegelt; e++, pg >>= sizeof(TYPE)) { \ + if (pg & 1) { \ + tmp[e] = OP(tmp[H(e)], n[s * nsegelt + H(e)]); \ + } \ + } \ + } \ + memcpy(vd, tmp, 16); \ + clear_tail(vd, 16, simd_maxsz(desc)); \ +} + +DO_VPQ(sve2p1_addqv_b, uint8_t, H1, 0, DO_ADD) +DO_VPQ(sve2p1_addqv_h, uint16_t, H2, 0, DO_ADD) +DO_VPQ(sve2p1_addqv_s, uint32_t, H4, 0, DO_ADD) +DO_VPQ(sve2p1_addqv_d, uint64_t, H8, 0, DO_ADD) + +DO_VPQ(sve2p1_smaxqv_b, int8_t, H1, INT8_MIN, DO_MAX) +DO_VPQ(sve2p1_smaxqv_h, int16_t, H2, INT16_MIN, DO_MAX) +DO_VPQ(sve2p1_smaxqv_s, int32_t, H4, INT32_MIN, DO_MAX) +DO_VPQ(sve2p1_smaxqv_d, int64_t, H8, INT64_MIN, DO_MAX) + +DO_VPQ(sve2p1_sminqv_b, int8_t, H1, INT8_MAX, DO_MIN) +DO_VPQ(sve2p1_sminqv_h, int16_t, H2, INT16_MAX, DO_MIN) +DO_VPQ(sve2p1_sminqv_s, int32_t, H4, INT32_MAX, DO_MIN) +DO_VPQ(sve2p1_sminqv_d, int64_t, H8, INT64_MAX, DO_MIN) + +DO_VPQ(sve2p1_umaxqv_b, uint8_t, H1, 0, DO_MAX) +DO_VPQ(sve2p1_umaxqv_h, uint16_t, H2, 0, DO_MAX) +DO_VPQ(sve2p1_umaxqv_s, uint32_t, H4, 0, DO_MAX) +DO_VPQ(sve2p1_umaxqv_d, uint64_t, H8, 0, DO_MAX) + +DO_VPQ(sve2p1_uminqv_b, uint8_t, H1, -1, DO_MIN) +DO_VPQ(sve2p1_uminqv_h, uint16_t, H2, -1, DO_MIN) +DO_VPQ(sve2p1_uminqv_s, uint32_t, H4, -1, DO_MIN) +DO_VPQ(sve2p1_uminqv_d, uint64_t, H8, -1, DO_MIN) + +#undef DO_VPQ + /* Two vector operand, one scalar operand, unpredicated. */ #define DO_ZZI(NAME, TYPE, OP) \ void HELPER(NAME)(void *vd, void *vn, uint64_t s64, uint32_t desc) \ 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(SXTW, aa64_sve, gen_gvec_ool_arg_zpz, TRANS_FEAT(UXTW, aa64_sve, gen_gvec_ool_arg_zpz, a->esz == 3 ? gen_helper_sve_uxtw_d : NULL, a, 0) +static gen_helper_gvec_3 * const addqv_fns[4] = { + gen_helper_sve2p1_addqv_b, gen_helper_sve2p1_addqv_h, + gen_helper_sve2p1_addqv_s, gen_helper_sve2p1_addqv_d, +}; +TRANS_FEAT(ADDQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, addqv_fns[a->esz], a, 0) + +static gen_helper_gvec_3 * const smaxqv_fns[4] = { + gen_helper_sve2p1_smaxqv_b, gen_helper_sve2p1_smaxqv_h, + gen_helper_sve2p1_smaxqv_s, gen_helper_sve2p1_smaxqv_d, +}; +TRANS_FEAT(SMAXQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, smaxqv_fns[a->esz], a, 0) + +static gen_helper_gvec_3 * const sminqv_fns[4] = { + gen_helper_sve2p1_sminqv_b, gen_helper_sve2p1_sminqv_h, + gen_helper_sve2p1_sminqv_s, gen_helper_sve2p1_sminqv_d, +}; +TRANS_FEAT(SMINQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, sminqv_fns[a->esz], a, 0) + +static gen_helper_gvec_3 * const umaxqv_fns[4] = { + gen_helper_sve2p1_umaxqv_b, gen_helper_sve2p1_umaxqv_h, + gen_helper_sve2p1_umaxqv_s, gen_helper_sve2p1_umaxqv_d, +}; +TRANS_FEAT(UMAXQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, umaxqv_fns[a->esz], a, 0) + +static gen_helper_gvec_3 * const uminqv_fns[4] = { + gen_helper_sve2p1_uminqv_b, gen_helper_sve2p1_uminqv_h, + gen_helper_sve2p1_uminqv_s, gen_helper_sve2p1_uminqv_d, +}; +TRANS_FEAT(UMINQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, uminqv_fns[a->esz], a, 0) + /* *** SVE Integer Reduction Group */ -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-83-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 2 + target/arm/tcg/vec_internal.h | 74 ++++++++++++++++++++++++++++++++++ target/arm/tcg/sve.decode | 6 +++ target/arm/tcg/sve_helper.c | 28 +++++++++++++ target/arm/tcg/translate-sve.c | 36 +++++++++++++++++ 5 files changed, 146 insertions(+) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2p1_uminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2p1_uminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2p1_uminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2p1_uminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(pext, TCG_CALL_NO_RWG, void, ptr, i32, i32) diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_internal.h +++ b/target/arm/tcg/vec_internal.h @@ -XXX,XX +XXX,XX @@ bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst); float32 sve_f16_to_f32(float16 f, float_status *fpst); float16 sve_f32_to_f16(float32 f, float_status *fpst); +/* + * Decode helper functions for predicate as counter. + */ + +typedef struct { + unsigned count; + unsigned lg2_stride; + bool invert; +} DecodeCounter; + +static inline DecodeCounter +decode_counter(unsigned png, unsigned vl, unsigned v_esz) +{ + DecodeCounter ret = { }; + + /* C.f. Arm pseudocode CounterToPredicate. */ + if (likely(png & 0xf)) { + unsigned p_esz = ctz32(png); + + /* + * maxbit = log2(pl(bits) * 4) + * = log2(vl(bytes) * 4) + * = log2(vl) + 2 + * maxbit_mask = ones<maxbit:0> + * = (1 << (maxbit + 1)) - 1 + * = (1 << (log2(vl) + 2 + 1)) - 1 + * = (1 << (log2(vl) + 3)) - 1 + * = (pow2ceil(vl) << 3) - 1 + */ + ret.count = png & (((unsigned)pow2ceil(vl) << 3) - 1); + ret.count >>= p_esz + 1; + + ret.invert = (png >> 15) & 1; + + /* + * The Arm pseudocode for CounterToPredicate expands the count to + * a set of bits, and then the operation proceeds as for the original + * interpretation of predicates as a set of bits. + * + * We can avoid the expansion by adjusting the count and supplying + * an element stride. + */ + if (unlikely(p_esz != v_esz)) { + if (p_esz < v_esz) { + /* + * For predicate esz < vector esz, the expanded predicate + * will have more bits set than will be consumed. + * Adjust the count down, rounding up. + * Consider p_esz = MO_8, v_esz = MO_64, count 14: + * The expanded predicate would be + * 0011 1111 1111 1111 + * The significant bits are + * ...1 ...1 ...1 ...1 + */ + unsigned shift = v_esz - p_esz; + unsigned trunc = ret.count >> shift; + ret.count = trunc + (ret.count != (trunc << shift)); + } else { + /* + * For predicate esz > vector esz, the expanded predicate + * will have bits set only at power-of-two multiples of + * the vector esz. Bits at other multiples will all be + * false. Adjust the count up, and supply the caller + * with a stride of elements to skip. + */ + unsigned shift = p_esz - v_esz; + ret.count <<= shift; + ret.lg2_stride = shift; + } + } + } + return ret; +} + #endif /* TARGET_ARM_VEC_INTERNAL_H */ diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ %rn_ax2 6:4 !function=times_2 %pnd 0:3 !function=plus_8 +%pnn 5:3 !function=plus_8 ########################################################################### # Named attribute sets. These are used to make nice(er) names @@ -XXX,XX +XXX,XX @@ WHILE_lt_cnt4 00100101 .. 1 ..... 0110 . 1 ..... 1 . ... @while_cnt WHILE_gt_cnt2 00100101 .. 1 ..... 0100 . 0 ..... 1 . ... @while_cnt WHILE_gt_cnt4 00100101 .. 1 ..... 0110 . 0 ..... 1 . ... @while_cnt +# SVE2.1 extract mask predicate from predicate-as-counter +&pext rd rn esz imm +PEXT_1 00100101 esz:2 1 00000 0111 00 imm:2 ... 1 rd:4 &pext rn=%pnn +PEXT_2 00100101 esz:2 1 00000 0111 010 imm:1 ... 1 rd:4 &pext rn=%pnn + ### SVE Integer Wide Immediate - Unpredicated Group # SVE broadcast floating-point immediate (unpredicated) 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 @@ DO_FCVTLT(sve2_fcvtlt_sd, uint64_t, uint32_t, H1_8, H1_4, float32_to_float64) #undef DO_FCVTLT #undef DO_FCVTNT + +void HELPER(pext)(void *vd, uint32_t png, uint32_t desc) +{ + int pl = FIELD_EX32(desc, PREDDESC, OPRSZ); + int vl = pl * 8; + unsigned v_esz = FIELD_EX32(desc, PREDDESC, ESZ); + int part = FIELD_EX32(desc, PREDDESC, DATA); + DecodeCounter p = decode_counter(png, vl, v_esz); + uint64_t mask = pred_esz_masks[v_esz + p.lg2_stride]; + ARMPredicateReg *d = vd; + + /* + * Convert from element count to byte count and adjust + * for the portion of the 4*VL counter to be extracted. + */ + int b_count = (p.count << v_esz) - vl * part; + + memset(d, 0, sizeof(*d)); + if (p.invert) { + if (b_count <= 0) { + do_whilel(vd, mask, vl, vl); + } else if (b_count < vl) { + do_whileg(vd, mask, vl - b_count, vl); + } + } else if (b_count > 0) { + do_whilel(vd, mask, MIN(b_count, vl), vl); + } +} 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 trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) return true; } +static bool do_pext(DisasContext *s, arg_pext *a, int n) +{ + TCGv_i32 t_png; + TCGv_ptr t_pd; + int pl; + + if (!sve_access_check(s)) { + return true; + } + + t_png = tcg_temp_new_i32(); + tcg_gen_ld16u_i32(t_png, tcg_env, + pred_full_reg_offset(s, a->rn) ^ + (HOST_BIG_ENDIAN ? 6 : 0)); + + t_pd = tcg_temp_new_ptr(); + pl = pred_full_reg_size(s); + + for (int i = 0; i < n; ++i) { + int rd = (a->rd + i) % 16; + int part = a->imm * n + i; + unsigned desc = 0; + + desc = FIELD_DP32(desc, PREDDESC, OPRSZ, pl); + desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); + desc = FIELD_DP32(desc, PREDDESC, DATA, part); + + tcg_gen_addi_ptr(t_pd, tcg_env, pred_full_reg_offset(s, rd)); + gen_helper_pext(t_pd, t_png, tcg_constant_i32(desc)); + } + return true; +} + +TRANS_FEAT(PEXT_1, aa64_sme2_or_sve2p1, do_pext, a, 1) +TRANS_FEAT(PEXT_2, aa64_sme2_or_sve2p1, do_pext, a, 2) + /* *** SVE Integer Wide Immediate - Unpredicated Group */ -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-84-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 5 + target/arm/tcg/sme.decode | 9 + target/arm/tcg/sme_helper.c | 317 +++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 31 ++++ 4 files changed, 362 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme2_fclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i3 DEF_HELPER_FLAGS_5(sme2_fclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sme2_fclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sme2_bfclamp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sme2_sel_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) +DEF_HELPER_FLAGS_5(sme2_sel_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) +DEF_HELPER_FLAGS_5(sme2_sel_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) +DEF_HELPER_FLAGS_5(sme2_sel_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ UCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 1 \ UCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 1 \ &zzz_en zd=%zd_ax4 n=4 +### SME2 Multi-vector SVE Select + +%sel_pg 10:3 !function=plus_8 + +SEL 11000001 esz:2 1 ....0 100 ... ....0 ....0 \ + n=2 zd=%zd_ax2 zn=%zn_ax2 zm=%zm_ax2 pg=%sel_pg +SEL 11000001 esz:2 1 ...01 100 ... ...00 ...00 \ + n=4 zd=%zd_ax4 zn=%zn_ax4 zm=%zm_ax4 pg=%sel_pg + ### SME Multiple Zero &zero_za rv off ngrp nvec 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 @@ FCLAMP(sme2_fclamp_d, float64, H8) FCLAMP(sme2_bfclamp, bfloat16, H2) #undef FCLAMP + +void HELPER(sme2_sel_b)(void *vd, void *vn, void *vm, + uint32_t png, uint32_t desc) +{ + int vl = simd_oprsz(desc); + int nreg = simd_data(desc); + int elements = vl / sizeof(uint8_t); + DecodeCounter p = decode_counter(png, vl, MO_8); + + if (p.lg2_stride == 0) { + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint8_t *d = vd + r * sizeof(ARMVectorReg); + uint8_t *n = vn + r * sizeof(ARMVectorReg); + uint8_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, n, vl); /* all true */ + } else if (elements <= split) { + memcpy(d, m, vl); /* all false */ + } else { + for (int e = 0; e < split; e++) { + d[H1(e)] = m[H1(e)]; + } + for (int e = split; e < elements; e++) { + d[H1(e)] = n[H1(e)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint8_t *d = vd + r * sizeof(ARMVectorReg); + uint8_t *n = vn + r * sizeof(ARMVectorReg); + uint8_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, m, vl); /* all false */ + } else if (elements <= split) { + memcpy(d, n, vl); /* all true */ + } else { + for (int e = 0; e < split; e++) { + d[H1(e)] = n[H1(e)]; + } + for (int e = split; e < elements; e++) { + d[H1(e)] = m[H1(e)]; + } + } + } + } + } else { + int estride = 1 << p.lg2_stride; + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint8_t *d = vd + r * sizeof(ARMVectorReg); + uint8_t *n = vn + r * sizeof(ARMVectorReg); + uint8_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e++) { + d[H1(e)] = m[H1(e)]; + } + for (; e < elements; e += estride) { + d[H1(e)] = n[H1(e)]; + for (int i = 1; i < estride; i++) { + d[H1(e + i)] = m[H1(e + i)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint8_t *d = vd + r * sizeof(ARMVectorReg); + uint8_t *n = vn + r * sizeof(ARMVectorReg); + uint8_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e += estride) { + d[H1(e)] = n[H1(e)]; + for (int i = 1; i < estride; i++) { + d[H1(e + i)] = m[H1(e + i)]; + } + } + for (; e < elements; e++) { + d[H1(e)] = m[H1(e)]; + } + } + } + } +} + +void HELPER(sme2_sel_h)(void *vd, void *vn, void *vm, + uint32_t png, uint32_t desc) +{ + int vl = simd_oprsz(desc); + int nreg = simd_data(desc); + int elements = vl / sizeof(uint16_t); + DecodeCounter p = decode_counter(png, vl, MO_16); + + if (p.lg2_stride == 0) { + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint16_t *d = vd + r * sizeof(ARMVectorReg); + uint16_t *n = vn + r * sizeof(ARMVectorReg); + uint16_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, n, vl); /* all true */ + } else if (elements <= split) { + memcpy(d, m, vl); /* all false */ + } else { + for (int e = 0; e < split; e++) { + d[H2(e)] = m[H2(e)]; + } + for (int e = split; e < elements; e++) { + d[H2(e)] = n[H2(e)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint16_t *d = vd + r * sizeof(ARMVectorReg); + uint16_t *n = vn + r * sizeof(ARMVectorReg); + uint16_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, m, vl); /* all false */ + } else if (elements <= split) { + memcpy(d, n, vl); /* all true */ + } else { + for (int e = 0; e < split; e++) { + d[H2(e)] = n[H2(e)]; + } + for (int e = split; e < elements; e++) { + d[H2(e)] = m[H2(e)]; + } + } + } + } + } else { + int estride = 1 << p.lg2_stride; + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint16_t *d = vd + r * sizeof(ARMVectorReg); + uint16_t *n = vn + r * sizeof(ARMVectorReg); + uint16_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e++) { + d[H2(e)] = m[H2(e)]; + } + for (; e < elements; e += estride) { + d[H2(e)] = n[H2(e)]; + for (int i = 1; i < estride; i++) { + d[H2(e + i)] = m[H2(e + i)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint16_t *d = vd + r * sizeof(ARMVectorReg); + uint16_t *n = vn + r * sizeof(ARMVectorReg); + uint16_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e += estride) { + d[H2(e)] = n[H2(e)]; + for (int i = 1; i < estride; i++) { + d[H2(e + i)] = m[H2(e + i)]; + } + } + for (; e < elements; e++) { + d[H2(e)] = m[H2(e)]; + } + } + } + } +} + +void HELPER(sme2_sel_s)(void *vd, void *vn, void *vm, + uint32_t png, uint32_t desc) +{ + int vl = simd_oprsz(desc); + int nreg = simd_data(desc); + int elements = vl / sizeof(uint32_t); + DecodeCounter p = decode_counter(png, vl, MO_32); + + if (p.lg2_stride == 0) { + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint32_t *d = vd + r * sizeof(ARMVectorReg); + uint32_t *n = vn + r * sizeof(ARMVectorReg); + uint32_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, n, vl); /* all true */ + } else if (elements <= split) { + memcpy(d, m, vl); /* all false */ + } else { + for (int e = 0; e < split; e++) { + d[H4(e)] = m[H4(e)]; + } + for (int e = split; e < elements; e++) { + d[H4(e)] = n[H4(e)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint32_t *d = vd + r * sizeof(ARMVectorReg); + uint32_t *n = vn + r * sizeof(ARMVectorReg); + uint32_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, m, vl); /* all false */ + } else if (elements <= split) { + memcpy(d, n, vl); /* all true */ + } else { + for (int e = 0; e < split; e++) { + d[H4(e)] = n[H4(e)]; + } + for (int e = split; e < elements; e++) { + d[H4(e)] = m[H4(e)]; + } + } + } + } + } else { + /* p.esz must be MO_64, so stride must be 2. */ + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint32_t *d = vd + r * sizeof(ARMVectorReg); + uint32_t *n = vn + r * sizeof(ARMVectorReg); + uint32_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e++) { + d[H4(e)] = m[H4(e)]; + } + for (; e < elements; e += 2) { + d[H4(e)] = n[H4(e)]; + d[H4(e + 1)] = m[H4(e + 1)]; + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint32_t *d = vd + r * sizeof(ARMVectorReg); + uint32_t *n = vn + r * sizeof(ARMVectorReg); + uint32_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e += 2) { + d[H4(e)] = n[H4(e)]; + d[H4(e + 1)] = m[H4(e + 1)]; + } + for (; e < elements; e++) { + d[H4(e)] = m[H4(e)]; + } + } + } + } +} + +void HELPER(sme2_sel_d)(void *vd, void *vn, void *vm, + uint32_t png, uint32_t desc) +{ + int vl = simd_oprsz(desc); + int nreg = simd_data(desc); + int elements = vl / sizeof(uint64_t); + DecodeCounter p = decode_counter(png, vl, MO_64); + + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint64_t *d = vd + r * sizeof(ARMVectorReg); + uint64_t *n = vn + r * sizeof(ARMVectorReg); + uint64_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, n, vl); /* all true */ + } else if (elements <= split) { + memcpy(d, m, vl); /* all false */ + } else { + memcpy(d, m, split * sizeof(uint64_t)); + memcpy(d + split, n + split, + (elements - split) * sizeof(uint64_t)); + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint64_t *d = vd + r * sizeof(ARMVectorReg); + uint64_t *n = vn + r * sizeof(ARMVectorReg); + uint64_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, m, vl); /* all false */ + } else if (elements <= split) { + memcpy(d, n, vl); /* all true */ + } else { + memcpy(d, n, split * sizeof(uint64_t)); + memcpy(d + split, m + split, + (elements - split) * sizeof(uint64_t)); + } + } + } +} 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 gen_helper_gvec_3 * const uclamp_fns[] = { gen_helper_sme2_uclamp_d, }; TRANS(UCLAMP, do_clamp, a, uclamp_fns) + +static bool trans_SEL(DisasContext *s, arg_SEL *a) +{ + typedef void sme_sel_fn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); + static sme_sel_fn * const fns[4] = { + gen_helper_sme2_sel_b, gen_helper_sme2_sel_h, + gen_helper_sme2_sel_s, gen_helper_sme2_sel_d + }; + + if (!dc_isar_feature(aa64_sme2, s)) { + return false; + } + if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, a->n); + TCGv_ptr t_d = tcg_temp_new_ptr(); + TCGv_ptr t_n = tcg_temp_new_ptr(); + TCGv_ptr t_m = tcg_temp_new_ptr(); + TCGv_i32 png = tcg_temp_new_i32(); + + tcg_gen_addi_ptr(t_d, tcg_env, vec_full_reg_offset(s, a->zd)); + tcg_gen_addi_ptr(t_n, tcg_env, vec_full_reg_offset(s, a->zn)); + tcg_gen_addi_ptr(t_m, tcg_env, vec_full_reg_offset(s, a->zm)); + + tcg_gen_ld16u_i32(png, tcg_env, pred_full_reg_offset(s, a->pg) + ^ (HOST_BIG_ENDIAN ? 