The following changes since commit 5a67d7735d4162630769ef495cf813244fc850df: Merge remote-tracking branch 'remotes/berrange-gitlab/tags/tls-deps-pull-request' into staging (2021-07-02 08:22:39 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210702 for you to fetch changes up to 04ea4d3cfd0a21b248ece8eb7a9436a3d9898dd8: target/arm: Implement MVE shifts by register (2021-07-02 11:48:38 +0100) ---------------------------------------------------------------- target-arm queue: * more MVE instructions * hw/gpio/gpio_pwr: use shutdown function for reboot * target/arm: Check NaN mode before silencing NaN * tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine * hw/arm: Add basic power management to raspi. * docs/system/arm: Add quanta-gbs-bmc, quanta-q7l1-bmc ---------------------------------------------------------------- Joe Komlodi (1): target/arm: Check NaN mode before silencing NaN Maxim Uvarov (1): hw/gpio/gpio_pwr: use shutdown function for reboot Nolan Leake (1): hw/arm: Add basic power management to raspi. Patrick Venture (2): docs/system/arm: Add quanta-q7l1-bmc reference docs/system/arm: Add quanta-gbs-bmc reference Peter Maydell (18): target/arm: Fix MVE widening/narrowing VLDR/VSTR offset calculation target/arm: Fix bugs in MVE VRMLALDAVH, VRMLSLDAVH target/arm: Make asimd_imm_const() public target/arm: Use asimd_imm_const for A64 decode target/arm: Use dup_const() instead of bitfield_replicate() target/arm: Implement MVE logical immediate insns target/arm: Implement MVE vector shift left by immediate insns target/arm: Implement MVE vector shift right by immediate insns target/arm: Implement MVE VSHLL target/arm: Implement MVE VSRI, VSLI target/arm: Implement MVE VSHRN, VRSHRN target/arm: Implement MVE saturating narrowing shifts target/arm: Implement MVE VSHLC target/arm: Implement MVE VADDLV target/arm: Implement MVE long shifts by immediate target/arm: Implement MVE long shifts by register target/arm: Implement MVE shifts by immediate target/arm: Implement MVE shifts by register Philippe Mathieu-Daudé (1): tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine docs/system/arm/aspeed.rst | 1 + docs/system/arm/nuvoton.rst | 5 +- include/hw/arm/bcm2835_peripherals.h | 3 +- include/hw/misc/bcm2835_powermgt.h | 29 ++ target/arm/helper-mve.h | 108 +++++++ target/arm/translate.h | 41 +++ target/arm/mve.decode | 177 ++++++++++- target/arm/t32.decode | 71 ++++- hw/arm/bcm2835_peripherals.c | 13 +- hw/gpio/gpio_pwr.c | 2 +- hw/misc/bcm2835_powermgt.c | 160 ++++++++++ target/arm/helper-a64.c | 12 +- target/arm/mve_helper.c | 524 +++++++++++++++++++++++++++++++-- target/arm/translate-a64.c | 86 +----- target/arm/translate-mve.c | 261 +++++++++++++++- target/arm/translate-neon.c | 81 ----- target/arm/translate.c | 327 +++++++++++++++++++- target/arm/vfp_helper.c | 24 +- hw/misc/meson.build | 1 + tests/acceptance/boot_linux_console.py | 43 +++ 20 files changed, 1760 insertions(+), 209 deletions(-) create mode 100644 include/hw/misc/bcm2835_powermgt.h create mode 100644 hw/misc/bcm2835_powermgt.c From: Patrick Venture <venture@google.com> Adds a line-item reference to the supported quanta-q71l-bmc aspeed entry. Signed-off-by: Patrick Venture <venture@google.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Message-id: 20210615192848.1065297-2-venture@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/aspeed.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/aspeed.rst +++ b/docs/system/arm/aspeed.rst @@ -XXX,XX +XXX,XX @@ etc. AST2400 SoC based machines : - ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC +- ``quanta-q71l-bmc`` OpenBMC Quanta BMC AST2500 SoC based machines : -- 2.20.1 From: Patrick Venture <venture@google.com> Add line item reference to quanta-gbs-bmc machine. Signed-off-by: Patrick Venture <venture@google.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Message-id: 20210615192848.1065297-3-venture@google.com [PMM: fixed underline Sphinx warning] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ -Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``) -===================================================== +Nuvoton iBMC boards (``*-bmc``, ``npcm750-evb``, ``quanta-gsj``) +================================================================ The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are designed to be used as Baseboard Management Controllers (BMCs) in various @@ -XXX,XX +XXX,XX @@ segment. The following machines are based on this chip : The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and Hyperscale applications. The following machines are based on this chip : +- ``quanta-gbs-bmc`` Quanta GBS server BMC - ``quanta-gsj`` Quanta GSJ server BMC There are also two more SoCs, NPCM710 and NPCM705, which are single-core -- 2.20.1 From: Nolan Leake <nolan@sigbus.net> This is just enough to make reboot and poweroff work. Works for linux, u-boot, and the arm trusted firmware. Not tested, but should work for plan9, and bare-metal/hobby OSes, since they seem to generally do what linux does for reset. The watchdog timer functionality is not yet implemented. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/64 Signed-off-by: Nolan Leake <nolan@sigbus.net> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210625210209.1870217-1-nolan@sigbus.net [PMM: tweaked commit title; fixed region size to 0x200; moved header file to include/] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 3 +- include/hw/misc/bcm2835_powermgt.h | 29 +++++ hw/arm/bcm2835_peripherals.c | 13 ++- hw/misc/bcm2835_powermgt.c | 160 +++++++++++++++++++++++++++ hw/misc/meson.build | 1 + 5 files changed, 204 insertions(+), 2 deletions(-) create mode 100644 include/hw/misc/bcm2835_powermgt.h create mode 100644 hw/misc/bcm2835_powermgt.c diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/bcm2835_mphi.h" #include "hw/misc/bcm2835_thermal.h" #include "hw/misc/bcm2835_cprman.h" +#include "hw/misc/bcm2835_powermgt.h" #include "hw/sd/sdhci.h" #include "hw/sd/bcm2835_sdhost.h" #include "hw/gpio/bcm2835_gpio.h" @@ -XXX,XX +XXX,XX @@ struct BCM2835PeripheralState { BCM2835MphiState mphi; UnimplementedDeviceState txp; UnimplementedDeviceState armtmr; - UnimplementedDeviceState powermgt; + BCM2835PowerMgtState powermgt; BCM2835CprmanState cprman; PL011State uart0; BCM2835AuxState aux; diff --git a/include/hw/misc/bcm2835_powermgt.h b/include/hw/misc/bcm2835_powermgt.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/bcm2835_powermgt.h @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 Power Management emulation + * + * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com> + * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net> + * + * 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 BCM2835_POWERMGT_H +#define BCM2835_POWERMGT_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_BCM2835_POWERMGT "bcm2835-powermgt" +OBJECT_DECLARE_SIMPLE_TYPE(BCM2835PowerMgtState, BCM2835_POWERMGT) + +struct BCM2835PowerMgtState { + SysBusDevice busdev; + MemoryRegion iomem; + + uint32_t rstc; + uint32_t rsts; + uint32_t wdog; +}; + +#endif diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr", OBJECT(&s->gpu_bus_mr)); + + /* Power Management */ + object_initialize_child(obj, "powermgt", &s->powermgt, + TYPE_BCM2835_POWERMGT); } static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, INTERRUPT_USB)); + /* Power Management */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->powermgt), errp)) { + return; + } + + memory_region_add_subregion(&s->peri_mr, PM_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->powermgt), 0)); + create_unimp(s, &s->txp, "bcm2835-txp", TXP_OFFSET, 0x1000); create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); - create_unimp(s, &s->powermgt, "bcm2835-powermgt", PM_OFFSET, 0x114); create_unimp(s, &s->i2s, "bcm2835-i2s", I2S_OFFSET, 0x100); create_unimp(s, &s->smi, "bcm2835-smi", SMI_OFFSET, 0x100); create_unimp(s, &s->spi[0], "bcm2835-spi0", SPI0_OFFSET, 0x20); diff --git a/hw/misc/bcm2835_powermgt.c b/hw/misc/bcm2835_powermgt.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/bcm2835_powermgt.c @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 Power Management emulation + * + * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com> + * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/bcm2835_powermgt.h" +#include "migration/vmstate.h" +#include "sysemu/runstate.h" + +#define PASSWORD 0x5a000000 +#define PASSWORD_MASK 0xff000000 + +#define R_RSTC 0x1c +#define V_RSTC_RESET 0x20 +#define R_RSTS 0x20 +#define V_RSTS_POWEROFF 0x555 /* Linux uses partition 63 to indicate halt. */ +#define R_WDOG 0x24 + +static uint64_t bcm2835_powermgt_read(void *opaque, hwaddr offset, + unsigned size) +{ + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; + uint32_t res = 0; + + switch (offset) { + case R_RSTC: + res = s->rstc; + break; + case R_RSTS: + res = s->rsts; + break; + case R_WDOG: + res = s->wdog; + break; + + default: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_read: Unknown offset 0x%08"HWADDR_PRIx + "\n", offset); + res = 0; + break; + } + + return res; +} + +static void bcm2835_powermgt_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; + + if ((value & PASSWORD_MASK) != PASSWORD) { + qemu_log_mask(LOG_GUEST_ERROR, + "bcm2835_powermgt_write: Bad password 0x%"PRIx64 + " at offset 0x%08"HWADDR_PRIx"\n", + value, offset); + return; + } + + value = value & ~PASSWORD_MASK; + + switch (offset) { + case R_RSTC: + s->rstc = value; + if (value & V_RSTC_RESET) { + if ((s->rsts & 0xfff) == V_RSTS_POWEROFF) { + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + } else { + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); + } + } + break; + case R_RSTS: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_write: RSTS\n"); + s->rsts = value; + break; + case R_WDOG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_write: WDOG\n"); + s->wdog = value; + break; + + default: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_write: Unknown offset 0x%08"HWADDR_PRIx + "\n", offset); + break; + } +} + +static const MemoryRegionOps bcm2835_powermgt_ops = { + .read = bcm2835_powermgt_read, + .write = bcm2835_powermgt_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl.min_access_size = 4, + .impl.max_access_size = 4, +}; + +static const VMStateDescription vmstate_bcm2835_powermgt = { + .name = TYPE_BCM2835_POWERMGT, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(rstc, BCM2835PowerMgtState), + VMSTATE_UINT32(rsts, BCM2835PowerMgtState), + VMSTATE_UINT32(wdog, BCM2835PowerMgtState), + VMSTATE_END_OF_LIST() + } +}; + +static void bcm2835_powermgt_init(Object *obj) +{ + BCM2835PowerMgtState *s = BCM2835_POWERMGT(obj); + + memory_region_init_io(&s->iomem, obj, &bcm2835_powermgt_ops, s, + TYPE_BCM2835_POWERMGT, 0x200); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); +} + +static void bcm2835_powermgt_reset(DeviceState *dev) +{ + BCM2835PowerMgtState *s = BCM2835_POWERMGT(dev); + + /* https://elinux.org/BCM2835_registers#PM */ + s->rstc = 0x00000102; + s->rsts = 0x00001000; + s->wdog = 0x00000000; +} + +static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = bcm2835_powermgt_reset; + dc->vmsd = &vmstate_bcm2835_powermgt; +} + +static TypeInfo bcm2835_powermgt_info = { + .name = TYPE_BCM2835_POWERMGT, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(BCM2835PowerMgtState), + .class_init = bcm2835_powermgt_class_init, + .instance_init = bcm2835_powermgt_init, +}; + +static void bcm2835_powermgt_register_types(void) +{ + type_register_static(&bcm2835_powermgt_info); +} + +type_init(bcm2835_powermgt_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 @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files( 'bcm2835_rng.c', 'bcm2835_thermal.c', 'bcm2835_cprman.c', + 'bcm2835_powermgt.c', )) softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c')) softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c')) -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Add a test booting and quickly shutdown a raspi2 machine, to test the power management model: (1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_raspi2_initrd: console: [ 0.000000] Booting Linux on physical CPU 0xf00 console: [ 0.000000] Linux version 4.14.98-v7+ (dom@dom-XPS-13-9370) (gcc version 4.9.3 (crosstool-NG crosstool-ng-1.22.0-88-g8460611)) #1200 SMP Tue Feb 12 20:27:48 GMT 2019 console: [ 0.000000] CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=10c5387d console: [ 0.000000] CPU: div instructions available: patching division code console: [ 0.000000] CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache console: [ 0.000000] OF: fdt: Machine model: Raspberry Pi 2 Model B ... console: Boot successful. console: cat /proc/cpuinfo console: / # cat /proc/cpuinfo ... console: processor : 3 console: model name : ARMv7 Processor rev 5 (v7l) console: BogoMIPS : 125.00 console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm console: CPU implementer : 0x41 console: CPU architecture: 7 console: CPU variant : 0x0 console: CPU part : 0xc07 console: CPU revision : 5 console: Hardware : BCM2835 console: Revision : 0000 console: Serial : 0000000000000000 console: cat /proc/iomem console: / # cat /proc/iomem console: 00000000-3bffffff : System RAM console: 00008000-00afffff : Kernel code console: 00c00000-00d468ef : Kernel data console: 3f006000-3f006fff : dwc_otg console: 3f007000-3f007eff : /soc/dma@7e007000 console: 3f00b880-3f00b8bf : /soc/mailbox@7e00b880 console: 3f100000-3f100027 : /soc/watchdog@7e100000 console: 3f101000-3f102fff : /soc/cprman@7e101000 console: 3f200000-3f2000b3 : /soc/gpio@7e200000 PASS (24.59 s) RESULTS : PASS 1 | ERROR 0 | FAIL 0 | SKIP 0 | WARN 0 | INTERRUPT 0 | CANCEL 0 JOB TIME : 25.02 s Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Message-id: 20210531113837.1689775-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 43 ++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ from avocado import skip from avocado import skipUnless from avocado_qemu import Test +from avocado_qemu import exec_command from avocado_qemu import exec_command_and_wait_for_pattern from avocado_qemu import interrupt_interactive_console_until_pattern from avocado_qemu import wait_for_console_pattern @@ -XXX,XX +XXX,XX @@ def test_arm_raspi2_uart0(self): """ self.do_test_arm_raspi2(0) + def test_arm_raspi2_initrd(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:raspi2 + """ + deb_url = ('http://archive.raspberrypi.org/debian/' + 'pool/main/r/raspberrypi-firmware/' + 'raspberrypi-kernel_1.20190215-1_armhf.deb') + deb_hash = 'cd284220b32128c5084037553db3c482426f3972' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, '/boot/kernel7.img') + dtb_path = self.extract_from_deb(deb_path, '/boot/bcm2709-rpi-2-b.dtb') + + initrd_url = ('https://github.com/groeck/linux-build-test/raw/' + '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' + 'arm/rootfs-armv7a.cpio.gz') + initrd_hash = '604b2e45cdf35045846b8bbfbf2129b1891bdc9c' + initrd_path_gz = self.fetch_asset(initrd_url, asset_hash=initrd_hash) + initrd_path = os.path.join(self.workdir, 'rootfs.cpio') + archive.gzip_uncompress(initrd_path_gz, initrd_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'earlycon=pl011,0x3f201000 console=ttyAMA0 ' + 'panic=-1 noreboot ' + + 'dwc_otg.fiq_fsm_enable=0') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-initrd', initrd_path, + '-append', kernel_command_line, + '-no-reboot') + self.vm.launch() + self.wait_for_console_pattern('Boot successful.') + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'BCM2835') + exec_command_and_wait_for_pattern(self, 'cat /proc/iomem', + '/soc/cprman@7e101000') + exec_command(self, 'halt') + # Wait for VM to shut down gracefully + self.vm.wait() + def test_arm_exynos4210_initrd(self): """ :avocado: tags=arch:arm -- 2.20.1 From: Joe Komlodi <joe.komlodi@xilinx.com> If the CPU is running in default NaN mode (FPCR.DN == 1) and we execute FRSQRTE, FRECPE, or FRECPX with a signaling NaN, parts_silence_nan_frac() will assert due to fpst->default_nan_mode being set. To avoid this, we check to see what NaN mode we're running in before we call floatxx_silence_nan(). Signed-off-by: Joe Komlodi <joe.komlodi@xilinx.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1624662174-175828-2-git-send-email-joe.komlodi@xilinx.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.c | 12 +++++++++--- target/arm/vfp_helper.c | 24 ++++++++++++++++++------ 2 files changed, 27 insertions(+), 9 deletions(-) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) float16 nan = a; if (float16_is_signaling_nan(a, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float16_silence_nan(a, fpst); + if (!fpst->default_nan_mode) { + nan = float16_silence_nan(a, fpst); + } } if (fpst->default_nan_mode) { nan = float16_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ float32 HELPER(frecpx_f32)(float32 a, void *fpstp) float32 nan = a; if (float32_is_signaling_nan(a, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float32_silence_nan(a, fpst); + if (!fpst->default_nan_mode) { + nan = float32_silence_nan(a, fpst); + } } if (fpst->default_nan_mode) { nan = float32_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ float64 HELPER(frecpx_f64)(float64 a, void *fpstp) float64 nan = a; if (float64_is_signaling_nan(a, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float64_silence_nan(a, fpst); + if (!fpst->default_nan_mode) { + nan = float64_silence_nan(a, fpst); + } } if (fpst->default_nan_mode) { nan = float64_default_nan(fpst); diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp) float16 nan = f16; if (float16_is_signaling_nan(f16, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float16_silence_nan(f16, fpst); + if (!fpst->default_nan_mode) { + nan = float16_silence_nan(f16, fpst); + } } if (fpst->default_nan_mode) { nan = float16_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ float32 HELPER(recpe_f32)(float32 input, void *fpstp) float32 nan = f32; if (float32_is_signaling_nan(f32, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float32_silence_nan(f32, fpst); + if (!fpst->default_nan_mode) { + nan = float32_silence_nan(f32, fpst); + } } if (fpst->default_nan_mode) { nan = float32_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp) float64 nan = f64; if (float64_is_signaling_nan(f64, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float64_silence_nan(f64, fpst); + if (!fpst->default_nan_mode) { + nan = float64_silence_nan(f64, fpst); + } } if (fpst->default_nan_mode) { nan = float64_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp) float16 nan = f16; if (float16_is_signaling_nan(f16, s)) { float_raise(float_flag_invalid, s); - nan = float16_silence_nan(f16, s); + if (!s->default_nan_mode) { + nan = float16_silence_nan(f16, fpstp); + } } if (s->default_nan_mode) { nan = float16_default_nan(s); @@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) float32 nan = f32; if (float32_is_signaling_nan(f32, s)) { float_raise(float_flag_invalid, s); - nan = float32_silence_nan(f32, s); + if (!s->default_nan_mode) { + nan = float32_silence_nan(f32, fpstp); + } } if (s->default_nan_mode) { nan = float32_default_nan(s); @@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) float64 nan = f64; if (float64_is_signaling_nan(f64, s)) { float_raise(float_flag_invalid, s); - nan = float64_silence_nan(f64, s); + if (!s->default_nan_mode) { + nan = float64_silence_nan(f64, fpstp); + } } if (s->default_nan_mode) { nan = float64_default_nan(s); -- 2.20.1 From: Maxim Uvarov <maxim.uvarov@linaro.org> qemu has 2 type of functions: shutdown and reboot. Shutdown function has to be used for machine shutdown. Otherwise we cause a reset with a bogus "cause" value, when we intended a shutdown. Signed-off-by: Maxim Uvarov <maxim.uvarov@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210625111842.3790-3-maxim.uvarov@linaro.org [PMM: tweaked commit message] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/gpio/gpio_pwr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/gpio/gpio_pwr.c b/hw/gpio/gpio_pwr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/gpio_pwr.c +++ b/hw/gpio/gpio_pwr.c @@ -XXX,XX +XXX,XX @@ static void gpio_pwr_reset(void *opaque, int n, int level) static void gpio_pwr_shutdown(void *opaque, int n, int level) { if (level) { - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); } } -- 2.20.1 In do_ldst(), the calculation of the offset needs to be based on the size of the memory access, not the size of the elements in the vector. This meant we were getting it wrong for the widening and narrowing variants of the various VLDR and VSTR insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-2-peter.maydell@linaro.org --- target/arm/translate-mve.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool mve_skip_first_beat(DisasContext *s) } } -static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) +static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn, + unsigned msize) { TCGv_i32 addr; uint32_t offset; @@ -XXX,XX +XXX,XX @@ static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) return true; } - offset = a->imm << a->size; + offset = a->imm << msize; if (!a->a) { offset = -offset; } @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a) { gen_helper_mve_vstrw, gen_helper_mve_vldrw }, { NULL, NULL } }; - return do_ldst(s, a, ldstfns[a->size][a->l]); + return do_ldst(s, a, ldstfns[a->size][a->l], a->size); } -#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST) \ +#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST, MSIZE) \ static bool trans_##OP(DisasContext *s, arg_VLDR_VSTR *a) \ { \ static MVEGenLdStFn * const ldstfns[2][2] = { \ { gen_helper_mve_##ST, gen_helper_mve_##SLD }, \ { NULL, gen_helper_mve_##ULD }, \ }; \ - return do_ldst(s, a, ldstfns[a->u][a->l]); \ + return do_ldst(s, a, ldstfns[a->u][a->l], MSIZE); \ } -DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h) -DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w) -DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w) +DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8) +DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8) +DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16) static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { -- 2.20.1 The initial implementation of the MVE VRMLALDAVH and VRMLSLDAVH insns had some bugs: * the 32x32 multiply of elements was being done as 32x32->32, not 32x32->64 * we were incorrectly maintaining the accumulator in its full 72-bit form across all 4 beats of the insn; in the pseudocode it is squashed back into the 64 bits of the RdaHi:RdaLo registers after each beat In particular, fixing the second of these allows us to recast the implementation to avoid 128-bit arithmetic entirely. Since the element size here is always 4, we can also drop the parameterization of ESIZE to make the code a little more readable. Suggested-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-3-peter.maydell@linaro.org --- target/arm/mve_helper.c | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "qemu/int128.h" #include "cpu.h" #include "internals.h" #include "vec_internal.h" @@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=) DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=) /* - * Rounding multiply add long dual accumulate high: we must keep - * a 72-bit internal accumulator value and return the top 64 bits. + * Rounding multiply add long dual accumulate high. In the pseudocode + * this is implemented with a 72-bit internal accumulator value of which + * the top 64 bits are returned. We optimize this to avoid having to + * use 128-bit arithmetic -- we can do this because the 74-bit accumulator + * is squashed back into 64-bits after each beat. */ -#define DO_LDAVH(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC, TO128) \ +#define DO_LDAVH(OP, TYPE, LTYPE, XCHG, SUB) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ void *vm, uint64_t a) \ { \ uint16_t mask = mve_element_mask(env); \ unsigned e; \ TYPE *n = vn, *m = vm; \ - Int128 acc = int128_lshift(TO128(a), 8); \ - for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ if (mask & 1) { \ + LTYPE mul; \ if (e & 1) { \ - acc = ODDACC(acc, TO128(n[H##ESIZE(e - 1 * XCHG)] * \ - m[H##ESIZE(e)])); \ + mul = (LTYPE)n[H4(e - 1 * XCHG)] * m[H4(e)]; \ + if (SUB) { \ + mul = -mul; \ + } \ } else { \ - acc = EVENACC(acc, TO128(n[H##ESIZE(e + 1 * XCHG)] * \ - m[H##ESIZE(e)])); \ + mul = (LTYPE)n[H4(e + 1 * XCHG)] * m[H4(e)]; \ } \ - acc = int128_add(acc, int128_make64(1 << 7)); \ + mul = (mul >> 8) + ((mul >> 7) & 1); \ + a += mul; \ } \ } \ mve_advance_vpt(env); \ - return int128_getlo(int128_rshift(acc, 8)); \ + return a; \ } -DO_LDAVH(vrmlaldavhsw, 4, int32_t, false, int128_add, int128_add, int128_makes64) -DO_LDAVH(vrmlaldavhxsw, 4, int32_t, true, int128_add, int128_add, int128_makes64) +DO_LDAVH(vrmlaldavhsw, int32_t, int64_t, false, false) +DO_LDAVH(vrmlaldavhxsw, int32_t, int64_t, true, false) -DO_LDAVH(vrmlaldavhuw, 4, uint32_t, false, int128_add, int128_add, int128_make64) +DO_LDAVH(vrmlaldavhuw, uint32_t, uint64_t, false, false) -DO_LDAVH(vrmlsldavhsw, 4, int32_t, false, int128_add, int128_sub, int128_makes64) -DO_LDAVH(vrmlsldavhxsw, 4, int32_t, true, int128_add, int128_sub, int128_makes64) +DO_LDAVH(vrmlsldavhsw, int32_t, int64_t, false, true) +DO_LDAVH(vrmlsldavhxsw, int32_t, int64_t, true, true) /* Vector add across vector */ #define DO_VADDV(OP, ESIZE, TYPE) \ -- 2.20.1 The function asimd_imm_const() in translate-neon.c is an implementation of the pseudocode AdvSIMDExpandImm(), which we will also want for MVE. Move the implementation to translate.c, with a prototype in translate.h. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-4-peter.maydell@linaro.org --- target/arm/translate.h | 16 ++++++++++ target/arm/translate-neon.c | 63 ------------------------------------- target/arm/translate.c | 57 +++++++++++++++++++++++++++++++++ 3 files changed, 73 insertions(+), 63 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) return opc | s->be_data; } +/** + * asimd_imm_const: Expand an encoded SIMD constant value + * + * Expand a SIMD constant value. This is essentially the pseudocode + * AdvSIMDExpandImm, except that we also perform the boolean NOT needed for + * VMVN and VBIC (when cmode < 14 && op == 1). + * + * The combination cmode == 15 op == 1 is a reserved encoding for AArch32; + * callers must catch this. + * + * cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 was UNPREDICTABLE in v7A but + * is either not unpredictable or merely CONSTRAINED UNPREDICTABLE in v8A; + * we produce an immediate constant value of 0 in these cases. + */ +uint64_t asimd_imm_const(uint32_t imm, int cmode, int op); + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh) DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs) DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu) -static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) -{ - /* - * Expand the encoded constant. - * Note that cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE. - * We choose to not special-case this and will behave as if a - * valid constant encoding of 0 had been given. - * cmode = 15 op = 1 must UNDEF; we assume decode has handled that. - */ - switch (cmode) { - case 0: case 1: - /* no-op */ - break; - case 2: case 3: - imm <<= 8; - break; - case 4: case 5: - imm <<= 16; - break; - case 6: case 7: - imm <<= 24; - break; - case 8: case 9: - imm |= imm << 16; - break; - case 10: case 11: - imm = (imm << 8) | (imm << 24); - break; - case 12: - imm = (imm << 8) | 0xff; - break; - case 13: - imm = (imm << 16) | 0xffff; - break; - case 14: - if (op) { - /* - * This is the only case where the top and bottom 32 bits - * of the encoded constant differ. - */ - uint64_t imm64 = 0; - int n; - - for (n = 0; n < 8; n++) { - if (imm & (1 << n)) { - imm64 |= (0xffULL << (n * 8)); - } - } - return imm64; - } - imm |= (imm << 8) | (imm << 16) | (imm << 24); - break; - case 15: - imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) - | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); - break; - } - if (op) { - imm = ~imm; - } - return dup_const(MO_32, imm); -} - static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a, GVecGen2iFn *fn) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void arm_translate_init(void) a64_translate_init(); } +uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) +{ + /* Expand the encoded constant as per AdvSIMDExpandImm pseudocode */ + switch (cmode) { + case 0: case 1: + /* no-op */ + break; + case 2: case 3: + imm <<= 8; + break; + case 4: case 5: + imm <<= 16; + break; + case 6: case 7: + imm <<= 24; + break; + case 8: case 9: + imm |= imm << 16; + break; + case 10: case 11: + imm = (imm << 8) | (imm << 24); + break; + case 12: + imm = (imm << 8) | 0xff; + break; + case 13: + imm = (imm << 16) | 0xffff; + break; + case 14: + if (op) { + /* + * This is the only case where the top and bottom 32 bits + * of the encoded constant differ. + */ + uint64_t imm64 = 0; + int n; + + for (n = 0; n < 8; n++) { + if (imm & (1 << n)) { + imm64 |= (0xffULL << (n * 8)); + } + } + return imm64; + } + imm |= (imm << 8) | (imm << 16) | (imm << 24); + break; + case 15: + imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) + | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); + break; + } + if (op) { + imm = ~imm; + } + return dup_const(MO_32, imm); +} + /* Generate a label used for skipping this instruction */ void arm_gen_condlabel(DisasContext *s) { -- 2.20.1 The A64 AdvSIMD modified-immediate grouping uses almost the same constant encoding that A32 Neon does; reuse asimd_imm_const() (to which we add the AArch64-specific case for cmode 15 op 1) instead of reimplementing it all. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-5-peter.maydell@linaro.org --- target/arm/translate.h | 3 +- target/arm/translate-a64.c | 86 ++++---------------------------------- target/arm/translate.c | 17 +++++++- 3 files changed, 24 insertions(+), 82 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) * VMVN and VBIC (when cmode < 14 && op == 1). * * The combination cmode == 15 op == 1 is a reserved encoding for AArch32; - * callers must catch this. + * callers must catch this; we return the 64-bit constant value defined + * for AArch64. * * cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 was UNPREDICTABLE in v7A but * is either not unpredictable or merely CONSTRAINED UNPREDICTABLE in v8A; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) { int rd = extract32(insn, 0, 5); int cmode = extract32(insn, 12, 4); - int cmode_3_1 = extract32(cmode, 1, 3); - int cmode_0 = extract32(cmode, 0, 1); int o2 = extract32(insn, 11, 1); uint64_t abcdefgh = extract32(insn, 5, 5) | (extract32(insn, 16, 3) << 5); bool is_neg = extract32(insn, 29, 1); @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) return; } - /* See AdvSIMDExpandImm() in ARM ARM */ - switch (cmode_3_1) { - case 0: /* Replicate(Zeros(24):imm8, 2) */ - case 1: /* Replicate(Zeros(16):imm8:Zeros(8), 2) */ - case 2: /* Replicate(Zeros(8):imm8:Zeros(16), 2) */ - case 3: /* Replicate(imm8:Zeros(24), 2) */ - { - int shift = cmode_3_1 * 8; - imm = bitfield_replicate(abcdefgh << shift, 32); - break; - } - case 4: /* Replicate(Zeros(8):imm8, 4) */ - case 5: /* Replicate(imm8:Zeros(8), 4) */ - { - int shift = (cmode_3_1 & 0x1) * 8; - imm = bitfield_replicate(abcdefgh << shift, 16); - break; - } - case 6: - if (cmode_0) { - /* Replicate(Zeros(8):imm8:Ones(16), 2) */ - imm = (abcdefgh << 16) | 0xffff; - } else { - /* Replicate(Zeros(16):imm8:Ones(8), 2) */ - imm = (abcdefgh << 8) | 0xff; - } - imm = bitfield_replicate(imm, 32); - break; - case 7: - if (!cmode_0 && !is_neg) { - imm = bitfield_replicate(abcdefgh, 8); - } else if (!cmode_0 && is_neg) { - int i; - imm = 0; - for (i = 0; i < 8; i++) { - if ((abcdefgh) & (1 << i)) { - imm |= 0xffULL << (i * 8); - } - } - } else if (cmode_0) { - if (is_neg) { - imm = (abcdefgh & 0x3f) << 48; - if (abcdefgh & 0x80) { - imm |= 0x8000000000000000ULL; - } - if (abcdefgh & 0x40) { - imm |= 0x3fc0000000000000ULL; - } else { - imm |= 0x4000000000000000ULL; - } - } else { - if (o2) { - /* FMOV (vector, immediate) - half-precision */ - imm = vfp_expand_imm(MO_16, abcdefgh); - /* now duplicate across the lanes */ - imm = bitfield_replicate(imm, 16); - } else { - imm = (abcdefgh & 0x3f) << 19; - if (abcdefgh & 0x80) { - imm |= 0x80000000; - } - if (abcdefgh & 0x40) { - imm |= 0x3e000000; - } else { - imm |= 0x40000000; - } - imm |= (imm << 32); - } - } - } - break; - default: - g_assert_not_reached(); - } - - if (cmode_3_1 != 7 && is_neg) { - imm = ~imm; + if (cmode == 15 && o2 && !is_neg) { + /* FMOV (vector, immediate) - half-precision */ + imm = vfp_expand_imm(MO_16, abcdefgh); + /* now duplicate across the lanes */ + imm = bitfield_replicate(imm, 16); + } else { + imm = asimd_imm_const(abcdefgh, cmode, is_neg); } if (!((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9)) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) case 14: if (op) { /* - * This is the only case where the top and bottom 32 bits - * of the encoded constant differ. + * This and cmode == 15 op == 1 are the only cases where + * the top and bottom 32 bits of the encoded constant differ. */ uint64_t imm64 = 0; int n; @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) imm |= (imm << 8) | (imm << 16) | (imm << 24); break; case 15: + if (op) { + /* Reserved encoding for AArch32; valid for AArch64 */ + uint64_t imm64 = (uint64_t)(imm & 0x3f) << 48; + if (imm & 0x80) { + imm64 |= 0x8000000000000000ULL; + } + if (imm & 0x40) { + imm64 |= 0x3fc0000000000000ULL; + } else { + imm64 |= 0x4000000000000000ULL; + } + return imm64; + } imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); break; -- 2.20.1 Use dup_const() instead of bitfield_replicate() in disas_simd_mod_imm(). (We can't replace the other use of bitfield_replicate() in this file, in logic_imm_decode_wmask(), because that location needs to handle 2 and 4 bit elements, which dup_const() cannot.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-6-peter.maydell@linaro.org --- target/arm/translate-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) /* FMOV (vector, immediate) - half-precision */ imm = vfp_expand_imm(MO_16, abcdefgh); /* now duplicate across the lanes */ - imm = bitfield_replicate(imm, 16); + imm = dup_const(MO_16, imm); } else { imm = asimd_imm_const(abcdefgh, cmode, is_neg); } -- 2.20.1 Implement the MVE logical-immediate insns (VMOV, VMVN, VORR and VBIC). These have essentially the same encoding as their Neon equivalents, and we implement the decode in the same way. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-7-peter.maydell@linaro.org --- target/arm/helper-mve.h | 4 +++ target/arm/mve.decode | 17 +++++++++++++ target/arm/mve_helper.c | 24 ++++++++++++++++++ target/arm/translate-mve.c | 50 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 95 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) +DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) +DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ # VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit %size_28 28:1 !function=plus_1 +# 1imm format immediate +%imm_28_16_0 28:1 16:3 0:4 + &vldr_vstr rn qd imm p a w size l u &1op qd qm size &2op qd qm qn size &2scalar qd qn rm size +&1imm qd imm cmode op @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2op_nosz .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn size=0 @2op_sz28 .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn \ size=%size_28 +@1imm .... .... .... .... .... cmode:4 .. op:1 . .... &1imm qd=%qd imm=%imm_28_16_0 # The _rev suffix indicates that Vn and Vm are reversed. This is # the case for shifts. In the Arm ARM these insns are documented @@ -XXX,XX +XXX,XX @@ VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rd # Predicate operations %mask_22_13 22:1 13:3 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 + +# Logical immediate operations (1 reg and modified-immediate) + +# The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but +# not in a way we can conveniently represent in decodetree without +# a lot of repetition: +# VORR: op=0, (cmode & 1) && cmode < 12 +# VBIC: op=1, (cmode & 1) && cmode < 12 +# VMOV: everything else +# So we have a single decode line and check the cmode/op in the +# trans function. +Vimm_1r 111 . 1111 1 . 00 0 ... ... 0 .... 0 1 . 1 .... @1imm diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_1OP(vnegw, 4, int32_t, DO_NEG) DO_1OP(vfnegh, 8, uint64_t, DO_FNEGH) DO_1OP(vfnegs, 8, uint64_t, DO_FNEGS) +/* + * 1 operand immediates: Vda is destination and possibly also one source. + * All these insns work at 64-bit widths. + */ +#define DO_1OP_IMM(OP, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vda, uint64_t imm) \ + { \ + uint64_t *da = vda; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / 8; e++, mask >>= 8) { \ + mergemask(&da[H8(e)], FN(da[H8(e)], imm), mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_MOVI(N, I) (I) +#define DO_ANDI(N, I) ((N) & (I)) +#define DO_ORRI(N, I) ((N) | (I)) + +DO_1OP_IMM(vmovi, DO_MOVI) +DO_1OP_IMM(vandi, DO_ANDI) +DO_1OP_IMM(vorri, DO_ORRI) + #define DO_2OP(OP, ESIZE, TYPE, FN) \ void HELPER(glue(mve_, OP))(CPUARMState *env, \ void *vd, void *vn, void *vm) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VADDV(DisasContext *s, arg_VADDV *a) mve_update_eci(s); return true; } + +static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn) +{ + TCGv_ptr qd; + uint64_t imm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + imm = asimd_imm_const(a->imm, a->cmode, a->op); + + qd = mve_qreg_ptr(a->qd); + fn(cpu_env, qd, tcg_constant_i64(imm)); + tcg_temp_free_ptr(qd); + mve_update_eci(s); + return true; +} + +static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a) +{ + /* Handle decode of cmode/op here between VORR/VBIC/VMOV */ + MVEGenOneOpImmFn *fn; + + if ((a->cmode & 1) && a->cmode < 12) { + if (a->op) { + /* + * For op=1, the immediate will be inverted by asimd_imm_const(), + * so the VBIC becomes a logical AND operation. + */ + fn = gen_helper_mve_vandi; + } else { + fn = gen_helper_mve_vorri; + } + } else { + /* There is one unallocated cmode/op combination in this space */ + if (a->cmode == 15 && a->op == 1) { + return false; + } + /* asimd_imm_const() sorts out VMVNI vs VMOVI for us */ + fn = gen_helper_mve_vmovi; + } + return do_1imm(s, a, fn); +} -- 2.20.1 Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL and VQSHLU. The size-and-immediate encoding here is the same as Neon, and we handle it the same way neon-dp.decode does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-8-peter.maydell@linaro.org --- target/arm/helper-mve.h | 16 +++++++++++ target/arm/mve.decode | 23 +++++++++++++++ target/arm/mve_helper.c | 57 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 51 ++++++++++++++++++++++++++++++++++ 4 files changed, 147 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) + +DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshlui_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshlui_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshlui_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2op qd qm qn size &2scalar qd qn rm size &1imm qd imm cmode op +&2shift qd qm shift size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2scalar .... .... .. size:2 .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn @2scalar_nosz .... .... .... .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn +@2_shl_b .... .... .. 001 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0 +@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 +@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2 + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 # So we have a single decode line and check the cmode/op in the # trans function. Vimm_1r 111 . 1111 1 . 00 0 ... ... 0 .... 0 1 . 1 .... @1imm + +# Shifts by immediate + +VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b +VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h +VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w + +VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b +VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h +VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w + +VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b +VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h +VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w + +VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_b +VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_h +VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_w diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT(vqsubsw, 4, int32_t, DO_SQSUB_W) WRAP_QRSHL_HELPER(do_sqrshl_bhs, N, M, true, satp) #define DO_UQRSHL_OP(N, M, satp) \ WRAP_QRSHL_HELPER(do_uqrshl_bhs, N, M, true, satp) +#define DO_SUQSHL_OP(N, M, satp) \ + WRAP_QRSHL_HELPER(do_suqrshl_bhs, N, M, false, satp) DO_2OP_SAT_S(vqshls, DO_SQSHL_OP) DO_2OP_SAT_U(vqshlu, DO_UQSHL_OP) @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvsw, 4, uint32_t) DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) + +/* Shifts by immediate */ +#define DO_2SHIFT(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + TYPE *d = vd, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], \ + FN(m[H##ESIZE(e)], shift), mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2SHIFT_SAT(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + TYPE *d = vd, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], \ + FN(m[H##ESIZE(e)], shift, &sat), mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +/* provide unsigned 2-op shift helpers for all sizes */ +#define DO_2SHIFT_U(OP, FN) \ + DO_2SHIFT(OP##b, 1, uint8_t, FN) \ + DO_2SHIFT(OP##h, 2, uint16_t, FN) \ + DO_2SHIFT(OP##w, 4, uint32_t, FN) + +#define DO_2SHIFT_SAT_U(OP, FN) \ + DO_2SHIFT_SAT(OP##b, 1, uint8_t, FN) \ + DO_2SHIFT_SAT(OP##h, 2, uint16_t, FN) \ + DO_2SHIFT_SAT(OP##w, 4, uint32_t, FN) +#define DO_2SHIFT_SAT_S(OP, FN) \ + DO_2SHIFT_SAT(OP##b, 1, int8_t, FN) \ + DO_2SHIFT_SAT(OP##h, 2, int16_t, FN) \ + DO_2SHIFT_SAT(OP##w, 4, int32_t, FN) + +DO_2SHIFT_U(vshli_u, DO_VSHLU) +DO_2SHIFT_SAT_U(vqshli_u, DO_UQSHL_OP) +DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) +DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); @@ -XXX,XX +XXX,XX @@ static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a) } return do_1imm(s, a, fn); } + +static bool do_2shift(DisasContext *s, arg_2shift *a, MVEGenTwoOpShiftFn fn, + bool negateshift) +{ + TCGv_ptr qd, qm; + int shift = a->shift; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* + * When we handle a right shift insn using a left-shift helper + * which permits a negative shift count to indicate a right-shift, + * we must negate the shift count. + */ + if (negateshift) { + shift = -shift; + } + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, tcg_constant_i32(shift)); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +#define DO_2SHIFT(INSN, FN, NEGATESHIFT) \ + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_2shift(s, a, fns[a->size], NEGATESHIFT); \ + } + +DO_2SHIFT(VSHLI, vshli_u, false) +DO_2SHIFT(VQSHLI_S, vqshli_s, false) +DO_2SHIFT(VQSHLI_U, vqshli_u, false) +DO_2SHIFT(VQSHLUI, vqshlui_s, false) -- 2.20.1 Implement the MVE vector shift right by immediate insns VSHRI and VRSHRI. As with Neon, we implement these by using helper functions which perform left shifts but allow negative shift counts to indicate right shifts. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-9-peter.maydell@linaro.org --- target/arm/helper-mve.h | 12 ++++++++++++ target/arm/translate.h | 20 ++++++++++++++++++++ target/arm/mve.decode | 28 ++++++++++++++++++++++++++++ target/arm/mve_helper.c | 7 +++++++ target/arm/translate-mve.c | 5 +++++ target/arm/translate-neon.c | 18 ------------------ 6 files changed, 72 insertions(+), 18 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqshlui_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqshlui_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqshlui_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vrshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline int times_2_plus_1(DisasContext *s, int x) return x * 2 + 1; } +static inline int rsub_64(DisasContext *s, int x) +{ + return 64 - x; +} + +static inline int rsub_32(DisasContext *s, int x) +{ + return 32 - x; +} + +static inline int rsub_16(DisasContext *s, int x) +{ + return 16 - x; +} + +static inline int rsub_8(DisasContext *s, int x) +{ + return 8 - x; +} + static inline int arm_dc_feature(DisasContext *dc, int feature) { return (dc->features & (1ULL << feature)) != 0; diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ @2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 @2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2 +# Right shifts are encoded as N - shift, where N is the element size in bits. +%rshift_i5 16:5 !function=rsub_32 +%rshift_i4 16:4 !function=rsub_16 +%rshift_i3 16:3 !function=rsub_8 + +@2_shr_b .... .... .. 001 ... .... .... .... .... &2shift qd=%qd qm=%qm \ + size=0 shift=%rshift_i3 +@2_shr_h .... .... .. 01 .... .... .... .... .... &2shift qd=%qd qm=%qm \ + size=1 shift=%rshift_i4 +@2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ + size=2 shift=%rshift_i5 + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_b VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_h VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_w + +VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b +VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h +VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w + +VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b +VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h +VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w + +VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b +VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h +VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w + +VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b +VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h +VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvuw, 4, uint32_t) DO_2SHIFT(OP##b, 1, uint8_t, FN) \ DO_2SHIFT(OP##h, 2, uint16_t, FN) \ DO_2SHIFT(OP##w, 4, uint32_t, FN) +#define DO_2SHIFT_S(OP, FN) \ + DO_2SHIFT(OP##b, 1, int8_t, FN) \ + DO_2SHIFT(OP##h, 2, int16_t, FN) \ + DO_2SHIFT(OP##w, 4, int32_t, FN) #define DO_2SHIFT_SAT_U(OP, FN) \ DO_2SHIFT_SAT(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvuw, 4, uint32_t) DO_2SHIFT_SAT(OP##w, 4, int32_t, FN) DO_2SHIFT_U(vshli_u, DO_VSHLU) +DO_2SHIFT_S(vshli_s, DO_VSHLS) DO_2SHIFT_SAT_U(vqshli_u, DO_UQSHL_OP) DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) +DO_2SHIFT_U(vrshli_u, DO_VRSHLU) +DO_2SHIFT_S(vrshli_s, DO_VRSHLS) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHLI, vshli_u, false) DO_2SHIFT(VQSHLI_S, vqshli_s, false) DO_2SHIFT(VQSHLI_U, vqshli_u, false) DO_2SHIFT(VQSHLUI, vqshlui_s, false) +/* These right shifts use a left-shift helper with negated shift count */ +DO_2SHIFT(VSHRI_S, vshli_s, true) +DO_2SHIFT(VSHRI_U, vshli_u, true) +DO_2SHIFT(VRSHRI_S, vrshli_s, true) +DO_2SHIFT(VRSHRI_U, vrshli_u, true) diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ static inline int plus1(DisasContext *s, int x) return x + 1; } -static inline int rsub_64(DisasContext *s, int x) -{ - return 64 - x; -} - -static inline int rsub_32(DisasContext *s, int x) -{ - return 32 - x; -} -static inline int rsub_16(DisasContext *s, int x) -{ - return 16 - x; -} -static inline int rsub_8(DisasContext *s, int x) -{ - return 8 - x; -} - static inline int neon_3same_fp_size(DisasContext *s, int x) { /* Convert 0==fp32, 1==fp16 into a MO_* value */ -- 2.20.1 Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org --- target/arm/helper-mve.h | 9 +++++++ target/arm/mve.decode | 53 +++++++++++++++++++++++++++++++++++--- target/arm/mve_helper.c | 32 +++++++++++++++++++++++ target/arm/translate-mve.c | 15 +++++++++++ 4 files changed, 105 insertions(+), 4 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshllbuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ @2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 @2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2 +@2_shll_b .... .... ... 01 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0 +@2_shll_h .... .... ... 1 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 +# VSHLL encoding T2 where shift == esize +@2_shll_esize_b .... .... .... 00 .. .... .... .... .... &2shift \ + qd=%qd qm=%qm size=0 shift=8 +@2_shll_esize_h .... .... .... 01 .. .... .... .... .... &2shift \ + qd=%qd qm=%qm size=1 shift=16 + # Right shifts are encoded as N - shift, where N is the element size in bits. %rshift_i5 16:5 !function=rsub_32 %rshift_i4 16:4 !function=rsub_16 @@ -XXX,XX +XXX,XX @@ VADD 1110 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op VSUB 1111 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op -VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op -VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op +# The VSHLL T2 encoding is not a @2op pattern, but is here because it +# overlaps what would be size=0b11 VMULH/VRMULH +{ + VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b + VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h -VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op -VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op +} + +{ + VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b + VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + + VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op +} + +{ + VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b + VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op +} + +{ + VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b + VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + + VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op +} VMAX_S 111 0 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op VMAX_U 111 1 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op @@ -XXX,XX +XXX,XX @@ VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w + +# VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file +VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b +VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h + +VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b +VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h + +VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b +VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h + +VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b +VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) DO_2SHIFT_U(vrshli_u, DO_VRSHLU) DO_2SHIFT_S(vrshli_s, DO_VRSHLS) + +/* + * Long shifts taking half-sized inputs from top or bottom of the input + * vector and producing a double-width result. ESIZE, TYPE are for + * the input, and LESIZE, LTYPE for the output. + * Unlike the normal shift helpers, we do not handle negative shift counts, + * because the long shift is strictly left-only. + */ +#define DO_VSHLL(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + LTYPE *d = vd; \ + TYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned le; \ + assert(shift <= 16); \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + LTYPE r = (LTYPE)m[H##ESIZE(le * 2 + TOP)] << shift; \ + mergemask(&d[H##LESIZE(le)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSHLL_ALL(OP, TOP) \ + DO_VSHLL(OP##sb, TOP, 1, int8_t, 2, int16_t) \ + DO_VSHLL(OP##ub, TOP, 1, uint8_t, 2, uint16_t) \ + DO_VSHLL(OP##sh, TOP, 2, int16_t, 4, int32_t) \ + DO_VSHLL(OP##uh, TOP, 2, uint16_t, 4, uint32_t) \ + +DO_VSHLL_ALL(vshllb, false) +DO_VSHLL_ALL(vshllt, true) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHRI_S, vshli_s, true) DO_2SHIFT(VSHRI_U, vshli_u, true) DO_2SHIFT(VRSHRI_S, vrshli_s, true) DO_2SHIFT(VRSHRI_U, vrshli_u, true) + +#define DO_VSHLL(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + }; \ + return do_2shift(s, a, fns[a->size], false); \ + } + +DO_VSHLL(VSHLL_BS, vshllbs) +DO_VSHLL(VSHLL_BU, vshllbu) +DO_VSHLL(VSHLL_TS, vshllts) +DO_VSHLL(VSHLL_TU, vshlltu) -- 2.20.1 Implement the MVE VSRI and VSLI insns, which perform a shift-and-insert operation. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-11-peter.maydell@linaro.org --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 9 ++++++++ target/arm/mve_helper.c | 42 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 3 +++ 4 files changed, 62 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vsrib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vsrih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h + +# Shift-and-insert +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_b +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_h +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w + +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) DO_2SHIFT_U(vrshli_u, DO_VRSHLU) DO_2SHIFT_S(vrshli_s, DO_VRSHLS) +/* Shift-and-insert; we always work with 64 bits at a time */ +#define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + uint64_t *d = vd, *m = vm; \ + uint16_t mask; \ + uint64_t shiftmask; \ + unsigned e; \ + if (shift == 0 || shift == ESIZE * 8) { \ + /* \ + * Only VSLI can shift by 0; only VSRI can shift by <dt>. \ + * The generic logic would give the right answer for 0 but \ + * fails for <dt>. \ + */ \ + goto done; \ + } \ + assert(shift < ESIZE * 8); \ + mask = mve_element_mask(env); \ + /* ESIZE / 2 gives the MO_* value if ESIZE is in [1,2,4] */ \ + shiftmask = dup_const(ESIZE / 2, MASKFN(ESIZE * 8, shift)); \ + for (e = 0; e < 16 / 8; e++, mask >>= 8) { \ + uint64_t r = (SHIFTFN(m[H8(e)], shift) & shiftmask) | \ + (d[H8(e)] & ~shiftmask); \ + mergemask(&d[H8(e)], r, mask); \ + } \ +done: \ + mve_advance_vpt(env); \ + } + +#define DO_SHL(N, SHIFT) ((N) << (SHIFT)) +#define DO_SHR(N, SHIFT) ((N) >> (SHIFT)) +#define SHL_MASK(EBITS, SHIFT) MAKE_64BIT_MASK((SHIFT), (EBITS) - (SHIFT)) +#define SHR_MASK(EBITS, SHIFT) MAKE_64BIT_MASK(0, (EBITS) - (SHIFT)) + +DO_2SHIFT_INSERT(vsrib, 1, DO_SHR, SHR_MASK) +DO_2SHIFT_INSERT(vsrih, 2, DO_SHR, SHR_MASK) +DO_2SHIFT_INSERT(vsriw, 4, DO_SHR, SHR_MASK) +DO_2SHIFT_INSERT(vslib, 1, DO_SHL, SHL_MASK) +DO_2SHIFT_INSERT(vslih, 2, DO_SHL, SHL_MASK) +DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK) + /* * Long shifts taking half-sized inputs from top or bottom of the input * vector and producing a double-width result. ESIZE, TYPE are for diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHRI_U, vshli_u, true) DO_2SHIFT(VRSHRI_S, vrshli_s, true) DO_2SHIFT(VRSHRI_U, vrshli_u, true) +DO_2SHIFT(VSRI, vsri, false) +DO_2SHIFT(VSLI, vsli, false) + #define DO_VSHLL(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ { \ -- 2.20.1 Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN. do_urshr() is borrowed from sve_helper.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-12-peter.maydell@linaro.org --- target/arm/helper-mve.h | 10 ++++++++++ target/arm/mve.decode | 11 +++++++++++ target/arm/mve_helper.c | 40 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 15 ++++++++++++++ 4 files changed, 76 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w + +# Narrowing shifts (which only support b and h sizes) +VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b +VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h +VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b +VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h + +VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b +VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h +VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b +VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK) DO_VSHLL_ALL(vshllb, false) DO_VSHLL_ALL(vshllt, true) + +/* + * Narrowing right shifts, taking a double sized input, shifting it + * and putting the result in either the top or bottom half of the output. + * ESIZE, TYPE are the output, and LESIZE, LTYPE the input. + */ +#define DO_VSHRN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned le; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + TYPE r = FN(m[H##LESIZE(le)], shift); \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSHRN_ALL(OP, FN) \ + DO_VSHRN(OP##bb, false, 1, uint8_t, 2, uint16_t, FN) \ + DO_VSHRN(OP##bh, false, 2, uint16_t, 4, uint32_t, FN) \ + 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; + } +} + +DO_VSHRN_ALL(vshrn, DO_SHR) +DO_VSHRN_ALL(vrshrn, do_urshr) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VSHLL(VSHLL_BS, vshllbs) DO_VSHLL(VSHLL_BU, vshllbu) DO_VSHLL(VSHLL_TS, vshllts) DO_VSHLL(VSHLL_TU, vshlltu) + +#define DO_2SHIFT_N(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + }; \ + return do_2shift(s, a, fns[a->size], false); \ + } + +DO_2SHIFT_N(VSHRNB, vshrnb) +DO_2SHIFT_N(VSHRNT, vshrnt) +DO_2SHIFT_N(VRSHRNB, vrshrnb) +DO_2SHIFT_N(VRSHRNT, vrshrnt) -- 2.20.1 Implement the MVE saturating shift-right-and-narrow insns VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN. do_srshr() is borrowed from sve_helper.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-13-peter.maydell@linaro.org --- target/arm/helper-mve.h | 30 +++++++++++ target/arm/mve.decode | 28 ++++++++++ target/arm/mve_helper.c | 104 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 12 +++++ 4 files changed, 174 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h + +VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b +VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h +VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b +VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h +VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b +VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h +VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b +VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h + +VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b +VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h +VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b +VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h + +VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b +VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h +VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b +VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h +VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b +VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h +VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b +VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h + +VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b +VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h +VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b +VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t do_urshr(uint64_t x, unsigned sh) } } +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) + +static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max, + bool *satp) +{ + if (val > max) { + *satp = true; + return max; + } else if (val < min) { + *satp = true; + return min; + } else { + return val; + } +} + +/* Saturating narrowing right shifts */ +#define DO_VSHRN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + bool qc = false; \ + unsigned le; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + bool sat = false; \ + TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ + qc |= sat && (mask & 1 << (TOP * ESIZE)); \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSHRN_SAT_UB(BOP, TOP, FN) \ + DO_VSHRN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \ + DO_VSHRN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN) + +#define DO_VSHRN_SAT_UH(BOP, TOP, FN) \ + DO_VSHRN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \ + DO_VSHRN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN) + +#define DO_VSHRN_SAT_SB(BOP, TOP, FN) \ + DO_VSHRN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \ + DO_VSHRN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN) + +#define DO_VSHRN_SAT_SH(BOP, TOP, FN) \ + DO_VSHRN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \ + DO_VSHRN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN) + +#define DO_SHRN_SB(N, M, SATP) \ + do_sat_bhs((int64_t)(N) >> (M), INT8_MIN, INT8_MAX, SATP) +#define DO_SHRN_UB(N, M, SATP) \ + do_sat_bhs((uint64_t)(N) >> (M), 0, UINT8_MAX, SATP) +#define DO_SHRUN_B(N, M, SATP) \ + do_sat_bhs((int64_t)(N) >> (M), 0, UINT8_MAX, SATP) + +#define DO_SHRN_SH(N, M, SATP) \ + do_sat_bhs((int64_t)(N) >> (M), INT16_MIN, INT16_MAX, SATP) +#define DO_SHRN_UH(N, M, SATP) \ + do_sat_bhs((uint64_t)(N) >> (M), 0, UINT16_MAX, SATP) +#define DO_SHRUN_H(N, M, SATP) \ + do_sat_bhs((int64_t)(N) >> (M), 0, UINT16_MAX, SATP) + +#define DO_RSHRN_SB(N, M, SATP) \ + do_sat_bhs(do_srshr(N, M), INT8_MIN, INT8_MAX, SATP) +#define DO_RSHRN_UB(N, M, SATP) \ + do_sat_bhs(do_urshr(N, M), 0, UINT8_MAX, SATP) +#define DO_RSHRUN_B(N, M, SATP) \ + do_sat_bhs(do_srshr(N, M), 0, UINT8_MAX, SATP) + +#define DO_RSHRN_SH(N, M, SATP) \ + do_sat_bhs(do_srshr(N, M), INT16_MIN, INT16_MAX, SATP) +#define DO_RSHRN_UH(N, M, SATP) \ + do_sat_bhs(do_urshr(N, M), 0, UINT16_MAX, SATP) +#define DO_RSHRUN_H(N, M, SATP) \ + do_sat_bhs(do_srshr(N, M), 0, UINT16_MAX, SATP) + +DO_VSHRN_SAT_SB(vqshrnb_sb, vqshrnt_sb, DO_SHRN_SB) +DO_VSHRN_SAT_SH(vqshrnb_sh, vqshrnt_sh, DO_SHRN_SH) +DO_VSHRN_SAT_UB(vqshrnb_ub, vqshrnt_ub, DO_SHRN_UB) +DO_VSHRN_SAT_UH(vqshrnb_uh, vqshrnt_uh, DO_SHRN_UH) +DO_VSHRN_SAT_SB(vqshrunbb, vqshruntb, DO_SHRUN_B) +DO_VSHRN_SAT_SH(vqshrunbh, vqshrunth, DO_SHRUN_H) + +DO_VSHRN_SAT_SB(vqrshrnb_sb, vqrshrnt_sb, DO_RSHRN_SB) +DO_VSHRN_SAT_SH(vqrshrnb_sh, vqrshrnt_sh, DO_RSHRN_SH) +DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB) +DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) +DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) +DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_N(VSHRNB, vshrnb) DO_2SHIFT_N(VSHRNT, vshrnt) DO_2SHIFT_N(VRSHRNB, vrshrnb) DO_2SHIFT_N(VRSHRNT, vrshrnt) +DO_2SHIFT_N(VQSHRNB_S, vqshrnb_s) +DO_2SHIFT_N(VQSHRNT_S, vqshrnt_s) +DO_2SHIFT_N(VQSHRNB_U, vqshrnb_u) +DO_2SHIFT_N(VQSHRNT_U, vqshrnt_u) +DO_2SHIFT_N(VQSHRUNB, vqshrunb) +DO_2SHIFT_N(VQSHRUNT, vqshrunt) +DO_2SHIFT_N(VQRSHRNB_S, vqrshrnb_s) +DO_2SHIFT_N(VQRSHRNT_S, vqrshrnt_s) +DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u) +DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u) +DO_2SHIFT_N(VQRSHRUNB, vqrshrunb) +DO_2SHIFT_N(VQRSHRUNT, vqrshrunt) -- 2.20.1 Implement the MVE VSHLC insn, which performs a shift left of the entire vector with carry in bits provided from a general purpose register and carry out bits written back to that register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-14-peter.maydell@linaro.org --- target/arm/helper-mve.h | 2 ++ target/arm/mve.decode | 2 ++ target/arm/mve_helper.c | 38 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 30 ++++++++++++++++++++++++++++++ 4 files changed, 72 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h + +VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB) DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) + +uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, + uint32_t shift) +{ + uint32_t *d = vd; + uint16_t mask = mve_element_mask(env); + unsigned e; + uint32_t r; + + /* + * For each 32-bit element, we shift it left, bringing in the + * low 'shift' bits of rdm at the bottom. Bits shifted out at + * the top become the new rdm, if the predicate mask permits. + * The final rdm value is returned to update the register. + * shift == 0 here means "shift by 32 bits". + */ + if (shift == 0) { + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + r = rdm; + if (mask & 1) { + rdm = d[H4(e)]; + } + mergemask(&d[H4(e)], r, mask); + } + } else { + uint32_t shiftmask = MAKE_64BIT_MASK(0, shift); + + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + r = (d[H4(e)] << shift) | (rdm & shiftmask); + if (mask & 1) { + rdm = d[H4(e)] >> (32 - shift); + } + mergemask(&d[H4(e)], r, mask); + } + } + mve_advance_vpt(env); + return rdm; +} diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u) DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u) DO_2SHIFT_N(VQRSHRUNB, vqrshrunb) DO_2SHIFT_N(VQRSHRUNT, vqrshrunt) + +static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a) +{ + /* + * Whole Vector Left Shift with Carry. The carry is taken + * from a general purpose register and written back there. + * An imm of 0 means "shift by 32". + */ + TCGv_ptr qd; + TCGv_i32 rdm; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (a->rdm == 13 || a->rdm == 15) { + /* CONSTRAINED UNPREDICTABLE: we UNDEF */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rdm = load_reg(s, a->rdm); + gen_helper_mve_vshlc(rdm, cpu_env, qd, rdm, tcg_constant_i32(a->imm)); + store_reg(s, a->rdm, rdm); + tcg_temp_free_ptr(qd); + mve_update_eci(s); + return true; +} -- 2.20.1 Implement the MVE VADDLV insn; this is similar to VADDV, except that it accumulates 32-bit elements into a 64-bit accumulator stored in a pair of general-purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-15-peter.maydell@linaro.org --- target/arm/helper-mve.h | 3 ++ target/arm/mve.decode | 6 +++- target/arm/mve_helper.c | 19 ++++++++++++ target/arm/translate-mve.c | 63 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 90 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) +DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) + DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar # Vector add across vector -VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo +{ + VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo + VADDLV 111 u:1 1110 1 ... 1001 ... 0 1111 00 a:1 0 qm:3 0 \ + rdahi=%rdahi rdalo=%rdalo +} # Predicate operations %mask_22_13 22:1 13:3 diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) +#define DO_VADDLV(OP, TYPE, LTYPE) \ + uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ + uint64_t ra) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + if (mask & 1) { \ + ra += (LTYPE)m[H4(e)]; \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } \ + +DO_VADDLV(vaddlv_s, int32_t, int64_t) +DO_VADDLV(vaddlv_u, uint32_t, uint64_t) + /* Shifts by immediate */ #define DO_2SHIFT(OP, ESIZE, TYPE, FN) \ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VADDV(DisasContext *s, arg_VADDV *a) return true; } +static bool trans_VADDLV(DisasContext *s, arg_VADDLV *a) +{ + /* + * Vector Add Long Across Vector: accumulate the 32-bit + * elements of the vector into a 64-bit result stored in + * a pair of general-purpose registers. + * No need to check Qm's bank: it is only 3 bits in decode. + */ + TCGv_ptr qm; + TCGv_i64 rda; + TCGv_i32 rdalo, rdahi; + + if (!dc_isar_feature(aa32_mve, s)) { + return false; + } + /* + * rdahi == 13 is UNPREDICTABLE; rdahi == 15 is a related + * encoding; rdalo always has bit 0 clear so cannot be 13 or 15. + */ + if (a->rdahi == 13 || a->rdahi == 15) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* + * This insn is subject to beat-wise execution. Partial execution + * of an A=0 (no-accumulate) insn which does not execute the first + * beat must start with the current value of RdaHi:RdaLo, not zero. + */ + if (a->a || mve_skip_first_beat(s)) { + /* Accumulate input from RdaHi:RdaLo */ + rda = tcg_temp_new_i64(); + rdalo = load_reg(s, a->rdalo); + rdahi = load_reg(s, a->rdahi); + tcg_gen_concat_i32_i64(rda, rdalo, rdahi); + tcg_temp_free_i32(rdalo); + tcg_temp_free_i32(rdahi); + } else { + /* Accumulate starting at zero */ + rda = tcg_const_i64(0); + } + + qm = mve_qreg_ptr(a->qm); + if (a->u) { + gen_helper_mve_vaddlv_u(rda, cpu_env, qm, rda); + } else { + gen_helper_mve_vaddlv_s(rda, cpu_env, qm, rda); + } + tcg_temp_free_ptr(qm); + + rdalo = tcg_temp_new_i32(); + rdahi = tcg_temp_new_i32(); + tcg_gen_extrl_i64_i32(rdalo, rda); + tcg_gen_extrh_i64_i32(rdahi, rda); + store_reg(s, a->rdalo, rdalo); + store_reg(s, a->rdahi, rdahi); + tcg_temp_free_i64(rda); + mve_update_eci(s); + return true; +} + static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn) { TCGv_ptr qd; -- 2.20.1 The MVE extension to v8.1M includes some new shift instructions which sit entirely within the non-coprocessor part of the encoding space and which operate only on general-purpose registers. They take up the space which was previously UNPREDICTABLE MOVS and ORRS encodings with Rm == 13 or 15. Implement the long shifts by immediate, which perform shifts on a pair of general-purpose registers treated as a 64-bit quantity, with an immediate shift count between 1 and 32. Awkwardly, because the MOVS and ORRS trans functions do not UNDEF for the Rm==13,15 case, we need to explicitly emit code to UNDEF for the cases where v8.1M now requires that. (Trying to change MOVS and ORRS is too difficult, because the functions that generate the code are shared between a dozen different kinds of arithmetic or logical instruction for all A32, T16 and T32 encodings, and for some insns and some encodings Rm==13,15 are valid.) We make the helper functions we need for UQSHLL and SQSHLL take a 32-bit value which the helper casts to int8_t because we'll need these helpers also for the shift-by-register insns, where the shift count might be < 0 or > 32. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-16-peter.maydell@linaro.org --- target/arm/helper-mve.h | 3 ++ target/arm/translate.h | 1 + target/arm/t32.decode | 28 +++++++++++++ target/arm/mve_helper.c | 10 +++++ target/arm/translate.c | 90 +++++++++++++++++++++++++++++++++++++++++ 5 files changed, 132 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) + +DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr); typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); +typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); /** * arm_tbflags_from_tb: diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ &mcr !extern cp opc1 crn crm opc2 rt &mcrr !extern cp opc1 crm rt rt2 +&mve_shl_ri rdalo rdahi shim + +# rdahi: bits [3:1] from insn, bit 0 is 1 +# rdalo: bits [3:1] from insn, bit 0 is 0 +%rdahi_9 9:3 !function=times_2_plus_1 +%rdalo_17 17:3 !function=times_2 + # Data-processing (register) %imm5_12_6 12:3 6:2 @@ -XXX,XX +XXX,XX @@ @S_xrr_shi ....... .... . rn:4 .... .... .. shty:2 rm:4 \ &s_rrr_shi shim=%imm5_12_6 s=1 rd=0 +@mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \ + &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 + { TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi AND_rrri 1110101 0000 . .... 0 ... .... .... .... @s_rrr_shi } BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi { + # The v8.1M MVE shift insns overlap in encoding with MOVS/ORRS + # and are distinguished by having Rm==13 or 15. Those are UNPREDICTABLE + # cases for MOVS/ORRS. We decode the MVE cases first, ensuring that + # they explicitly call unallocated_encoding() for cases that must UNDEF + # (eg "using a new shift insn on a v8.1M CPU without MVE"), and letting + # the rest fall through (where ORR_rrri and MOV_rxri will end up + # handling them as r13 and r15 accesses with the same semantics as A32). + [ + LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri + LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri + ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri + + UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri + URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri + SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri + SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri + ] + MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, mve_advance_vpt(env); return rdm; } + +uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_sqrshl_d(n, (int8_t)shift, false, &env->QF); +} + +uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_uqrshl_d(n, (int8_t)shift, false, &env->QF); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_MOVT(DisasContext *s, arg_MOVW *a) return true; } +/* + * v8.1M MVE wide-shifts + */ +static bool do_mve_shl_ri(DisasContext *s, arg_mve_shl_ri *a, + WideShiftImmFn *fn) +{ + TCGv_i64 rda; + TCGv_i32 rdalo, rdahi; + + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ + return false; + } + if (a->rdahi == 15) { + /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */ + return false; + } + if (!dc_isar_feature(aa32_mve, s) || + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || + a->rdahi == 13) { + /* RdaHi == 13 is UNPREDICTABLE; we choose to UNDEF */ + unallocated_encoding(s); + return true; + } + + if (a->shim == 0) { + a->shim = 32; + } + + rda = tcg_temp_new_i64(); + rdalo = load_reg(s, a->rdalo); + rdahi = load_reg(s, a->rdahi); + tcg_gen_concat_i32_i64(rda, rdalo, rdahi); + + fn(rda, rda, a->shim); + + tcg_gen_extrl_i64_i32(rdalo, rda); + tcg_gen_extrh_i64_i32(rdahi, rda); + store_reg(s, a->rdalo, rdalo); + store_reg(s, a->rdahi, rdahi); + tcg_temp_free_i64(rda); + + return true; +} + +static bool trans_ASRL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, tcg_gen_sari_i64); +} + +static bool trans_LSLL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, tcg_gen_shli_i64); +} + +static bool trans_LSRL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, tcg_gen_shri_i64); +} + +static void gen_mve_sqshll(TCGv_i64 r, TCGv_i64 n, int64_t shift) +{ + gen_helper_mve_sqshll(r, cpu_env, n, tcg_constant_i32(shift)); +} + +static bool trans_SQSHLL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, gen_mve_sqshll); +} + +static void gen_mve_uqshll(TCGv_i64 r, TCGv_i64 n, int64_t shift) +{ + gen_helper_mve_uqshll(r, cpu_env, n, tcg_constant_i32(shift)); +} + +static bool trans_UQSHLL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, gen_mve_uqshll); +} + +static bool trans_SRSHRL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, gen_srshr64_i64); +} + +static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, gen_urshr64_i64); +} + /* * Multiply and multiply accumulate */ -- 2.20.1 Implement the MVE long shifts by register, which perform shifts on a pair of general-purpose registers treated as a 64-bit quantity, with the shift count in another general-purpose register, which might be either positive or negative. Like the long-shifts-by-immediate, these encodings sit in the space that was previously the UNPREDICTABLE MOVS/ORRS with Rm==13,15. Because LSLL_rr and ASRL_rr overlap with both MOV_rxri/ORR_rrri and also with CSEL (as one of the previously-UNPREDICTABLE Rm==13 cases), we have to move the CSEL pattern into the same decodetree group. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-17-peter.maydell@linaro.org --- target/arm/helper-mve.h | 6 +++ target/arm/translate.h | 1 + target/arm/t32.decode | 16 +++++-- target/arm/mve_helper.c | 93 +++++++++++++++++++++++++++++++++++++++++ target/arm/translate.c | 69 ++++++++++++++++++++++++++++++ 5 files changed, 182 insertions(+), 3 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_3(mve_sshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_ushll, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); +typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); /** * arm_tbflags_from_tb: diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ &mcrr !extern cp opc1 crm rt rt2 &mve_shl_ri rdalo rdahi shim +&mve_shl_rr rdalo rdahi rm # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 @@ -XXX,XX +XXX,XX @@ @mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \ &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 +@mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ + &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 { TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri + + LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr + ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr + UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr + SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr + UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr + SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr ] MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi + + # v8.1M CSEL and friends + CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4 } { MVN_rxri 1110101 0011 . 1111 0 ... .... .... .... @s_rxr_shi @@ -XXX,XX +XXX,XX @@ SBC_rrri 1110101 1011 . .... 0 ... .... .... .... @s_rrr_shi } RSB_rrri 1110101 1110 . .... 