6 : 0)); + + fns[a->esz](t_d, t_n, t_m, png, tcg_constant_i32(desc)); + } + return true; +} -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-85-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 15 ++++++++++++ target/arm/tcg/sve.decode | 5 ++++ target/arm/tcg/sve_helper.c | 42 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sve.c | 3 +++ 4 files changed, 65 insertions(+) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2p1_uminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2p1_uminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(pext, TCG_CALL_NO_RWG, void, ptr, i32, i32) + +DEF_HELPER_FLAGS_4(sve2p1_orqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_orqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_orqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_orqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_eorqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_eorqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_eorqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_eorqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_andqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_andqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_andqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_andqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ ORV 00000100 .. 011 000 001 ... ..... ..... @rd_pg_rn EORV 00000100 .. 011 001 001 ... ..... ..... @rd_pg_rn ANDV 00000100 .. 011 010 001 ... ..... ..... @rd_pg_rn +# SVE2.1 bitwise logical reduction (quadwords) +ORQV 00000100 .. 011 100 001 ... ..... ..... @rd_pg_rn +EORQV 00000100 .. 011 101 001 ... ..... ..... @rd_pg_rn +ANDQV 00000100 .. 011 110 001 ... ..... ..... @rd_pg_rn + # SVE constructive prefix (predicated) MOVPRFX_z 00000100 .. 010 000 001 ... ..... ..... @rd_pg_rn MOVPRFX_m 00000100 .. 010 001 001 ... ..... ..... @rd_pg_rn 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 inline uint64_t expand_pred_s(uint8_t byte) return word[byte & 0x11]; } +static inline uint64_t expand_pred_d(uint8_t byte) +{ + return -(uint64_t)(byte & 1); +} + #define LOGICAL_PPPP(NAME, FUNC) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ #define DO_EOR(N, M) (N ^ M) #define DO_ORR(N, M) (N | M) #define DO_BIC(N, M) (N & ~M) +#define DO_ORC(N, M) (N | ~M) #define DO_ADD(N, M) (N + M) #define DO_SUB(N, M) (N - M) #define DO_MAX(N, M) ((N) >= (M) ? (N) : (M)) @@ -XXX,XX +XXX,XX @@ DO_ZZI(sve_umini_d, uint64_t, DO_MIN) #undef DO_ZZI +#define DO_LOGIC_QV(NAME, SUFF, INIT, VOP, POP) \ +void HELPER(NAME ## _ ## SUFF)(void *vd, void *vn, void *vg, uint32_t desc) \ +{ \ + unsigned seg = simd_oprsz(desc) / 16; \ + uint64_t r0 = INIT, r1 = INIT; \ + for (unsigned s = 0; s < seg; s++) { \ + uint64_t p0 = expand_pred_##SUFF(*(uint8_t *)(vg + H1(s * 2))); \ + uint64_t p1 = expand_pred_##SUFF(*(uint8_t *)(vg + H1(s * 2 + 1))); \ + uint64_t v0 = *(uint64_t *)(vn + s * 16); \ + uint64_t v1 = *(uint64_t *)(vn + s * 16 + 8); \ + v0 = POP(v0, p0), v1 = POP(v1, p1); \ + r0 = VOP(r0, v0), r1 = VOP(r1, v1); \ + } \ + *(uint64_t *)(vd + 0) = r0; \ + *(uint64_t *)(vd + 8) = r1; \ + clear_tail(vd, 16, simd_maxsz(desc)); \ +} + +DO_LOGIC_QV(sve2p1_orqv, b, 0, DO_ORR, DO_AND) +DO_LOGIC_QV(sve2p1_orqv, h, 0, DO_ORR, DO_AND) +DO_LOGIC_QV(sve2p1_orqv, s, 0, DO_ORR, DO_AND) +DO_LOGIC_QV(sve2p1_orqv, d, 0, DO_ORR, DO_AND) + +DO_LOGIC_QV(sve2p1_eorqv, b, 0, DO_EOR, DO_AND) +DO_LOGIC_QV(sve2p1_eorqv, h, 0, DO_EOR, DO_AND) +DO_LOGIC_QV(sve2p1_eorqv, s, 0, DO_EOR, DO_AND) +DO_LOGIC_QV(sve2p1_eorqv, d, 0, DO_EOR, DO_AND) + +DO_LOGIC_QV(sve2p1_andqv, b, -1, DO_AND, DO_ORC) +DO_LOGIC_QV(sve2p1_andqv, h, -1, DO_AND, DO_ORC) +DO_LOGIC_QV(sve2p1_andqv, s, -1, DO_AND, DO_ORC) +DO_LOGIC_QV(sve2p1_andqv, d, -1, DO_AND, DO_ORC) + +#undef DO_LOGIC_QV + #undef DO_AND #undef DO_ORR #undef DO_EOR #undef DO_BIC +#undef DO_ORC #undef DO_ADD #undef DO_SUB #undef DO_MAX 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 @@ DO_ZPZ(NOT_zpz, aa64_sve, sve_not_zpz) DO_ZPZ(ABS, aa64_sve, sve_abs) DO_ZPZ(NEG, aa64_sve, sve_neg) DO_ZPZ(RBIT, aa64_sve, sve_rbit) +DO_ZPZ(ORQV, aa64_sme2p1_or_sve2p1, sve2p1_orqv) +DO_ZPZ(EORQV, aa64_sme2p1_or_sve2p1, sve2p1_eorqv) +DO_ZPZ(ANDQV, aa64_sme2p1_or_sve2p1, sve2p1_andqv) static gen_helper_gvec_3 * const fabs_fns[4] = { NULL, gen_helper_sve_fabs_h, -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-86-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 49 ++++++++++++++++++++++++ target/arm/tcg/sve.decode | 8 ++++ target/arm/tcg/sve_helper.c | 70 +++++++++++++++++++++------------- target/arm/tcg/translate-sve.c | 48 +++++++++++++++++++++++ 4 files changed, 148 insertions(+), 27 deletions(-) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ah_fminv_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_4(sve_ah_fminv_d, TCG_CALL_NO_RWG, i64, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_faddqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_faddqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_faddqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_fmaxnmqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fmaxnmqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fmaxnmqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_fminnmqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fminnmqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fminnmqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_fmaxqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fmaxqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fmaxqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_fminqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fminqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fminqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_ah_fmaxqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_ah_fmaxqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_ah_fmaxqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_ah_fminqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_ah_fminqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_ah_fminqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + DEF_HELPER_FLAGS_5(sve_fadda_h, TCG_CALL_NO_RWG, i64, i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fadda_s, TCG_CALL_NO_RWG, diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ FMINNMV 01100101 .. 000 101 001 ... ..... ..... @rd_pg_rn FMAXV 01100101 .. 000 110 001 ... ..... ..... @rd_pg_rn FMINV 01100101 .. 000 111 001 ... ..... ..... @rd_pg_rn +### SVE FP recursive reduction (quadwords) + +FADDQV 01100100 .. 010 000 101 ... ..... ..... @rd_pg_rn +FMAXNMQV 01100100 .. 010 100 101 ... ..... ..... @rd_pg_rn +FMINNMQV 01100100 .. 010 101 101 ... ..... ..... @rd_pg_rn +FMAXQV 01100100 .. 010 110 101 ... ..... ..... @rd_pg_rn +FMINQV 01100100 .. 010 111 101 ... ..... ..... @rd_pg_rn + ## SVE Floating Point Unary Operations - Unpredicated Group FRECPE 01100101 .. 001 110 001100 ..... ..... @rd_rn 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 @@ uint32_t HELPER(sve_whilecg)(void *vd, uint32_t count, uint32_t pred_desc) * The recursion is bounded to depth 7 (128 fp16 elements), so there's * little to gain with a more complex non-recursive form. */ -#define DO_REDUCE(NAME, TYPE, H, FUNC, IDENT) \ -static TYPE NAME##_reduce(TYPE *data, float_status *status, uintptr_t n) \ +#define DO_REDUCE(NAME, SUF, TYPE, H, FUNC, IDENT) \ +static TYPE FUNC##_reduce(TYPE *data, float_status *status, uintptr_t n) \ { \ if (n == 1) { \ return *data; \ } else { \ uintptr_t half = n / 2; \ - TYPE lo = NAME##_reduce(data, status, half); \ - TYPE hi = NAME##_reduce(data + half, status, half); \ + TYPE lo = FUNC##_reduce(data, status, half); \ + TYPE hi = FUNC##_reduce(data + half, status, half); \ return FUNC(lo, hi, status); \ } \ } \ -uint64_t HELPER(NAME)(void *vn, void *vg, float_status *s, uint32_t desc) \ +uint64_t helper_sve_##NAME##v_##SUF(void *vn, void *vg, \ + float_status *s, uint32_t desc) \ { \ uintptr_t i, oprsz = simd_oprsz(desc), maxsz = simd_data(desc); \ TYPE data[sizeof(ARMVectorReg) / sizeof(TYPE)]; \ @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(NAME)(void *vn, void *vg, float_status *s, uint32_t desc) \ for (; i < maxsz; i += sizeof(TYPE)) { \ *(TYPE *)((void *)data + i) = IDENT; \ } \ - return NAME##_reduce(data, s, maxsz / sizeof(TYPE)); \ + return FUNC##_reduce(data, s, maxsz / sizeof(TYPE)); \ +} \ +void helper_sve2p1_##NAME##qv_##SUF(void *vd, void *vn, void *vg, \ + float_status *status, uint32_t desc) \ +{ \ + unsigned oprsz = simd_oprsz(desc), segments = oprsz / 16; \ + for (unsigned e = 0; e < 16; e += sizeof(TYPE)) { \ + TYPE data[ARM_MAX_VQ]; \ + for (unsigned s = 0; s < segments; s++) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(s * 2)); \ + TYPE nn = *(TYPE *)(vn + H(s * 16 + H(e))); \ + data[s] = (pg >> e) & 1 ? nn : IDENT; \ + } \ + *(TYPE *)(vd + H(e)) = FUNC##_reduce(data, status, segments); \ + } \ + clear_tail(vd, 16, simd_maxsz(desc)); \ } -DO_REDUCE(sve_faddv_h, float16, H1_2, float16_add, float16_zero) -DO_REDUCE(sve_faddv_s, float32, H1_4, float32_add, float32_zero) -DO_REDUCE(sve_faddv_d, float64, H1_8, float64_add, float64_zero) +DO_REDUCE(fadd,h, float16, H1_2, float16_add, float16_zero) +DO_REDUCE(fadd,s, float32, H1_4, float32_add, float32_zero) +DO_REDUCE(fadd,d, float64, H1_8, float64_add, float64_zero) /* Identity is floatN_default_nan, without the function call. */ -DO_REDUCE(sve_fminnmv_h, float16, H1_2, float16_minnum, 0x7E00) -DO_REDUCE(sve_fminnmv_s, float32, H1_4, float32_minnum, 0x7FC00000) -DO_REDUCE(sve_fminnmv_d, float64, H1_8, float64_minnum, 0x7FF8000000000000ULL) +DO_REDUCE(fminnm,h, float16, H1_2, float16_minnum, 0x7E00) +DO_REDUCE(fminnm,s, float32, H1_4, float32_minnum, 0x7FC00000) +DO_REDUCE(fminnm,d, float64, H1_8, float64_minnum, 0x7FF8000000000000ULL) -DO_REDUCE(sve_fmaxnmv_h, float16, H1_2, float16_maxnum, 0x7E00) -DO_REDUCE(sve_fmaxnmv_s, float32, H1_4, float32_maxnum, 0x7FC00000) -DO_REDUCE(sve_fmaxnmv_d, float64, H1_8, float64_maxnum, 0x7FF8000000000000ULL) +DO_REDUCE(fmaxnm,h, float16, H1_2, float16_maxnum, 0x7E00) +DO_REDUCE(fmaxnm,s, float32, H1_4, float32_maxnum, 0x7FC00000) +DO_REDUCE(fmaxnm,d, float64, H1_8, float64_maxnum, 0x7FF8000000000000ULL) -DO_REDUCE(sve_fminv_h, float16, H1_2, float16_min, float16_infinity) -DO_REDUCE(sve_fminv_s, float32, H1_4, float32_min, float32_infinity) -DO_REDUCE(sve_fminv_d, float64, H1_8, float64_min, float64_infinity) +DO_REDUCE(fmin,h, float16, H1_2, float16_min, float16_infinity) +DO_REDUCE(fmin,s, float32, H1_4, float32_min, float32_infinity) +DO_REDUCE(fmin,d, float64, H1_8, float64_min, float64_infinity) -DO_REDUCE(sve_fmaxv_h, float16, H1_2, float16_max, float16_chs(float16_infinity)) -DO_REDUCE(sve_fmaxv_s, float32, H1_4, float32_max, float32_chs(float32_infinity)) -DO_REDUCE(sve_fmaxv_d, float64, H1_8, float64_max, float64_chs(float64_infinity)) +DO_REDUCE(fmax,h, float16, H1_2, float16_max, float16_chs(float16_infinity)) +DO_REDUCE(fmax,s, float32, H1_4, float32_max, float32_chs(float32_infinity)) +DO_REDUCE(fmax,d, float64, H1_8, float64_max, float64_chs(float64_infinity)) -DO_REDUCE(sve_ah_fminv_h, float16, H1_2, helper_vfp_ah_minh, float16_infinity) -DO_REDUCE(sve_ah_fminv_s, float32, H1_4, helper_vfp_ah_mins, float32_infinity) -DO_REDUCE(sve_ah_fminv_d, float64, H1_8, helper_vfp_ah_mind, float64_infinity) +DO_REDUCE(ah_fmin,h, float16, H1_2, helper_vfp_ah_minh, float16_infinity) +DO_REDUCE(ah_fmin,s, float32, H1_4, helper_vfp_ah_mins, float32_infinity) +DO_REDUCE(ah_fmin,d, float64, H1_8, helper_vfp_ah_mind, float64_infinity) -DO_REDUCE(sve_ah_fmaxv_h, float16, H1_2, helper_vfp_ah_maxh, +DO_REDUCE(ah_fmax,h, float16, H1_2, helper_vfp_ah_maxh, float16_chs(float16_infinity)) -DO_REDUCE(sve_ah_fmaxv_s, float32, H1_4, helper_vfp_ah_maxs, +DO_REDUCE(ah_fmax,s, float32, H1_4, helper_vfp_ah_maxs, float32_chs(float32_infinity)) -DO_REDUCE(sve_ah_fmaxv_d, float64, H1_8, helper_vfp_ah_maxd, +DO_REDUCE(ah_fmax,d, float64, H1_8, helper_vfp_ah_maxd, float64_chs(float64_infinity)) #undef DO_REDUCE 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 @@ DO_VPZ_AH(FMAXV, fmaxv) #undef DO_VPZ +static gen_helper_gvec_3_ptr * const faddqv_fns[4] = { + NULL, gen_helper_sve2p1_faddqv_h, + gen_helper_sve2p1_faddqv_s, gen_helper_sve2p1_faddqv_d, +}; +TRANS_FEAT(FADDQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + faddqv_fns[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + +static gen_helper_gvec_3_ptr * const fmaxnmqv_fns[4] = { + NULL, gen_helper_sve2p1_fmaxnmqv_h, + gen_helper_sve2p1_fmaxnmqv_s, gen_helper_sve2p1_fmaxnmqv_d, +}; +TRANS_FEAT(FMAXNMQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + fmaxnmqv_fns[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + +static gen_helper_gvec_3_ptr * const fminnmqv_fns[4] = { + NULL, gen_helper_sve2p1_fminnmqv_h, + gen_helper_sve2p1_fminnmqv_s, gen_helper_sve2p1_fminnmqv_d, +}; +TRANS_FEAT(FMINNMQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + fminnmqv_fns[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + +static gen_helper_gvec_3_ptr * const fmaxqv_fns[4] = { + NULL, gen_helper_sve2p1_fmaxqv_h, + gen_helper_sve2p1_fmaxqv_s, gen_helper_sve2p1_fmaxqv_d, +}; +static gen_helper_gvec_3_ptr * const fmaxqv_ah_fns[4] = { + NULL, gen_helper_sve2p1_ah_fmaxqv_h, + gen_helper_sve2p1_ah_fmaxqv_s, gen_helper_sve2p1_ah_fmaxqv_d, +}; +TRANS_FEAT(FMAXQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + (s->fpcr_ah ? fmaxqv_fns : fmaxqv_ah_fns)[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + +static gen_helper_gvec_3_ptr * const fminqv_fns[4] = { + NULL, gen_helper_sve2p1_fminqv_h, + gen_helper_sve2p1_fminqv_s, gen_helper_sve2p1_fminqv_d, +}; +static gen_helper_gvec_3_ptr * const fminqv_ah_fns[4] = { + NULL, gen_helper_sve2p1_ah_fminqv_h, + gen_helper_sve2p1_ah_fminqv_s, gen_helper_sve2p1_ah_fminqv_d, +}; +TRANS_FEAT(FMINQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + (s->fpcr_ah ? fminqv_fns : fminqv_ah_fns)[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + /* *** SVE Floating Point Unary Operations - Unpredicated Group */ -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-87-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 6 ++++++ target/arm/tcg/translate-sve.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_ex esz=2 BFMLALB_zzzw 01100100 11 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 BFMLALT_zzzw 01100100 11 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_ex esz=2 +BFMLSLB_zzzw 01100100 11 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm_ex esz=2 +BFMLSLT_zzzw 01100100 11 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_ex esz=2 ### SVE2 floating-point dot-product FDOT_zzzz 01100100 00 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 BFDOT_zzzz 01100100 01 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 ### SVE2 floating-point multiply-add long (indexed) + FMLALB_zzxw 01100100 10 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2 FMLALT_zzxw 01100100 10 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 FMLSLB_zzxw 01100100 10 1 ..... 0110.0 ..... ..... @rrxr_3a esz=2 FMLSLT_zzxw 01100100 10 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2 + BFMLALB_zzxw 01100100 11 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2 BFMLALT_zzxw 01100100 11 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 +BFMLSLB_zzxw 01100100 11 1 ..... 0110.0 ..... ..... @rrxr_3a esz=2 +BFMLSLT_zzxw 01100100 11 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2 ### SVE2 floating-point dot-product (indexed) 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 do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false) TRANS_FEAT(BFMLALT_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, true) +static bool do_BFMLSL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + if (s->fpcr_ah) { + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl, + a->rd, a->rn, a->rm, a->ra, sel, FPST_AH); + } else { + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl, + a->rd, a->rn, a->rm, a->ra, sel, FPST_A64); + } +} + +TRANS_FEAT(BFMLSLB_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, false) +TRANS_FEAT(BFMLSLT_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, true) + +static bool do_BFMLSL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) +{ + if (s->fpcr_ah) { + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl_idx, + a->rd, a->rn, a->rm, a->ra, + (a->index << 1) | sel, FPST_AH); + } else { + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl_idx, + a->rd, a->rn, a->rm, a->ra, + (a->index << 1) | sel, FPST_A64); + } +} + +TRANS_FEAT(BFMLSLB_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, false) +TRANS_FEAT(BFMLSLT_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, true) + static bool trans_PSEL(DisasContext *s, arg_psel *a) { int vl = vec_full_reg_size(s); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-88-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 1 + target/arm/tcg/sve.decode | 3 ++- target/arm/tcg/sve_helper.c | 21 +++++++++++++++++++++ target/arm/tcg/translate-sve.c | 30 ++++++++++++++++++++++++++++++ 4 files changed, 54 insertions(+), 1 deletion(-) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_brkn, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) +DEF_HELPER_FLAGS_2(sve2p1_cntp_c, TCG_CALL_NO_RWG_SE, i64, i32, i32) DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ BRKN 00100101 0. 01100001 .... 0 .... 0 .... @pd_pg_pn_s ### SVE Predicate Count Group # SVE predicate count -CNTP 00100101 .. 100 000 10 .... 0 .... ..... @rd_pg4_pn +CNTP 00100101 .. 100 000 10 .... 0 .... ..... @rd_pg4_pn +CNTP_c 00100101 esz:2 100 000 10 000 vl:1 1 rn:4 rd:5 # SVE inc/dec register by predicate count INCDECP_r 00100101 .. 10110 d:1 10001 00 .... ..... @incdec_pred u=1 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 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) return sum; } +uint64_t HELPER(sve2p1_cntp_c)(uint32_t png, uint32_t desc) +{ + int pl = FIELD_EX32(desc, PREDDESC, OPRSZ); + int vl = pl * 8; + unsigned v_esz = FIELD_EX32(desc, PREDDESC, ESZ); + int lg2_width = FIELD_EX32(desc, PREDDESC, DATA) + 1; + DecodeCounter p = decode_counter(png, vl, v_esz); + unsigned maxelem = (vl << lg2_width) >> v_esz; + unsigned count = p.count; + + if (p.invert) { + if (count >= maxelem) { + return 0; + } + count = maxelem - count; + } else { + count = MIN(count, maxelem); + } + return count >> p.lg2_stride; +} + /* C.f. Arm pseudocode EncodePredCount */ static uint64_t encode_pred_count(uint32_t elements, uint32_t count, uint32_t esz, bool invert) 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 trans_CNTP(DisasContext *s, arg_CNTP *a) return true; } +static bool trans_CNTP_c(DisasContext *s, arg_CNTP_c *a) +{ + TCGv_i32 t_png; + uint32_t desc = 0; + + if (dc_isar_feature(aa64_sve2p1, s)) { + if (!sve_access_check(s)) { + return true; + } + } else if (dc_isar_feature(aa64_sme2, s)) { + if (!sme_sm_enabled_check(s)) { + return true; + } + } else { + return false; + } + + t_png = tcg_temp_new_i32(); + tcg_gen_ld16u_i32(t_png, tcg_env, + pred_full_reg_offset(s, a->rn) ^ + (HOST_BIG_ENDIAN ? 