0 ... .... .... .... @s_rrr_shi -# v8.1M CSEL and friends -CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4 - # Data-processing (register-shifted register) MOV_rxrr 1111 1010 0 shty:2 s:1 rm:4 1111 rd:4 0000 rs:4 \ diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, return rdm; } +uint64_t HELPER(mve_sshrl)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_sqrshl_d(n, -(int8_t)shift, false, NULL); +} + +uint64_t HELPER(mve_ushll)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_uqrshl_d(n, (int8_t)shift, false, NULL); +} + uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift) { return do_sqrshl_d(n, (int8_t)shift, false, &env->QF); @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift) { return do_uqrshl_d(n, (int8_t)shift, false, &env->QF); } + +uint64_t HELPER(mve_sqrshrl)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_sqrshl_d(n, -(int8_t)shift, true, &env->QF); +} + +uint64_t HELPER(mve_uqrshll)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_uqrshl_d(n, (int8_t)shift, true, &env->QF); +} + +/* Operate on 64-bit values, but saturate at 48 bits */ +static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + if (shift <= -48) { + /* Rounding the sign bit always produces 0. */ + if (round) { + return 0; + } + return src >> 63; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < 48) { + int64_t val = src << shift; + int64_t extval = sextract64(val, 0, 48); + if (!sat || val == extval) { + return extval; + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return (1ULL << 47) - (src >= 0); +} + +/* Operate on 64-bit values, but saturate at 48 bits */ +static inline uint64_t do_uqrshl48_d(uint64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + uint64_t val, extval; + + if (shift <= -(48 + round)) { + return 0; + } else if (shift < 0) { + if (round) { + val = src >> (-shift - 1); + val = (val >> 1) + (val & 1); + } else { + val = src >> -shift; + } + extval = extract64(val, 0, 48); + if (!sat || val == extval) { + return extval; + } + } else if (shift < 48) { + uint64_t val = src << shift; + uint64_t extval = extract64(val, 0, 48); + if (!sat || val == extval) { + return extval; + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return MAKE_64BIT_MASK(0, 48); +} + +uint64_t HELPER(mve_sqrshrl48)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_sqrshl48_d(n, -(int8_t)shift, true, &env->QF); +} + +uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a) return do_mve_shl_ri(s, a, gen_urshr64_i64); } +static bool do_mve_shl_rr(DisasContext *s, arg_mve_shl_rr *a, WideShiftFn *fn) +{ + TCGv_i64 rda; + TCGv_i32 rdalo, rdahi; + + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ + return false; + } + if (a->rdahi == 15) { + /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */ + return false; + } + if (!dc_isar_feature(aa32_mve, s) || + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || + a->rdahi == 13 || a->rm == 13 || a->rm == 15 || + a->rm == a->rdahi || a->rm == a->rdalo) { + /* These rdahi/rdalo/rm cases are UNPREDICTABLE; we choose to UNDEF */ + unallocated_encoding(s); + return true; + } + + rda = tcg_temp_new_i64(); + rdalo = load_reg(s, a->rdalo); + rdahi = load_reg(s, a->rdahi); + tcg_gen_concat_i32_i64(rda, rdalo, rdahi); + + /* The helper takes care of the sign-extension of the low 8 bits of Rm */ + fn(rda, cpu_env, rda, cpu_R[a->rm]); + + tcg_gen_extrl_i64_i32(rdalo, rda); + tcg_gen_extrh_i64_i32(rdahi, rda); + store_reg(s, a->rdalo, rdalo); + store_reg(s, a->rdahi, rdahi); + tcg_temp_free_i64(rda); + + return true; +} + +static bool trans_LSLL_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_ushll); +} + +static bool trans_ASRL_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_sshrl); +} + +static bool trans_UQRSHLL64_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_uqrshll); +} + +static bool trans_SQRSHRL64_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl); +} + +static bool trans_UQRSHLL48_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_uqrshll48); +} + +static bool trans_SQRSHRL48_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl48); +} + /* * Multiply and multiply accumulate */ -- 2.20.1 Implement the MVE shifts by immediate, which perform shifts on a single general-purpose register. These patterns overlap with the long-shift-by-immediates, so we have to rearrange the grouping a little here. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-18-peter.maydell@linaro.org --- target/arm/helper-mve.h | 3 ++ target/arm/translate.h | 1 + target/arm/t32.decode | 31 ++++++++++++++----- target/arm/mve_helper.c | 10 ++++++ target/arm/translate.c | 68 +++++++++++++++++++++++++++++++++++++++-- 5 files changed, 104 insertions(+), 9 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) + +DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); +typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift); /** * arm_tbflags_from_tb: diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ &mve_shl_ri rdalo rdahi shim &mve_shl_rr rdalo rdahi rm +&mve_sh_ri rda shim # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 @@ -XXX,XX +XXX,XX @@ &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 @mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 +@mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \ + &mve_sh_ri shim=%imm5_12_6 { TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi # the rest fall through (where ORR_rrri and MOV_rxri will end up # handling them as r13 and r15 accesses with the same semantics as A32). [ - LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri - LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri - ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri + { + UQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 00 1111 @mve_sh_ri + LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri + UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri + } - UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri - URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri - SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri - SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri + { + URSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 01 1111 @mve_sh_ri + LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri + URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri + } + + { + SRSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 10 1111 @mve_sh_ri + ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri + SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri + } + + { + SQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 11 1111 @mve_sh_ri + SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri + } LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift) { return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF); } + +uint32_t HELPER(mve_uqshl)(CPUARMState *env, uint32_t n, uint32_t shift) +{ + return do_uqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); +} + +uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift) +{ + return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) { - TCGv_i32 t = tcg_temp_new_i32(); + TCGv_i32 t; + /* Handle shift by the input size for the benefit of trans_SRSHR_ri */ + if (sh == 32) { + tcg_gen_movi_i32(d, 0); + return; + } + t = tcg_temp_new_i32(); tcg_gen_extract_i32(t, a, sh - 1, 1); tcg_gen_sari_i32(d, a, sh); tcg_gen_add_i32(d, d, t); @@ -XXX,XX +XXX,XX @@ static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) { - TCGv_i32 t = tcg_temp_new_i32(); + TCGv_i32 t; + /* Handle shift by the input size for the benefit of trans_URSHR_ri */ + if (sh == 32) { + tcg_gen_extract_i32(d, a, sh - 1, 1); + return; + } + t = tcg_temp_new_i32(); tcg_gen_extract_i32(t, a, sh - 1, 1); tcg_gen_shri_i32(d, a, sh); tcg_gen_add_i32(d, d, t); @@ -XXX,XX +XXX,XX @@ static bool trans_SQRSHRL48_rr(DisasContext *s, arg_mve_shl_rr *a) return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl48); } +static bool do_mve_sh_ri(DisasContext *s, arg_mve_sh_ri *a, ShiftImmFn *fn) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ + return false; + } + if (!dc_isar_feature(aa32_mve, s) || + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || + a->rda == 13 || a->rda == 15) { + /* These rda cases are UNPREDICTABLE; we choose to UNDEF */ + unallocated_encoding(s); + return true; + } + + if (a->shim == 0) { + a->shim = 32; + } + fn(cpu_R[a->rda], cpu_R[a->rda], a->shim); + + return true; +} + +static bool trans_URSHR_ri(DisasContext *s, arg_mve_sh_ri *a) +{ + return do_mve_sh_ri(s, a, gen_urshr32_i32); +} + +static bool trans_SRSHR_ri(DisasContext *s, arg_mve_sh_ri *a) +{ + return do_mve_sh_ri(s, a, gen_srshr32_i32); +} + +static void gen_mve_sqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift) +{ + gen_helper_mve_sqshl(r, cpu_env, n, tcg_constant_i32(shift)); +} + +static bool trans_SQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) +{ + return do_mve_sh_ri(s, a, gen_mve_sqshl); +} + +static void gen_mve_uqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift) +{ + gen_helper_mve_uqshl(r, cpu_env, n, tcg_constant_i32(shift)); +} + +static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) +{ + return do_mve_sh_ri(s, a, gen_mve_uqshl); +} + /* * Multiply and multiply accumulate */ -- 2.20.1 Implement the MVE shifts by register, which perform shifts on a single general-purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-19-peter.maydell@linaro.org --- target/arm/helper-mve.h | 2 ++ target/arm/translate.h | 1 + target/arm/t32.decode | 18 ++++++++++++++---- target/arm/mve_helper.c | 10 ++++++++++ target/arm/translate.c | 30 ++++++++++++++++++++++++++++++ 5 files changed, 57 insertions(+), 4 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift); +typedef void ShiftFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); /** * arm_tbflags_from_tb: diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ &mve_shl_ri rdalo rdahi shim &mve_shl_rr rdalo rdahi rm &mve_sh_ri rda shim +&mve_sh_rr rda rm # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 @@ -XXX,XX +XXX,XX @@ &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 @mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \ &mve_sh_ri shim=%imm5_12_6 +@mve_sh_rr ....... .... . rda:4 rm:4 .... .... .... &mve_sh_rr { TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri } - LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr - ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr - UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr - SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr + { + UQRSHL_rr 1110101 0010 1 .... .... 1111 0000 1101 @mve_sh_rr + LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr + UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr + } + + { + SQRSHR_rr 1110101 0010 1 .... .... 1111 0010 1101 @mve_sh_rr + ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr + SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr + } + UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr ] diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift) { return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); } + +uint32_t HELPER(mve_uqrshl)(CPUARMState *env, uint32_t n, uint32_t shift) +{ + return do_uqrshl_bhs(n, (int8_t)shift, 32, true, &env->QF); +} + +uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift) +{ + return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) return do_mve_sh_ri(s, a, gen_mve_uqshl); } +static bool do_mve_sh_rr(DisasContext *s, arg_mve_sh_rr *a, ShiftFn *fn) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ + return false; + } + if (!dc_isar_feature(aa32_mve, s) || + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || + a->rda == 13 || a->rda == 15 || a->rm == 13 || a->rm == 15 || + a->rm == a->rda) { + /* These rda/rm cases are UNPREDICTABLE; we choose to UNDEF */ + unallocated_encoding(s); + return true; + } + + /* The helper takes care of the sign-extension of the low 8 bits of Rm */ + fn(cpu_R[a->rda], cpu_env, cpu_R[a->rda], cpu_R[a->rm]); + return true; +} + +static bool trans_SQRSHR_rr(DisasContext *s, arg_mve_sh_rr *a) +{ + return do_mve_sh_rr(s, a, gen_helper_mve_sqrshr); +} + +static bool trans_UQRSHL_rr(DisasContext *s, arg_mve_sh_rr *a) +{ + return do_mve_sh_rr(s, a, gen_helper_mve_uqrshl); +} + /* * Multiply and multiply accumulate */ -- 2.20.1 Hi; here's the latest target-arm queue. Mostly this is refactoring and cleanup type patches. thanks -- PMM The following changes since commit c60be6e3e38cb36dc66129e757ec4b34152232be: Merge tag 'pull-sp-20231025' of https://gitlab.com/rth7680/qemu into staging (2023-10-27 09:43:53 +0900) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20231027 for you to fetch changes up to df93de987f423a0ed918c425f5dbd9a25d3c6229: hw/net/cadence_gem: enforce 32 bits variable size for CRC (2023-10-27 15:27:06 +0100) ---------------------------------------------------------------- target-arm queue: * Correct minor errors in Cortex-A710 definition * Implement Neoverse N2 CPU model * Refactor feature test functions out into separate header * Fix syndrome for FGT traps on ERET * Remove 'hw/arm/boot.h' includes from various header files * pxa2xx: Refactoring/cleanup * Avoid using 'first_cpu' when first ARM CPU is reachable * misc/led: LED state is set opposite of what is expected * hw/net/cadence_gen: clean up to use FIELD macros * hw/net/cadence_gem: perform PHY access on write only * hw/net/cadence_gem: enforce 32 bits variable size for CRC ---------------------------------------------------------------- Glenn Miles (1): misc/led: LED state is set opposite of what is expected Luc Michel (11): hw/net/cadence_gem: use REG32 macro for register definitions hw/net/cadence_gem: use FIELD for screening registers hw/net/cadence_gem: use FIELD to describe NWCTRL register fields hw/net/cadence_gem: use FIELD to describe NWCFG register fields hw/net/cadence_gem: use FIELD to describe DMACFG register fields hw/net/cadence_gem: use FIELD to describe [TX|RX]STATUS register fields hw/net/cadence_gem: use FIELD to describe IRQ register fields hw/net/cadence_gem: use FIELD to describe DESCONF6 register fields hw/net/cadence_gem: use FIELD to describe PHYMNTNC register fields hw/net/cadence_gem: perform PHY access on write only hw/net/cadence_gem: enforce 32 bits variable size for CRC Peter Maydell (9): target/arm: Correct minor errors in Cortex-A710 definition target/arm: Implement Neoverse N2 CPU model target/arm: Move feature test functions to their own header target/arm: Move ID_AA64MMFR1 and ID_AA64MMFR2 tests together target/arm: Move ID_AA64MMFR0 tests up to before MMFR1 and MMFR2 target/arm: Move ID_AA64ISAR* test functions together target/arm: Move ID_AA64PFR* tests together target/arm: Move ID_AA64DFR* feature tests together target/arm: Fix syndrome for FGT traps on ERET Philippe Mathieu-Daudé (20): hw/arm/allwinner-a10: Remove 'hw/arm/boot.h' from header hw/arm/allwinner-h3: Remove 'hw/arm/boot.h' from header hw/arm/allwinner-r40: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx25: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx31: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx6: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx6ul: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx7: Remove 'hw/arm/boot.h' from header hw/arm/xlnx-versal: Remove 'hw/arm/boot.h' from header hw/arm/xlnx-zynqmp: Remove 'hw/arm/boot.h' from header hw/sd/pxa2xx: Realize sysbus device before accessing it hw/sd/pxa2xx: Do not open-code sysbus_create_simple() hw/pcmcia/pxa2xx: Realize sysbus device before accessing it hw/pcmcia/pxa2xx: Do not open-code sysbus_create_simple() hw/pcmcia/pxa2xx: Inline pxa2xx_pcmcia_init() hw/intc/pxa2xx: Convert to Resettable interface hw/intc/pxa2xx: Pass CPU reference using QOM link property hw/intc/pxa2xx: Factor pxa2xx_pic_realize() out of pxa2xx_pic_init() hw/arm/pxa2xx: Realize PXA2XX_I2C device before accessing it hw/arm: Avoid using 'first_cpu' when first ARM CPU is reachable docs/system/arm/virt.rst | 1 + bsd-user/arm/target_arch.h | 1 + include/hw/arm/allwinner-a10.h | 1 - include/hw/arm/allwinner-h3.h | 1 - include/hw/arm/allwinner-r40.h | 1 - include/hw/arm/fsl-imx25.h | 1 - include/hw/arm/fsl-imx31.h | 1 - include/hw/arm/fsl-imx6.h | 1 - include/hw/arm/fsl-imx6ul.h | 1 - include/hw/arm/fsl-imx7.h | 1 - include/hw/arm/pxa.h | 2 - include/hw/arm/xlnx-versal.h | 1 - include/hw/arm/xlnx-zynqmp.h | 1 - linux-user/aarch64/target_prctl.h | 2 + target/arm/cpu-features.h | 994 ++++++++++++++++++++++++++++++++++++++ target/arm/cpu.h | 971 ------------------------------------- target/arm/internals.h | 1 + target/arm/tcg/translate.h | 2 +- hw/arm/armv7m.c | 1 + hw/arm/bananapi_m2u.c | 3 +- hw/arm/cubieboard.c | 1 + hw/arm/exynos4_boards.c | 7 +- hw/arm/imx25_pdk.c | 1 + hw/arm/kzm.c | 1 + hw/arm/mcimx6ul-evk.c | 1 + hw/arm/mcimx7d-sabre.c | 1 + hw/arm/orangepi.c | 3 +- hw/arm/pxa2xx.c | 17 +- hw/arm/pxa2xx_pic.c | 38 +- hw/arm/realview.c | 2 +- hw/arm/sabrelite.c | 1 + hw/arm/sbsa-ref.c | 1 + hw/arm/virt.c | 1 + hw/arm/xilinx_zynq.c | 2 +- hw/arm/xlnx-versal-virt.c | 1 + hw/arm/xlnx-zcu102.c | 1 + hw/intc/armv7m_nvic.c | 1 + hw/misc/led.c | 2 +- hw/net/cadence_gem.c | 884 ++++++++++++++++++--------------- hw/pcmcia/pxa2xx.c | 15 - hw/sd/pxa2xx_mmci.c | 7 +- linux-user/aarch64/cpu_loop.c | 1 + linux-user/aarch64/signal.c | 1 + linux-user/arm/signal.c | 1 + linux-user/elfload.c | 4 + linux-user/mmap.c | 4 + target/arm/arch_dump.c | 1 + target/arm/cpu.c | 1 + target/arm/cpu64.c | 1 + target/arm/debug_helper.c | 1 + target/arm/gdbstub.c | 1 + target/arm/helper.c | 1 + target/arm/kvm64.c | 1 + target/arm/machine.c | 1 + target/arm/ptw.c | 1 + target/arm/tcg/cpu64.c | 115 ++++- target/arm/tcg/hflags.c | 1 + target/arm/tcg/m_helper.c | 1 + target/arm/tcg/op_helper.c | 1 + target/arm/tcg/pauth_helper.c | 1 + target/arm/tcg/tlb_helper.c | 1 + target/arm/tcg/translate-a64.c | 4 +- target/arm/vfp_helper.c | 1 + 63 files changed, 1702 insertions(+), 1419 deletions(-) create mode 100644 target/arm/cpu-features.h Correct a couple of minor errors in the Cortex-A710 definition: * ID_AA64DFR0_EL1.DebugVer is 9 (indicating Armv8.4 debug architecture) * ID_AA64ISAR1_EL1.APA is 5 (indicating more PAuth support) * there is an IMPDEF CPUCFR_EL1, like that on the Neoverse-N1 Fixes: e3d45c0a89576 ("target/arm: Implement cortex-a710") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20230915185453.1871167-2-peter.maydell@linaro.org --- target/arm/tcg/cpu64.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) 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 @@ static const ARMCPRegInfo cortex_a710_cp_reginfo[] = { { .name = "CPUPFR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 6, .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + /* + * Report CPUCFR_EL1.SCU as 1, as we do not implement the DSU + * (and in particular its system registers). + */ + { .name = "CPUCFR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 0, .opc2 = 0, + .access = PL1_R, .type = ARM_CP_CONST, .resetvalue = 4 }, /* * Stub RAMINDEX, as we don't actually implement caches, BTB, @@ -XXX,XX +XXX,XX @@ static void aarch64_a710_initfn(Object *obj) cpu->isar.id_aa64pfr0 = 0x1201111120111112ull; /* GIC filled in later */ cpu->isar.id_aa64pfr1 = 0x0000000000000221ull; cpu->isar.id_aa64zfr0 = 0x0000110100110021ull; /* with Crypto */ - cpu->isar.id_aa64dfr0 = 0x000011f010305611ull; + cpu->isar.id_aa64dfr0 = 0x000011f010305619ull; cpu->isar.id_aa64dfr1 = 0; cpu->id_aa64afr0 = 0; cpu->id_aa64afr1 = 0; cpu->isar.id_aa64isar0 = 0x0221111110212120ull; /* with Crypto */ - cpu->isar.id_aa64isar1 = 0x0010111101211032ull; + cpu->isar.id_aa64isar1 = 0x0010111101211052ull; cpu->isar.id_aa64mmfr0 = 0x0000022200101122ull; cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; cpu->isar.id_aa64mmfr2 = 0x1221011110101011ull; -- 2.34.1 Implement a model of the Neoverse N2 CPU. This is an Armv9.0-A processor very similar to the Cortex-A710. The differences are: * no FEAT_EVT * FEAT_DGH (data gathering hint) * FEAT_NV (not yet implemented in QEMU) * Statistical Profiling Extension (not implemented in QEMU) * 48 bit physical address range, not 40 * CTR_EL0.DIC = 1 (no explicit icache cleaning needed) * PMCR_EL0.N = 6 (always 6 PMU counters, not 20) Because it has 48-bit physical address support, we can use this CPU in the sbsa-ref board as well as the virt board. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20230915185453.1871167-3-peter.maydell@linaro.org --- docs/system/arm/virt.rst | 1 + hw/arm/sbsa-ref.c | 1 + hw/arm/virt.c | 1 + target/arm/tcg/cpu64.c | 103 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 106 insertions(+) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -XXX,XX +XXX,XX @@ Supported guest CPU types: - ``host`` (with KVM only) - ``neoverse-n1`` (64-bit) - ``neoverse-v1`` (64-bit) +- ``neoverse-n2`` (64-bit) - ``max`` (same as ``host`` for KVM; best possible emulation with TCG) Note that the default is ``cortex-a15``, so for an AArch64 guest you must diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static const char * const valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a72"), ARM_CPU_TYPE_NAME("neoverse-n1"), ARM_CPU_TYPE_NAME("neoverse-v1"), + ARM_CPU_TYPE_NAME("neoverse-n2"), ARM_CPU_TYPE_NAME("max"), }; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static const char *valid_cpus[] = { ARM_CPU_TYPE_NAME("a64fx"), ARM_CPU_TYPE_NAME("neoverse-n1"), ARM_CPU_TYPE_NAME("neoverse-v1"), + ARM_CPU_TYPE_NAME("neoverse-n2"), #endif ARM_CPU_TYPE_NAME("cortex-a53"), ARM_CPU_TYPE_NAME("cortex-a57"), 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 @@ static void aarch64_a710_initfn(Object *obj) aarch64_add_sve_properties(obj); } +/* Extra IMPDEF regs in the N2 beyond those in the A710 */ +static const ARMCPRegInfo neoverse_n2_cp_reginfo[] = { + { .name = "CPURNDBR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 3, .opc2 = 0, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPURNDPEID_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 3, .opc2 = 1, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, +}; + +static void aarch64_neoverse_n2_initfn(Object *obj) +{ + ARMCPU *cpu = ARM_CPU(obj); + + cpu->dtb_compatible = "arm,neoverse-n2"; + set_feature(&cpu->env, ARM_FEATURE_V8); + set_feature(&cpu->env, ARM_FEATURE_NEON); + set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_AARCH64); + set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); + set_feature(&cpu->env, ARM_FEATURE_EL2); + set_feature(&cpu->env, ARM_FEATURE_EL3); + set_feature(&cpu->env, ARM_FEATURE_PMU); + + /* Ordered by Section B.5: AArch64 ID registers */ + cpu->midr = 0x410FD493; /* r0p3 */ + cpu->revidr = 0; + cpu->isar.id_pfr0 = 0x21110131; + cpu->isar.id_pfr1 = 0x00010000; /* GIC filled in later */ + cpu->isar.id_dfr0 = 0x16011099; + cpu->id_afr0 = 0; + cpu->isar.id_mmfr0 = 0x10201105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01260000; + cpu->isar.id_mmfr3 = 0x02122211; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00010142; + cpu->isar.id_isar5 = 0x11011121; /* with Crypto */ + cpu->isar.id_mmfr4 = 0x01021110; + cpu->isar.id_isar6 = 0x01111111; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x13211111; + cpu->isar.mvfr2 = 0x00000043; + cpu->isar.id_pfr2 = 0x00000011; + cpu->isar.id_aa64pfr0 = 0x1201111120111112ull; /* GIC filled in later */ + cpu->isar.id_aa64pfr1 = 0x0000000000000221ull; + cpu->isar.id_aa64zfr0 = 0x0000110100110021ull; /* with Crypto */ + cpu->isar.id_aa64dfr0 = 0x000011f210305619ull; + cpu->isar.id_aa64dfr1 = 0; + cpu->id_aa64afr0 = 0; + cpu->id_aa64afr1 = 0; + cpu->isar.id_aa64isar0 = 0x0221111110212120ull; /* with Crypto */ + cpu->isar.id_aa64isar1 = 0x0011111101211052ull; + cpu->isar.id_aa64mmfr0 = 0x0000022200101125ull; + cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; + cpu->isar.id_aa64mmfr2 = 0x1221011112101011ull; + cpu->clidr = 0x0000001482000023ull; + cpu->gm_blocksize = 4; + cpu->ctr = 0x00000004b444c004ull; + cpu->dcz_blocksize = 4; + /* TODO FEAT_MPAM: mpamidr_el1 = 0x0000_0001_001e_01ff */ + + /* Section B.7.2: PMCR_EL0 */ + cpu->isar.reset_pmcr_el0 = 0x3000; /* with 6 counters */ + + /* Section B.8.9: ICH_VTR_EL2 */ + cpu->gic_num_lrs = 4; + cpu->gic_vpribits = 5; + cpu->gic_vprebits = 5; + cpu->gic_pribits = 5; + + /* Section 14: Scalable Vector Extensions support */ + cpu->sve_vq.supported = 1 << 0; /* 128bit */ + + /* + * The Neoverse N2 TRM does not list CCSIDR values. The layout of + * the caches are in text in Table 7-1, Table 8-1, and Table 9-1. + * + * L1: 4-way set associative 64-byte line size, total 64K. + * L2: 8-way set associative 64 byte line size, total either 512K or 1024K. + */ + cpu->ccsidr[0] = make_ccsidr64(4, 64, 64 * KiB); /* L1 dcache */ + cpu->ccsidr[1] = cpu->ccsidr[0]; /* L1 icache */ + cpu->ccsidr[2] = make_ccsidr64(8, 64, 512 * KiB); /* L2 cache */ + + /* FIXME: Not documented -- copied from neoverse-v1 */ + cpu->reset_sctlr = 0x30c50838; + + /* + * The Neoverse N2 has all of the Cortex-A710 IMPDEF registers, + * and a few more RNG related ones. + */ + define_arm_cp_regs(cpu, cortex_a710_cp_reginfo); + define_arm_cp_regs(cpu, neoverse_n2_cp_reginfo); + + aarch64_add_pauth_properties(obj); + aarch64_add_sve_properties(obj); +} + /* * -cpu max: a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-arm is defined in cpu32.c; @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo aarch64_cpus[] = { { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, { .name = "neoverse-n1", .initfn = aarch64_neoverse_n1_initfn }, { .name = "neoverse-v1", .initfn = aarch64_neoverse_v1_initfn }, + { .name = "neoverse-n2", .initfn = aarch64_neoverse_n2_initfn }, }; static void aarch64_cpu_register_types(void) -- 2.34.1 The feature test functions isar_feature_*() now take up nearly a thousand lines in target/arm/cpu.h. This header file is included by a lot of source files, most of which don't need these functions. Move the feature test functions to their own header file. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-2-peter.maydell@linaro.org --- bsd-user/arm/target_arch.h | 1 + linux-user/aarch64/target_prctl.h | 2 + target/arm/cpu-features.h | 994 ++++++++++++++++++++++++++++++ target/arm/cpu.h | 971 ----------------------------- target/arm/internals.h | 1 + target/arm/tcg/translate.h | 2 +- hw/arm/armv7m.c | 1 + hw/intc/armv7m_nvic.c | 1 + linux-user/aarch64/cpu_loop.c | 1 + linux-user/aarch64/signal.c | 1 + linux-user/arm/signal.c | 1 + linux-user/elfload.c | 4 + linux-user/mmap.c | 4 + target/arm/arch_dump.c | 1 + target/arm/cpu.c | 1 + target/arm/cpu64.c | 1 + target/arm/debug_helper.c | 1 + target/arm/gdbstub.c | 1 + target/arm/helper.c | 1 + target/arm/kvm64.c | 1 + target/arm/machine.c | 1 + target/arm/ptw.c | 1 + target/arm/tcg/cpu64.c | 1 + target/arm/tcg/hflags.c | 1 + target/arm/tcg/m_helper.c | 1 + target/arm/tcg/op_helper.c | 1 + target/arm/tcg/pauth_helper.c | 1 + target/arm/tcg/tlb_helper.c | 1 + target/arm/vfp_helper.c | 1 + 29 files changed, 1028 insertions(+), 972 deletions(-) create mode 100644 target/arm/cpu-features.h diff --git a/bsd-user/arm/target_arch.h b/bsd-user/arm/target_arch.h index XXXXXXX..XXXXXXX 100644 --- a/bsd-user/arm/target_arch.h +++ b/bsd-user/arm/target_arch.h @@ -XXX,XX +XXX,XX @@ #define TARGET_ARCH_H #include "qemu.h" +#include "target/arm/cpu-features.h" void target_cpu_set_tls(CPUARMState *env, target_ulong newtls); target_ulong target_cpu_get_tls(CPUARMState *env); diff --git a/linux-user/aarch64/target_prctl.h b/linux-user/aarch64/target_prctl.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_prctl.h +++ b/linux-user/aarch64/target_prctl.h @@ -XXX,XX +XXX,XX @@ #ifndef AARCH64_TARGET_PRCTL_H #define AARCH64_TARGET_PRCTL_H +#include "target/arm/cpu-features.h" + static abi_long do_prctl_sve_get_vl(CPUArchState *env) { ARMCPU *cpu = env_archcpu(env); diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU Arm CPU -- feature test functions + * + * Copyright (c) 2023 Linaro Ltd + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef TARGET_ARM_FEATURES_H +#define TARGET_ARM_FEATURES_H + +/* + * Naming convention for isar_feature functions: + * Functions which test 32-bit ID registers should have _aa32_ in + * their name. Functions which test 64-bit ID registers should have + * _aa64_ in their name. These must only be used in code where we + * know for certain that the CPU has AArch32 or AArch64 respectively + * or where the correct answer for a CPU which doesn't implement that + * CPU state is "false" (eg when generating A32 or A64 code, if adding + * system registers that are specific to that CPU state, for "should + * we let this system register bit be set" tests where the 32-bit + * flavour of the register doesn't have the bit, and so on). + * Functions which simply ask "does this feature exist at all" have + * _any_ in their name, and always return the logical OR of the _aa64_ + * and the _aa32_ function. + */ + +/* + * 32-bit feature tests via id registers. + */ +static inline bool isar_feature_aa32_thumb_div(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) != 0; +} + +static inline bool isar_feature_aa32_arm_div(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1; +} + +static inline bool isar_feature_aa32_lob(const ARMISARegisters *id) +{ + /* (M-profile) low-overhead loops and branch future */ + return FIELD_EX32(id->id_isar0, ID_ISAR0, CMPBRANCH) >= 3; +} + +static inline bool isar_feature_aa32_jazelle(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0; +} + +static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; +} + +static inline bool isar_feature_aa32_pmull(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) > 1; +} + +static inline bool isar_feature_aa32_sha1(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA1) != 0; +} + +static inline bool isar_feature_aa32_sha2(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA2) != 0; +} + +static inline bool isar_feature_aa32_crc32(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, CRC32) != 0; +} + +static inline bool isar_feature_aa32_rdm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, RDM) != 0; +} + +static inline bool isar_feature_aa32_vcma(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, VCMA) != 0; +} + +static inline bool isar_feature_aa32_jscvt(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, JSCVT) != 0; +} + +static inline bool isar_feature_aa32_dp(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0; +} + +static inline bool isar_feature_aa32_fhm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, FHM) != 0; +} + +static inline bool isar_feature_aa32_sb(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, SB) != 0; +} + +static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0; +} + +static inline bool isar_feature_aa32_bf16(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, BF16) != 0; +} + +static inline bool isar_feature_aa32_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, I8MM) != 0; +} + +static inline bool isar_feature_aa32_ras(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr0, ID_PFR0, RAS) != 0; +} + +static inline bool isar_feature_aa32_mprofile(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr1, ID_PFR1, MPROGMOD) != 0; +} + +static inline bool isar_feature_aa32_m_sec_state(const ARMISARegisters *id) +{ + /* + * Return true if M-profile state handling insns + * (VSCCLRM, CLRM, FPCTX access insns) are implemented + */ + return FIELD_EX32(id->id_pfr1, ID_PFR1, SECURITY) >= 3; +} + +static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) +{ + /* Sadly this is encoded differently for A-profile and M-profile */ + if (isar_feature_aa32_mprofile(id)) { + return FIELD_EX32(id->mvfr1, MVFR1, FP16) > 0; + } else { + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) >= 3; + } +} + +static inline bool isar_feature_aa32_mve(const ARMISARegisters *id) +{ + /* + * Return true if MVE is supported (either integer or floating point). + * We must check for M-profile as the MVFR1 field means something + * else for A-profile. + */ + return isar_feature_aa32_mprofile(id) && + FIELD_EX32(id->mvfr1, MVFR1, MVE) > 0; +} + +static inline bool isar_feature_aa32_mve_fp(const ARMISARegisters *id) +{ + /* + * Return true if MVE is supported (either integer or floating point). + * We must check for M-profile as the MVFR1 field means something + * else for A-profile. + */ + return isar_feature_aa32_mprofile(id) && + FIELD_EX32(id->mvfr1, MVFR1, MVE) >= 2; +} + +static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id) +{ + /* + * Return true if either VFP or SIMD is implemented. + * In this case, a minimum of VFP w/ D0-D15. + */ + return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) > 0; +} + +static inline bool isar_feature_aa32_simd_r32(const ARMISARegisters *id) +{ + /* Return true if D16-D31 are implemented */ + return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) >= 2; +} + +static inline bool isar_feature_aa32_fpshvec(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr0, MVFR0, FPSHVEC) > 0; +} + +static inline bool isar_feature_aa32_fpsp_v2(const ARMISARegisters *id) +{ + /* Return true if CPU supports single precision floating point, VFPv2 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPSP) > 0; +} + +static inline bool isar_feature_aa32_fpsp_v3(const ARMISARegisters *id) +{ + /* Return true if CPU supports single precision floating point, VFPv3 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPSP) >= 2; +} + +static inline bool isar_feature_aa32_fpdp_v2(const ARMISARegisters *id) +{ + /* Return true if CPU supports double precision floating point, VFPv2 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPDP) > 0; +} + +static inline bool isar_feature_aa32_fpdp_v3(const ARMISARegisters *id) +{ + /* Return true if CPU supports double precision floating point, VFPv3 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPDP) >= 2; +} + +static inline bool isar_feature_aa32_vfp(const ARMISARegisters *id) +{ + return isar_feature_aa32_fpsp_v2(id) || isar_feature_aa32_fpdp_v2(id); +} + +/* + * We always set the FP and SIMD FP16 fields to indicate identical + * levels of support (assuming SIMD is implemented at all), so + * we only need one set of accessors. + */ +static inline bool isar_feature_aa32_fp16_spconv(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 0; +} + +static inline bool isar_feature_aa32_fp16_dpconv(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 1; +} + +/* + * Note that this ID register field covers both VFP and Neon FMAC, + * so should usually be tested in combination with some other + * check that confirms the presence of whichever of VFP or Neon is + * relevant, to avoid accidentally enabling a Neon feature on + * a VFP-no-Neon core or vice-versa. + */ +static inline bool isar_feature_aa32_simdfmac(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr1, MVFR1, SIMDFMAC) != 0; +} + +static inline bool isar_feature_aa32_vsel(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 1; +} + +static inline bool isar_feature_aa32_vcvt_dr(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 2; +} + +static inline bool isar_feature_aa32_vrint(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 3; +} + +static inline bool isar_feature_aa32_vminmaxnm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 4; +} + +static inline bool isar_feature_aa32_pxn(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr0, ID_MMFR0, VMSA) >= 4; +} + +static inline bool isar_feature_aa32_pan(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) != 0; +} + +static inline bool isar_feature_aa32_ats1e1(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) >= 2; +} + +static inline bool isar_feature_aa32_pmuv3p1(const ARMISARegisters *id) +{ + /* 0xf means "non-standard IMPDEF PMU" */ + return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 4 && + FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; +} + +static inline bool isar_feature_aa32_pmuv3p4(const ARMISARegisters *id) +{ + /* 0xf means "non-standard IMPDEF PMU" */ + return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 5 && + FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; +} + +static inline bool isar_feature_aa32_pmuv3p5(const ARMISARegisters *id) +{ + /* 0xf means "non-standard IMPDEF PMU" */ + return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 6 && + FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; +} + +static inline bool isar_feature_aa32_hpd(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, HPDS) != 0; +} + +static inline bool isar_feature_aa32_ac2(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, AC2) != 0; +} + +static inline bool isar_feature_aa32_ccidx(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, CCIDX) != 0; +} + +static inline bool isar_feature_aa32_tts2uxn(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, XNX) != 0; +} + +static inline bool isar_feature_aa32_half_evt(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, EVT) >= 1; +} + +static inline bool isar_feature_aa32_evt(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, EVT) >= 2; +} + +static inline bool isar_feature_aa32_dit(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr0, ID_PFR0, DIT) != 0; +} + +static inline bool isar_feature_aa32_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr2, ID_PFR2, SSBS) != 0; +} + +static inline bool isar_feature_aa32_debugv7p1(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 5; +} + +static inline bool isar_feature_aa32_debugv8p2(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 8; +} + +static inline bool isar_feature_aa32_doublelock(const ARMISARegisters *id) +{ + return FIELD_EX32(id->dbgdevid, DBGDEVID, DOUBLELOCK) > 0; +} + +/* + * 64-bit feature tests via id registers. + */ +static inline bool isar_feature_aa64_aes(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) != 0; +} + +static inline bool isar_feature_aa64_pmull(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) > 1; +} + +static inline bool isar_feature_aa64_sha1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA1) != 0; +} + +static inline bool isar_feature_aa64_sha256(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) != 0; +} + +static inline bool isar_feature_aa64_sha512(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) > 1; +} + +static inline bool isar_feature_aa64_crc32(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, CRC32) != 0; +} + +static inline bool isar_feature_aa64_atomics(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, ATOMIC) != 0; +} + +static inline bool isar_feature_aa64_rdm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RDM) != 0; +} + +static inline bool isar_feature_aa64_sha3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA3) != 0; +} + +static inline bool isar_feature_aa64_sm3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM3) != 0; +} + +static inline bool isar_feature_aa64_sm4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM4) != 0; +} + +static inline bool isar_feature_aa64_dp(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, DP) != 0; +} + +static inline bool isar_feature_aa64_fhm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, FHM) != 0; +} + +static inline bool isar_feature_aa64_condm_4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TS) != 0; +} + +static inline bool isar_feature_aa64_condm_5(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TS) >= 2; +} + +static inline bool isar_feature_aa64_rndr(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RNDR) != 0; +} + +static inline bool isar_feature_aa64_jscvt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, JSCVT) != 0; +} + +static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; +} + +/* + * These are the values from APA/API/APA3. + * In general these must be compared '>=', per the normal Arm ARM + * treatment of fields in ID registers. + */ +typedef enum { + PauthFeat_None = 0, + PauthFeat_1 = 1, + PauthFeat_EPAC = 2, + PauthFeat_2 = 3, + PauthFeat_FPAC = 4, + PauthFeat_FPACCOMBINED = 5, +} ARMPauthFeature; + +static inline ARMPauthFeature +isar_feature_pauth_feature(const ARMISARegisters *id) +{ + /* + * Architecturally, only one of {APA,API,APA3} may be active (non-zero) + * and the other two must be zero. Thus we may avoid conditionals. + */ + return (FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) | + FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, API) | + FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3)); +} + +static inline bool isar_feature_aa64_pauth(const ARMISARegisters *id) +{ + /* + * Return true if any form of pauth is enabled, as this + * predicate controls migration of the 128-bit keys. + */ + return isar_feature_pauth_feature(id) != PauthFeat_None; +} + +static inline bool isar_feature_aa64_pauth_qarma5(const ARMISARegisters *id) +{ + /* + * Return true if pauth is enabled with the architected QARMA5 algorithm. + * QEMU will always enable or disable both APA and GPA. + */ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) != 0; +} + +static inline bool isar_feature_aa64_pauth_qarma3(const ARMISARegisters *id) +{ + /* + * Return true if pauth is enabled with the architected QARMA3 algorithm. + * QEMU will always enable or disable both APA3 and GPA3. + */ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3) != 0; +} + +static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; +} + +static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; +} + +static inline bool isar_feature_aa64_sb(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0; +} + +static inline bool isar_feature_aa64_predinv(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SPECRES) != 0; +} + +static inline bool isar_feature_aa64_frint(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FRINTTS) != 0; +} + +static inline bool isar_feature_aa64_dcpop(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) != 0; +} + +static inline bool isar_feature_aa64_dcpodp(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) >= 2; +} + +static inline bool isar_feature_aa64_bf16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) != 0; +} + +static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) +{ + /* We always set the AdvSIMD and FP fields identically. */ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) != 0xf; +} + +static inline bool isar_feature_aa64_fp16(const ARMISARegisters *id) +{ + /* We always set the AdvSIMD and FP fields identically wrt FP16. */ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; +} + +static inline bool isar_feature_aa64_aa32(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL0) >= 2; +} + +static inline bool isar_feature_aa64_aa32_el1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL1) >= 2; +} + +static inline bool isar_feature_aa64_aa32_el2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL2) >= 2; +} + +static inline bool isar_feature_aa64_ras(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RAS) != 0; +} + +static inline bool isar_feature_aa64_doublefault(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RAS) >= 2; +} + +static inline bool isar_feature_aa64_sve(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0; +} + +static inline bool isar_feature_aa64_sel2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SEL2) != 0; +} + +static inline bool isar_feature_aa64_rme(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RME) != 0; +} + +static inline bool isar_feature_aa64_vh(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, VH) != 0; +} + +static inline bool isar_feature_aa64_lor(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, LO) != 0; +} + +static inline bool isar_feature_aa64_pan(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) != 0; +} + +static inline bool isar_feature_aa64_ats1e1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) >= 2; +} + +static inline bool isar_feature_aa64_pan3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) >= 3; +} + +static inline bool isar_feature_aa64_hcx(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HCX) != 0; +} + +static inline bool isar_feature_aa64_tidcp1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR1, TIDCP1) != 0; +} + +static inline bool isar_feature_aa64_uao(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, UAO) != 0; +} + +static inline bool isar_feature_aa64_st(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, ST) != 0; +} + +static inline bool isar_feature_aa64_lse2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, AT) != 0; +} + +static inline bool isar_feature_aa64_fwb(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, FWB) != 0; +} + +static inline bool isar_feature_aa64_ids(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, IDS) != 0; +} + +static inline bool isar_feature_aa64_half_evt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 1; +} + +static inline bool isar_feature_aa64_evt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 2; +} + +static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; +} + +static inline bool isar_feature_aa64_mte_insn_reg(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) != 0; +} + +static inline bool isar_feature_aa64_mte(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) >= 2; +} + +static inline bool isar_feature_aa64_sme(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SME) != 0; +} + +static inline bool isar_feature_aa64_pmuv3p1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 4 && + FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; +} + +static inline bool isar_feature_aa64_pmuv3p4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 5 && + FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; +} + +static inline bool isar_feature_aa64_pmuv3p5(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 6 && + FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; +} + +static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; +} + +static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; +} + +static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; +} + +static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; +} + +static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; +} + +static inline bool isar_feature_aa64_tgran4_2_lpa2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); + return t >= 3 || (t == 0 && isar_feature_aa64_tgran4_lpa2(id)); +} + +static inline bool isar_feature_aa64_tgran16_lpa2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 2; +} + +static inline bool isar_feature_aa64_tgran16_2_lpa2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); + return t >= 3 || (t == 0 && isar_feature_aa64_tgran16_lpa2(id)); +} + +static inline bool isar_feature_aa64_tgran4(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 0; +} + +static inline bool isar_feature_aa64_tgran16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 1; +} + +static inline bool isar_feature_aa64_tgran64(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64) >= 0; +} + +static inline bool isar_feature_aa64_tgran4_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran4(id)); +} + +static inline bool isar_feature_aa64_tgran16_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran16(id)); +} + +static inline bool isar_feature_aa64_tgran64_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran64(id)); +} + +static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; +} + +static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; +} + +static inline bool isar_feature_aa64_lva(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0; +} + +static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; +} + +static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0; +} + +static inline bool isar_feature_aa64_hdbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) >= 2; +} + +static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; +} + +static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; +} + +static inline bool isar_feature_aa64_scxtnum(const ARMISARegisters *id) +{ + int key = FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, CSV2); + if (key >= 2) { + return true; /* FEAT_CSV2_2 */ + } + if (key == 1) { + key = FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, CSV2_FRAC); + return key >= 2; /* FEAT_CSV2_1p2 */ + } + return false; +} + +static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; +} + +static inline bool isar_feature_aa64_debugv8p2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, DEBUGVER) >= 8; +} + +static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0; +} + +static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) != 0; +} + +static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2; +} + +static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; +} + +static inline bool isar_feature_aa64_sve_bf16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BFLOAT16) != 0; +} + +static inline bool isar_feature_aa64_sve2_sha3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SHA3) != 0; +} + +static inline bool isar_feature_aa64_sve2_sm4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SM4) != 0; +} + +static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, I8MM) != 0; +} + +static inline bool isar_feature_aa64_sve_f32mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F32MM) != 0; +} + +static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F64MM) != 0; +} + +static inline bool isar_feature_aa64_sme_f64f64(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, F64F64); +} + +static inline bool isar_feature_aa64_sme_i16i64(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, I16I64) == 0xf; +} + +static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, FA64); +} + +static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; +} + +static inline bool isar_feature_aa64_mops(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, MOPS); +} + +/* + * Feature tests for "does this exist in either 32-bit or 64-bit?" + */ +static inline bool isar_feature_any_fp16(const ARMISARegisters *id) +{ + return isar_feature_aa64_fp16(id) || isar_feature_aa32_fp16_arith(id); +} + +static inline bool isar_feature_any_predinv(const ARMISARegisters *id) +{ + return isar_feature_aa64_predinv(id) || isar_feature_aa32_predinv(id); +} + +static inline bool isar_feature_any_pmuv3p1(const ARMISARegisters *id) +{ + return isar_feature_aa64_pmuv3p1(id) || isar_feature_aa32_pmuv3p1(id); +} + +static inline bool isar_feature_any_pmuv3p4(const ARMISARegisters *id) +{ + return isar_feature_aa64_pmuv3p4(id) || isar_feature_aa32_pmuv3p4(id); +} + +static inline bool isar_feature_any_pmuv3p5(const ARMISARegisters *id) +{ + return isar_feature_aa64_pmuv3p5(id) || isar_feature_aa32_pmuv3p5(id); +} + +static inline bool isar_feature_any_ccidx(const ARMISARegisters *id) +{ + return isar_feature_aa64_ccidx(id) || isar_feature_aa32_ccidx(id); +} + +static inline bool isar_feature_any_tts2uxn(const ARMISARegisters *id) +{ + return isar_feature_aa64_tts2uxn(id) || isar_feature_aa32_tts2uxn(id); +} + +static inline bool isar_feature_any_debugv8p2(const ARMISARegisters *id) +{ + return isar_feature_aa64_debugv8p2(id) || isar_feature_aa32_debugv8p2(id); +} + +static inline bool isar_feature_any_ras(const ARMISARegisters *id) +{ + return isar_feature_aa64_ras(id) || isar_feature_aa32_ras(id); +} + +static inline bool isar_feature_any_half_evt(const ARMISARegisters *id) +{ + return isar_feature_aa64_half_evt(id) || isar_feature_aa32_half_evt(id); +} + +static inline bool isar_feature_any_evt(const ARMISARegisters *id) +{ + return isar_feature_aa64_evt(id) || isar_feature_aa32_evt(id); +} + +/* + * Forward to the above feature tests given an ARMCPU pointer. + */ +#define cpu_isar_feature(name, cpu) \ + ({ ARMCPU *cpu_ = (cpu); isar_feature_##name(&cpu_->isar); }) + +#endif 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 @@ static inline target_ulong cpu_untagged_addr(CPUState *cs, target_ulong x) } #endif -/* - * Naming convention for isar_feature functions: - * Functions which test 32-bit ID registers should have _aa32_ in - * their name. Functions which test 64-bit ID registers should have - * _aa64_ in their name. These must only be used in code where we - * know for certain that the CPU has AArch32 or AArch64 respectively - * or where the correct answer for a CPU which doesn't implement that - * CPU state is "false" (eg when generating A32 or A64 code, if adding - * system registers that are specific to that CPU state, for "should - * we let this system register bit be set" tests where the 32-bit - * flavour of the register doesn't have the bit, and so on). - * Functions which simply ask "does this feature exist at all" have - * _any_ in their name, and always return the logical OR of the _aa64_ - * and the _aa32_ function. - */ - -/* - * 