6 : 0)); + + desc = FIELD_DP32(desc, PREDDESC, OPRSZ, pred_full_reg_size(s)); + desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); + desc = FIELD_DP32(desc, PREDDESC, DATA, a->vl); + + gen_helper_sve2p1_cntp_c(cpu_reg(s, a->rd), t_png, tcg_constant_i32(desc)); + return true; +} + static bool trans_INCDECP_r(DisasContext *s, arg_incdec_pred *a) { if (!dc_isar_feature(aa64_sve, s)) { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-89-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 6 ++++++ target/arm/tcg/translate-sve.c | 21 +++++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ DUP_s 00000101 .. 1 00000 001110 ..... ..... @rd_rn DUP_x 00000101 .. 1 ..... 001000 rn:5 rd:5 \ &rri imm=%imm7_22_16 +# SVE Permute Vector - one source quadwords +DUPQ 00000101 001 imm:4 1 001001 rn:5 rd:5 &rri_esz esz=0 +DUPQ 00000101 001 imm:3 10 001001 rn:5 rd:5 &rri_esz esz=1 +DUPQ 00000101 001 imm:2 100 001001 rn:5 rd:5 &rri_esz esz=2 +DUPQ 00000101 001 imm:1 1000 001001 rn:5 rd:5 &rri_esz esz=3 + # SVE insert SIMD&FP scalar register INSR_f 00000101 .. 1 10100 001110 ..... ..... @rdn_rm 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 trans_DUP_x(DisasContext *s, arg_DUP_x *a) return true; } +static bool trans_DUPQ(DisasContext *s, arg_DUPQ *a) +{ + unsigned vl, dofs, nofs; + + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + vl = vec_full_reg_size(s); + dofs = vec_full_reg_offset(s, a->rd); + nofs = vec_reg_offset(s, a->rn, a->imm, a->esz); + + for (unsigned i = 0; i < vl; i += 16) { + tcg_gen_gvec_dup_mem(a->esz, dofs + i, nofs + i, 16, 16); + } + return true; +} + static void do_insr_i64(DisasContext *s, arg_rrr_esz *a, TCGv_i64 val) { typedef void gen_insr(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-90-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 2 ++ target/arm/tcg/translate-sve.c | 49 ++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ DUPQ 00000101 001 imm:3 10 001001 rn:5 rd:5 &rri_esz esz=1 DUPQ 00000101 001 imm:2 100 001001 rn:5 rd:5 &rri_esz esz=2 DUPQ 00000101 001 imm:1 1000 001001 rn:5 rd:5 &rri_esz esz=3 +EXTQ 00000101 0110 imm:4 001001 rn:5 rd:5 &rri + # SVE insert SIMD&FP scalar register INSR_f 00000101 .. 1 10100 001110 ..... ..... @rdn_rm 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 do_EXT(DisasContext *s, int rd, int rn, int rm, int imm) TRANS_FEAT(EXT, aa64_sve, do_EXT, a->rd, a->rn, a->rm, a->imm) TRANS_FEAT(EXT_sve2, aa64_sve2, do_EXT, a->rd, a->rn, (a->rn + 1) % 32, a->imm) +static bool trans_EXTQ(DisasContext *s, arg_EXTQ *a) +{ + unsigned vl, dofs, sofs0, sofs1, sofs2, imm; + + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + imm = a->imm; + if (imm == 0) { + /* So far we never optimize Zdn with MOVPRFX, so zd = zn is a nop. */ + return true; + } + + vl = vec_full_reg_size(s); + dofs = vec_full_reg_offset(s, a->rd); + sofs2 = vec_full_reg_offset(s, a->rn); + + if (imm & 8) { + sofs0 = dofs + 8; + sofs1 = sofs2; + sofs2 += 8; + } else { + sofs0 = dofs; + sofs1 = dofs + 8; + } + imm = (imm & 7) << 3; + + for (unsigned i = 0; i < vl; i += 16) { + TCGv_i64 s0 = tcg_temp_new_i64(); + TCGv_i64 s1 = tcg_temp_new_i64(); + TCGv_i64 s2 = tcg_temp_new_i64(); + + tcg_gen_ld_i64(s0, tcg_env, sofs0 + i); + tcg_gen_ld_i64(s1, tcg_env, sofs1 + i); + tcg_gen_ld_i64(s2, tcg_env, sofs2 + i); + + tcg_gen_extract2_i64(s0, s0, s1, imm); + tcg_gen_extract2_i64(s1, s1, s2, imm); + + tcg_gen_st_i64(s0, tcg_env, dofs + i); + tcg_gen_st_i64(s1, tcg_env, dofs + i + 8); + } + return true; +} + /* *** SVE Permute - Unpredicated Group */ -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-91-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 8 +++ target/arm/tcg/vec_internal.h | 34 ++++++++++++ target/arm/tcg/sve.decode | 17 ++++++ target/arm/tcg/sve_helper.c | 50 +++++++++++++++++ target/arm/tcg/translate-sve.c | 98 ++++++++++++++++++++++++++++++++++ 5 files changed, 207 insertions(+) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2p1_andqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2p1_andqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2p1_andqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2p1_andqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(pmov_pv_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(pmov_pv_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(pmov_pv_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(pmov_vp_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(pmov_vp_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(pmov_vp_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_internal.h +++ b/target/arm/tcg/vec_internal.h @@ -XXX,XX +XXX,XX @@ decode_counter(unsigned png, unsigned vl, unsigned v_esz) return ret; } +/* Extract @len bits from an array of uint64_t at offset @pos bits. */ +static inline uint64_t extractn(uint64_t *p, unsigned pos, unsigned len) +{ + uint64_t x; + + p += pos / 64; + pos = pos % 64; + + x = p[0]; + if (pos + len > 64) { + x = (x >> pos) | (p[1] << (-pos & 63)); + pos = 0; + } + return extract64(x, pos, len); +} + +/* Deposit @len bits into an array of uint64_t at offset @pos bits. */ +static inline void depositn(uint64_t *p, unsigned pos, + unsigned len, uint64_t val) +{ + p += pos / 64; + pos = pos % 64; + + if (pos + len <= 64) { + p[0] = deposit64(p[0], pos, len, val); + } else { + unsigned len0 = 64 - pos; + unsigned len1 = len - len0; + + p[0] = deposit64(p[0], pos, len0, val); + p[1] = deposit64(p[1], 0, len1, val >> len0); + } +} + #endif /* TARGET_ARM_VEC_INTERNAL_H */ diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ %size_23 23:2 %dtype_23_13 23:2 13:2 %index3_22_19 22:1 19:2 +%index3_22_17 22:1 17:2 %index3_19_11 19:2 11:1 %index2_20_11 20:1 11:1 @@ -XXX,XX +XXX,XX @@ INSR_r 00000101 .. 1 00100 001110 ..... ..... @rdn_rm # SVE reverse vector elements REV_v 00000101 .. 1 11000 001110 ..... ..... @rd_rn +# SVE move predicate to/from vector + +PMOV_pv 00000101 00 101 01 0001110 rn:5 0 rd:4 \ + &rri_esz esz=0 imm=0 +PMOV_pv 00000101 00 101 1 imm:1 0001110 rn:5 0 rd:4 &rri_esz esz=1 +PMOV_pv 00000101 01 101 imm:2 0001110 rn:5 0 rd:4 &rri_esz esz=2 +PMOV_pv 00000101 1. 101 .. 0001110 rn:5 0 rd:4 \ + &rri_esz esz=3 imm=%index3_22_17 + +PMOV_vp 00000101 00 101 01 1001110 0 rn:4 rd:5 \ + &rri_esz esz=0 imm=0 +PMOV_vp 00000101 00 101 1 imm:1 1001110 0 rn:4 rd:5 &rri_esz esz=1 +PMOV_vp 00000101 01 101 imm:2 1001110 0 rn:4 rd:5 &rri_esz esz=2 +PMOV_vp 00000101 1. 101 .. 1001110 0 rn:4 rd:5 \ + &rri_esz esz=3 imm=%index3_22_17 + # SVE vector table lookup TBL 00000101 .. 1 ..... 001100 ..... ..... @rd_rn_rm 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 @@ void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t desc) } } +/* + * TODO: This could use half_shuffle64 and similar bit tricks to + * expand blocks of bits at once. + */ +#define DO_PMOV_PV(NAME, ESIZE) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + unsigned vl = simd_oprsz(desc); \ + unsigned idx = simd_data(desc); \ + unsigned elements = vl / ESIZE; \ + ARMPredicateReg *d = vd; \ + ARMVectorReg *s = vs; \ + memset(d, 0, sizeof(*d)); \ + for (unsigned e = 0; e < elements; ++e) { \ + depositn(d->p, e * ESIZE, 1, extractn(s->d, elements * idx + e, 1)); \ + } \ +} + +DO_PMOV_PV(pmov_pv_h, 2) +DO_PMOV_PV(pmov_pv_s, 4) +DO_PMOV_PV(pmov_pv_d, 8) + +#undef DO_PMOV_PV + +/* + * TODO: This could use half_unshuffle64 and similar bit tricks to + * compress blocks of bits at once. + */ +#define DO_PMOV_VP(NAME, ESIZE) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + unsigned vl = simd_oprsz(desc); \ + unsigned idx = simd_data(desc); \ + unsigned elements = vl / ESIZE; \ + ARMVectorReg *d = vd; \ + ARMPredicateReg *s = vs; \ + if (idx == 0) { \ + memset(d, 0, vl); \ + } \ + for (unsigned e = 0; e < elements; ++e) { \ + depositn(d->d, elements * idx + e, 1, extractn(s->p, e * ESIZE, 1)); \ + } \ +} + +DO_PMOV_VP(pmov_vp_h, 2) +DO_PMOV_VP(pmov_vp_s, 4) +DO_PMOV_VP(pmov_vp_d, 8) + +#undef DO_PMOV_VP + typedef void tb_impl_fn(void *, void *, void *, void *, uintptr_t, bool); static inline void do_tbl1(void *vd, void *vn, void *vm, uint32_t desc, 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 gen_helper_gvec_3 * const tbx_fns[4] = { }; TRANS_FEAT(TBX, aa64_sve2, gen_gvec_ool_arg_zzz, tbx_fns[a->esz], a, 0) +static bool trans_PMOV_pv(DisasContext *s, arg_PMOV_pv *a) +{ + static gen_helper_gvec_2 * const fns[4] = { + NULL, gen_helper_pmov_pv_h, + gen_helper_pmov_pv_s, gen_helper_pmov_pv_d + }; + unsigned vl, pl, vofs, pofs; + TCGv_i64 tmp; + + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + vl = vec_full_reg_size(s); + if (a->esz != MO_8) { + tcg_gen_gvec_2_ool(pred_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vl, vl, a->imm, fns[a->esz]); + return true; + } + + /* + * Copy the low PL bytes from vector Zn, zero-extending to a + * multiple of 8 bytes, so that Pd is properly cleared. + */ + + pl = vl / 8; + pofs = pred_full_reg_offset(s, a->rd); + vofs = vec_full_reg_offset(s, a->rn); + + QEMU_BUILD_BUG_ON(sizeof(ARMPredicateReg) != 32); + for (unsigned i = 32; i >= 8; i >>= 1) { + if (pl & i) { + tcg_gen_gvec_mov(MO_64, pofs, vofs, i, i); + pofs += i; + vofs += i; + } + } + switch (pl & 7) { + case 0: + return true; + case 2: + tmp = tcg_temp_new_i64(); + tcg_gen_ld16u_i64(tmp, tcg_env, vofs + (HOST_BIG_ENDIAN ? 6 : 0)); + break; + case 4: + tmp = tcg_temp_new_i64(); + tcg_gen_ld32u_i64(tmp, tcg_env, vofs + (HOST_BIG_ENDIAN ? 4 : 0)); + break; + case 6: + tmp = tcg_temp_new_i64(); + tcg_gen_ld_i64(tmp, tcg_env, vofs); + tcg_gen_extract_i64(tmp, tmp, 0, 48); + break; + default: + g_assert_not_reached(); + } + tcg_gen_st_i64(tmp, tcg_env, pofs); + return true; +} + +static bool trans_PMOV_vp(DisasContext *s, arg_PMOV_pv *a) +{ + static gen_helper_gvec_2 * const fns[4] = { + NULL, gen_helper_pmov_vp_h, + gen_helper_pmov_vp_s, gen_helper_pmov_vp_d + }; + unsigned vl; + + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + vl = vec_full_reg_size(s); + + if (a->esz == MO_8) { + /* + * The low PL bytes are copied from Pn to Zd unchanged. + * We know that the unused portion of Pn is zero, and + * that imm == 0, so the balance of Zd must be zeroed. + */ + tcg_gen_gvec_mov(MO_64, vec_full_reg_offset(s, a->rd), + pred_full_reg_offset(s, a->rn), + size_for_gvec(vl / 8), vl); + } else { + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->rd), + pred_full_reg_offset(s, a->rn), + vl, vl, a->imm, fns[a->esz]); + } + return true; +} + static bool trans_UNPK(DisasContext *s, arg_UNPK *a) { static gen_helper_gvec_2 * const fns[4][2] = { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-92-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 10 ++++++++++ target/arm/tcg/sve.decode | 6 ++++++ target/arm/tcg/sve_helper.c | 29 +++++++++++++++++++++++++++++ target/arm/tcg/translate-sve.c | 19 ++++++++++++++++++- 4 files changed, 63 insertions(+), 1 deletion(-) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_zip_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_zip_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_zip_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_zipq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_zipq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_zipq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_zipq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_uzp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_uzp_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uzpq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uzpq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uzpq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uzpq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_trn_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ UZP2_q 00000101 10 1 ..... 000 011 ..... ..... @rd_rn_rm_e0 TRN1_q 00000101 10 1 ..... 000 110 ..... ..... @rd_rn_rm_e0 TRN2_q 00000101 10 1 ..... 000 111 ..... ..... @rd_rn_rm_e0 +# SVE2.1 permute vector elements (quadwords) +ZIPQ1 01000100 .. 0 ..... 111 000 ..... ..... @rd_rn_rm +ZIPQ2 01000100 .. 0 ..... 111 001 ..... ..... @rd_rn_rm +UZPQ1 01000100 .. 0 ..... 111 010 ..... ..... @rd_rn_rm +UZPQ2 01000100 .. 0 ..... 111 011 ..... ..... @rd_rn_rm + ### SVE Permute - Predicated Group # SVE compress active elements 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 @@ DO_UZP(sve_uzp_s, uint32_t, H1_4) DO_UZP(sve_uzp_d, uint64_t, H1_8) DO_UZP(sve2_uzp_q, Int128, ) +typedef void perseg_zzz_fn(void *vd, void *vn, void *vm, uint32_t desc); + +static void do_perseg_zzz(void *vd, void *vn, void *vm, + uint32_t desc, perseg_zzz_fn *fn) +{ + intptr_t oprsz = simd_oprsz(desc); + + desc = simd_desc(16, 16, simd_data(desc)); + for (intptr_t i = 0; i < oprsz; i += 16) { + fn(vd + i, vn + i, vm + i, desc); + } +} + +#define DO_PERSEG_ZZZ(NAME, FUNC) \ + void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ + { do_perseg_zzz(vd, vn, vm, desc, FUNC); } + +DO_PERSEG_ZZZ(sve2p1_uzpq_b, helper_sve_uzp_b) +DO_PERSEG_ZZZ(sve2p1_uzpq_h, helper_sve_uzp_h) +DO_PERSEG_ZZZ(sve2p1_uzpq_s, helper_sve_uzp_s) +DO_PERSEG_ZZZ(sve2p1_uzpq_d, helper_sve_uzp_d) + +DO_PERSEG_ZZZ(sve2p1_zipq_b, helper_sve_zip_b) +DO_PERSEG_ZZZ(sve2p1_zipq_h, helper_sve_zip_h) +DO_PERSEG_ZZZ(sve2p1_zipq_s, helper_sve_zip_s) +DO_PERSEG_ZZZ(sve2p1_zipq_d, helper_sve_zip_d) + +#undef DO_PERSEG_ZZZ + #define DO_TRN(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ 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_NONSTREAMING(ZIP2_q, aa64_sve_f64mm, do_interleave_q, gen_helper_sve2_zip_q, a, QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2) +static gen_helper_gvec_3 * const zipq_fns[4] = { + gen_helper_sve2p1_zipq_b, gen_helper_sve2p1_zipq_h, + gen_helper_sve2p1_zipq_s, gen_helper_sve2p1_zipq_d, +}; +TRANS_FEAT(ZIPQ1, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + zipq_fns[a->esz], a, 0) +TRANS_FEAT(ZIPQ2, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + zipq_fns[a->esz], a, 16 / 2) + static gen_helper_gvec_3 * const uzp_fns[4] = { gen_helper_sve_uzp_b, gen_helper_sve_uzp_h, gen_helper_sve_uzp_s, gen_helper_sve_uzp_d, }; - TRANS_FEAT(UZP1_z, aa64_sve, gen_gvec_ool_arg_zzz, uzp_fns[a->esz], a, 0) TRANS_FEAT(UZP2_z, aa64_sve, gen_gvec_ool_arg_zzz, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT_NONSTREAMING(UZP1_q, aa64_sve_f64mm, do_interleave_q, TRANS_FEAT_NONSTREAMING(UZP2_q, aa64_sve_f64mm, do_interleave_q, gen_helper_sve2_uzp_q, a, 16) +static gen_helper_gvec_3 * const uzpq_fns[4] = { + gen_helper_sve2p1_uzpq_b, gen_helper_sve2p1_uzpq_h, + gen_helper_sve2p1_uzpq_s, gen_helper_sve2p1_uzpq_d, +}; +TRANS_FEAT(UZPQ1, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + uzpq_fns[a->esz], a, 0) +TRANS_FEAT(UZPQ2, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + uzpq_fns[a->esz], a, 1 << a->esz) + static gen_helper_gvec_3 * const trn_fns[4] = { gen_helper_sve_trn_b, gen_helper_sve_trn_h, gen_helper_sve_trn_s, gen_helper_sve_trn_d, -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-93-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 10 ++++++++++ target/arm/tcg/sve.decode | 3 +++ target/arm/tcg/sve_helper.c | 10 ++++++++++ target/arm/tcg/translate-sve.c | 14 ++++++++++++++ 4 files changed, 37 insertions(+) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_tbl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tblq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tblq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tblq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tblq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve2_tbx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_tbx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_tbx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_tbx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tbxq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tbxq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tbxq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tbxq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(sve_sunpk_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_sunpk_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_sunpk_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ ZIPQ2 01000100 .. 0 ..... 111 001 ..... ..... @rd_rn_rm UZPQ1 01000100 .. 0 ..... 111 010 ..... ..... @rd_rn_rm UZPQ2 01000100 .. 0 ..... 111 011 ..... ..... @rd_rn_rm +TBLQ 01000100 .. 0 ..... 111 110 ..... ..... @rd_rn_rm +TBXQ 00000101 .. 1 ..... 001 101 ..... ..... @rd_rn_rm + ### SVE Permute - Predicated Group # SVE compress active elements 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 @@ DO_PERSEG_ZZZ(sve2p1_zipq_h, helper_sve_zip_h) DO_PERSEG_ZZZ(sve2p1_zipq_s, helper_sve_zip_s) DO_PERSEG_ZZZ(sve2p1_zipq_d, helper_sve_zip_d) +DO_PERSEG_ZZZ(sve2p1_tblq_b, helper_sve_tbl_b) +DO_PERSEG_ZZZ(sve2p1_tblq_h, helper_sve_tbl_h) +DO_PERSEG_ZZZ(sve2p1_tblq_s, helper_sve_tbl_s) +DO_PERSEG_ZZZ(sve2p1_tblq_d, helper_sve_tbl_d) + +DO_PERSEG_ZZZ(sve2p1_tbxq_b, helper_sve2_tbx_b) +DO_PERSEG_ZZZ(sve2p1_tbxq_h, helper_sve2_tbx_h) +DO_PERSEG_ZZZ(sve2p1_tbxq_s, helper_sve2_tbx_s) +DO_PERSEG_ZZZ(sve2p1_tbxq_d, helper_sve2_tbx_d) + #undef DO_PERSEG_ZZZ #define DO_TRN(NAME, TYPE, H) \ 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 gen_helper_gvec_4 * const sve2_tbl_fns[4] = { TRANS_FEAT(TBL_sve2, aa64_sve2, gen_gvec_ool_zzzz, sve2_tbl_fns[a->esz], a->rd, a->rn, (a->rn + 1) % 32, a->rm, 0) +static gen_helper_gvec_3 * const tblq_fns[4] = { + gen_helper_sve2p1_tblq_b, gen_helper_sve2p1_tblq_h, + gen_helper_sve2p1_tblq_s, gen_helper_sve2p1_tblq_d +}; +TRANS_FEAT(TBLQ, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + tblq_fns[a->esz], a, 0) + static gen_helper_gvec_3 * const tbx_fns[4] = { gen_helper_sve2_tbx_b, gen_helper_sve2_tbx_h, gen_helper_sve2_tbx_s, gen_helper_sve2_tbx_d }; TRANS_FEAT(TBX, aa64_sve2, gen_gvec_ool_arg_zzz, tbx_fns[a->esz], a, 0) +static gen_helper_gvec_3 * const tbxq_fns[4] = { + gen_helper_sve2p1_tbxq_b, gen_helper_sve2p1_tbxq_h, + gen_helper_sve2p1_tbxq_s, gen_helper_sve2p1_tbxq_d +}; +TRANS_FEAT(TBXQ, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + tbxq_fns[a->esz], a, 0) + static bool trans_PMOV_pv(DisasContext *s, arg_PMOV_pv *a) { static gen_helper_gvec_2 * const fns[4] = { -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Implement the SVE2p1 consecutive register LD1/ST1, and the SME2 strided register LD1/ST1. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-94-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 16 ++ target/arm/tcg/sve.decode | 50 ++++ target/arm/tcg/sve_helper.c | 493 +++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sve.c | 103 +++++++ 4 files changed, 662 insertions(+) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(pmov_pv_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(pmov_vp_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(pmov_vp_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(pmov_vp_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2p1_ld1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) + +DEF_HELPER_FLAGS_5(sve2p1_st1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm FCLAMP 01100100 .. 