32-bit feature tests via id registers. - */ -static inline bool isar_feature_aa32_thumb_div(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) != 0; -} - -static inline bool isar_feature_aa32_arm_div(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1; -} - -static inline bool isar_feature_aa32_lob(const ARMISARegisters *id) -{ - /* (M-profile) low-overhead loops and branch future */ - return FIELD_EX32(id->id_isar0, ID_ISAR0, CMPBRANCH) >= 3; -} - -static inline bool isar_feature_aa32_jazelle(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0; -} - -static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; -} - -static inline bool isar_feature_aa32_pmull(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) > 1; -} - -static inline bool isar_feature_aa32_sha1(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA1) != 0; -} - -static inline bool isar_feature_aa32_sha2(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA2) != 0; -} - -static inline bool isar_feature_aa32_crc32(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, CRC32) != 0; -} - -static inline bool isar_feature_aa32_rdm(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, RDM) != 0; -} - -static inline bool isar_feature_aa32_vcma(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, VCMA) != 0; -} - -static inline bool isar_feature_aa32_jscvt(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, JSCVT) != 0; -} - -static inline bool isar_feature_aa32_dp(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0; -} - -static inline bool isar_feature_aa32_fhm(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, FHM) != 0; -} - -static inline bool isar_feature_aa32_sb(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, SB) != 0; -} - -static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0; -} - -static inline bool isar_feature_aa32_bf16(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, BF16) != 0; -} - -static inline bool isar_feature_aa32_i8mm(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, I8MM) != 0; -} - -static inline bool isar_feature_aa32_ras(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_pfr0, ID_PFR0, RAS) != 0; -} - -static inline bool isar_feature_aa32_mprofile(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_pfr1, ID_PFR1, MPROGMOD) != 0; -} - -static inline bool isar_feature_aa32_m_sec_state(const ARMISARegisters *id) -{ - /* - * Return true if M-profile state handling insns - * (VSCCLRM, CLRM, FPCTX access insns) are implemented - */ - return FIELD_EX32(id->id_pfr1, ID_PFR1, SECURITY) >= 3; -} - -static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) -{ - /* Sadly this is encoded differently for A-profile and M-profile */ - if (isar_feature_aa32_mprofile(id)) { - return FIELD_EX32(id->mvfr1, MVFR1, FP16) > 0; - } else { - return FIELD_EX32(id->mvfr1, MVFR1, FPHP) >= 3; - } -} - -static inline bool isar_feature_aa32_mve(const ARMISARegisters *id) -{ - /* - * Return true if MVE is supported (either integer or floating point). - * We must check for M-profile as the MVFR1 field means something - * else for A-profile. - */ - return isar_feature_aa32_mprofile(id) && - FIELD_EX32(id->mvfr1, MVFR1, MVE) > 0; -} - -static inline bool isar_feature_aa32_mve_fp(const ARMISARegisters *id) -{ - /* - * Return true if MVE is supported (either integer or floating point). - * We must check for M-profile as the MVFR1 field means something - * else for A-profile. - */ - return isar_feature_aa32_mprofile(id) && - FIELD_EX32(id->mvfr1, MVFR1, MVE) >= 2; -} - -static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id) -{ - /* - * Return true if either VFP or SIMD is implemented. - * In this case, a minimum of VFP w/ D0-D15. - */ - return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) > 0; -} - -static inline bool isar_feature_aa32_simd_r32(const ARMISARegisters *id) -{ - /* Return true if D16-D31 are implemented */ - return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) >= 2; -} - -static inline bool isar_feature_aa32_fpshvec(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr0, MVFR0, FPSHVEC) > 0; -} - -static inline bool isar_feature_aa32_fpsp_v2(const ARMISARegisters *id) -{ - /* Return true if CPU supports single precision floating point, VFPv2 */ - return FIELD_EX32(id->mvfr0, MVFR0, FPSP) > 0; -} - -static inline bool isar_feature_aa32_fpsp_v3(const ARMISARegisters *id) -{ - /* Return true if CPU supports single precision floating point, VFPv3 */ - return FIELD_EX32(id->mvfr0, MVFR0, FPSP) >= 2; -} - -static inline bool isar_feature_aa32_fpdp_v2(const ARMISARegisters *id) -{ - /* Return true if CPU supports double precision floating point, VFPv2 */ - return FIELD_EX32(id->mvfr0, MVFR0, FPDP) > 0; -} - -static inline bool isar_feature_aa32_fpdp_v3(const ARMISARegisters *id) -{ - /* Return true if CPU supports double precision floating point, VFPv3 */ - return FIELD_EX32(id->mvfr0, MVFR0, FPDP) >= 2; -} - -static inline bool isar_feature_aa32_vfp(const ARMISARegisters *id) -{ - return isar_feature_aa32_fpsp_v2(id) || isar_feature_aa32_fpdp_v2(id); -} - -/* - * We always set the FP and SIMD FP16 fields to indicate identical - * levels of support (assuming SIMD is implemented at all), so - * we only need one set of accessors. - */ -static inline bool isar_feature_aa32_fp16_spconv(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 0; -} - -static inline bool isar_feature_aa32_fp16_dpconv(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 1; -} - -/* - * Note that this ID register field covers both VFP and Neon FMAC, - * so should usually be tested in combination with some other - * check that confirms the presence of whichever of VFP or Neon is - * relevant, to avoid accidentally enabling a Neon feature on - * a VFP-no-Neon core or vice-versa. - */ -static inline bool isar_feature_aa32_simdfmac(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr1, MVFR1, SIMDFMAC) != 0; -} - -static inline bool isar_feature_aa32_vsel(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 1; -} - -static inline bool isar_feature_aa32_vcvt_dr(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 2; -} - -static inline bool isar_feature_aa32_vrint(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 3; -} - -static inline bool isar_feature_aa32_vminmaxnm(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 4; -} - -static inline bool isar_feature_aa32_pxn(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr0, ID_MMFR0, VMSA) >= 4; -} - -static inline bool isar_feature_aa32_pan(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) != 0; -} - -static inline bool isar_feature_aa32_ats1e1(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) >= 2; -} - -static inline bool isar_feature_aa32_pmuv3p1(const ARMISARegisters *id) -{ - /* 0xf means "non-standard IMPDEF PMU" */ - return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 4 && - FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; -} - -static inline bool isar_feature_aa32_pmuv3p4(const ARMISARegisters *id) -{ - /* 0xf means "non-standard IMPDEF PMU" */ - return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 5 && - FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; -} - -static inline bool isar_feature_aa32_pmuv3p5(const ARMISARegisters *id) -{ - /* 0xf means "non-standard IMPDEF PMU" */ - return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 6 && - FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; -} - -static inline bool isar_feature_aa32_hpd(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, HPDS) != 0; -} - -static inline bool isar_feature_aa32_ac2(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, AC2) != 0; -} - -static inline bool isar_feature_aa32_ccidx(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, CCIDX) != 0; -} - -static inline bool isar_feature_aa32_tts2uxn(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, XNX) != 0; -} - -static inline bool isar_feature_aa32_half_evt(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, EVT) >= 1; -} - -static inline bool isar_feature_aa32_evt(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, EVT) >= 2; -} - -static inline bool isar_feature_aa32_dit(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_pfr0, ID_PFR0, DIT) != 0; -} - -static inline bool isar_feature_aa32_ssbs(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_pfr2, ID_PFR2, SSBS) != 0; -} - -static inline bool isar_feature_aa32_debugv7p1(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 5; -} - -static inline bool isar_feature_aa32_debugv8p2(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 8; -} - -static inline bool isar_feature_aa32_doublelock(const ARMISARegisters *id) -{ - return FIELD_EX32(id->dbgdevid, DBGDEVID, DOUBLELOCK) > 0; -} - -/* - * 64-bit feature tests via id registers. - */ -static inline bool isar_feature_aa64_aes(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) != 0; -} - -static inline bool isar_feature_aa64_pmull(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) > 1; -} - -static inline bool isar_feature_aa64_sha1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA1) != 0; -} - -static inline bool isar_feature_aa64_sha256(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) != 0; -} - -static inline bool isar_feature_aa64_sha512(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) > 1; -} - -static inline bool isar_feature_aa64_crc32(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, CRC32) != 0; -} - -static inline bool isar_feature_aa64_atomics(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, ATOMIC) != 0; -} - -static inline bool isar_feature_aa64_rdm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RDM) != 0; -} - -static inline bool isar_feature_aa64_sha3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA3) != 0; -} - -static inline bool isar_feature_aa64_sm3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM3) != 0; -} - -static inline bool isar_feature_aa64_sm4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM4) != 0; -} - -static inline bool isar_feature_aa64_dp(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, DP) != 0; -} - -static inline bool isar_feature_aa64_fhm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, FHM) != 0; -} - -static inline bool isar_feature_aa64_condm_4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TS) != 0; -} - -static inline bool isar_feature_aa64_condm_5(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TS) >= 2; -} - -static inline bool isar_feature_aa64_rndr(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RNDR) != 0; -} - -static inline bool isar_feature_aa64_jscvt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, JSCVT) != 0; -} - -static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; -} - -/* - * These are the values from APA/API/APA3. - * In general these must be compared '>=', per the normal Arm ARM - * treatment of fields in ID registers. - */ -typedef enum { - PauthFeat_None = 0, - PauthFeat_1 = 1, - PauthFeat_EPAC = 2, - PauthFeat_2 = 3, - PauthFeat_FPAC = 4, - PauthFeat_FPACCOMBINED = 5, -} ARMPauthFeature; - -static inline ARMPauthFeature -isar_feature_pauth_feature(const ARMISARegisters *id) -{ - /* - * Architecturally, only one of {APA,API,APA3} may be active (non-zero) - * and the other two must be zero. Thus we may avoid conditionals. - */ - return (FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) | - FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, API) | - FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3)); -} - -static inline bool isar_feature_aa64_pauth(const ARMISARegisters *id) -{ - /* - * Return true if any form of pauth is enabled, as this - * predicate controls migration of the 128-bit keys. - */ - return isar_feature_pauth_feature(id) != PauthFeat_None; -} - -static inline bool isar_feature_aa64_pauth_qarma5(const ARMISARegisters *id) -{ - /* - * Return true if pauth is enabled with the architected QARMA5 algorithm. - * QEMU will always enable or disable both APA and GPA. - */ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) != 0; -} - -static inline bool isar_feature_aa64_pauth_qarma3(const ARMISARegisters *id) -{ - /* - * Return true if pauth is enabled with the architected QARMA3 algorithm. - * QEMU will always enable or disable both APA3 and GPA3. - */ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3) != 0; -} - -static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; -} - -static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; -} - -static inline bool isar_feature_aa64_sb(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0; -} - -static inline bool isar_feature_aa64_predinv(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SPECRES) != 0; -} - -static inline bool isar_feature_aa64_frint(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FRINTTS) != 0; -} - -static inline bool isar_feature_aa64_dcpop(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) != 0; -} - -static inline bool isar_feature_aa64_dcpodp(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) >= 2; -} - -static inline bool isar_feature_aa64_bf16(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) != 0; -} - -static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) -{ - /* We always set the AdvSIMD and FP fields identically. */ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) != 0xf; -} - -static inline bool isar_feature_aa64_fp16(const ARMISARegisters *id) -{ - /* We always set the AdvSIMD and FP fields identically wrt FP16. */ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; -} - -static inline bool isar_feature_aa64_aa32(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL0) >= 2; -} - -static inline bool isar_feature_aa64_aa32_el1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL1) >= 2; -} - -static inline bool isar_feature_aa64_aa32_el2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL2) >= 2; -} - -static inline bool isar_feature_aa64_ras(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RAS) != 0; -} - -static inline bool isar_feature_aa64_doublefault(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RAS) >= 2; -} - -static inline bool isar_feature_aa64_sve(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0; -} - -static inline bool isar_feature_aa64_sel2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SEL2) != 0; -} - -static inline bool isar_feature_aa64_rme(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RME) != 0; -} - -static inline bool isar_feature_aa64_vh(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, VH) != 0; -} - -static inline bool isar_feature_aa64_lor(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, LO) != 0; -} - -static inline bool isar_feature_aa64_pan(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) != 0; -} - -static inline bool isar_feature_aa64_ats1e1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) >= 2; -} - -static inline bool isar_feature_aa64_pan3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) >= 3; -} - -static inline bool isar_feature_aa64_hcx(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HCX) != 0; -} - -static inline bool isar_feature_aa64_tidcp1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR1, TIDCP1) != 0; -} - -static inline bool isar_feature_aa64_uao(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, UAO) != 0; -} - -static inline bool isar_feature_aa64_st(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, ST) != 0; -} - -static inline bool isar_feature_aa64_lse2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, AT) != 0; -} - -static inline bool isar_feature_aa64_fwb(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, FWB) != 0; -} - -static inline bool isar_feature_aa64_ids(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, IDS) != 0; -} - -static inline bool isar_feature_aa64_half_evt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 1; -} - -static inline bool isar_feature_aa64_evt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 2; -} - -static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; -} - -static inline bool isar_feature_aa64_mte_insn_reg(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) != 0; -} - -static inline bool isar_feature_aa64_mte(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) >= 2; -} - -static inline bool isar_feature_aa64_sme(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SME) != 0; -} - -static inline bool isar_feature_aa64_pmuv3p1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 4 && - FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; -} - -static inline bool isar_feature_aa64_pmuv3p4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 5 && - FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; -} - -static inline bool isar_feature_aa64_pmuv3p5(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 6 && - FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; -} - -static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; -} - -static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; -} - -static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; -} - -static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; -} - -static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; -} - -static inline bool isar_feature_aa64_tgran4_2_lpa2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); - return t >= 3 || (t == 0 && isar_feature_aa64_tgran4_lpa2(id)); -} - -static inline bool isar_feature_aa64_tgran16_lpa2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 2; -} - -static inline bool isar_feature_aa64_tgran16_2_lpa2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); - return t >= 3 || (t == 0 && isar_feature_aa64_tgran16_lpa2(id)); -} - -static inline bool isar_feature_aa64_tgran4(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 0; -} - -static inline bool isar_feature_aa64_tgran16(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 1; -} - -static inline bool isar_feature_aa64_tgran64(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64) >= 0; -} - -static inline bool isar_feature_aa64_tgran4_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran4(id)); -} - -static inline bool isar_feature_aa64_tgran16_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran16(id)); -} - -static inline bool isar_feature_aa64_tgran64_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran64(id)); -} - -static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; -} - -static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; -} - -static inline bool isar_feature_aa64_lva(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0; -} - -static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; -} - -static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0; -} - -static inline bool isar_feature_aa64_hdbs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) >= 2; -} - -static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; -} - -static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; -} - -static inline bool isar_feature_aa64_scxtnum(const ARMISARegisters *id) -{ - int key = FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, CSV2); - if (key >= 2) { - return true; /* FEAT_CSV2_2 */ - } - if (key == 1) { - key = FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, CSV2_FRAC); - return key >= 2; /* FEAT_CSV2_1p2 */ - } - return false; -} - -static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; -} - -static inline bool isar_feature_aa64_debugv8p2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, DEBUGVER) >= 8; -} - -static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0; -} - -static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) != 0; -} - -static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2; -} - -static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; -} - -static inline bool isar_feature_aa64_sve_bf16(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BFLOAT16) != 0; -} - -static inline bool isar_feature_aa64_sve2_sha3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SHA3) != 0; -} - -static inline bool isar_feature_aa64_sve2_sm4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SM4) != 0; -} - -static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, I8MM) != 0; -} - -static inline bool isar_feature_aa64_sve_f32mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F32MM) != 0; -} - -static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F64MM) != 0; -} - -static inline bool isar_feature_aa64_sme_f64f64(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, F64F64); -} - -static inline bool isar_feature_aa64_sme_i16i64(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, I16I64) == 0xf; -} - -static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, FA64); -} - -static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; -} - -static inline bool isar_feature_aa64_mops(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, MOPS); -} - -/* - * Feature tests for "does this exist in either 32-bit or 64-bit?" - */ -static inline bool isar_feature_any_fp16(const ARMISARegisters *id) -{ - return isar_feature_aa64_fp16(id) || isar_feature_aa32_fp16_arith(id); -} - -static inline bool isar_feature_any_predinv(const ARMISARegisters *id) -{ - return isar_feature_aa64_predinv(id) || isar_feature_aa32_predinv(id); -} - -static inline bool isar_feature_any_pmuv3p1(const ARMISARegisters *id) -{ - return isar_feature_aa64_pmuv3p1(id) || isar_feature_aa32_pmuv3p1(id); -} - -static inline bool isar_feature_any_pmuv3p4(const ARMISARegisters *id) -{ - return isar_feature_aa64_pmuv3p4(id) || isar_feature_aa32_pmuv3p4(id); -} - -static inline bool isar_feature_any_pmuv3p5(const ARMISARegisters *id) -{ - return isar_feature_aa64_pmuv3p5(id) || isar_feature_aa32_pmuv3p5(id); -} - -static inline bool isar_feature_any_ccidx(const ARMISARegisters *id) -{ - return isar_feature_aa64_ccidx(id) || isar_feature_aa32_ccidx(id); -} - -static inline bool isar_feature_any_tts2uxn(const ARMISARegisters *id) -{ - return isar_feature_aa64_tts2uxn(id) || isar_feature_aa32_tts2uxn(id); -} - -static inline bool isar_feature_any_debugv8p2(const ARMISARegisters *id) -{ - return isar_feature_aa64_debugv8p2(id) || isar_feature_aa32_debugv8p2(id); -} - -static inline bool isar_feature_any_ras(const ARMISARegisters *id) -{ - return isar_feature_aa64_ras(id) || isar_feature_aa32_ras(id); -} - -static inline bool isar_feature_any_half_evt(const ARMISARegisters *id) -{ - return isar_feature_aa64_half_evt(id) || isar_feature_aa32_half_evt(id); -} - -static inline bool isar_feature_any_evt(const ARMISARegisters *id) -{ - return isar_feature_aa64_evt(id) || isar_feature_aa32_evt(id); -} - -/* - * Forward to the above feature tests given an ARMCPU pointer. - */ -#define cpu_isar_feature(name, cpu) \ - ({ ARMCPU *cpu_ = (cpu); isar_feature_##name(&cpu_->isar); }) - #endif 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 @@ #include "hw/registerfields.h" #include "tcg/tcg-gvec-desc.h" #include "syndrome.h" +#include "cpu-features.h" /* register banks for CPU modes */ #define BANK_USRSYS 0 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 @@ #include "exec/translator.h" #include "exec/helper-gen.h" #include "internals.h" - +#include "cpu-features.h" /* internal defines */ diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "qemu/log.h" #include "target/arm/idau.h" +#include "target/arm/cpu-features.h" #include "migration/vmstate.h" /* Bitbanded IO. Each word corresponds to a single bit. */ diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/tcg.h" #include "sysemu/runstate.h" #include "target/arm/cpu.h" +#include "target/arm/cpu-features.h" #include "exec/exec-all.h" #include "exec/memop.h" #include "qemu/log.h" diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/cpu_loop.c +++ b/linux-user/aarch64/cpu_loop.c @@ -XXX,XX +XXX,XX @@ #include "qemu/guest-random.h" #include "semihosting/common-semi.h" #include "target/arm/syndrome.h" +#include "target/arm/cpu-features.h" #define get_user_code_u32(x, gaddr, env) \ ({ abi_long __r = get_user_u32((x), (gaddr)); \ 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 @@ #include "user-internals.h" #include "signal-common.h" #include "linux-user/trace.h" +#include "target/arm/cpu-features.h" struct target_sigcontext { uint64_t fault_address; diff --git a/linux-user/arm/signal.c b/linux-user/arm/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/arm/signal.c +++ b/linux-user/arm/signal.c @@ -XXX,XX +XXX,XX @@ #include "user-internals.h" #include "signal-common.h" #include "linux-user/trace.h" +#include "target/arm/cpu-features.h" struct target_sigcontext { abi_ulong trap_no; 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 @@ #include "target_signal.h" #include "accel/tcg/debuginfo.h" +#ifdef TARGET_ARM +#include "target/arm/cpu-features.h" +#endif + #ifdef _ARCH_PPC64 #undef ARCH_DLINFO #undef ELF_PLATFORM diff --git a/linux-user/mmap.c b/linux-user/mmap.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/mmap.c +++ b/linux-user/mmap.c @@ -XXX,XX +XXX,XX @@ #include "target_mman.h" #include "qemu/interval-tree.h" +#ifdef TARGET_ARM +#include "target/arm/cpu-features.h" +#endif + static pthread_mutex_t mmap_mutex = PTHREAD_MUTEX_INITIALIZER; static __thread int mmap_lock_count; diff --git a/target/arm/arch_dump.c b/target/arm/arch_dump.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/arch_dump.c +++ b/target/arm/arch_dump.