1 ..... 001001 ..... ..... @rda_rn_rm + +### SVE2p1 multi-vec contiguous load + +&zcrr_ldst rd png rn rm esz nreg +&zcri_ldst rd png rn imm esz nreg +%png 10:3 !function=plus_8 +%zd_ax2 1:4 !function=times_2 +%zd_ax4 2:3 !function=times_4 + +LD1_zcrr 10100000000 rm:5 0 esz:2 ... rn:5 .... - \ + &zcrr_ldst %png rd=%zd_ax2 nreg=2 +LD1_zcrr 10100000000 rm:5 1 esz:2 ... rn:5 ... 0- \ + &zcrr_ldst %png rd=%zd_ax4 nreg=4 + +ST1_zcrr 10100000001 rm:5 0 esz:2 ... rn:5 .... - \ + &zcrr_ldst %png rd=%zd_ax2 nreg=2 +ST1_zcrr 10100000001 rm:5 1 esz:2 ... rn:5 ... 0- \ + &zcrr_ldst %png rd=%zd_ax4 nreg=4 + +LD1_zcri 101000000100 imm:s4 0 esz:2 ... rn:5 .... - \ + &zcri_ldst %png rd=%zd_ax2 nreg=2 +LD1_zcri 101000000100 imm:s4 1 esz:2 ... rn:5 ... 0- \ + &zcri_ldst %png rd=%zd_ax4 nreg=4 + +ST1_zcri 101000000110 imm:s4 0 esz:2 ... rn:5 .... - \ + &zcri_ldst %png rd=%zd_ax2 nreg=2 +ST1_zcri 101000000110 imm:s4 1 esz:2 ... rn:5 ... 0- \ + &zcri_ldst %png rd=%zd_ax4 nreg=4 + +# Note: N bit and 0 bit (for nreg4) still mashed in rd. +# This is handled within gen_ldst_c(). +LD1_zcrr_stride 10100001000 rm:5 0 esz:2 ... rn:5 rd:5 \ + &zcrr_ldst %png nreg=2 +LD1_zcrr_stride 10100001000 rm:5 1 esz:2 ... rn:5 rd:5 \ + &zcrr_ldst %png nreg=4 + +ST1_zcrr_stride 10100001001 rm:5 0 esz:2 ... rn:5 rd:5 \ + &zcrr_ldst %png nreg=2 +ST1_zcrr_stride 10100001001 rm:5 1 esz:2 ... rn:5 rd:5 \ + &zcrr_ldst %png nreg=4 + +LD1_zcri_stride 101000010100 imm:s4 0 esz:2 ... rn:5 rd:5 \ + &zcri_ldst %png nreg=2 +LD1_zcri_stride 101000010100 imm:s4 1 esz:2 ... rn:5 rd:5 \ + &zcri_ldst %png nreg=4 + +ST1_zcri_stride 101000010110 imm:s4 0 esz:2 ... rn:5 rd:5 \ + &zcri_ldst %png nreg=2 +ST1_zcri_stride 101000010110 imm:s4 1 esz:2 ... rn:5 rd:5 \ + &zcri_ldst %png nreg=4 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 @@ DO_ST1_ZPZ_D(dd_be, zd, MO_64) #undef DO_ST1_ZPZ_S #undef DO_ST1_ZPZ_D +/* + * SVE2.1 consecutive register load/store + */ + +static unsigned sve2p1_cont_ldst_elements(SVEContLdSt *info, vaddr addr, + uint32_t png, intptr_t reg_max, + int N, int v_esz) +{ + const int esize = 1 << v_esz; + intptr_t reg_off_first = -1, reg_off_last = -1, reg_off_split; + DecodeCounter p = decode_counter(png, reg_max, v_esz); + unsigned b_count = p.count << v_esz; + unsigned b_stride = 1 << (v_esz + p.lg2_stride); + intptr_t page_split; + + /* Set all of the element indices to -1, and the TLB data to 0. */ + memset(info, -1, offsetof(SVEContLdSt, page)); + memset(info->page, 0, sizeof(info->page)); + + if (p.invert) { + if (b_count >= reg_max * N) { + return 0; + } + reg_off_first = b_count; + reg_off_last = reg_max * N - b_stride; + } else { + if (b_count == 0) { + return 0; + } + reg_off_first = 0; + reg_off_last = MIN(b_count - esize, reg_max * N - b_stride); + } + + info->reg_off_first[0] = reg_off_first; + info->mem_off_first[0] = reg_off_first; + + page_split = -(addr | TARGET_PAGE_MASK); + if (reg_off_last + esize <= page_split || reg_off_first >= page_split) { + /* The entire operation fits within a single page. */ + info->reg_off_last[0] = reg_off_last; + return b_stride; + } + + info->page_split = page_split; + reg_off_split = ROUND_DOWN(page_split, esize); + + /* + * This is the last full element on the first page, but it is not + * necessarily active. If there is no full element, i.e. the first + * active element is the one that's split, this value remains -1. + * It is useful as iteration bounds. + */ + if (reg_off_split != 0) { + info->reg_off_last[0] = ROUND_DOWN(reg_off_split - esize, b_stride); + } + + /* Determine if an unaligned element spans the pages. */ + if (page_split & (esize - 1)) { + /* It is helpful to know if the split element is active. */ + if ((reg_off_split & (b_stride - 1)) == 0) { + info->reg_off_split = reg_off_split; + info->mem_off_split = reg_off_split; + } + reg_off_split += esize; + } + + /* + * We do want the first active element on the second page, because + * this may affect the address reported in an exception. + */ + reg_off_split = ROUND_UP(reg_off_split, b_stride); + if (reg_off_split <= reg_off_last) { + info->reg_off_first[1] = reg_off_split; + info->mem_off_first[1] = reg_off_split; + info->reg_off_last[1] = reg_off_last; + } + return b_stride; +} + +static void sve2p1_cont_ldst_watchpoints(SVEContLdSt *info, CPUARMState *env, + target_ulong addr, unsigned estride, + int esize, int wp_access, uintptr_t ra) +{ +#ifndef CONFIG_USER_ONLY + intptr_t count_off, count_last; + int flags0 = info->page[0].flags; + int flags1 = info->page[1].flags; + + if (likely(!((flags0 | flags1) & TLB_WATCHPOINT))) { + return; + } + + /* Indicate that watchpoints are handled. */ + info->page[0].flags = flags0 & ~TLB_WATCHPOINT; + info->page[1].flags = flags1 & ~TLB_WATCHPOINT; + + if (flags0 & TLB_WATCHPOINT) { + count_off = info->reg_off_first[0]; + count_last = info->reg_off_split; + if (count_last < 0) { + count_last = info->reg_off_last[0]; + } + do { + cpu_check_watchpoint(env_cpu(env), addr + count_off, + esize, info->page[0].attrs, wp_access, ra); + count_off += estride; + } while (count_off <= count_last); + } + + count_off = info->reg_off_first[1]; + if ((flags1 & TLB_WATCHPOINT) && count_off >= 0) { + count_last = info->reg_off_last[1]; + do { + cpu_check_watchpoint(env_cpu(env), addr + count_off, + esize, info->page[1].attrs, + wp_access, ra); + count_off += estride; + } while (count_off <= count_last); + } +#endif +} + +static void sve2p1_cont_ldst_mte_check(SVEContLdSt *info, CPUARMState *env, + target_ulong addr, unsigned estride, + int esize, uint32_t mtedesc, + uintptr_t ra) +{ + intptr_t count_off, count_last; + + /* + * TODO: estride is always a small power of two, <= 8. + * Manipulate the stride within the loops such that + * - first iteration hits addr + off, as required, + * - second iteration hits ALIGN_UP(addr, 16), + * - other iterations advance addr by 16. + * This will minimize the probing to once per MTE granule. + */ + + /* Process the page only if MemAttr == Tagged. */ + if (info->page[0].tagged) { + count_off = info->reg_off_first[0]; + count_last = info->reg_off_split; + if (count_last < 0) { + count_last = info->reg_off_last[0]; + } + + do { + mte_check(env, mtedesc, addr + count_off, ra); + count_off += estride; + } while (count_off <= count_last); + } + + count_off = info->reg_off_first[1]; + if (count_off >= 0 && info->page[1].tagged) { + count_last = info->reg_off_last[1]; + do { + mte_check(env, mtedesc, addr + count_off, ra); + count_off += estride; + } while (count_off <= count_last); + } +} + +static inline QEMU_ALWAYS_INLINE +void sve2p1_ld1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr, + uint32_t png, uint32_t desc, + const uintptr_t ra, const MemOp esz, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2; + const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4); + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + const intptr_t reg_max = simd_oprsz(desc); + const unsigned esize = 1 << esz; + intptr_t count_off, count_last; + intptr_t reg_off, reg_last, reg_n; + SVEContLdSt info; + unsigned estride, flags; + void *host; + + estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz); + if (estride == 0) { + /* The entire predicate was false; no load occurs. */ + for (unsigned n = 0; n < N; n++) { + memset(zd + n * rstride, 0, reg_max); + } + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, ra); + + /* Handle watchpoints for all active elements. */ + sve2p1_cont_ldst_watchpoints(&info, env, addr, estride, + esize, BP_MEM_READ, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve2p1_cont_ldst_mte_check(&info, env, estride, addr, + esize, mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. Perform the load + * into scratch memory to preserve register state until the end. + */ + ARMVectorReg scratch[4] = { }; + + count_off = info.reg_off_first[0]; + count_last = info.reg_off_last[1]; + if (count_last < 0) { + count_last = info.reg_off_split; + if (count_last < 0) { + count_last = info.reg_off_last[0]; + } + } + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + + do { + reg_last = MIN(count_last - count_off, reg_max - esize); + do { + tlb_fn(env, &scratch[reg_n], reg_off, addr + count_off, ra); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + for (unsigned n = 0; n < N; ++n) { + memcpy(&zd[n * rstride], &scratch[n], reg_max); + } + return; + } + + /* The entire operation is in RAM, on valid pages. */ + + for (unsigned n = 0; n < N; ++n) { + memset(&zd[n * rstride], 0, reg_max); + } + + count_off = info.reg_off_first[0]; + count_last = info.reg_off_last[0]; + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + host = info.page[0].host; + + set_helper_retaddr(ra); + + do { + reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize); + do { + host_fn(&zd[reg_n * rstride], reg_off, host + count_off); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + clear_helper_retaddr(); + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + count_off = info.reg_off_split; + if (unlikely(count_off >= 0)) { + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra); + } + + count_off = info.reg_off_first[1]; + if (unlikely(count_off >= 0)) { + count_last = info.reg_off_last[1]; + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + host = info.page[1].host; + + set_helper_retaddr(ra); + + do { + reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize); + do { + host_fn(&zd[reg_n * rstride], reg_off, host + count_off); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + clear_helper_retaddr(); + } +} + +void HELPER(sve2p1_ld1bb_c)(CPUARMState *env, void *vd, target_ulong addr, + uint32_t png, uint32_t desc) +{ + sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), MO_8, + sve_ld1bb_host, sve_ld1bb_tlb); +} + +#define DO_LD1_2(NAME, ESZ) \ +void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd, \ + target_ulong addr, uint32_t png, \ + uint32_t desc) \ +{ \ + sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ + sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ +} \ +void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd, \ + target_ulong addr, uint32_t png, \ + uint32_t desc) \ +{ \ + sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ + sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ +} + +DO_LD1_2(ld1hh, MO_16) +DO_LD1_2(ld1ss, MO_32) +DO_LD1_2(ld1dd, MO_64) + +#undef DO_LD1_2 + +static inline QEMU_ALWAYS_INLINE +void sve2p1_st1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr, + uint32_t png, uint32_t desc, + const uintptr_t ra, const int esz, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2; + const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4); + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + const intptr_t reg_max = simd_oprsz(desc); + const unsigned esize = 1 << esz; + intptr_t count_off, count_last; + intptr_t reg_off, reg_last, reg_n; + SVEContLdSt info; + unsigned estride, flags; + void *host; + + estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz); + if (estride == 0) { + /* The entire predicate was false; no store occurs. */ + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_STORE, ra); + + /* Handle watchpoints for all active elements. */ + sve2p1_cont_ldst_watchpoints(&info, env, addr, estride, + esize, BP_MEM_WRITE, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve2p1_cont_ldst_mte_check(&info, env, estride, addr, + esize, mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. Perform the load + * into scratch memory to preserve register state until the end. + */ + count_off = info.reg_off_first[0]; + count_last = info.reg_off_last[1]; + if (count_last < 0) { + count_last = info.reg_off_split; + if (count_last < 0) { + count_last = info.reg_off_last[0]; + } + } + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + + do { + reg_last = MIN(count_last - count_off, reg_max - esize); + do { + tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + return; + } + + /* The entire operation is in RAM, on valid pages. */ + + count_off = info.reg_off_first[0]; + count_last = info.reg_off_last[0]; + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + host = info.page[0].host; + + set_helper_retaddr(ra); + + do { + reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize); + do { + host_fn(&zd[reg_n * rstride], reg_off, host + count_off); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + clear_helper_retaddr(); + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + count_off = info.reg_off_split; + if (unlikely(count_off >= 0)) { + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra); + } + + count_off = info.reg_off_first[1]; + if (unlikely(count_off >= 0)) { + count_last = info.reg_off_last[1]; + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + host = info.page[1].host; + + set_helper_retaddr(ra); + + do { + reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize); + do { + host_fn(&zd[reg_n * rstride], reg_off, host + count_off); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + clear_helper_retaddr(); + } +} + +void HELPER(sve2p1_st1bb_c)(CPUARMState *env, void *vd, target_ulong addr, + uint32_t png, uint32_t desc) +{ + sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), MO_8, + sve_st1bb_host, sve_st1bb_tlb); +} + +#define DO_ST1_2(NAME, ESZ) \ +void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd, \ + target_ulong addr, uint32_t png, \ + uint32_t desc) \ +{ \ + sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ + sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ +} \ +void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd, \ + target_ulong addr, uint32_t png, \ + uint32_t desc) \ +{ \ + sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ + sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ +} + +DO_ST1_2(st1hh, MO_16) +DO_ST1_2(st1ss, MO_32) +DO_ST1_2(st1dd, MO_64) + +#undef DO_ST1_2 + void HELPER(sve2_eor3)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc) / 8; 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(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, gen_helper_sme2_uqcvtn_sh, a->rd, a->rn, 0) TRANS_FEAT(SQCVTUN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, gen_helper_sme2_sqcvtun_sh, a->rd, a->rn, 0) + +static bool gen_ldst_c(DisasContext *s, TCGv_i64 addr, int zd, int png, + MemOp esz, bool is_write, int n, bool strided) +{ + typedef void ldst_c_fn(TCGv_env, TCGv_ptr, TCGv_i64, + TCGv_i32, TCGv_i32); + static ldst_c_fn * const f_ldst[2][2][4] = { + { { gen_helper_sve2p1_ld1bb_c, + gen_helper_sve2p1_ld1hh_le_c, + gen_helper_sve2p1_ld1ss_le_c, + gen_helper_sve2p1_ld1dd_le_c, }, + { gen_helper_sve2p1_ld1bb_c, + gen_helper_sve2p1_ld1hh_be_c, + gen_helper_sve2p1_ld1ss_be_c, + gen_helper_sve2p1_ld1dd_be_c, } }, + + { { gen_helper_sve2p1_st1bb_c, + gen_helper_sve2p1_st1hh_le_c, + gen_helper_sve2p1_st1ss_le_c, + gen_helper_sve2p1_st1dd_le_c, }, + { gen_helper_sve2p1_st1bb_c, + gen_helper_sve2p1_st1hh_be_c, + gen_helper_sve2p1_st1ss_be_c, + gen_helper_sve2p1_st1dd_be_c, } } + }; + + TCGv_i32 t_png, t_desc; + TCGv_ptr t_zd; + uint32_t desc, lg2_rstride = 0; + bool be = s->be_data == MO_BE; + + assert(n == 2 || n == 4); + if (strided) { + lg2_rstride = 3; + if (n == 4) { + /* Validate ZD alignment. */ + if (zd & 4) { + return false; + } + lg2_rstride = 2; + } + /* Ignore non-temporal bit */ + zd &= ~8; + } + + if (strided || !dc_isar_feature(aa64_sve2p1, s) + ? !sme_sm_enabled_check(s) + : !sve_access_check(s)) { + return true; + } + + if (!s->mte_active[0]) { + addr = clean_data_tbi(s, addr); + } + + desc = n == 2 ? 0 : 1; + desc = desc | (lg2_rstride << 1); + desc = make_svemte_desc(s, vec_full_reg_size(s), 1, esz, is_write, desc); + t_desc = tcg_constant_i32(desc); + + t_png = tcg_temp_new_i32(); + tcg_gen_ld16u_i32(t_png, tcg_env, + pred_full_reg_offset(s, png) ^ + (HOST_BIG_ENDIAN ? 6 : 0)); + + t_zd = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(t_zd, tcg_env, vec_full_reg_offset(s, zd)); + + f_ldst[is_write][be][esz](tcg_env, t_zd, addr, t_png, t_desc); + return true; +} + +static bool gen_ldst_zcrr_c(DisasContext *s, arg_zcrr_ldst *a, + bool is_write, bool strided) +{ + TCGv_i64 addr = tcg_temp_new_i64(); + + tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->esz); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write, + a->nreg, strided); +} + +static bool gen_ldst_zcri_c(DisasContext *s, arg_zcri_ldst *a, + bool is_write, bool strided) +{ + TCGv_i64 addr = tcg_temp_new_i64(); + + tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), + a->imm * a->nreg * vec_full_reg_size(s)); + return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write, + a->nreg, strided); +} + +TRANS_FEAT(LD1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, false, false) +TRANS_FEAT(LD1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, false, false) +TRANS_FEAT(ST1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, true, false) +TRANS_FEAT(ST1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, true, false) + +TRANS_FEAT(LD1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, false, true) +TRANS_FEAT(LD1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, false, true) +TRANS_FEAT(ST1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, true, true) +TRANS_FEAT(ST1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, true, true) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> The msz > esz encodings are reserved, and some of them are about to be reused. Split these patterns so that the new insns do not overlap. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-95-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve.decode | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ # Stores; user must fill in ESZ, MSZ, NREG as needed. @rprr_store ....... .. .. rm:5 ... pg:3 rn:5 rd:5 &rprr_store -@rpri_store_msz ....... msz:2 .. . imm:s4 ... pg:3 rn:5 rd:5 &rpri_store +@rpri_store ....... .. .. . imm:s4 ... pg:3 rn:5 rd:5 &rpri_store @rprr_store_esz_n0 ....... .. esz:2 rm:5 ... pg:3 rn:5 rd:5 \ &rprr_store nreg=0 @rprr_scatter_store ....... msz:2 .. rm:5 ... pg:3 rn:5 rd:5 \ @@ -XXX,XX +XXX,XX @@ STR_zri 1110010 11 0. ..... 010 ... ..... ..... @rd_rn_i9 # SVE contiguous store (scalar plus immediate) # ST1B, ST1H, ST1W, ST1D; require msz <= esz -ST_zpri 1110010 .. esz:2 0.... 111 ... ..... ..... \ - @rpri_store_msz nreg=0 +ST_zpri 1110010 00 esz:2 0.... 111 ... ..... ..... \ + @rpri_store msz=0 nreg=0 +ST_zpri 1110010 01 esz:2 0.... 111 ... ..... ..... \ + @rpri_store msz=1 nreg=0 +ST_zpri 1110010 10 10 0.... 111 ... ..... ..... \ + @rpri_store msz=2 esz=2 nreg=0 +ST_zpri 1110010 10 11 0.... 111 ... ..... ..... \ + @rpri_store msz=2 esz=3 nreg=0 +ST_zpri 1110010 11 11 0.... 111 ... ..... ..... \ + @rpri_store msz=3 esz=3 nreg=0 # SVE contiguous store (scalar plus scalar) # ST1B, ST1H, ST1W, ST1D; require msz <= esz @@ -XXX,XX +XXX,XX @@ ST_zprr 1110010 00 .. ..... 010 ... ..... ..... \ @rprr_store_esz_n0 msz=0 ST_zprr 1110010 01 .. ..... 010 ... ..... ..... \ @rprr_store_esz_n0 msz=1 -ST_zprr 1110010 10 .. ..... 010 ... ..... ..... \ - @rprr_store_esz_n0 msz=2 +ST_zprr 1110010 10 10 ..... 010 ... ..... ..... \ + @rprr_store msz=2 esz=2 nreg=0 +ST_zprr 1110010 10 11 ..... 010 ... ..... ..... \ + @rprr_store msz=2 esz=3 nreg=0 ST_zprr 1110010 11 11 ..... 010 ... ..... ..... \ @rprr_store msz=3 esz=3 nreg=0 # SVE contiguous non-temporal store (scalar plus immediate) (nreg == 0) # SVE store multiple structures (scalar plus immediate) (nreg != 0) ST_zpri 1110010 .. nreg:2 1.... 111 ... ..... ..... \ - @rpri_store_msz esz=%size_23 + @rpri_store msz=%size_23 esz=%size_23 # SVE contiguous non-temporal store (scalar plus scalar) (nreg == 0) # SVE store multiple structures (scalar plus scalar) (nreg != 0) -ST_zprr 1110010 msz:2 nreg:2 ..... 011 ... ..... ..... \ - @rprr_store esz=%size_23 +ST_zprr 1110010 .. nreg:2 ..... 011 ... ..... ..... \ + @rprr_store msz=%size_23 esz=%size_23 # SVE 32-bit scatter store (scalar plus 32-bit scaled offsets) # Require msz > 0 && msz <= esz. -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-96-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 22 +++++ target/arm/tcg/sve_ldst_internal.h | 26 ++++++ target/arm/tcg/sve.decode | 20 +++++ target/arm/tcg/sve_helper.c | 6 ++ target/arm/tcg/translate-sve.c | 136 +++++++++++++++++++++++------ 5 files changed, 183 insertions(+), 27 deletions(-) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ld1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1squ_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1dqu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1squ_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1dqu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld2bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ld1hds_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sdu_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sds_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1squ_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1dqu_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1sdu_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sds_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1squ_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1dqu_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ldff1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_st1hd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1dq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1dq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_st1bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st2bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st3bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_st1hd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1dq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1dq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_6(sve_ldbsu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldhsu_le_zsu, TCG_CALL_NO_WG, diff --git a/target/arm/tcg/sve_ldst_internal.h b/target/arm/tcg/sve_ldst_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve_ldst_internal.h +++ b/target/arm/tcg/sve_ldst_internal.h @@ -XXX,XX +XXX,XX @@ DO_ST_PRIM_2(sd, H1_8, uint64_t, uint32_t, stl) DO_LD_PRIM_2(dd, H1_8, uint64_t, uint64_t, ldq) DO_ST_PRIM_2(dd, H1_8, uint64_t, uint64_t, stq) +#define DO_LD_PRIM_3(NAME, FUNC) \ + static inline void sve_##NAME##_host(void *vd, \ + intptr_t reg_off, void *host) \ + { sve_##FUNC##_host(vd, reg_off, host); \ + *(uint64_t *)(vd + reg_off + 8) = 0; } \ + static inline void sve_##NAME##_tlb(CPUARMState *env, void *vd, \ + intptr_t reg_off, target_ulong addr, uintptr_t ra) \ + { sve_##FUNC##_tlb(env, vd, reg_off, addr, ra); \ + *(uint64_t *)(vd + reg_off + 8) = 0; } + +DO_LD_PRIM_3(ld1squ_be, ld1sdu_be) +DO_LD_PRIM_3(ld1squ_le, ld1sdu_le) +DO_LD_PRIM_3(ld1dqu_be, ld1dd_be) +DO_LD_PRIM_3(ld1dqu_le, ld1dd_le) + +#define sve_st1sq_be_host sve_st1sd_be_host +#define sve_st1sq_le_host sve_st1sd_le_host +#define sve_st1sq_be_tlb sve_st1sd_be_tlb +#define sve_st1sq_le_tlb sve_st1sd_le_tlb + +#define sve_st1dq_be_host sve_st1dd_be_host +#define sve_st1dq_le_host sve_st1dd_le_host +#define sve_st1dq_be_tlb sve_st1dd_be_tlb +#define sve_st1dq_le_tlb sve_st1dd_le_tlb + #undef DO_LD_TLB #undef DO_ST_TLB #undef DO_LD_HOST @@ -XXX,XX +XXX,XX @@ DO_ST_PRIM_2(dd, H1_8, uint64_t, uint64_t, stq) #undef DO_ST_PRIM_1 #undef DO_LD_PRIM_2 #undef DO_ST_PRIM_2 +#undef DO_LD_PRIM_3 /* * Resolve the guest virtual address to info->host and info->flags. diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ LD1_zpiz 1000010 .. 01 ..... 1.. ... ..... ..... \ # SVE contiguous load (scalar plus scalar) LD_zprr 1010010 .... ..... 010 ... ..... ..... @rprr_load_dt nreg=0 +# LD1W (128-bit element) +LD_zprr 1010010 1000 rm:5 100 pg:3 rn:5 rd:5 \ + &rprr_load dtype=16 nreg=0 +# LD1D (128-bit element) +LD_zprr 1010010 1100 rm:5 100 pg:3 rn:5 rd:5 \ + &rprr_load dtype=17 nreg=0 # SVE contiguous first-fault load (scalar plus scalar) LDFF1_zprr 1010010 .... ..... 011 ... ..... ..... @rprr_load_dt nreg=0 # SVE contiguous load (scalar plus immediate) LD_zpri 1010010 .... 0.... 101 ... ..... ..... @rpri_load_dt nreg=0 +# LD1W (128-bit element) +LD_zpri 1010010 1000 1 imm:s4 001 pg:3 rn:5 rd:5 \ + &rpri_load dtype=16 nreg=0 +# LD1D (128-bit element) +LD_zpri 1010010 1100 1 imm:s4 001 pg:3 rn:5 rd:5 \ + &rpri_load dtype=17 nreg=0 # SVE contiguous non-fault load (scalar plus immediate) LDNF1_zpri 1010010 .... 1.... 101 ... ..... ..... @rpri_load_dt nreg=0 @@ -XXX,XX +XXX,XX @@ ST_zpri 1110010 10 11 0.... 111 ... ..... ..... \ @rpri_store msz=2 esz=3 nreg=0 ST_zpri 1110010 11 11 0.... 111 ... ..... ..... \ @rpri_store msz=3 esz=3 nreg=0 +ST_zpri 1110010 10 00 0.... 111 ... ..... ..... \ + @rpri_store msz=2 esz=4 nreg=0 +ST_zpri 1110010 11 10 0.... 111 ... ..... ..... \ + @rpri_store msz=3 esz=4 nreg=0 # SVE contiguous store (scalar plus scalar) # ST1B, ST1H, ST1W, ST1D; require msz <= esz @@ -XXX,XX +XXX,XX @@ ST_zprr 1110010 10 11 ..... 010 ... ..... ..... \ @rprr_store msz=2 esz=3 nreg=0 ST_zprr 1110010 11 11 ..... 010 ... ..... ..... \ @rprr_store msz=3 esz=3 nreg=0 +ST_zprr 1110010 10 00 ..... 010 ... ..... ..... \ + @rprr_store msz=2 esz=4 nreg=0 +ST_zprr 1110010 11 10 ..... 010 ... ..... ..... \ + @rprr_store msz=3 esz=4 nreg=0 # SVE contiguous non-temporal store (scalar plus immediate) (nreg == 0) # SVE store multiple structures (scalar plus immediate) (nreg != 0) 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 @@ DO_LD1_2(ld1sds, MO_64, MO_32) DO_LD1_2(ld1dd, MO_64, MO_64) +DO_LD1_2(ld1squ, MO_32, MO_128) +DO_LD1_2(ld1dqu, MO_64, MO_128) + #undef DO_LD1_1 #undef DO_LD1_2 @@ -XXX,XX +XXX,XX @@ DO_STN_2(2, dd, MO_64, MO_64) DO_STN_2(3, dd, MO_64, MO_64) DO_STN_2(4, dd, MO_64, MO_64) +DO_STN_2(1, sq, MO_128, MO_32) +DO_STN_2(1, dq, MO_128, MO_64) + #undef DO_STN_1 #undef DO_STN_2 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 trans_STR_pri(DisasContext *s, arg_rri *a) */ /* The memory mode of the dtype. */ -static const MemOp dtype_mop[16] = { +static const MemOp dtype_mop[19] = { MO_UB, MO_UB, MO_UB, MO_UB, MO_SL, MO_UW, MO_UW, MO_UW, MO_SW, MO_SW, MO_UL, MO_UL, - MO_SB, MO_SB, MO_SB, MO_UQ + MO_SB, MO_SB, MO_SB, MO_UQ, + /* Artificial values used by decode */ + MO_UL, MO_UQ, MO_128, }; #define dtype_msz(x) (dtype_mop[x] & MO_SIZE) /* The vector element size of dtype. */ -static const uint8_t dtype_esz[16] = { +static const uint8_t dtype_esz[19] = { 0, 1, 2, 3, 3, 1, 2, 3, 3, 2, 2, 3, - 3, 2, 1, 3 + 3, 2, 1, 3, + /* Artificial values used by decode */ + 4, 4, 4, }; uint32_t make_svemte_desc(DisasContext *s, unsigned vsz, uint32_t nregs, @@ -XXX,XX +XXX,XX @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, } /* Indexed by [mte][be][dtype][nreg] */ -static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { +static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = { { /* mte inactive, little-endian */ { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, { gen_helper_sve_ld1dd_le_r, gen_helper_sve_ld2dd_le_r, - gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r } }, + gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r }, + + { gen_helper_sve_ld1squ_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dqu_le_r, NULL, NULL, NULL }, + }, /* mte inactive, big-endian */ { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, { gen_helper_sve_ld1dd_be_r, gen_helper_sve_ld2dd_be_r, - gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r } } }, + gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r }, + + { gen_helper_sve_ld1squ_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dqu_be_r, NULL, NULL, NULL }, + }, + }, { /* mte active, little-endian */ { { gen_helper_sve_ld1bb_r_mte, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { { gen_helper_sve_ld1dd_le_r_mte, gen_helper_sve_ld2dd_le_r_mte, gen_helper_sve_ld3dd_le_r_mte, - gen_helper_sve_ld4dd_le_r_mte } }, + gen_helper_sve_ld4dd_le_r_mte }, + + { gen_helper_sve_ld1squ_le_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1dqu_le_r_mte, NULL, NULL, NULL }, + }, /* mte active, big-endian */ { { gen_helper_sve_ld1bb_r_mte, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { { gen_helper_sve_ld1dd_be_r_mte, gen_helper_sve_ld2dd_be_r_mte, gen_helper_sve_ld3dd_be_r_mte, - gen_helper_sve_ld4dd_be_r_mte } } }, + gen_helper_sve_ld4dd_be_r_mte }, + + { gen_helper_sve_ld1squ_be_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1dqu_be_r_mte, NULL, NULL, NULL }, + }, + }, }; static void do_ld_zpa(DisasContext *s, int zt, int pg, @@ -XXX,XX +XXX,XX @@ static void do_ld_zpa(DisasContext *s, int zt, int pg, static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a) { - if (a->rm == 31 || !dc_isar_feature(aa64_sve, s)) { + if (a->rm == 31) { return false; } + + /* dtypes 16 and 17 are artificial, representing 128-bit element */ + if (a->dtype < 16) { + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + } else { + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; + } + if (sve_access_check(s)) { TCGv_i64 addr = tcg_temp_new_i64(); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); @@ -XXX,XX +XXX,XX @@ static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a) static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a) { - if (!dc_isar_feature(aa64_sve, s)) { - return false; + /* dtypes 16 and 17 are artificial, representing 128-bit element */ + if (a->dtype < 16) { + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + } else { + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; } + if (sve_access_check(s)) { int vsz = vec_full_reg_size(s); int elements = vsz >> dtype_esz[a->dtype]; @@ -XXX,XX +XXX,XX @@ static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a) static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz, int esz, int nreg) { - static gen_helper_gvec_mem * const fn_single[2][2][4][4] = { + static gen_helper_gvec_mem * const fn_single[2][2][4][5] = { { { { gen_helper_sve_st1bb_r, gen_helper_sve_st1bh_r, gen_helper_sve_st1bs_r, @@ -XXX,XX +XXX,XX @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, gen_helper_sve_st1hd_le_r }, { NULL, NULL, gen_helper_sve_st1ss_le_r, - gen_helper_sve_st1sd_le_r }, + gen_helper_sve_st1sd_le_r, + gen_helper_sve_st1sq_le_r, }, { NULL, NULL, NULL, - gen_helper_sve_st1dd_le_r } }, + gen_helper_sve_st1dd_le_r, + gen_helper_sve_st1dq_le_r, } }, { { gen_helper_sve_st1bb_r, gen_helper_sve_st1bh_r, gen_helper_sve_st1bs_r, @@ -XXX,XX +XXX,XX @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, gen_helper_sve_st1hd_be_r }, { NULL, NULL, gen_helper_sve_st1ss_be_r, - gen_helper_sve_st1sd_be_r }, + gen_helper_sve_st1sd_be_r, + gen_helper_sve_st1sq_be_r }, { NULL, NULL, NULL, - gen_helper_sve_st1dd_be_r } } }, + gen_helper_sve_st1dd_be_r, + gen_helper_sve_st1dq_be_r } } }, { { { gen_helper_sve_st1bb_r_mte, gen_helper_sve_st1bh_r_mte, @@ -XXX,XX +XXX,XX @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, gen_helper_sve_st1hd_le_r_mte }, { NULL, NULL, gen_helper_sve_st1ss_le_r_mte, - gen_helper_sve_st1sd_le_r_mte }, + gen_helper_sve_st1sd_le_r_mte, + gen_helper_sve_st1sq_le_r_mte }, { NULL, NULL, NULL, - gen_helper_sve_st1dd_le_r_mte } }, + gen_helper_sve_st1dd_le_r_mte, + gen_helper_sve_st1dq_le_r_mte } }, { { gen_helper_sve_st1bb_r_mte, gen_helper_sve_st1bh_r_mte, gen_helper_sve_st1bs_r_mte, @@ -XXX,XX +XXX,XX @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, gen_helper_sve_st1hd_be_r_mte }, { NULL, NULL, gen_helper_sve_st1ss_be_r_mte, - gen_helper_sve_st1sd_be_r_mte }, + gen_helper_sve_st1sd_be_r_mte, + gen_helper_sve_st1sq_be_r_mte }, { NULL, NULL, NULL, - gen_helper_sve_st1dd_be_r_mte } } }, + gen_helper_sve_st1dd_be_r_mte, + gen_helper_sve_st1dq_be_r_mte } } }, }; static gen_helper_gvec_mem * const fn_multiple[2][2][3][4] = { { { { gen_helper_sve_st2bb_r, @@ -XXX,XX +XXX,XX @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a) { - if (!dc_isar_feature(aa64_sve, s)) { - return false; - } if (a->rm == 31 || a->msz > a->esz) { return false; } + switch (a->esz) { + case MO_8 ... MO_64: + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + break; + case MO_128: + assert(a->msz < a->esz); + assert(a->nreg == 0); + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; + break; + default: + g_assert_not_reached(); + } + if (sve_access_check(s)) { TCGv_i64 addr = tcg_temp_new_i64(); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->msz); @@ -XXX,XX +XXX,XX @@ static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a) static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a) { - if (!dc_isar_feature(aa64_sve, s)) { - return false; - } if (a->msz > a->esz) { return false; } + switch (a->esz) { + case MO_8 ... MO_64: + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + break; + case MO_128: + assert(a->msz < a->esz); + assert(a->nreg == 0); + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; + break; + default: + g_assert_not_reached(); + } + if (sve_access_check(s)) { int vsz = vec_full_reg_size(s); int elements = vsz >> a->esz; -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Move from sme_helper.c to the shared header. Add a comment noting the lack of atomicity. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-97-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/sve_ldst_internal.h | 63 ++++++++++++++++++++++++++++++ target/arm/tcg/sme_helper.c | 44 +++------------------ 2 files changed, 69 insertions(+), 38 deletions(-) diff --git a/target/arm/tcg/sve_ldst_internal.h b/target/arm/tcg/sve_ldst_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve_ldst_internal.h +++ b/target/arm/tcg/sve_ldst_internal.h @@ -XXX,XX +XXX,XX @@ DO_LD_PRIM_3(ld1dqu_le, ld1dd_le) #define sve_st1dq_be_tlb sve_st1dd_be_tlb #define sve_st1dq_le_tlb sve_st1dd_le_tlb +/* + * The ARMVectorReg elements are stored in host-endian 64-bit units. + * For 128-bit quantities, the sequence defined by the Elem[] pseudocode + * corresponds to storing the two 64-bit pieces in little-endian order. + */ +/* FIXME: Nothing in this file makes any effort at atomicity. */ + +static inline void sve_ld1qq_be_host(void *vd, intptr_t reg_off, void *host) +{ + sve_ld1dd_be_host(vd, reg_off + 8, host); + sve_ld1dd_be_host(vd, reg_off, host + 8); +} + +static inline void sve_ld1qq_le_host(void *vd, intptr_t reg_off, void *host) +{ + sve_ld1dd_le_host(vd, reg_off, host); + sve_ld1dd_le_host(vd, reg_off + 8, host + 8); +} + +static inline void +sve_ld1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong addr, uintptr_t ra) +{ + sve_ld1dd_be_tlb(env, vd, reg_off + 8, addr, ra); + sve_ld1dd_be_tlb(env, vd, reg_off, addr + 8, ra); +} + +static inline void +sve_ld1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong addr, uintptr_t ra) +{ + sve_ld1dd_le_tlb(env, vd, reg_off, addr, ra); + sve_ld1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra); +} + +static inline void sve_st1qq_be_host(void *vd, intptr_t reg_off, void *host) +{ + sve_st1dd_be_host(vd, reg_off + 8, host); + sve_st1dd_be_host(vd, reg_off, host + 8); +} + +static inline void sve_st1qq_le_host(void *vd, intptr_t reg_off, void *host) +{ + sve_st1dd_le_host(vd, reg_off, host); + sve_st1dd_le_host(vd, reg_off + 8, host + 8); +} + +static inline void +sve_st1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong addr, uintptr_t ra) +{ + sve_st1dd_be_tlb(env, vd, reg_off + 8, addr, ra); + sve_st1dd_be_tlb(env, vd, reg_off, addr + 8, ra); +} + +static inline void +sve_st1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong addr, uintptr_t ra) +{ + sve_st1dd_le_tlb(env, vd, reg_off, addr, ra); + sve_st1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra); +} + #undef DO_LD_TLB #undef DO_ST_TLB #undef DO_LD_HOST 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 @@ static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za, \ TLB(env, useronly_clean_ptr(addr), val, ra); \ } -/* - * The ARMVectorReg elements are stored in host-endian 64-bit units. - * For 128-bit quantities, the sequence defined by the Elem[] pseudocode - * corresponds to storing the two 64-bit pieces in little-endian order. - */ -#define DO_LDQ(HNAME, VNAME, BE, HOST, TLB) \ -static inline void HNAME##_host(void *za, intptr_t off, void *host) \ -{ \ - uint64_t val0 = HOST(host), val1 = HOST(host + 8); \ - uint64_t *ptr = za + off; \ - ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ -} \ +#define DO_LDQ(HNAME, VNAME) \ static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ { \ HNAME##_host(za, tile_vslice_offset(off), host); \ } \ -static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ - target_ulong addr, uintptr_t ra) \ -{ \ - uint64_t val0 = TLB(env, useronly_clean_ptr(addr), ra); \ - uint64_t val1 = TLB(env, useronly_clean_ptr(addr + 8), ra); \ - uint64_t *ptr = za + off; \ - ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ -} \ static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ target_ulong addr, uintptr_t ra) \ { \ HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra); \ } -#define DO_STQ(HNAME, VNAME, BE, HOST, TLB) \ -static inline void HNAME##_host(void *za, intptr_t off, void *host) \ -{ \ - uint64_t *ptr = za + off; \ - HOST(host, ptr[BE]); \ - HOST(host + 8, ptr[!BE]); \ -} \ +#define DO_STQ(HNAME, VNAME) \ static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ { \ HNAME##_host(za, tile_vslice_offset(off), host); \ } \ -static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ - target_ulong addr, uintptr_t ra) \ -{ \ - uint64_t *ptr = za + off; \ - TLB(env, useronly_clean_ptr(addr), ptr[BE], ra); \ - TLB(env, useronly_clean_ptr(addr + 8), ptr[!BE], ra); \ -} \ static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ target_ulong addr, uintptr_t ra) \ { \ @@ -XXX,XX +XXX,XX @@ DO_LD(ld1s_le, uint32_t, ldl_le_p, cpu_ldl_le_data_ra) DO_LD(ld1d_be, uint64_t, ldq_be_p, cpu_ldq_be_data_ra) DO_LD(ld1d_le, uint64_t, ldq_le_p, cpu_ldq_le_data_ra) -DO_LDQ(sve_ld1qq_be, sme_ld1q_be, 1, ldq_be_p, cpu_ldq_be_data_ra) -DO_LDQ(sve_ld1qq_le, sme_ld1q_le, 0, ldq_le_p, cpu_ldq_le_data_ra) +DO_LDQ(sve_ld1qq_be, sme_ld1q_be) +DO_LDQ(sve_ld1qq_le, sme_ld1q_le) DO_ST(st1b, uint8_t, stb_p, cpu_stb_data_ra) DO_ST(st1h_be, uint16_t, stw_be_p, cpu_stw_be_data_ra) @@ -XXX,XX +XXX,XX @@ DO_ST(st1s_le, uint32_t, stl_le_p, cpu_stl_le_data_ra) DO_ST(st1d_be, uint64_t, stq_be_p, cpu_stq_be_data_ra) DO_ST(st1d_le, uint64_t, stq_le_p, cpu_stq_le_data_ra) -DO_STQ(sve_st1qq_be, sme_st1q_be, 1, stq_be_p, cpu_stq_be_data_ra) -DO_STQ(sve_st1qq_le, sme_st1q_le, 0, stq_le_p, cpu_stq_le_data_ra) +DO_STQ(sve_st1qq_be, sme_st1q_be) +DO_STQ(sve_st1qq_le, sme_st1q_le) #undef DO_LD #undef DO_ST -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-98-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 32 +++++++++ target/arm/tcg/sve.decode | 31 +++++++++ target/arm/tcg/sve_helper.c | 8 +++ target/arm/tcg/translate-sve.c | 116 ++++++++++++++++++++++++--------- 4 files changed, 156 insertions(+), 31 deletions(-) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ld2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld2qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ld2dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld4dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld2qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1bhu_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bsu_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bdu_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_st2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st2qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_st1bh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_st2dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st3dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st4dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st2qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_st1bh_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bs_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bd_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ @rprr_load_dt ....... dtype:4 rm:5 ... pg:3 rn:5 rd:5 &rprr_load @rpri_load_dt ....... dtype:4 . imm:s4 ... pg:3 rn:5 rd:5 &rpri_load +@rprr_load ....... .... rm:5 ... pg:3 rn:5 rd:5 &rprr_load +@rpri_load ....... .... . imm:s4 ... pg:3 rn:5 rd:5 &rpri_load + @rprr_load_msz ....... .... rm:5 ... pg:3 rn:5 rd:5 \ &rprr_load dtype=%msz_dtype @rpri_load_msz ....... .... . imm:s4 ... pg:3 rn:5 rd:5 \ @@ -XXX,XX +XXX,XX @@ LDNF1_zpri 1010010 .... 1.... 101 ... ..... ..... @rpri_load_dt nreg=0 # SVE load multiple structures (scalar plus scalar) # LD2B, LD2H, LD2W, LD2D; etc. LD_zprr 1010010 .. nreg:2 ..... 110 ... ..... ..... @rprr_load_msz +# LD[234]Q +LD_zprr 1010010 01 01 ..... 100 ... ..... ..... \ + @rprr_load dtype=18 nreg=1 +LD_zprr 1010010 10 01 ..... 100 ... ..... ..... \ + @rprr_load dtype=18 nreg=2 +LD_zprr 1010010 11 01 ..... 100 ... ..... ..... \ + @rprr_load dtype=18 nreg=3 # SVE contiguous non-temporal load (scalar plus immediate) # LDNT1B, LDNT1H, LDNT1W, LDNT1D # SVE load multiple structures (scalar plus immediate) # LD2B, LD2H, LD2W, LD2D; etc. LD_zpri 1010010 .. nreg:2 0.... 111 ... ..... ..... @rpri_load_msz +# LD[234]Q +LD_zpri 1010010 01 001 .... 111 ... ..... ..... \ + @rpri_load dtype=18 nreg=1 +LD_zpri 1010010 10 001 .... 111 ... ..... ..... \ + @rpri_load dtype=18 nreg=2 +LD_zpri 1010010 11 001 .... 111 ... ..... ..... \ + @rpri_load dtype=18 nreg=3 # SVE load and broadcast quadword (scalar plus scalar) LD1RQ_zprr 1010010 .. 00 ..... 000 ... ..... ..... \ @@ -XXX,XX +XXX,XX @@ ST_zprr 1110010 11 10 ..... 010 ... ..... ..... \ # SVE store multiple structures (scalar plus immediate) (nreg != 0) ST_zpri 1110010 .. nreg:2 1.... 111 ... ..... ..... \ @rpri_store msz=%size_23 esz=%size_23 +# ST[234]Q +ST_zpri 11100100 01 00 .... 000 ... ..... ..... \ + @rpri_store msz=4 esz=4 nreg=1 +ST_zpri 11100100 10 00 .... 000 ... ..... ..... \ + @rpri_store msz=4 esz=4 nreg=2 +ST_zpri 11100100 11 00 .... 000 ... ..... ..... \ + @rpri_store msz=4 esz=4 nreg=3 # SVE contiguous non-temporal store (scalar plus scalar) (nreg == 0) # SVE store multiple structures (scalar plus scalar) (nreg != 0) ST_zprr 1110010 .. nreg:2 ..... 011 ... ..... ..... \ @rprr_store msz=%size_23 esz=%size_23 +# ST[234]Q +ST_zprr 11100100 01 1 ..... 000 ... ..... ..... \ + @rprr_store msz=4 esz=4 nreg=1 +ST_zprr 11100100 10 1 ..... 000 ... ..... ..... \ + @rprr_store msz=4 esz=4 nreg=2 +ST_zprr 11100100 11 1 ..... 000 ... ..... ..... \ + @rprr_store msz=4 esz=4 nreg=3 # SVE 32-bit scatter store (scalar plus 32-bit scaled offsets) # Require msz > 0 && msz <= esz. 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 @@ DO_LDN_2(2, dd, MO_64) DO_LDN_2(3, dd, MO_64) DO_LDN_2(4, dd, MO_64) +DO_LDN_2(2, qq, MO_128) +DO_LDN_2(3, qq, MO_128) +DO_LDN_2(4, qq, MO_128) + #undef DO_LDN_1 #undef DO_LDN_2 @@ -XXX,XX +XXX,XX @@ DO_STN_2(4, dd, MO_64, MO_64) DO_STN_2(1, sq, MO_128, MO_32) DO_STN_2(1, dq, MO_128, MO_64) +DO_STN_2(2, qq, MO_128, MO_128) +DO_STN_2(3, qq, MO_128, MO_128) +DO_STN_2(4, qq, MO_128, MO_128) + #undef DO_STN_1 #undef DO_STN_2 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 inline int expand_imm_sh8u(DisasContext *s, int x) */ static inline int msz_dtype(DisasContext *s, int msz) { - static const uint8_t dtype[4] = { 0, 5, 10, 15 }; + static const uint8_t dtype[5] = { 0, 5, 10, 15, 18 }; return dtype[msz]; } @@ -XXX,XX +XXX,XX @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, } /* Indexed by [mte][be][dtype][nreg] */ -static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = { +static gen_helper_gvec_mem * const ldr_fns[2][2][19][4] = { { /* mte inactive, little-endian */ { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = { { gen_helper_sve_ld1squ_le_r, NULL, NULL, NULL }, { gen_helper_sve_ld1dqu_le_r, NULL, NULL, NULL }, + { NULL, gen_helper_sve_ld2qq_le_r, + gen_helper_sve_ld3qq_le_r, gen_helper_sve_ld4qq_le_r }, }, /* mte inactive, big-endian */ @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = { { gen_helper_sve_ld1squ_be_r, NULL, NULL, NULL }, { gen_helper_sve_ld1dqu_be_r, NULL, NULL, NULL }, + { NULL, gen_helper_sve_ld2qq_be_r, + gen_helper_sve_ld3qq_be_r, gen_helper_sve_ld4qq_be_r }, }, }, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = { { gen_helper_sve_ld1squ_le_r_mte, NULL, NULL, NULL }, { gen_helper_sve_ld1dqu_le_r_mte, NULL, NULL, NULL }, + { NULL, + gen_helper_sve_ld2qq_le_r_mte, + gen_helper_sve_ld3qq_le_r_mte, + gen_helper_sve_ld4qq_le_r_mte }, }, /* mte active, big-endian */ @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = { { gen_helper_sve_ld1squ_be_r_mte, NULL, NULL, NULL }, { gen_helper_sve_ld1dqu_be_r_mte, NULL, NULL, NULL }, + { NULL, + gen_helper_sve_ld2qq_be_r_mte, + gen_helper_sve_ld3qq_be_r_mte, + gen_helper_sve_ld4qq_be_r_mte }, }, }, }; @@ -XXX,XX +XXX,XX @@ static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a) return false; } - /* dtypes 16 and 17 are artificial, representing 128-bit element */ - if (a->dtype < 16) { + /* dtypes 16-18 are artificial, representing 128-bit element */ + switch (a->dtype) { + case 0 ... 15: if (!dc_isar_feature(aa64_sve, s)) { return false; } - } else { + break; + case 16: case 17: if (!dc_isar_feature(aa64_sve2p1, s)) { return false; } s->is_nonstreaming = true; + break; + case 18: + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + break; + default: + g_assert_not_reached(); } if (sve_access_check(s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a) static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a) { - /* dtypes 16 and 17 are artificial, representing 128-bit element */ - if (a->dtype < 16) { + /* dtypes 16-18 are artificial, representing 128-bit element */ + switch (a->dtype) { + case 0 ... 15: if (!dc_isar_feature(aa64_sve, s)) { return false; } - } else { + break; + case 16: case 17: if (!dc_isar_feature(aa64_sve2p1, s)) { return false; } s->is_nonstreaming = true; + break; + case 18: + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + break; + default: + g_assert_not_reached(); } if (sve_access_check(s)) { @@ -XXX,XX +XXX,XX @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, gen_helper_sve_st1dd_be_r_mte, gen_helper_sve_st1dq_be_r_mte } } }, }; - static gen_helper_gvec_mem * const fn_multiple[2][2][3][4] = { + static gen_helper_gvec_mem * const fn_multiple[2][2][3][5] = { { { { gen_helper_sve_st2bb_r, gen_helper_sve_st2hh_le_r, gen_helper_sve_st2ss_le_r, - gen_helper_sve_st2dd_le_r }, + gen_helper_sve_st2dd_le_r, + gen_helper_sve_st2qq_le_r }, { gen_helper_sve_st3bb_r, gen_helper_sve_st3hh_le_r, gen_helper_sve_st3ss_le_r, - gen_helper_sve_st3dd_le_r }, + gen_helper_sve_st3dd_le_r, + gen_helper_sve_st3qq_le_r }, { gen_helper_sve_st4bb_r, gen_helper_sve_st4hh_le_r, gen_helper_sve_st4ss_le_r, - gen_helper_sve_st4dd_le_r } }, + gen_helper_sve_st4dd_le_r, + gen_helper_sve_st4qq_le_r } }, { { gen_helper_sve_st2bb_r, gen_helper_sve_st2hh_be_r, gen_helper_sve_st2ss_be_r, - gen_helper_sve_st2dd_be_r }, + gen_helper_sve_st2dd_be_r, + gen_helper_sve_st2qq_be_r }, { gen_helper_sve_st3bb_r, gen_helper_sve_st3hh_be_r, gen_helper_sve_st3ss_be_r, - gen_helper_sve_st3dd_be_r }, + gen_helper_sve_st3dd_be_r, + gen_helper_sve_st3qq_be_r }, { gen_helper_sve_st4bb_r, gen_helper_sve_st4hh_be_r, gen_helper_sve_st4ss_be_r, - gen_helper_sve_st4dd_be_r } } }, + gen_helper_sve_st4dd_be_r, + gen_helper_sve_st4qq_be_r } } }, { { { gen_helper_sve_st2bb_r_mte, gen_helper_sve_st2hh_le_r_mte, gen_helper_sve_st2ss_le_r_mte, - gen_helper_sve_st2dd_le_r_mte }, + gen_helper_sve_st2dd_le_r_mte, + gen_helper_sve_st2qq_le_r_mte }, { gen_helper_sve_st3bb_r_mte, gen_helper_sve_st3hh_le_r_mte, gen_helper_sve_st3ss_le_r_mte, - gen_helper_sve_st3dd_le_r_mte }, + gen_helper_sve_st3dd_le_r_mte, + gen_helper_sve_st3qq_le_r_mte }, { gen_helper_sve_st4bb_r_mte, gen_helper_sve_st4hh_le_r_mte, gen_helper_sve_st4ss_le_r_mte, - gen_helper_sve_st4dd_le_r_mte } }, + gen_helper_sve_st4dd_le_r_mte, + gen_helper_sve_st4qq_le_r_mte } }, { { gen_helper_sve_st2bb_r_mte, gen_helper_sve_st2hh_be_r_mte, gen_helper_sve_st2ss_be_r_mte, - gen_helper_sve_st2dd_be_r_mte }, + gen_helper_sve_st2dd_be_r_mte, + gen_helper_sve_st2qq_be_r_mte }, { gen_helper_sve_st3bb_r_mte, gen_helper_sve_st3hh_be_r_mte, gen_helper_sve_st3ss_be_r_mte, - gen_helper_sve_st3dd_be_r_mte }, + gen_helper_sve_st3dd_be_r_mte, + gen_helper_sve_st3qq_be_r_mte }, { gen_helper_sve_st4bb_r_mte, gen_helper_sve_st4hh_be_r_mte, gen_helper_sve_st4ss_be_r_mte, - gen_helper_sve_st4dd_be_r_mte } } }, + gen_helper_sve_st4dd_be_r_mte, + gen_helper_sve_st4qq_be_r_mte } } }, }; gen_helper_gvec_mem *fn; int be = s->be_data == MO_BE; @@ -XXX,XX +XXX,XX @@ static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a) } break; case MO_128: - assert(a->msz < a->esz); - assert(a->nreg == 0); - if (!dc_isar_feature(aa64_sve2p1, s)) { - return false; + if (a->nreg == 0) { + assert(a->msz < a->esz); + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; + } else { + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } } - s->is_nonstreaming = true; break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a) } break; case MO_128: - assert(a->msz < a->esz); - assert(a->nreg == 0); - if (!dc_isar_feature(aa64_sve2p1, s)) { - return false; + if (a->nreg == 0) { + assert(a->msz < a->esz); + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; + } else { + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } } - s->is_nonstreaming = true; break; default: g_assert_not_reached(); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-99-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 16 ++++++++++++++++ target/arm/tcg/sve.decode | 8 ++++++++ target/arm/tcg/sve_helper.c | 6 ++++++ target/arm/tcg/translate-sve.c | 34 ++++++++++++++++++++++++++++++++-- 4 files changed, 62 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_ldsds_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldsds_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldqq_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldqq_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbsu_zsu_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_ldsds_le_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldsds_be_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldqq_le_zd_mte, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldqq_be_zd_mte, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbsu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stdd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stqq_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stqq_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbs_zsu_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stdd_be_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stqq_le_zd_mte, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stqq_be_zd_mte, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -XXX,XX +XXX,XX @@ LD1_zprz 1100010 10 1. ..... 1.. ... ..... ..... \ LD1_zprz 1100010 11 1. ..... 11. ... ..... ..... \ @rprr_g_load_sc esz=3 msz=3 u=1 +# LD1Q +LD1_zprz 1100 0100 000 rm:5 101 pg:3 rn:5 rd:5 \ + &rprr_gather_load u=0 ff=0 xs=2 esz=4 msz=4 scale=0 + # SVE 64-bit gather load (vector plus immediate) LD1_zpiz 1100010 .. 01 ..... 1.. ... ..... ..... \ @rpri_g_load esz=3 @@ -XXX,XX +XXX,XX @@ ST1_zprz 1110010 .. 01 ..... 101 ... ..... ..... \ ST1_zprz 1110010 .. 00 ..... 101 ... ..... ..... \ @rprr_scatter_store xs=2 esz=3 scale=0 +# ST1Q +ST1_zprz 1110 0100 001 rm:5 001 pg:3 rn:5 rd:5 \ + &rprr_scatter_store xs=2 msz=4 esz=4 scale=0 + # SVE 64-bit scatter store (vector plus immediate) ST1_zpiz 1110010 .. 10 ..... 101 ... ..... ..... \ @rpri_scatter_store esz=3 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 @@ DO_LD1_ZPZ_D(dd_be, zsu, MO_64) DO_LD1_ZPZ_D(dd_be, zss, MO_64) DO_LD1_ZPZ_D(dd_be, zd, MO_64) +DO_LD1_ZPZ_D(qq_le, zd, MO_128) +DO_LD1_ZPZ_D(qq_be, zd, MO_128) + #undef DO_LD1_ZPZ_S #undef DO_LD1_ZPZ_D @@ -XXX,XX +XXX,XX @@ DO_ST1_ZPZ_D(sd_be, zd, MO_32) DO_ST1_ZPZ_D(dd_le, zd, MO_64) DO_ST1_ZPZ_D(dd_be, zd, MO_64) +DO_ST1_ZPZ_D(qq_le, zd, MO_128) +DO_ST1_ZPZ_D(qq_be, zd, MO_128) + #undef DO_ST1_ZPZ_S #undef DO_ST1_ZPZ_D 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 @@ gather_load_fn64[2][2][2][3][2][4] = { gen_helper_sve_ldffdd_be_zd_mte, } } } } }, }; +static gen_helper_gvec_mem_scatter * const +gather_load_fn128[2][2] = { + { gen_helper_sve_ldqq_le_zd, + gen_helper_sve_ldqq_be_zd }, + { gen_helper_sve_ldqq_le_zd_mte, + gen_helper_sve_ldqq_be_zd_mte } +}; + static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a) { gen_helper_gvec_mem_scatter *fn = NULL; bool be = s->be_data == MO_BE; bool mte = s->mte_active[0]; - if (!dc_isar_feature(aa64_sve, s)) { + if (a->esz < MO_128 + ? !dc_isar_feature(aa64_sve, s) + : !dc_isar_feature(aa64_sve2p1, s)) { return false; } s->is_nonstreaming = true; @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a) case MO_64: fn = gather_load_fn64[mte][be][a->ff][a->xs][a->u][a->msz]; break; + case MO_128: + assert(!a->ff && a->u && a->xs == 2 && a->msz == MO_128); + fn = gather_load_fn128[mte][be]; + break; + default: + g_assert_not_reached(); } assert(fn != NULL); @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem_scatter * const scatter_store_fn64[2][2][3][4] = { gen_helper_sve_stdd_be_zd_mte, } } }, }; +static gen_helper_gvec_mem_scatter * const +scatter_store_fn128[2][2] = { + { gen_helper_sve_stqq_le_zd, + gen_helper_sve_stqq_be_zd }, + { gen_helper_sve_stqq_le_zd_mte, + gen_helper_sve_stqq_be_zd_mte } +}; + static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a) { gen_helper_gvec_mem_scatter *fn; @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a) if (a->esz < a->msz || (a->msz == 0 && a->scale)) { return false; } - if (!dc_isar_feature(aa64_sve, s)) { + if (a->esz < MO_128 + ? !dc_isar_feature(aa64_sve, s) + : !dc_isar_feature(aa64_sve2p1, s)) { return false; } s->is_nonstreaming = true; @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a) case MO_64: fn = scatter_store_fn64[mte][be][a->xs][a->msz]; break; + case MO_128: + assert(a->xs == 2 && a->msz == MO_128); + fn = scatter_store_fn128[mte][be]; + break; default: g_assert_not_reached(); } -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-100-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 6 ++++ target/arm/tcg/sme.decode | 36 ++++++++++++++++++++ target/arm/tcg/sme_helper.c | 60 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 46 +++++++++++++++++++------- 4 files changed, 137 insertions(+), 11 deletions(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sme2_mova_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sme2_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sme_ld1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_ld1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_ld1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ MOVA_za2 11000000 00 00011 00 .. 010 00 off:3 zr:4 0 \ MOVA_za4 11000000 00 00011 00 .. 011 00 off:3 zr:3 00 \ &mova_a rv=%mova_rv +### SME Move and Zero + +MOVAZ_za2 11000000 00000110 0 .. 01010 off:3 zr:4 0 \ + &mova_a rv=%mova_rv +MOVAZ_za4 11000000 00000110 0 .. 01110 off:3 zr:3 00 \ + &mova_a rv=%mova_rv + +MOVAZ_zt 11000000 00 00001 0 v:1 .. 0001 off:4 zr:5 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVAZ_zt 11000000 01 00001 0 v:1 .. 0001 za:1 off:3 zr:5 \ + &mova_t rs=%mova_rs esz=1 +MOVAZ_zt 11000000 10 00001 0 v:1 .. 0001 za:2 off:2 zr:5 \ + &mova_t rs=%mova_rs esz=2 +MOVAZ_zt 11000000 11 00001 0 v:1 .. 0001 za:3 off:1 zr:5 \ + &mova_t rs=%mova_rs esz=3 +MOVAZ_zt 11000000 11 00001 1 v:1 .. 0001 za:4 zr:5 \ + &mova_t rs=%mova_rs esz=4 off=0 + +MOVAZ_zt2 11000000 00 00011 0 v:1 .. 00010 off:3 zr:4 0 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVAZ_zt2 11000000 01 00011 0 v:1 .. 00010 za:1 off:2 zr:4 0 \ + &mova_t rs=%mova_rs esz=1 +MOVAZ_zt2 11000000 10 00011 0 v:1 .. 00010 za:2 off:1 zr:4 0 \ + &mova_t rs=%mova_rs esz=2 +MOVAZ_zt2 11000000 11 00011 0 v:1 .. 00010 za:3 zr:4 0 \ + &mova_t rs=%mova_rs esz=3 off=0 + +MOVAZ_zt4 11000000 00 00011 0 v:1 .. 001100 off:2 zr:3 00 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVAZ_zt4 11000000 01 00011 0 v:1 .. 001100 za:1 off:1 zr:3 00 \ + &mova_t rs=%mova_rs esz=1 +MOVAZ_zt4 11000000 10 00011 0 v:1 .. 001100 za:2 zr:3 00 \ + &mova_t rs=%mova_rs esz=2 off=0 +MOVAZ_zt4 11000000 11 00011 0 v:1 .. 00110 za:3 zr:3 00 \ + &mova_t rs=%mova_rs esz=3 off=0 + ### SME Move into/from ZT0 MOVT_rzt 1100 0000 0100 1100 0 off:3 00 11111 rt:5 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(sme2_mova_zc_d)(void *vdst, void *vsrc, uint32_t desc) } } +void HELPER(sme2p1_movaz_zc_b)(void *vdst, void *vsrc, uint32_t desc) +{ + uint8_t *src = vsrc; + uint8_t *dst = vdst; + size_t i, n = simd_oprsz(desc); + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + src[tile_vslice_index(i)] = 0; + } +} + +void HELPER(sme2p1_movaz_zc_h)(void *vdst, void *vsrc, uint32_t desc) +{ + uint16_t *src = vsrc; + uint16_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 2; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + src[tile_vslice_index(i)] = 0; + } +} + +void HELPER(sme2p1_movaz_zc_s)(void *vdst, void *vsrc, uint32_t desc) +{ + uint32_t *src = vsrc; + uint32_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 4; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + src[tile_vslice_index(i)] = 0; + } +} + +void HELPER(sme2p1_movaz_zc_d)(void *vdst, void *vsrc, uint32_t desc) +{ + uint64_t *src = vsrc; + uint64_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 8; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + src[tile_vslice_index(i)] = 0; + } +} + +void HELPER(sme2p1_movaz_zc_q)(void *vdst, void *vsrc, uint32_t desc) +{ + Int128 *src = vsrc; + Int128 *dst = vdst; + size_t i, n = simd_oprsz(desc) / 16; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + memset(&src[tile_vslice_index(i)], 0, 16); + } +} + /* * Clear elements in a tile slice comprising len bytes. */ 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_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec) TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false) TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true) -static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec) +static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, + bool to_vec, bool zero) { static gen_helper_gvec_2 * const cz_fns[] = { gen_helper_sme2_mova_cz_b, gen_helper_sme2_mova_cz_h, @@ -XXX,XX +XXX,XX @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec) gen_helper_sme2_mova_zc_b, gen_helper_sme2_mova_zc_h, gen_helper_sme2_mova_zc_s, gen_helper_sme2_mova_zc_d, }; + static gen_helper_gvec_2 * const zc_z_fns[] = { + gen_helper_sme2p1_movaz_zc_b, gen_helper_sme2p1_movaz_zc_h, + gen_helper_sme2p1_movaz_zc_s, gen_helper_sme2p1_movaz_zc_d, + gen_helper_sme2p1_movaz_zc_q, + }; TCGv_ptr t_za; int svl, bytes_per_op = n << a->esz; @@ -XXX,XX +XXX,XX @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec) return true; } + assert(a->esz <= MO_64 + zero); + if (!sme_smza_enabled_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec) TCGv_ptr t_zr = vec_full_reg_ptr(s, a->zr * n + i); t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off * n + i, 1, n, a->v); - if (to_vec) { + if (zero) { + zc_z_fns[a->esz](t_zr, t_za, t_desc); + } else if (to_vec) { zc_fns[a->esz](t_zr, t_za, t_desc); } else { cz_fns[a->esz](t_za, t_zr, t_desc); @@ -XXX,XX +XXX,XX @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec) a->off * n + i, 1, n, a->v); if (to_vec) { tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, 0, svl, svl); + if (zero) { + tcg_gen_gvec_dup_imm_var(MO_8, t_za, 0, svl, svl, 0); + } } else { tcg_gen_gvec_mov_var(MO_8, t_za, 0, tcg_env, o_zr, svl, svl); } @@ -XXX,XX +XXX,XX @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec) return true; } -TRANS_FEAT(MOVA_tz2, aa64_sme2, do_mova_tile_n, a, 2, false) -TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false) -TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true) -TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true) +TRANS_FEAT(MOVA_tz2, aa64_sme2, do_mova_tile_n, a, 2, false, false) +TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false, false) +TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true, false) +TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true, false) -static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec) +TRANS_FEAT(MOVAZ_zt, aa64_sme2p1, do_mova_tile_n, a, 1, true, true) +TRANS_FEAT(MOVAZ_zt2, aa64_sme2p1, do_mova_tile_n, a, 2, true, true) +TRANS_FEAT(MOVAZ_zt4, aa64_sme2p1, do_mova_tile_n, a, 4, true, true) + +static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, + bool to_vec, bool zero) { TCGv_ptr t_za; int svl; @@ -XXX,XX +XXX,XX @@ static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec) if (to_vec) { tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, o_za, svl, svl); + if (zero) { + tcg_gen_gvec_dup_imm_var(MO_8, t_za, o_za, svl, svl, 0); + } } else { tcg_gen_gvec_mov_var(MO_8, t_za, o_za, tcg_env, o_zr, svl, svl); } @@ -XXX,XX +XXX,XX @@ static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec) return true; } -TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false) -TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false) -TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true) -TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true) +TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false, false) +TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false, false) +TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true, false) +TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true, false) + +TRANS_FEAT(MOVAZ_za2, aa64_sme2p1, do_mova_array_n, a, 2, true, true) +TRANS_FEAT(MOVAZ_za4, aa64_sme2p1, do_mova_array_n, a, 4, true, true) static bool do_movt(DisasContext *s, arg_MOVT_rzt *a, void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long)) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-101-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper.h | 24 ++++++++++ target/arm/tcg/sme.decode | 42 ++++++++++++++++ target/arm/tcg/translate-sme.c | 56 ++++++++++++++++++++++ target/arm/tcg/vec_helper.c | 88 ++++++++++++++++++++++++++++++++++ 4 files changed, 210 insertions(+) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_uminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_luti2_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti2_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti2_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti4_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti4_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti4_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ ZERO_za 11000000 000011 110 .. 0000000000 00. \ &zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4 ZERO_za 11000000 000011 111 .. 0000000000 00. \ &zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4 + +### SME Lookup Table Read + +&lut zd zn idx + +# LUTI2, consecutive +LUTI2_c_1b 1100 0000 1100 11 idx:4 00 00 zn:5 zd:5 &lut +LUTI2_c_1h 1100 0000 1100 11 idx:4 01 00 zn:5 zd:5 &lut +LUTI2_c_1s 1100 0000 1100 11 idx:4 10 00 zn:5 zd:5 &lut + +LUTI2_c_2b 1100 0000 1000 11 idx:3 1 00 00 zn:5 .... 0 &lut zd=%zd_ax2 +LUTI2_c_2h 1100 0000 1000 11 idx:3 1 01 00 zn:5 .... 0 &lut zd=%zd_ax2 +LUTI2_c_2s 1100 0000 1000 11 idx:3 1 10 00 zn:5 .... 0 &lut zd=%zd_ax2 + +LUTI2_c_4b 1100 0000 1000 11 idx:2 10 00 00 zn:5 ... 00 &lut zd=%zd_ax4 +LUTI2_c_4h 1100 0000 1000 11 idx:2 10 01 00 zn:5 ... 00 &lut zd=%zd_ax4 +LUTI2_c_4s 1100 0000 1000 11 idx:2 10 10 00 zn:5 ... 00 &lut zd=%zd_ax4 + +# LUTI2, strided (must check zd alignment) +LUTI2_s_2b 1100 0000 1001 11 idx:3 1 00 00 zn:5 zd:5 &lut +LUTI2_s_2h 1100 0000 1001 11 idx:3 1 01 00 zn:5 zd:5 &lut + +LUTI2_s_4b 1100 0000 1001 11 idx:2 10 00 00 zn:5 zd:5 &lut +LUTI2_s_4h 1100 0000 1001 11 idx:2 10 01 00 zn:5 zd:5 &lut + +# LUTI4, consecutive +LUTI4_c_1b 1100 0000 1100 101 idx:3 00 00 zn:5 zd:5 &lut +LUTI4_c_1h 1100 0000 1100 101 idx:3 01 00 zn:5 zd:5 &lut +LUTI4_c_1s 1100 0000 1100 101 idx:3 10 00 zn:5 zd:5 &lut + +LUTI4_c_2b 1100 0000 1000 101 idx:2 1 00 00 zn:5 .... 0 &lut zd=%zd_ax2 +LUTI4_c_2h 1100 0000 1000 101 idx:2 1 01 00 zn:5 .... 0 &lut zd=%zd_ax2 +LUTI4_c_2s 1100 0000 1000 101 idx:2 1 10 00 zn:5 .... 0 &lut zd=%zd_ax2 + +LUTI4_c_4h 1100 0000 1000 101 idx:1 10 01 00 zn:5 ... 00 &lut zd=%zd_ax4 +LUTI4_c_4s 1100 0000 1000 101 idx:1 10 10 00 zn:5 ... 00 &lut zd=%zd_ax4 + +# LUTI4, strided (must check zd alignment) +LUTI4_s_2b 1100 0000 1001 101 idx:2 1 00 00 zn:5 zd:5 &lut +LUTI4_s_2h 1100 0000 1001 101 idx:2 1 01 00 zn:5 zd:5 &lut + +LUTI4_s_4h 1100 0000 1001 101 idx:1 10 01 00 zn:5 zd:5 &lut 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 trans_SEL(DisasContext *s, arg_SEL *a) } return true; } + +static bool do_lut(DisasContext *s, arg_lut *a, + gen_helper_gvec_2_ptr *fn, bool strided) +{ + if (sme_sm_enabled_check(s) && sme2_zt0_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + tcg_env, svl, svl, strided | (a->idx << 1), fn); + } + return true; +} + +TRANS_FEAT(LUTI2_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1b, false) +TRANS_FEAT(LUTI2_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1h, false) +TRANS_FEAT(LUTI2_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1s, false) + +TRANS_FEAT(LUTI2_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2b, false) +TRANS_FEAT(LUTI2_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2h, false) +TRANS_FEAT(LUTI2_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2s, false) + +TRANS_FEAT(LUTI2_c_4b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4b, false) +TRANS_FEAT(LUTI2_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4h, false) +TRANS_FEAT(LUTI2_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4s, false) + +TRANS_FEAT(LUTI4_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1b, false) +TRANS_FEAT(LUTI4_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1h, false) +TRANS_FEAT(LUTI4_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1s, false) + +TRANS_FEAT(LUTI4_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2b, false) +TRANS_FEAT(LUTI4_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2h, false) +TRANS_FEAT(LUTI4_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2s, false) + +TRANS_FEAT(LUTI4_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4h, false) +TRANS_FEAT(LUTI4_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4s, false) + +static bool do_lut_s4(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn) +{ + return !(a->zd & 0b01100) && do_lut(s, a, fn, true); +} + +static bool do_lut_s8(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn) +{ + return !(a->zd & 0b01000) && do_lut(s, a, fn, true); +} + +TRANS_FEAT(LUTI2_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2b) +TRANS_FEAT(LUTI2_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2h) + +TRANS_FEAT(LUTI2_s_4b, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4b) +TRANS_FEAT(LUTI2_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4h) + +TRANS_FEAT(LUTI4_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2b) +TRANS_FEAT(LUTI4_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2h) + +TRANS_FEAT(LUTI4_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti4_4h) 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_ursqrte_s)(void *vd, void *vn, uint32_t desc) } clear_tail(d, opr_sz, simd_maxsz(desc)); } + +static inline void do_lut_b(void *zd, uint64_t *indexes, uint64_t *table, + unsigned elements, unsigned segbase, + unsigned dstride, unsigned isize, + unsigned tsize, unsigned nreg) +{ + for (unsigned r = 0; r < nreg; ++r) { + uint8_t *dst = zd + dstride * r; + unsigned base = segbase + r * elements; + + for (unsigned e = 0; e < elements; ++e) { + unsigned index = extractn(indexes, (base + e) * isize, isize); + dst[H1(e)] = extractn(table, index * tsize, 8); + } + } +} + +static inline void do_lut_h(void *zd, uint64_t *indexes, uint64_t *table, + unsigned elements, unsigned segbase, + unsigned dstride, unsigned isize, + unsigned tsize, unsigned nreg) +{ + for (unsigned r = 0; r < nreg; ++r) { + uint16_t *dst = zd + dstride * r; + unsigned base = segbase + r * elements; + + for (unsigned e = 0; e < elements; ++e) { + unsigned index = extractn(indexes, (base + e) * isize, isize); + dst[H2(e)] = extractn(table, index * tsize, 16); + } + } +} + +static inline void do_lut_s(void *zd, uint64_t *indexes, uint32_t *table, + unsigned elements, unsigned segbase, + unsigned dstride, unsigned isize, + unsigned tsize, unsigned nreg) +{ + for (unsigned r = 0; r < nreg; ++r) { + uint32_t *dst = zd + dstride * r; + unsigned base = segbase + r * elements; + + for (unsigned e = 0; e < elements; ++e) { + unsigned index = extractn(indexes, (base + e) * isize, isize); + dst[H4(e)] = table[H4(index)]; + } + } +} + +#define DO_SME2_LUT(ISIZE, NREG, SUFF, ESIZE) \ +void helper_sme2_luti##ISIZE##_##NREG##SUFF \ + (void *zd, void *zn, CPUARMState *env, uint32_t desc) \ +{ \ + unsigned vl = simd_oprsz(desc); \ + unsigned strided = extract32(desc, SIMD_DATA_SHIFT, 1); \ + unsigned idx = extract32(desc, SIMD_DATA_SHIFT + 1, 4); \ + unsigned elements = vl / ESIZE; \ + unsigned dstride = (!strided ? 1 : NREG == 4 ? 4 : 8); \ + unsigned segments = (ESIZE * 8) / (ISIZE * NREG); \ + unsigned segment = idx & (segments - 1); \ + ARMVectorReg indexes; \ + memcpy(&indexes, zn, vl); \ + do_lut_##SUFF(zd, indexes.d, (void *)env->za_state.zt0, elements, \ + segment * NREG * elements, \ + dstride * sizeof(ARMVectorReg), ISIZE, 32, NREG); \ +} + +DO_SME2_LUT(2,1,b, 1) +DO_SME2_LUT(2,1,h, 2) +DO_SME2_LUT(2,1,s, 4) +DO_SME2_LUT(2,2,b, 1) +DO_SME2_LUT(2,2,h, 2) +DO_SME2_LUT(2,2,s, 4) +DO_SME2_LUT(2,4,b, 1) +DO_SME2_LUT(2,4,h, 2) +DO_SME2_LUT(2,4,s, 4) + +DO_SME2_LUT(4,1,b, 1) +DO_SME2_LUT(4,1,h, 2) +DO_SME2_LUT(4,1,s, 4) +DO_SME2_LUT(4,2,b, 1) +DO_SME2_LUT(4,2,h, 2) +DO_SME2_LUT(4,2,s, 4) +DO_SME2_LUT(4,4,b, 1) +DO_SME2_LUT(4,4,h, 2) +DO_SME2_LUT(4,4,s, 4) + +#undef DO_SME2_LUT -- 2.43.0 The pattern we currently have as FMOPA_h is the "widening" insn that takes fp16 inputs and produces single-precision outputs. This is unlike FMOPA_s and FMOPA_d, which are non-widening produce outputs the same size as their inputs. SME2 introduces a non-widening fp16 FMOPA operation; rename FMOPA_h to FMOPA_w_h (for 'widening'), so we can use FMOPA_h for the non-widening version, giving it a name in line with the other non-widening ops FMOPA_s and FMOPA_d. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-102-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 2 +- target/arm/tcg/sme.decode | 2 +- target/arm/tcg/sme_helper.c | 4 ++-- target/arm/tcg/translate-sme.c | 4 ++-- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_7(sme_fmopa_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 -FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 +FMOPA_w_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32 SUMOPA_s 1010000 0 10 1 ..... ... ... ..... . 00 .. @op_32 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 @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, return float32_add(sum, t32, s_std); } -void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, CPUARMState *env, uint32_t desc) +void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) { intptr_t row, col, oprsz = simd_maxsz(desc); uint32_t neg = simd_data(desc) * 0x80008000u; 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, return true; } -TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_env, a, - MO_32, gen_helper_sme_fmopa_h) +TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a, + MO_32, gen_helper_sme_fmopa_w_h) TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, FPST_ZA, gen_helper_sme_fmopa_s) TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, -- 2.43.0 Our current BFMOPA opcode pattern is the widening version of the insn. Rename it to BFMOPA_w, to make way for the non-widening version added in SME2. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-103-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 2 +- target/arm/tcg/sme.decode | 2 +- target/arm/tcg/sme_helper.c | 4 ++-- target/arm/tcg/translate-sme.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_7(sme_bfmopa, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 -BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 +BFMOPA_w 10000001 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_w_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32 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(sme2_fvdot_idx_h)(void *vd, void *vn, void *vm, void *va, } } -void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, - void *vpn, void *vpm, CPUARMState *env, uint32_t desc) +void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm, + void *vpn, void *vpm, CPUARMState *env, uint32_t desc) { intptr_t row, col, oprsz = simd_maxsz(desc); uint32_t neg = simd_data(desc) * 0x80008000u; 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 @@ TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, FPST_ZA, gen_helper_sme_fmopa_d) -TRANS_FEAT(BFMOPA, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa) +TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa_w) TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s) TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s) -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> For non-widening, we can use float_muladd_negate_product, For widening, which uses dot-product, we need to handle the negation explicitly. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-104-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 19 +++++ target/arm/tcg/vec_internal.h | 5 ++ target/arm/tcg/sme_helper.c | 141 +++++++++++++++++++++++++++------ target/arm/tcg/translate-sme.c | 27 ++++--- 4 files changed, 160 insertions(+), 32 deletions(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_7(sme_fmops_w_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_fmops_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_fmops_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_bfmops_w, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_7(sme_ah_fmops_w_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_ah_fmops_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_ah_fmops_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_ah_bfmops_w, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, env, i32) + DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sme_umopa_s, TCG_CALL_NO_RWG, diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_internal.h +++ b/target/arm/tcg/vec_internal.h @@ -XXX,XX +XXX,XX @@ bool is_ebf(CPUARMState *env, float_status *statusp, float_status *oddstatusp); /* * Negate as for FPCR.AH=1 -- do not negate NaNs. */ +static inline float16 bfloat16_ah_chs(float16 a) +{ + return bfloat16_is_any_nan(a) ? a : bfloat16_chs(a); +} + static inline float16 float16_ah_chs(float16 a) { return float16_is_any_nan(a) ? a : float16_chs(a); 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_addva_d)(void *vzda, void *vzn, void *vpn, } } -void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, float_status *fpst, uint32_t desc) +static void do_fmopa_s(void *vza, void *vzn, void *vzm, uint16_t *pn, + uint16_t *pm, float_status *fpst, uint32_t desc, + uint32_t negx, int negf) { intptr_t row, col, oprsz = simd_maxsz(desc); - uint32_t neg = simd_data(desc) << 31; - uint16_t *pn = vpn, *pm = vpm; for (row = 0; row < oprsz; ) { uint16_t pa = pn[H2(row >> 4)]; do { if (pa & 1) { void *vza_row = vza + tile_vslice_offset(row); - uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ neg; + uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ negx; for (col = 0; col < oprsz; ) { uint16_t pb = pm[H2(col >> 4)]; @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, if (pb & 1) { uint32_t *a = vza_row + H1_4(col); uint32_t *m = vzm + H1_4(col); - *a = float32_muladd(n, *m, *a, 0, fpst); + *a = float32_muladd(n, *m, *a, negf, fpst); } col += 4; pb >>= 4; @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, } } -void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, +void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_s(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0); +} + +void HELPER(sme_fmops_s)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_s(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 31, 0); +} + +void HELPER(sme_ah_fmops_s)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_s(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, + float_muladd_negate_product); +} + +static void do_fmopa_d(uint64_t *za, uint64_t *zn, uint64_t *zm, uint8_t *pn, + uint8_t *pm, float_status *fpst, uint32_t desc, + uint64_t negx, int negf) { intptr_t row, col, oprsz = simd_oprsz(desc) / 8; - uint64_t neg = (uint64_t)simd_data(desc) << 63; - uint64_t *za = vza, *zn = vzn, *zm = vzm; - uint8_t *pn = vpn, *pm = vpm; for (row = 0; row < oprsz; ++row) { if (pn[H1(row)] & 1) { uint64_t *za_row = &za[tile_vslice_index(row)]; - uint64_t n = zn[row] ^ neg; + uint64_t n = zn[row] ^ negx; for (col = 0; col < oprsz; ++col) { if (pm[H1(col)] & 1) { uint64_t *a = &za_row[col]; - *a = float64_muladd(n, zm[col], *a, 0, fpst); + *a = float64_muladd(n, zm[col], *a, negf, fpst); } } } } } +void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_d(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0); +} + +void HELPER(sme_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_d(vza, vzn, vzm, vpn, vpm, fpst, desc, 1ull << 63, 0); +} + +void HELPER(sme_ah_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_d(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, + float_muladd_negate_product); +} + /* * Alter PAIR as needed for controlling predicates being false, * and for NEG on an enabled row element. @@ -XXX,XX +XXX,XX @@ static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg) return pair; } +static inline uint32_t f16mop_ah_neg_adj_pair(uint32_t pair, uint32_t pg) +{ + uint32_t l = pg & 1 ? float16_ah_chs(pair) : 0; + uint32_t h = pg & 4 ? float16_ah_chs(pair >> 16) : 0; + return l | (h << 16); +} + +static inline uint32_t bf16mop_ah_neg_adj_pair(uint32_t pair, uint32_t pg) +{ + uint32_t l = pg & 1 ? bfloat16_ah_chs(pair) : 0; + uint32_t h = pg & 4 ? bfloat16_ah_chs(pair >> 16) : 0; + return l | (h << 16); +} + static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, float_status *s_f16, float_status *s_std, float_status *s_odd) @@ -XXX,XX +XXX,XX @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, return float32_add(sum, t32, s_std); } -void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, CPUARMState *env, uint32_t desc) +static void do_fmopa_w_h(void *vza, void *vzn, void *vzm, uint16_t *pn, + uint16_t *pm, CPUARMState *env, uint32_t desc, + uint32_t negx, bool ah_neg) { intptr_t row, col, oprsz = simd_maxsz(desc); - uint32_t neg = simd_data(desc) * 0x80008000u; - uint16_t *pn = vpn, *pm = vpm; float_status fpst_odd = env->vfp.fp_status[FPST_ZA]; set_float_rounding_mode(float_round_to_odd, &fpst_odd); @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn, void *vza_row = vza + tile_vslice_offset(row); uint32_t n = *(uint32_t *)(vzn + H1_4(row)); - n = f16mop_adj_pair(n, prow, neg); + if (ah_neg) { + n = f16mop_ah_neg_adj_pair(n, prow); + } else { + n = f16mop_adj_pair(n, prow, negx); + } for (col = 0; col < oprsz; ) { uint16_t pcol = pm[H2(col >> 4)]; @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn, } } +void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_fmopa_w_h(vza, vzn, vzm, vpn, vpm, env, desc, 0, false); +} + +void HELPER(sme_fmops_w_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_fmopa_w_h(vza, vzn, vzm, vpn, vpm, env, desc, 0x80008000u, false); +} + +void HELPER(sme_ah_fmops_w_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_fmopa_w_h(vza, vzn, vzm, vpn, vpm, env, desc, 0, true); +} + void HELPER(sme2_fdot_h)(void *vd, void *vn, void *vm, void *va, CPUARMState *env, uint32_t desc) { @@ -XXX,XX +XXX,XX @@ void HELPER(sme2_fvdot_idx_h)(void *vd, void *vn, void *vm, void *va, } } -void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm, - void *vpn, void *vpm, CPUARMState *env, uint32_t desc) +static void do_bfmopa_w(void *vza, void *vzn, void *vzm, + uint16_t *pn, uint16_t *pm, CPUARMState *env, + uint32_t desc, uint32_t negx, bool ah_neg) { intptr_t row, col, oprsz = simd_maxsz(desc); - uint32_t neg = simd_data(desc) * 0x80008000u; - uint16_t *pn = vpn, *pm = vpm; float_status fpst, fpst_odd; if (is_ebf(env, &fpst, &fpst_odd)) { @@ -XXX,XX +XXX,XX @@ void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm, void *vza_row = vza + tile_vslice_offset(row); uint32_t n = *(uint32_t *)(vzn + H1_4(row)); - n = f16mop_adj_pair(n, prow, neg); + if (ah_neg) { + n = bf16mop_ah_neg_adj_pair(n, prow); + } else { + n = f16mop_adj_pair(n, prow, negx); + } for (col = 0; col < oprsz; ) { uint16_t pcol = pm[H2(col >> 4)]; @@ -XXX,XX +XXX,XX @@ void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm, void *vza_row = vza + tile_vslice_offset(row); uint32_t n = *(uint32_t *)(vzn + H1_4(row)); - n = f16mop_adj_pair(n, prow, neg); + if (ah_neg) { + n = bf16mop_ah_neg_adj_pair(n, prow); + } else { + n = f16mop_adj_pair(n, prow, negx); + } for (col = 0; col < oprsz; ) { uint16_t pcol = pm[H2(col >> 4)]; @@ -XXX,XX +XXX,XX @@ void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm, } } +void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_bfmopa_w(vza, vzn, vzm, vpn, vpm, env, desc, 0, false); +} + +void HELPER(sme_bfmops_w)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_bfmopa_w(vza, vzn, vzm, vpn, vpm, env, desc, 0x80008000u, false); +} + +void HELPER(sme_ah_bfmops_w)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_bfmopa_w(vza, vzn, vzm, vpn, vpm, env, desc, 0, true); +} + typedef uint32_t IMOPFn32(uint32_t, uint32_t, uint32_t, uint8_t, bool); static inline void do_imopa_s(uint32_t *za, uint32_t *zn, uint32_t *zm, uint8_t *pn, uint8_t *pm, 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_fpst(DisasContext *s, arg_op *a, MemOp esz, gen_helper_gvec_5_ptr *fn) { int svl = streaming_vec_reg_size(s); - uint32_t desc = simd_desc(svl, svl, a->sub); + uint32_t desc = simd_desc(svl, svl, 0); TCGv_ptr za, zn, zm, pn, pm, fpst; if (!sme_smza_enabled_check(s)) { @@ -XXX,XX +XXX,XX @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz, gen_helper_gvec_5_ptr *fn) { int svl = streaming_vec_reg_size(s); - uint32_t desc = simd_desc(svl, svl, a->sub); + uint32_t desc = simd_desc(svl, svl, 0); TCGv_ptr za, zn, zm, pn, pm; if (!sme_smza_enabled_check(s)) { @@ -XXX,XX +XXX,XX @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz, return true; } -TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a, - MO_32, gen_helper_sme_fmopa_w_h) -TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, - MO_32, FPST_ZA, gen_helper_sme_fmopa_s) -TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, - MO_64, FPST_ZA, gen_helper_sme_fmopa_d) +TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a, MO_32, + !a->sub ? gen_helper_sme_fmopa_w_h + : !s->fpcr_ah ? gen_helper_sme_fmops_w_h + : gen_helper_sme_ah_fmops_w_h) +TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, FPST_ZA, + !a->sub ? gen_helper_sme_fmopa_s + : !s->fpcr_ah ? gen_helper_sme_fmops_s + : gen_helper_sme_ah_fmops_s) +TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, FPST_ZA, + !a->sub ? gen_helper_sme_fmopa_d + : !s->fpcr_ah ? gen_helper_sme_fmops_d + : gen_helper_sme_ah_fmops_d) -TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa_w) +TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32, + !a->sub ? gen_helper_sme_bfmopa_w + : !s->fpcr_ah ? gen_helper_sme_bfmops_w + : gen_helper_sme_ah_bfmops_w) TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s) TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s) -- 2.43.0 Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-105-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 6 ++++ target/arm/tcg/sme.decode | 2 ++ target/arm/tcg/sme_helper.c | 51 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 4 +++ 4 files changed, 63 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_7(sme_fmops_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_fmops_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_fmops_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_fmops_d, TCG_CALL_NO_RWG, @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_bfmops_w, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_7(sme_ah_fmops_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_ah_fmops_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_ah_fmops_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_ah_fmops_d, TCG_CALL_NO_RWG, diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 ### SME Outer Product &op zad zn zm pm pn sub:bool +@op_16 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 ... zad:1 &op @op_32 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 .. zad:2 &op @op_64 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 . zad:3 &op +FMOPA_h 10000001 100 ..... ... ... ..... . 100 . @op_16 FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 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_addva_d)(void *vzda, void *vzn, void *vpn, } } +static void do_fmopa_h(void *vza, void *vzn, void *vzm, uint16_t *pn, + uint16_t *pm, float_status *fpst, uint32_t desc, + uint16_t negx, int negf) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + + for (row = 0; row < oprsz; ) { + uint16_t pa = pn[H2(row >> 4)]; + do { + if (pa & 1) { + void *vza_row = vza + tile_vslice_offset(row); + uint16_t n = *(uint32_t *)(vzn + H1_2(row)) ^ negx; + + for (col = 0; col < oprsz; ) { + uint16_t pb = pm[H2(col >> 4)]; + do { + if (pb & 1) { + uint16_t *a = vza_row + H1_2(col); + uint16_t *m = vzm + H1_2(col); + *a = float16_muladd(n, *m, *a, negf, fpst); + } + col += 2; + pb >>= 2; + } while (col & 15); + } + } + row += 2; + pa >>= 2; + } while (row & 15); + } +} + +void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0); +} + +void HELPER(sme_fmops_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 15, 0); +} + +void HELPER(sme_ah_fmops_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, + float_muladd_negate_product); +} + static void do_fmopa_s(void *vza, void *vzn, void *vzm, uint16_t *pn, uint16_t *pm, float_status *fpst, uint32_t desc, uint32_t negx, int negf) 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 @@ TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a, MO_32, !a->sub ? gen_helper_sme_fmopa_w_h : !s->fpcr_ah ? gen_helper_sme_fmops_w_h : gen_helper_sme_ah_fmops_w_h) +TRANS_FEAT(FMOPA_h, aa64_sme_f16f16, do_outprod_fpst, a, MO_16, FPST_ZA_F16, + !a->sub ? gen_helper_sme_fmopa_h + : !s->fpcr_ah ? gen_helper_sme_fmops_h + : gen_helper_sme_ah_fmops_h) TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, FPST_ZA, !a->sub ? gen_helper_sme_fmopa_s : !s->fpcr_ah ? gen_helper_sme_fmops_s -- 2.43.0 Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-106-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 6 ++++ target/arm/tcg/sme.decode | 2 ++ target/arm/tcg/sme_helper.c | 51 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sme.c | 5 ++++ 4 files changed, 64 insertions(+) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_bfmopa, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_fmops_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmops_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_bfmops_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_bfmops, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_ah_fmops_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_ah_fmops_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_ah_bfmops_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_ah_bfmops, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -XXX,XX +XXX,XX @@ FMOPA_h 10000001 100 ..... ... ... ..... . 100 . @op_16 FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 +BFMOPA 10000001 101 ..... ... ... ..... . 100 . @op_16 + BFMOPA_w 10000001 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_w_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 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_ah_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn, float_muladd_negate_product); } +static void do_bfmopa(void *vza, void *vzn, void *vzm, uint16_t *pn, + uint16_t *pm, float_status *fpst, uint32_t desc, + uint16_t negx, int negf) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + + for (row = 0; row < oprsz; ) { + uint16_t pa = pn[H2(row >> 4)]; + do { + if (pa & 1) { + void *vza_row = vza + tile_vslice_offset(row); + uint16_t n = *(uint32_t *)(vzn + H1_2(row)) ^ negx; + + for (col = 0; col < oprsz; ) { + uint16_t pb = pm[H2(col >> 4)]; + do { + if (pb & 1) { + uint16_t *a = vza_row + H1_2(col); + uint16_t *m = vzm + H1_2(col); + *a = bfloat16_muladd(n, *m, *a, negf, fpst); + } + col += 2; + pb >>= 2; + } while (col & 15); + } + } + row += 2; + pa >>= 2; + } while (row & 15); + } +} + +void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0); +} + +void HELPER(sme_bfmops)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 15, 0); +} + +void HELPER(sme_ah_bfmops)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, + float_muladd_negate_product); +} + /* * Alter PAIR as needed for controlling predicates being false, * and for NEG on an enabled row element. 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 @@ TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, FPST_ZA, : !s->fpcr_ah ? gen_helper_sme_fmops_d : gen_helper_sme_ah_fmops_d) +TRANS_FEAT(BFMOPA, aa64_sme_b16b16, do_outprod_fpst, a, MO_16, FPST_ZA, + !a->sub ? gen_helper_sme_bfmopa + : !s->fpcr_ah ? gen_helper_sme_bfmops + : gen_helper_sme_ah_bfmops) + TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32, !a->sub ? gen_helper_sme_bfmopa_w : !s->fpcr_ah ? gen_helper_sme_bfmops_w -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-107-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 6 ++++++ target/arm/tcg/cpu64.c | 10 ++++++++-- 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_SM3 (Advanced SIMD SM3 instructions) - FEAT_SM4 (Advanced SIMD SM4 instructions) - FEAT_SME (Scalable Matrix Extension) +- FEAT_SME2 (Scalable Matrix Extension version 2) +- FEAT_SME2p1 (Scalable Matrix Extension version 2.1) +- FEAT_SME_B16B16 (Non-widening BFloat16 arithmetic for SME2) - FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode) +- FEAT_SME_F16F16 (Non-widening half-precision FP16 arithmetic for SME2) - FEAT_SME_F64F64 (Double-precision floating-point outer product instructions) - FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions) - FEAT_SVE (Scalable Vector Extension) - FEAT_SVE_AES (Scalable Vector AES instructions) +- FEAT_SVE_B16B16 (Non-widening BFloat16 arithmetic for SVE2) - FEAT_SVE_BitPerm (Scalable Vector Bit Permutes instructions) - FEAT_SVE_PMULL128 (Scalable Vector PMULL instructions) - FEAT_SVE_SHA3 (Scalable Vector SHA3 instructions) - FEAT_SVE_SM4 (Scalable Vector SM4 instructions) - FEAT_SVE2 (Scalable Vector Extension version 2) +- FEAT_SVE2p1 (Scalable Vector Extension version 2.1) - FEAT_SPECRES (Speculation restriction instructions) - FEAT_SSBS (Speculative Store Bypass Safe) - FEAT_SSBS2 (MRS and MSR instructions for SSBS version 2) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) */ t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */ t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */ - t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64PFR1, SME, 2); /* FEAT_SME2 */ t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_3 */ t = FIELD_DP64(t, ID_AA64PFR1, NMI, 1); /* FEAT_NMI */ SET_IDREG(isar, ID_AA64PFR1, t); @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) FIELD_DP64_IDREG(isar, ID_AA64MMFR3, SPEC_FPACC, 1); /* FEAT_FPACC_SPEC */ t = GET_IDREG(isar, ID_AA64ZFR0); - t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 2); /* FEAT_SVE2p1 */ t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2); /* FEAT_SVE_PMULL128 */ t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1); /* FEAT_SVE_BitPerm */ t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 2); /* FEAT_BF16, FEAT_EBF16 */ + t = FIELD_DP64(t, ID_AA64ZFR0, B16B16, 1); /* FEAT_SVE_B16B16 */ t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1); /* FEAT_SVE_SHA3 */ t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1); /* FEAT_SVE_SM4 */ t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1); /* FEAT_I8MM */ @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = GET_IDREG(isar, ID_AA64SMFR0); t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, BI32I32, 1); /* FEAT_SME2 */ t = FIELD_DP64(t, ID_AA64SMFR0, B16F32, 1); /* FEAT_SME */ t = FIELD_DP64(t, ID_AA64SMFR0, F16F32, 1); /* FEAT_SME */ t = FIELD_DP64(t, ID_AA64SMFR0, I8I32, 0xf); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, F16F16, 1); /* FEAT_SME_F16F16 */ + t = FIELD_DP64(t, ID_AA64SMFR0, B16B16, 1); /* FEAT_SME_B16B16 */ + t = FIELD_DP64(t, ID_AA64SMFR0, I16I32, 5); /* FEAT_SME2 */ t = FIELD_DP64(t, ID_AA64SMFR0, F64F64, 1); /* FEAT_SME_F64F64 */ t = FIELD_DP64(t, ID_AA64SMFR0, I16I64, 0xf); /* FEAT_SME_I16I64 */ + t = FIELD_DP64(t, ID_AA64SMFR0, SMEVER, 2); /* FEAT_SME2p1 */ t = FIELD_DP64(t, ID_AA64SMFR0, FA64, 1); /* FEAT_SME_FA64 */ SET_IDREG(isar, ID_AA64SMFR0, t); -- 2.43.0 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250704142112.1018902-108-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ uint64_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64); GET_FEATURE_ID(aa64_hbc, ARM_HWCAP2_A64_HBC); GET_FEATURE_ID(aa64_mops, ARM_HWCAP2_A64_MOPS); + GET_FEATURE_ID(aa64_sve2p1, ARM_HWCAP2_A64_SVE2P1); + GET_FEATURE_ID(aa64_sme2, (ARM_HWCAP2_A64_SME2 | + ARM_HWCAP2_A64_SME_I16I32 | + ARM_HWCAP2_A64_SME_BI32I32)); + GET_FEATURE_ID(aa64_sme2p1, ARM_HWCAP2_A64_SME2P1); + GET_FEATURE_ID(aa64_sme_b16b16, ARM_HWCAP2_A64_SME_B16B16); + GET_FEATURE_ID(aa64_sme_f16f16, ARM_HWCAP2_A64_SME_F16F16); + GET_FEATURE_ID(aa64_sve_b16b16, ARM_HWCAP2_A64_SVE_B16B16); return hwcaps; } -- 2.43.0