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "elf.h" #include "sysemu/dump.h" +#include "cpu-features.h" /* struct user_pt_regs from arch/arm64/include/uapi/asm/ptrace.h */ struct aarch64_user_regs { 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 @@ #include "hw/core/tcg-cpu-ops.h" #endif /* CONFIG_TCG */ #include "internals.h" +#include "cpu-features.h" #include "exec/exec-all.h" #include "hw/qdev-properties.h" #if !defined(CONFIG_USER_ONLY) 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 @@ #include "qapi/visitor.h" #include "hw/qdev-properties.h" #include "internals.h" +#include "cpu-features.h" #include "cpregs.h" void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/debug_helper.c +++ b/target/arm/debug_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "cpregs.h" #include "exec/exec-all.h" #include "exec/helper-proto.h" diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ #include "gdbstub/helpers.h" #include "sysemu/tcg.h" #include "internals.h" +#include "cpu-features.h" #include "cpregs.h" typedef struct RegisterSysregXmlParam { 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 @@ #include "trace.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "exec/helper-proto.h" #include "qemu/main-loop.h" #include "qemu/timer.h" diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/kvm_int.h" #include "kvm_arm.h" #include "internals.h" +#include "cpu-features.h" #include "hw/acpi/acpi.h" #include "hw/acpi/ghes.h" 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 @@ #include "sysemu/tcg.h" #include "kvm_arm.h" #include "internals.h" +#include "cpu-features.h" #include "migration/cpu.h" static bool vfp_needed(void *opaque) 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 @@ #include "exec/exec-all.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "idau.h" #ifdef CONFIG_TCG # include "tcg/oversized-guest.h" 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 @@ #include "hw/qdev-properties.h" #include "qemu/units.h" #include "internals.h" +#include "cpu-features.h" #include "cpregs.h" static uint64_t make_ccsidr64(unsigned assoc, unsigned linesize, 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 @@ #include "qemu/osdep.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "exec/helper-proto.h" #include "cpregs.h" 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 @@ #include "qemu/osdep.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "gdbstub/helpers.h" #include "exec/helper-proto.h" #include "qemu/main-loop.h" diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/helper-proto.h" #include "internals.h" +#include "cpu-features.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" #include "cpregs.h" diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/pauth_helper.c +++ b/target/arm/tcg/pauth_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" #include "exec/helper-proto.h" diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/tlb_helper.c +++ b/target/arm/tcg/tlb_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "exec/exec-all.h" #include "exec/helper-proto.h" diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/helper-proto.h" #include "internals.h" +#include "cpu-features.h" #ifdef CONFIG_TCG #include "qemu/log.h" #include "fpu/softfloat.h" -- 2.34.1 Our list of isar_feature functions is not in any particular order, but tests on fields of the same ID register tend to be grouped together. A few functions that are tests of fields in ID_AA64MMFR1 and ID_AA64MMFR2 are not in the same place as the rest; move them into their groups. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-3-peter.maydell@linaro.org --- target/arm/cpu-features.h | 60 +++++++++++++++++++-------------------- 1 file changed, 30 insertions(+), 30 deletions(-) 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_tidcp1(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR1, TIDCP1) != 0; } +static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0; +} + +static inline bool isar_feature_aa64_hdbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) >= 2; +} + +static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; +} + static inline bool isar_feature_aa64_uao(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, UAO) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_evt(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 2; } +static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; +} + +static inline bool isar_feature_aa64_lva(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0; +} + +static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; +} + static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; } -static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; -} - -static inline bool isar_feature_aa64_lva(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0; -} - -static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; -} - -static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0; -} - -static inline bool isar_feature_aa64_hdbs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) >= 2; -} - -static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; -} - static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; -- 2.34.1 Move the ID_AA64MMFR0 feature test functions up so they are before the ones for ID_AA64MMFR1 and ID_AA64MMFR2. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-4-peter.maydell@linaro.org --- target/arm/cpu-features.h | 120 +++++++++++++++++++------------------- 1 file changed, 60 insertions(+), 60 deletions(-) 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_rme(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RME) != 0; } +static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; +} + +static inline bool isar_feature_aa64_tgran4_2_lpa2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); + return t >= 3 || (t == 0 && isar_feature_aa64_tgran4_lpa2(id)); +} + +static inline bool isar_feature_aa64_tgran16_lpa2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 2; +} + +static inline bool isar_feature_aa64_tgran16_2_lpa2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); + return t >= 3 || (t == 0 && isar_feature_aa64_tgran16_lpa2(id)); +} + +static inline bool isar_feature_aa64_tgran4(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 0; +} + +static inline bool isar_feature_aa64_tgran16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 1; +} + +static inline bool isar_feature_aa64_tgran64(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64) >= 0; +} + +static inline bool isar_feature_aa64_tgran4_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran4(id)); +} + +static inline bool isar_feature_aa64_tgran16_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran16(id)); +} + +static inline bool isar_feature_aa64_tgran64_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran64(id)); +} + +static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; +} + static inline bool isar_feature_aa64_vh(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, VH) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; } -static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; -} - -static inline bool isar_feature_aa64_tgran4_2_lpa2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); - return t >= 3 || (t == 0 && isar_feature_aa64_tgran4_lpa2(id)); -} - -static inline bool isar_feature_aa64_tgran16_lpa2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 2; -} - -static inline bool isar_feature_aa64_tgran16_2_lpa2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); - return t >= 3 || (t == 0 && isar_feature_aa64_tgran16_lpa2(id)); -} - -static inline bool isar_feature_aa64_tgran4(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 0; -} - -static inline bool isar_feature_aa64_tgran16(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 1; -} - -static inline bool isar_feature_aa64_tgran64(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64) >= 0; -} - -static inline bool isar_feature_aa64_tgran4_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran4(id)); -} - -static inline bool isar_feature_aa64_tgran16_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran16(id)); -} - -static inline bool isar_feature_aa64_tgran64_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran64(id)); -} - -static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; -} - static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; -- 2.34.1 Move the feature test functions that test ID_AA64ISAR* fields together. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-5-peter.maydell@linaro.org --- target/arm/cpu-features.h | 70 +++++++++++++++++++-------------------- 1 file changed, 35 insertions(+), 35 deletions(-) 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_rndr(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RNDR) != 0; } +static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; +} + +static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; +} + static inline bool isar_feature_aa64_jscvt(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, JSCVT) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_pauth_qarma3(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3) != 0; } -static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; -} - -static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; -} - static inline bool isar_feature_aa64_sb(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_bf16(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) != 0; } +static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; +} + +static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; +} + +static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; +} + +static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; +} + +static inline bool isar_feature_aa64_mops(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, MOPS); +} + 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_pmuv3p5(const ARMISARegisters *id) FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; } -static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; -} - -static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; -} - -static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; -} - -static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; -} - static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; } -static inline bool isar_feature_aa64_mops(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, MOPS); -} - /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ -- 2.34.1 Move all the ID_AA64PFR* feature test functions together. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-6-peter.maydell@linaro.org --- target/arm/cpu-features.h | 86 +++++++++++++++++++-------------------- 1 file changed, 43 insertions(+), 43 deletions(-) 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_rme(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RME) != 0; } +static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; +} + +static inline bool isar_feature_aa64_scxtnum(const ARMISARegisters *id) +{ + int key = FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, CSV2); + if (key >= 2) { + return true; /* FEAT_CSV2_2 */ + } + if (key == 1) { + key = FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, CSV2_FRAC); + return key >= 2; /* FEAT_CSV2_1p2 */ + } + return false; +} + +static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; +} + +static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; +} + +static inline bool isar_feature_aa64_mte_insn_reg(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) != 0; +} + +static inline bool isar_feature_aa64_mte(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) >= 2; +} + +static inline bool isar_feature_aa64_sme(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SME) != 0; +} + static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) { return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; } -static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; -} - -static inline bool isar_feature_aa64_mte_insn_reg(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) != 0; -} - -static inline bool isar_feature_aa64_mte(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) >= 2; -} - -static inline bool isar_feature_aa64_sme(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SME) != 0; -} - static inline bool isar_feature_aa64_pmuv3p1(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 4 && @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_pmuv3p5(const ARMISARegisters *id) FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; } -static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; -} - -static inline bool isar_feature_aa64_scxtnum(const ARMISARegisters *id) -{ - int key = FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, CSV2); - if (key >= 2) { - return true; /* FEAT_CSV2_2 */ - } - if (key == 1) { - key = FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, CSV2_FRAC); - return key >= 2; /* FEAT_CSV2_1p2 */ - } - return false; -} - -static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; -} - static inline bool isar_feature_aa64_debugv8p2(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, DEBUGVER) >= 8; -- 2.34.1 Move all the ID_AA64DFR* feature test functions together. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-7-peter.maydell@linaro.org --- target/arm/cpu-features.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) 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_debugv8p2(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, DEBUGVER) >= 8; } +static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; +} + static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, FA64); } -static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; -} - /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ -- 2.34.1 In commit 442c9d682c94fc2 when we converted the ERET, ERETAA, ERETAB instructions to decodetree, the conversion accidentally lost the correct setting of the syndrome register when taking a trap because of the FEAT_FGT HFGITR_EL1.ERET bit. Instead of reporting a correct full syndrome value with the EC and IL bits, we only reported the low two bits of the syndrome, because the call to syn_erettrap() got dropped. Fix the syndrome values for these traps by reinstating the syn_erettrap() calls. Fixes: 442c9d682c94fc2 ("target/arm: Convert ERET, ERETAA, ERETAB to decodetree") Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024172438.2990945-1-peter.maydell@linaro.org --- target/arm/tcg/translate-a64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_ERET(DisasContext *s, arg_ERET *a) return false; } if (s->fgt_eret) { - gen_exception_insn_el(s, 0, EXCP_UDEF, 0, 2); + gen_exception_insn_el(s, 0, EXCP_UDEF, syn_erettrap(0), 2); return true; } dst = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool trans_ERETA(DisasContext *s, arg_reta *a) } /* The FGT trap takes precedence over an auth trap. */ if (s->fgt_eret) { - gen_exception_insn_el(s, 0, EXCP_UDEF, a->m ? 3 : 2, 2); + gen_exception_insn_el(s, 0, EXCP_UDEF, syn_erettrap(a->m ? 3 : 2), 2); return true; } dst = tcg_temp_new_i64(); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 1 - hw/arm/cubieboard.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #ifndef HW_ARM_ALLWINNER_A10_H #define HW_ARM_ALLWINNER_A10_H -#include "hw/arm/boot.h" #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/allwinner-a10-pic.h" #include "hw/net/allwinner_emac.h" diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-a10.h" +#include "hw/arm/boot.h" #include "hw/i2c/i2c.h" static struct arm_boot_info cubieboard_binfo = { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-h3.h | 1 - hw/arm/orangepi.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #define HW_ARM_ALLWINNER_H3_H #include "qom/object.h" -#include "hw/arm/boot.h" #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" #include "hw/misc/allwinner-h3-ccu.h" diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-h3.h" +#include "hw/arm/boot.h" static struct arm_boot_info orangepi_binfo; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-r40.h | 1 - hw/arm/bananapi_m2u.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/allwinner-r40.h b/include/hw/arm/allwinner-r40.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-r40.h +++ b/include/hw/arm/allwinner-r40.h @@ -XXX,XX +XXX,XX @@ #define HW_ARM_ALLWINNER_R40_H #include "qom/object.h" -#include "hw/arm/boot.h" #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" #include "hw/sd/allwinner-sdhost.h" diff --git a/hw/arm/bananapi_m2u.c b/hw/arm/bananapi_m2u.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bananapi_m2u.c +++ b/hw/arm/bananapi_m2u.c @@ -XXX,XX +XXX,XX @@ #include "hw/i2c/i2c.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-r40.h" +#include "hw/arm/boot.h" static struct arm_boot_info bpim2u_binfo; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx25.h | 1 - hw/arm/imx25_pdk.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx25.h b/include/hw/arm/fsl-imx25.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx25.h +++ b/include/hw/arm/fsl-imx25.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX25_H #define FSL_IMX25_H -#include "hw/arm/boot.h" #include "hw/intc/imx_avic.h" #include "hw/misc/imx25_ccm.h" #include "hw/char/imx_serial.h" diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx25_pdk.c +++ b/hw/arm/imx25_pdk.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "hw/qdev-properties.h" #include "hw/arm/fsl-imx25.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "qemu/error-report.h" #include "sysemu/qtest.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx31.h | 1 - hw/arm/kzm.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx31.h b/include/hw/arm/fsl-imx31.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx31.h +++ b/include/hw/arm/fsl-imx31.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX31_H #define FSL_IMX31_H -#include "hw/arm/boot.h" #include "hw/intc/imx_avic.h" #include "hw/misc/imx31_ccm.h" #include "hw/char/imx_serial.h" diff --git a/hw/arm/kzm.c b/hw/arm/kzm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/kzm.c +++ b/hw/arm/kzm.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx31.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "qemu/error-report.h" #include "exec/address-spaces.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx6.h | 1 - hw/arm/sabrelite.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx6.h b/include/hw/arm/fsl-imx6.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6.h +++ b/include/hw/arm/fsl-imx6.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX6_H #define FSL_IMX6_H -#include "hw/arm/boot.h" #include "hw/cpu/a9mpcore.h" #include "hw/misc/imx6_ccm.h" #include "hw/misc/imx6_src.h" diff --git a/hw/arm/sabrelite.c b/hw/arm/sabrelite.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sabrelite.c +++ b/hw/arm/sabrelite.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx6.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "hw/qdev-properties.h" #include "qemu/error-report.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx6ul.h | 1 - hw/arm/mcimx6ul-evk.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6ul.h +++ b/include/hw/arm/fsl-imx6ul.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX6UL_H #define FSL_IMX6UL_H -#include "hw/arm/boot.h" #include "hw/cpu/a15mpcore.h" #include "hw/misc/imx6ul_ccm.h" #include "hw/misc/imx6_src.h" diff --git a/hw/arm/mcimx6ul-evk.c b/hw/arm/mcimx6ul-evk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mcimx6ul-evk.c +++ b/hw/arm/mcimx6ul-evk.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx6ul.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "hw/qdev-properties.h" #include "qemu/error-report.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 1 - hw/arm/mcimx7d-sabre.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX7_H #define FSL_IMX7_H -#include "hw/arm/boot.h" #include "hw/cpu/a15mpcore.h" #include "hw/intc/imx_gpcv2.h" #include "hw/misc/imx7_ccm.h" diff --git a/hw/arm/mcimx7d-sabre.c b/hw/arm/mcimx7d-sabre.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mcimx7d-sabre.c +++ b/hw/arm/mcimx7d-sabre.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx7.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "hw/qdev-properties.h" #include "qemu/error-report.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 1 - hw/arm/xlnx-versal-virt.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) 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 @@ #define XLNX_VERSAL_H #include "hw/sysbus.h" -#include "hw/arm/boot.h" #include "hw/cpu/cluster.h" #include "hw/or-irq.h" #include "hw/sd/sdhci.h" diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/qdev-properties.h" #include "hw/arm/xlnx-versal.h" +#include "hw/arm/boot.h" #include "qom/object.h" #define TYPE_XLNX_VERSAL_VIRT_MACHINE MACHINE_TYPE_NAME("xlnx-versal-virt") -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-11-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 1 - hw/arm/xlnx-zcu102.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) 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 @@ #ifndef XLNX_ZYNQMP_H #define XLNX_ZYNQMP_H -#include "hw/arm/boot.h" #include "hw/intc/arm_gic.h" #include "hw/net/cadence_gem.h" #include "hw/char/cadence_uart.h" diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/xlnx-zynqmp.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "qemu/error-report.h" #include "qemu/log.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> sysbus_mmio_map() and sysbus_connect_irq() should not be called on unrealized device. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/pxa2xx_mmci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/sd/pxa2xx_mmci.c b/hw/sd/pxa2xx_mmci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/pxa2xx_mmci.c +++ b/hw/sd/pxa2xx_mmci.c @@ -XXX,XX +XXX,XX @@ PXA2xxMMCIState *pxa2xx_mmci_init(MemoryRegion *sysmem, dev = qdev_new(TYPE_PXA2XX_MMCI); sbd = SYS_BUS_DEVICE(dev); + sysbus_realize_and_unref(sbd, &error_fatal); sysbus_mmio_map(sbd, 0, base); sysbus_connect_irq(sbd, 0, irq); qdev_connect_gpio_out_named(dev, "rx-dma", 0, rx_dma); qdev_connect_gpio_out_named(dev, "tx-dma", 0, tx_dma); - sysbus_realize_and_unref(sbd, &error_fatal); return PXA2XX_MMCI(dev); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/pxa2xx_mmci.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/hw/sd/pxa2xx_mmci.c b/hw/sd/pxa2xx_mmci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/pxa2xx_mmci.c +++ b/hw/sd/pxa2xx_mmci.c @@ -XXX,XX +XXX,XX @@ PXA2xxMMCIState *pxa2xx_mmci_init(MemoryRegion *sysmem, qemu_irq irq, qemu_irq rx_dma, qemu_irq tx_dma) { DeviceState *dev; - SysBusDevice *sbd; - dev = qdev_new(TYPE_PXA2XX_MMCI); - sbd = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(sbd, &error_fatal); - sysbus_mmio_map(sbd, 0, base); - sysbus_connect_irq(sbd, 0, irq); + 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); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> sysbus_mmio_map() should not be called on unrealized device. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/pcmcia/pxa2xx.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/hw/pcmcia/pxa2xx.c b/hw/pcmcia/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pcmcia/pxa2xx.c +++ b/hw/pcmcia/pxa2xx.c @@ -XXX,XX +XXX,XX @@ PXA2xxPCMCIAState *pxa2xx_pcmcia_init(MemoryRegion *sysmem, hwaddr base) { DeviceState *dev; - PXA2xxPCMCIAState *s; dev = qdev_new(TYPE_PXA2XX_PCMCIA); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - s = PXA2XX_PCMCIA(dev); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - return s; + return PXA2XX_PCMCIA(dev); } static void pxa2xx_pcmcia_initfn(Object *obj) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/pcmcia/pxa2xx.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/hw/pcmcia/pxa2xx.c b/hw/pcmcia/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pcmcia/pxa2xx.c +++ b/hw/pcmcia/pxa2xx.c @@ -XXX,XX +XXX,XX @@ PXA2xxPCMCIAState *pxa2xx_pcmcia_init(MemoryRegion *sysmem, { DeviceState *dev; - dev = qdev_new(TYPE_PXA2XX_PCMCIA); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); + dev = sysbus_create_simple(TYPE_PXA2XX_PCMCIA, base, NULL); return PXA2XX_PCMCIA(dev); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 2 -- hw/arm/pxa2xx.c | 12 ++++++++---- hw/pcmcia/pxa2xx.c | 10 ---------- 3 files changed, 8 insertions(+), 16 deletions(-) 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_mmci_handlers(PXA2xxMMCIState *s, qemu_irq readonly, #define TYPE_PXA2XX_PCMCIA "pxa2xx-pcmcia" OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxPCMCIAState, PXA2XX_PCMCIA) -PXA2xxPCMCIAState *pxa2xx_pcmcia_init(MemoryRegion *sysmem, - hwaddr base); 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); diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa270_init(unsigned int sdram_size, const char *cpu_type) sysbus_create_simple("sysbus-ohci", 0x4c000000, qdev_get_gpio_in(s->pic, PXA2XX_PIC_USBH1)); - s->pcmcia[0] = pxa2xx_pcmcia_init(address_space, 0x20000000); - s->pcmcia[1] = pxa2xx_pcmcia_init(address_space, 0x30000000); + 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)); @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa255_init(unsigned int sdram_size) s->ssp[i] = (SSIBus *)qdev_get_child_bus(dev, "ssi"); } - s->pcmcia[0] = pxa2xx_pcmcia_init(address_space, 0x20000000); - s->pcmcia[1] = pxa2xx_pcmcia_init(address_space, 0x30000000); + 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)); diff --git a/hw/pcmcia/pxa2xx.c b/hw/pcmcia/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pcmcia/pxa2xx.c +++ b/hw/pcmcia/pxa2xx.c @@ -XXX,XX +XXX,XX @@ static void pxa2xx_pcmcia_set_irq(void *opaque, int line, int level) qemu_set_irq(s->irq, level); } -PXA2xxPCMCIAState *pxa2xx_pcmcia_init(MemoryRegion *sysmem, - hwaddr base) -{ - DeviceState *dev; - - dev = sysbus_create_simple(TYPE_PXA2XX_PCMCIA, base, NULL); - - return PXA2XX_PCMCIA(dev); -} - static void pxa2xx_pcmcia_initfn(Object *obj) { SysBusDevice *sbd = SYS_BUS_DEVICE(obj); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Factor reset code out of the DeviceRealize() handler. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20231020130331.50048-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx_pic.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -XXX,XX +XXX,XX @@ static int pxa2xx_pic_post_load(void *opaque, int version_id) return 0; } -DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) +static void pxa2xx_pic_reset_hold(Object *obj) { - DeviceState *dev = qdev_new(TYPE_PXA2XX_PIC); - PXA2xxPICState *s = PXA2XX_PIC(dev); - - s->cpu = cpu; + PXA2xxPICState *s = PXA2XX_PIC(obj); s->int_pending[0] = 0; s->int_pending[1] = 0; @@ -XXX,XX +XXX,XX @@ DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) 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); + PXA2xxPICState *s = PXA2XX_PIC(dev); + + s->cpu = cpu; sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_pxa2xx_pic_regs = { static void pxa2xx_pic_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->desc = "PXA2xx PIC"; dc->vmsd = &vmstate_pxa2xx_pic_regs; + rc->phases.hold = pxa2xx_pic_reset_hold; } static const TypeInfo pxa2xx_pic_info = { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> QOM objects shouldn't access each other internals fields except using the QOM API. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20231020130331.50048-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx_pic.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -XXX,XX +XXX,XX @@ #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" @@ -XXX,XX +XXX,XX @@ DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) DeviceState *dev = qdev_new(TYPE_PXA2XX_PIC); PXA2xxPICState *s = PXA2XX_PIC(dev); - s->cpu = cpu; + object_property_set_link(OBJECT(dev), "arm-cpu", + OBJECT(cpu), &error_abort); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_pxa2xx_pic_regs = { }, }; +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->desc = "PXA2xx PIC"; dc->vmsd = &vmstate_pxa2xx_pic_regs; rc->phases.hold = pxa2xx_pic_reset_hold; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20231020130331.50048-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx_pic.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -XXX,XX +XXX,XX @@ static void pxa2xx_pic_reset_hold(Object *obj) DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) { DeviceState *dev = qdev_new(TYPE_PXA2XX_PIC); - PXA2xxPICState *s = PXA2XX_PIC(dev); 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); @@ -XXX,XX +XXX,XX @@ DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) memory_region_init_io(&s->iomem, OBJECT(s), &pxa2xx_pic_ops, s, "pxa2xx-pic", 0x00100000); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); /* Enable IC coprocessor access. */ - define_arm_cp_regs_with_opaque(cpu, pxa_pic_cp_reginfo, s); - - return dev; + define_arm_cp_regs_with_opaque(s->cpu, pxa_pic_cp_reginfo, s); } static const VMStateDescription vmstate_pxa2xx_pic_regs = { @@ -XXX,XX +XXX,XX @@ static void pxa2xx_pic_class_init(ObjectClass *klass, void *data) 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; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> qbus_new(), called in i2c_init_bus(), should not be called on unrealized device. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20231020130331.50048-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ PXA2xxI2CState *pxa2xx_i2c_init(hwaddr base, 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); - /* FIXME: Should the slave device really be on a separate bus? */ - i2cbus = i2c_init_bus(dev, "dummy"); s->slave = PXA2XX_I2C_SLAVE(i2c_slave_create_simple(i2cbus, TYPE_PXA2XX_I2C_SLAVE, 0)); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Prefer using a well known local first CPU rather than a global one. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231025065909.57344-1-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/bananapi_m2u.c | 2 +- hw/arm/exynos4_boards.c | 7 ++++--- hw/arm/orangepi.c | 2 +- hw/arm/realview.c | 2 +- hw/arm/xilinx_zynq.c | 2 +- 5 files changed, 8 insertions(+), 7 deletions(-) diff --git a/hw/arm/bananapi_m2u.c b/hw/arm/bananapi_m2u.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bananapi_m2u.c +++ b/hw/arm/bananapi_m2u.c @@ -XXX,XX +XXX,XX @@ static void bpim2u_init(MachineState *machine) bpim2u_binfo.loader_start = r40->memmap[AW_R40_DEV_SDRAM]; bpim2u_binfo.ram_size = machine->ram_size; bpim2u_binfo.psci_conduit = QEMU_PSCI_CONDUIT_SMC; - arm_load_kernel(ARM_CPU(first_cpu), machine, &bpim2u_binfo); + arm_load_kernel(&r40->cpus[0], machine, &bpim2u_binfo); } static void bpim2u_machine_init(MachineClass *mc) diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4_boards.c +++ b/hw/arm/exynos4_boards.c @@ -XXX,XX +XXX,XX @@ exynos4_boards_init_common(MachineState *machine, static void nuri_init(MachineState *machine) { - exynos4_boards_init_common(machine, EXYNOS4_BOARD_NURI); + Exynos4BoardState *s = exynos4_boards_init_common(machine, + EXYNOS4_BOARD_NURI); - arm_load_kernel(ARM_CPU(first_cpu), machine, &exynos4_board_binfo); + arm_load_kernel(s->soc.cpu[0], machine, &exynos4_board_binfo); } static void smdkc210_init(MachineState *machine) @@ -XXX,XX +XXX,XX @@ static void smdkc210_init(MachineState *machine) lan9215_init(SMDK_LAN9118_BASE_ADDR, qemu_irq_invert(s->soc.irq_table[exynos4210_get_irq(37, 1)])); - arm_load_kernel(ARM_CPU(first_cpu), machine, &exynos4_board_binfo); + arm_load_kernel(s->soc.cpu[0], machine, &exynos4_board_binfo); } static void nuri_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) orangepi_binfo.loader_start = h3->memmap[AW_H3_DEV_SDRAM]; orangepi_binfo.ram_size = machine->ram_size; orangepi_binfo.psci_conduit = QEMU_PSCI_CONDUIT_SMC; - arm_load_kernel(ARM_CPU(first_cpu), machine, &orangepi_binfo); + arm_load_kernel(&h3->cpus[0], machine, &orangepi_binfo); } static void orangepi_machine_init(MachineClass *mc) diff --git a/hw/arm/realview.c b/hw/arm/realview.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/realview.c +++ b/hw/arm/realview.c @@ -XXX,XX +XXX,XX @@ static void realview_init(MachineState *machine, realview_binfo.ram_size = ram_size; realview_binfo.board_id = realview_board_id[board_type]; realview_binfo.loader_start = (board_type == BOARD_PB_A8 ? 0x70000000 : 0); - arm_load_kernel(ARM_CPU(first_cpu), machine, &realview_binfo); + arm_load_kernel(cpu, machine, &realview_binfo); } static void realview_eb_init(MachineState *machine) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) zynq_binfo.board_setup_addr = BOARD_SETUP_ADDR; zynq_binfo.write_board_setup = zynq_write_board_setup; - arm_load_kernel(ARM_CPU(first_cpu), machine, &zynq_binfo); + arm_load_kernel(cpu, machine, &zynq_binfo); } static void zynq_machine_class_init(ObjectClass *oc, void *data) -- 2.34.1 From: Glenn Miles <milesg@linux.vnet.ibm.com> Testing of the LED state showed that when the LED polarity was set to GPIO_POLARITY_ACTIVE_LOW and a low logic value was set on the input GPIO of the LED, the LED was being turn off when it was expected to be turned on. Fixes: ddb67f6402 ("hw/misc/led: Allow connecting from GPIO output") Signed-off-by: Glenn Miles <milesg@linux.vnet.ibm.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Andrew Jeffery <andrew@codeconstruct.com.au> Message-id: 20231024191945.4135036-1-milesg@linux.vnet.ibm.com Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/led.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/misc/led.c b/hw/misc/led.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/led.c +++ b/hw/misc/led.c @@ -XXX,XX +XXX,XX @@ static void led_set_state_gpio_handler(void *opaque, int line, int new_state) LEDState *s = LED(opaque); assert(line == 0); - led_set_state(s, !!new_state != s->gpio_active_high); + led_set_state(s, !!new_state == s->gpio_active_high); } static void led_reset(DeviceState *dev) -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Replace register defines with the REG32 macro from registerfields.h in the Cadence GEM device. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-2-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 527 +++++++++++++++++++++---------------------- 1 file changed, 261 insertions(+), 266 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ #include "hw/irq.h" #include "hw/net/cadence_gem.h" #include "hw/qdev-properties.h" +#include "hw/registerfields.h" #include "migration/vmstate.h" #include "qapi/error.h" #include "qemu/log.h" @@ -XXX,XX +XXX,XX @@ } \ } while (0) -#define GEM_NWCTRL (0x00000000 / 4) /* Network Control reg */ -#define GEM_NWCFG (0x00000004 / 4) /* Network Config reg */ -#define GEM_NWSTATUS (0x00000008 / 4) /* Network Status reg */ -#define GEM_USERIO (0x0000000C / 4) /* User IO reg */ -#define GEM_DMACFG (0x00000010 / 4) /* DMA Control reg */ -#define GEM_TXSTATUS (0x00000014 / 4) /* TX Status reg */ -#define GEM_RXQBASE (0x00000018 / 4) /* RX Q Base address reg */ -#define GEM_TXQBASE (0x0000001C / 4) /* TX Q Base address reg */ -#define GEM_RXSTATUS (0x00000020 / 4) /* RX Status reg */ -#define GEM_ISR (0x00000024 / 4) /* Interrupt Status reg */ -#define GEM_IER (0x00000028 / 4) /* Interrupt Enable reg */ -#define GEM_IDR (0x0000002C / 4) /* Interrupt Disable reg */ -#define GEM_IMR (0x00000030 / 4) /* Interrupt Mask reg */ -#define GEM_PHYMNTNC (0x00000034 / 4) /* Phy Maintenance reg */ -#define GEM_RXPAUSE (0x00000038 / 4) /* RX Pause Time reg */ -#define GEM_TXPAUSE (0x0000003C / 4) /* TX Pause Time reg */ -#define GEM_TXPARTIALSF (0x00000040 / 4) /* TX Partial Store and Forward */ -#define GEM_RXPARTIALSF (0x00000044 / 4) /* RX Partial Store and Forward */ -#define GEM_JUMBO_MAX_LEN (0x00000048 / 4) /* Max Jumbo Frame Size */ -#define GEM_HASHLO (0x00000080 / 4) /* Hash Low address reg */ -#define GEM_HASHHI (0x00000084 / 4) /* Hash High address reg */ -#define GEM_SPADDR1LO (0x00000088 / 4) /* Specific addr 1 low reg */ -#define GEM_SPADDR1HI (0x0000008C / 4) /* Specific addr 1 high reg */ -#define GEM_SPADDR2LO (0x00000090 / 4) /* Specific addr 2 low reg */ -#define GEM_SPADDR2HI (0x00000094 / 4) /* Specific addr 2 high reg */ -#define GEM_SPADDR3LO (0x00000098 / 4) /* Specific addr 3 low reg */ -#define GEM_SPADDR3HI (0x0000009C / 4) /* Specific addr 3 high reg */ -#define GEM_SPADDR4LO (0x000000A0 / 4) /* Specific addr 4 low reg */ -#define GEM_SPADDR4HI (0x000000A4 / 4) /* Specific addr 4 high reg */ -#define GEM_TIDMATCH1 (0x000000A8 / 4) /* Type ID1 Match reg */ -#define GEM_TIDMATCH2 (0x000000AC / 4) /* Type ID2 Match reg */ -#define GEM_TIDMATCH3 (0x000000B0 / 4) /* Type ID3 Match reg */ -#define GEM_TIDMATCH4 (0x000000B4 / 4) /* Type ID4 Match reg */ -#define GEM_WOLAN (0x000000B8 / 4) /* Wake on LAN reg */ -#define GEM_IPGSTRETCH (0x000000BC / 4) /* IPG Stretch reg */ -#define GEM_SVLAN (0x000000C0 / 4) /* Stacked VLAN reg */ -#define GEM_MODID (0x000000FC / 4) /* Module ID reg */ -#define GEM_OCTTXLO (0x00000100 / 4) /* Octets transmitted Low reg */ -#define GEM_OCTTXHI (0x00000104 / 4) /* Octets transmitted High reg */ -#define GEM_TXCNT (0x00000108 / 4) /* Error-free Frames transmitted */ -#define GEM_TXBCNT (0x0000010C / 4) /* Error-free Broadcast Frames */ -#define GEM_TXMCNT (0x00000110 / 4) /* Error-free Multicast Frame */ -#define GEM_TXPAUSECNT (0x00000114 / 4) /* Pause Frames Transmitted */ -#define GEM_TX64CNT (0x00000118 / 4) /* Error-free 64 TX */ -#define GEM_TX65CNT (0x0000011C / 4) /* Error-free 65-127 TX */ -#define GEM_TX128CNT (0x00000120 / 4) /* Error-free 128-255 TX */ -#define GEM_TX256CNT (0x00000124 / 4) /* Error-free 256-511 */ -#define GEM_TX512CNT (0x00000128 / 4) /* Error-free 512-1023 TX */ -#define GEM_TX1024CNT (0x0000012C / 4) /* Error-free 1024-1518 TX */ -#define GEM_TX1519CNT (0x00000130 / 4) /* Error-free larger than 1519 TX */ -#define GEM_TXURUNCNT (0x00000134 / 4) /* TX under run error counter */ -#define GEM_SINGLECOLLCNT (0x00000138 / 4) /* Single Collision Frames */ -#define GEM_MULTCOLLCNT (0x0000013C / 4) /* Multiple Collision Frames */ -#define GEM_EXCESSCOLLCNT (0x00000140 / 4) /* Excessive Collision Frames */ -#define GEM_LATECOLLCNT (0x00000144 / 4) /* Late Collision Frames */ -#define GEM_DEFERTXCNT (0x00000148 / 4) /* Deferred Transmission Frames */ -#define GEM_CSENSECNT (0x0000014C / 4) /* Carrier Sense Error Counter */ -#define GEM_OCTRXLO (0x00000150 / 4) /* Octets Received register Low */ -#define GEM_OCTRXHI (0x00000154 / 4) /* Octets Received register High */ -#define GEM_RXCNT (0x00000158 / 4) /* Error-free Frames Received */ -#define GEM_RXBROADCNT (0x0000015C / 4) /* Error-free Broadcast Frames RX */ -#define GEM_RXMULTICNT (0x00000160 / 4) /* Error-free Multicast Frames RX */ -#define GEM_RXPAUSECNT (0x00000164 / 4) /* Pause Frames Received Counter */ -#define GEM_RX64CNT (0x00000168 / 4) /* Error-free 64 byte Frames RX */ -#define GEM_RX65CNT (0x0000016C / 4) /* Error-free 65-127B Frames RX */ -#define GEM_RX128CNT (0x00000170 / 4) /* Error-free 128-255B Frames RX */ -#define GEM_RX256CNT (0x00000174 / 4) /* Error-free 256-512B Frames RX */ -#define GEM_RX512CNT (0x00000178 / 4) /* Error-free 512-1023B Frames RX */ -#define GEM_RX1024CNT (0x0000017C / 4) /* Error-free 1024-1518B Frames RX */ -#define GEM_RX1519CNT (0x00000180 / 4) /* Error-free 1519-max Frames RX */ -#define GEM_RXUNDERCNT (0x00000184 / 4) /* Undersize Frames Received */ -#define GEM_RXOVERCNT (0x00000188 / 4) /* Oversize Frames Received */ -#define GEM_RXJABCNT (0x0000018C / 4) /* Jabbers Received Counter */ -#define GEM_RXFCSCNT (0x00000190 / 4) /* Frame Check seq. Error Counter */ -#define GEM_RXLENERRCNT (0x00000194 / 4) /* Length Field Error Counter */ -#define GEM_RXSYMERRCNT (0x00000198 / 4) /* Symbol Error Counter */ -#define GEM_RXALIGNERRCNT (0x0000019C / 4) /* Alignment Error Counter */ -#define GEM_RXRSCERRCNT (0x000001A0 / 4) /* Receive Resource Error Counter */ -#define GEM_RXORUNCNT (0x000001A4 / 4) /* Receive Overrun Counter */ -#define GEM_RXIPCSERRCNT (0x000001A8 / 4) /* IP header Checksum Err Counter */ -#define GEM_RXTCPCCNT (0x000001AC / 4) /* TCP Checksum Error Counter */ -#define GEM_RXUDPCCNT (0x000001B0 / 4) /* UDP Checksum Error Counter */ +REG32(NWCTRL, 0x0) /* Network Control reg */ +REG32(NWCFG, 0x4) /* Network Config reg */ +REG32(NWSTATUS, 0x8) /* Network Status reg */ +REG32(USERIO, 0xc) /* User IO reg */ +REG32(DMACFG, 0x10) /* DMA Control reg */ +REG32(TXSTATUS, 0x14) /* TX Status reg */ +REG32(RXQBASE, 0x18) /* RX Q Base address reg */ +REG32(TXQBASE, 0x1c) /* TX Q Base address reg */ +REG32(RXSTATUS, 0x20) /* RX Status reg */ +REG32(ISR, 0x24) /* Interrupt Status reg */ +REG32(IER, 0x28) /* Interrupt Enable reg */ +REG32(IDR, 0x2c) /* Interrupt Disable reg */ +REG32(IMR, 0x30) /* Interrupt Mask reg */ +REG32(PHYMNTNC, 0x34) /* Phy Maintenance reg */ +REG32(RXPAUSE, 0x38) /* RX Pause Time reg */ +REG32(TXPAUSE, 0x3c) /* TX Pause Time reg */ +REG32(TXPARTIALSF, 0x40) /* TX Partial Store and Forward */ +REG32(RXPARTIALSF, 0x44) /* RX Partial Store and Forward */ +REG32(JUMBO_MAX_LEN, 0x48) /* Max Jumbo Frame Size */ +REG32(HASHLO, 0x80) /* Hash Low address reg */ +REG32(HASHHI, 0x84) /* Hash High address reg */ +REG32(SPADDR1LO, 0x88) /* Specific addr 1 low reg */ +REG32(SPADDR1HI, 0x8c) /* Specific addr 1 high reg */ +REG32(SPADDR2LO, 0x90) /* Specific addr 2 low reg */ +REG32(SPADDR2HI, 0x94) /* Specific addr 2 high reg */ +REG32(SPADDR3LO, 0x98) /* Specific addr 3 low reg */ +REG32(SPADDR3HI, 0x9c) /* Specific addr 3 high reg */ +REG32(SPADDR4LO, 0xa0) /* Specific addr 4 low reg */ +REG32(SPADDR4HI, 0xa4) /* Specific addr 4 high reg */ +REG32(TIDMATCH1, 0xa8) /* Type ID1 Match reg */ +REG32(TIDMATCH2, 0xac) /* Type ID2 Match reg */ +REG32(TIDMATCH3, 0xb0) /* Type ID3 Match reg */ +REG32(TIDMATCH4, 0xb4) /* Type ID4 Match reg */ +REG32(WOLAN, 0xb8) /* Wake on LAN reg */ +REG32(IPGSTRETCH, 0xbc) /* IPG Stretch reg */ +REG32(SVLAN, 0xc0) /* Stacked VLAN reg */ +REG32(MODID, 0xfc) /* Module ID reg */ +REG32(OCTTXLO, 0x100) /* Octects transmitted Low reg */ +REG32(OCTTXHI, 0x104) /* Octects transmitted High reg */ +REG32(TXCNT, 0x108) /* Error-free Frames transmitted */ +REG32(TXBCNT, 0x10c) /* Error-free Broadcast Frames */ +REG32(TXMCNT, 0x110) /* Error-free Multicast Frame */ +REG32(TXPAUSECNT, 0x114) /* Pause Frames Transmitted */ +REG32(TX64CNT, 0x118) /* Error-free 64 TX */ +REG32(TX65CNT, 0x11c) /* Error-free 65-127 TX */ +REG32(TX128CNT, 0x120) /* Error-free 128-255 TX */ +REG32(TX256CNT, 0x124) /* Error-free 256-511 */ +REG32(TX512CNT, 0x128) /* Error-free 512-1023 TX */ +REG32(TX1024CNT, 0x12c) /* Error-free 1024-1518 TX */ +REG32(TX1519CNT, 0x130) /* Error-free larger than 1519 TX */ +REG32(TXURUNCNT, 0x134) /* TX under run error counter */ +REG32(SINGLECOLLCNT, 0x138) /* Single Collision Frames */ +REG32(MULTCOLLCNT, 0x13c) /* Multiple Collision Frames */ +REG32(EXCESSCOLLCNT, 0x140) /* Excessive Collision Frames */ +REG32(LATECOLLCNT, 0x144) /* Late Collision Frames */ +REG32(DEFERTXCNT, 0x148) /* Deferred Transmission Frames */ +REG32(CSENSECNT, 0x14c) /* Carrier Sense Error Counter */ +REG32(OCTRXLO, 0x150) /* Octects Received register Low */ +REG32(OCTRXHI, 0x154) /* Octects Received register High */ +REG32(RXCNT, 0x158) /* Error-free Frames Received */ +REG32(RXBROADCNT, 0x15c) /* Error-free Broadcast Frames RX */ +REG32(RXMULTICNT, 0x160) /* Error-free Multicast Frames RX */ +REG32(RXPAUSECNT, 0x164) /* Pause Frames Received Counter */ +REG32(RX64CNT, 0x168) /* Error-free 64 byte Frames RX */ +REG32(RX65CNT, 0x16c) /* Error-free 65-127B Frames RX */ +REG32(RX128CNT, 0x170) /* Error-free 128-255B Frames RX */ +REG32(RX256CNT, 0x174) /* Error-free 256-512B Frames RX */ +REG32(RX512CNT, 0x178) /* Error-free 512-1023B Frames RX */ +REG32(RX1024CNT, 0x17c) /* Error-free 1024-1518B Frames RX */ +REG32(RX1519CNT, 0x180) /* Error-free 1519-max Frames RX */ +REG32(RXUNDERCNT, 0x184) /* Undersize Frames Received */ +REG32(RXOVERCNT, 0x188) /* Oversize Frames Received */ +REG32(RXJABCNT, 0x18c) /* Jabbers Received Counter */ +REG32(RXFCSCNT, 0x190) /* Frame Check seq. Error Counter */ +REG32(RXLENERRCNT, 0x194) /* Length Field Error Counter */ +REG32(RXSYMERRCNT, 0x198) /* Symbol Error Counter */ +REG32(RXALIGNERRCNT, 0x19c) /* Alignment Error Counter */ +REG32(RXRSCERRCNT, 0x1a0) /* Receive Resource Error Counter */ +REG32(RXORUNCNT, 0x1a4) /* Receive Overrun Counter */ +REG32(RXIPCSERRCNT, 0x1a8) /* IP header Checksum Err Counter */ +REG32(RXTCPCCNT, 0x1ac) /* TCP Checksum Error Counter */ +REG32(RXUDPCCNT, 0x1b0) /* UDP Checksum Error Counter */ -#define GEM_1588S (0x000001D0 / 4) /* 1588 Timer Seconds */ -#define GEM_1588NS (0x000001D4 / 4) /* 1588 Timer Nanoseconds */ -#define GEM_1588ADJ (0x000001D8 / 4) /* 1588 Timer Adjust */ -#define GEM_1588INC (0x000001DC / 4) /* 1588 Timer Increment */ -#define GEM_PTPETXS (0x000001E0 / 4) /* PTP Event Frame Transmitted (s) */ -#define GEM_PTPETXNS (0x000001E4 / 4) /* - * PTP Event Frame Transmitted (ns) - */ -#define GEM_PTPERXS (0x000001E8 / 4) /* PTP Event Frame Received (s) */ -#define GEM_PTPERXNS (0x000001EC / 4) /* PTP Event Frame Received (ns) */ -#define GEM_PTPPTXS (0x000001E0 / 4) /* PTP Peer Frame Transmitted (s) */ -#define GEM_PTPPTXNS (0x000001E4 / 4) /* PTP Peer Frame Transmitted (ns) */ -#define GEM_PTPPRXS (0x000001E8 / 4) /* PTP Peer Frame Received (s) */ -#define GEM_PTPPRXNS (0x000001EC / 4) /* PTP Peer Frame Received (ns) */ +REG32(1588S, 0x1d0) /* 1588 Timer Seconds */ +REG32(1588NS, 0x1d4) /* 1588 Timer Nanoseconds */ +REG32(1588ADJ, 0x1d8) /* 1588 Timer Adjust */ +REG32(1588INC, 0x1dc) /* 1588 Timer Increment */ +REG32(PTPETXS, 0x1e0) /* PTP Event Frame Transmitted (s) */ +REG32(PTPETXNS, 0x1e4) /* PTP Event Frame Transmitted (ns) */ +REG32(PTPERXS, 0x1e8) /* PTP Event Frame Received (s) */ +REG32(PTPERXNS, 0x1ec) /* PTP Event Frame Received (ns) */ +REG32(PTPPTXS, 0x1e0) /* PTP Peer Frame Transmitted (s) */ +REG32(PTPPTXNS, 0x1e4) /* PTP Peer Frame Transmitted (ns) */ +REG32(PTPPRXS, 0x1e8) /* PTP Peer Frame Received (s) */ +REG32(PTPPRXNS, 0x1ec) /* PTP Peer Frame Received (ns) */ /* Design Configuration Registers */ -#define GEM_DESCONF (0x00000280 / 4) -#define GEM_DESCONF2 (0x00000284 / 4) -#define GEM_DESCONF3 (0x00000288 / 4) -#define GEM_DESCONF4 (0x0000028C / 4) -#define GEM_DESCONF5 (0x00000290 / 4) -#define GEM_DESCONF6 (0x00000294 / 4) +REG32(DESCONF, 0x280) +REG32(DESCONF2, 0x284) +REG32(DESCONF3, 0x288) +REG32(DESCONF4, 0x28c) +REG32(DESCONF5, 0x290) +REG32(DESCONF6, 0x294) #define GEM_DESCONF6_64B_MASK (1U << 23) -#define GEM_DESCONF7 (0x00000298 / 4) +REG32(DESCONF7, 0x298) -#define GEM_INT_Q1_STATUS (0x00000400 / 4) -#define GEM_INT_Q1_MASK (0x00000640 / 4) +REG32(INT_Q1_STATUS, 0x400) +REG32(INT_Q1_MASK, 0x640) -#define GEM_TRANSMIT_Q1_PTR (0x00000440 / 4) -#define GEM_TRANSMIT_Q7_PTR (GEM_TRANSMIT_Q1_PTR + 6) +REG32(TRANSMIT_Q1_PTR, 0x440) +REG32(TRANSMIT_Q7_PTR, 0x458) -#define GEM_RECEIVE_Q1_PTR (0x00000480 / 4) -#define GEM_RECEIVE_Q7_PTR (GEM_RECEIVE_Q1_PTR + 6) +REG32(RECEIVE_Q1_PTR, 0x480) +REG32(RECEIVE_Q7_PTR, 0x498) -#define GEM_TBQPH (0x000004C8 / 4) -#define GEM_RBQPH (0x000004D4 / 4) +REG32(TBQPH, 0x4c8) +REG32(RBQPH, 0x4d4) -#define GEM_INT_Q1_ENABLE (0x00000600 / 4) -#define GEM_INT_Q7_ENABLE (GEM_INT_Q1_ENABLE + 6) +REG32(INT_Q1_ENABLE, 0x600) +REG32(INT_Q7_ENABLE, 0x618) -#define GEM_INT_Q1_DISABLE (0x00000620 / 4) -#define GEM_INT_Q7_DISABLE (GEM_INT_Q1_DISABLE + 6) +REG32(INT_Q1_DISABLE, 0x620) +REG32(INT_Q7_DISABLE, 0x638) -#define GEM_INT_Q1_MASK (0x00000640 / 4) -#define GEM_INT_Q7_MASK (GEM_INT_Q1_MASK + 6) - -#define GEM_SCREENING_TYPE1_REGISTER_0 (0x00000500 / 4) +REG32(SCREENING_TYPE1_REG0, 0x500) #define GEM_ST1R_UDP_PORT_MATCH_ENABLE (1 << 29) #define GEM_ST1R_DSTC_ENABLE (1 << 28) @@ -XXX,XX +XXX,XX @@ #define GEM_ST1R_QUEUE_SHIFT (0) #define GEM_ST1R_QUEUE_WIDTH (3 - GEM_ST1R_QUEUE_SHIFT + 1) -#define GEM_SCREENING_TYPE2_REGISTER_0 (0x00000540 / 4) +REG32(SCREENING_TYPE2_REG0, 0x540) #define GEM_ST2R_COMPARE_A_ENABLE (1 << 18) #define GEM_ST2R_COMPARE_A_SHIFT (13) @@ -XXX,XX +XXX,XX @@ #define GEM_ST2R_QUEUE_SHIFT (0) #define GEM_ST2R_QUEUE_WIDTH (3 - GEM_ST2R_QUEUE_SHIFT + 1) -#define GEM_SCREENING_TYPE2_ETHERTYPE_REG_0 (0x000006e0 / 4) -#define GEM_TYPE2_COMPARE_0_WORD_0 (0x00000700 / 4) +REG32(SCREENING_TYPE2_ETHERTYPE_REG0, 0x6e0) +REG32(TYPE2_COMPARE_0_WORD_0, 0x700) #define GEM_T2CW1_COMPARE_OFFSET_SHIFT (7) #define GEM_T2CW1_COMPARE_OFFSET_WIDTH (8 - GEM_T2CW1_COMPARE_OFFSET_SHIFT + 1) @@ -XXX,XX +XXX,XX @@ static inline uint64_t tx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc) { uint64_t ret = desc[0]; - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { ret |= (uint64_t)desc[2] << 32; } return ret; @@ -XXX,XX +XXX,XX @@ static inline uint64_t rx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc) { uint64_t ret = desc[0] & ~0x3UL; - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { ret |= (uint64_t)desc[2] << 32; } return ret; @@ -XXX,XX +XXX,XX @@ static inline int gem_get_desc_len(CadenceGEMState *s, bool rx_n_tx) { int ret = 2; - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { ret += 2; } - if (s->regs[GEM_DMACFG] & (rx_n_tx ? GEM_DMACFG_RX_BD_EXT + if (s->regs[R_DMACFG] & (rx_n_tx ? GEM_DMACFG_RX_BD_EXT : GEM_DMACFG_TX_BD_EXT)) { ret += 2; } @@ -XXX,XX +XXX,XX @@ static const uint8_t broadcast_addr[] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) { uint32_t size; - if (s->regs[GEM_NWCFG] & GEM_NWCFG_JUMBO_FRAME) { - size = s->regs[GEM_JUMBO_MAX_LEN]; + if (s->regs[R_NWCFG] & GEM_NWCFG_JUMBO_FRAME) { + size = s->regs[R_JUMBO_MAX_LEN]; if (size > s->jumbo_max_len) { size = s->jumbo_max_len; qemu_log_mask(LOG_GUEST_ERROR, "GEM_JUMBO_MAX_LEN reg cannot be" @@ -XXX,XX +XXX,XX @@ static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) } else if (tx) { size = 1518; } else { - size = s->regs[GEM_NWCFG] & GEM_NWCFG_RCV_1538 ? 1538 : 1518; + size = s->regs[R_NWCFG] & GEM_NWCFG_RCV_1538 ? 1538 : 1518; } return size; } @@ -XXX,XX +XXX,XX @@ static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) static void gem_set_isr(CadenceGEMState *s, int q, uint32_t flag) { if (q == 0) { - s->regs[GEM_ISR] |= flag & ~(s->regs[GEM_IMR]); + s->regs[R_ISR] |= flag & ~(s->regs[R_IMR]); } else { - s->regs[GEM_INT_Q1_STATUS + q - 1] |= flag & - ~(s->regs[GEM_INT_Q1_MASK + q - 1]); + s->regs[R_INT_Q1_STATUS + q - 1] |= flag & + ~(s->regs[R_INT_Q1_MASK + q - 1]); } } @@ -XXX,XX +XXX,XX @@ static void gem_init_register_masks(CadenceGEMState *s) unsigned int i; /* Mask of register bits which are read only */ memset(&s->regs_ro[0], 0, sizeof(s->regs_ro)); - s->regs_ro[GEM_NWCTRL] = 0xFFF80000; - s->regs_ro[GEM_NWSTATUS] = 0xFFFFFFFF; - s->regs_ro[GEM_DMACFG] = 0x8E00F000; - s->regs_ro[GEM_TXSTATUS] = 0xFFFFFE08; - s->regs_ro[GEM_RXQBASE] = 0x00000003; - s->regs_ro[GEM_TXQBASE] = 0x00000003; - s->regs_ro[GEM_RXSTATUS] = 0xFFFFFFF0; - s->regs_ro[GEM_ISR] = 0xFFFFFFFF; - s->regs_ro[GEM_IMR] = 0xFFFFFFFF; - s->regs_ro[GEM_MODID] = 0xFFFFFFFF; + s->regs_ro[R_NWCTRL] = 0xFFF80000; + s->regs_ro[R_NWSTATUS] = 0xFFFFFFFF; + s->regs_ro[R_DMACFG] = 0x8E00F000; + s->regs_ro[R_TXSTATUS] = 0xFFFFFE08; + s->regs_ro[R_RXQBASE] = 0x00000003; + s->regs_ro[R_TXQBASE] = 0x00000003; + s->regs_ro[R_RXSTATUS] = 0xFFFFFFF0; + s->regs_ro[R_ISR] = 0xFFFFFFFF; + s->regs_ro[R_IMR] = 0xFFFFFFFF; + s->regs_ro[R_MODID] = 0xFFFFFFFF; for (i = 0; i < s->num_priority_queues; i++) { - s->regs_ro[GEM_INT_Q1_STATUS + i] = 0xFFFFFFFF; - s->regs_ro[GEM_INT_Q1_ENABLE + i] = 0xFFFFF319; - s->regs_ro[GEM_INT_Q1_DISABLE + i] = 0xFFFFF319; - s->regs_ro[GEM_INT_Q1_MASK + i] = 0xFFFFFFFF; + s->regs_ro[R_INT_Q1_STATUS + i] = 0xFFFFFFFF; + s->regs_ro[R_INT_Q1_ENABLE + i] = 0xFFFFF319; + s->regs_ro[R_INT_Q1_DISABLE + i] = 0xFFFFF319; + s->regs_ro[R_INT_Q1_MASK + i] = 0xFFFFFFFF; } /* Mask of register bits which are clear on read */ memset(&s->regs_rtc[0], 0, sizeof(s->regs_rtc)); - s->regs_rtc[GEM_ISR] = 0xFFFFFFFF; + s->regs_rtc[R_ISR] = 0xFFFFFFFF; for (i = 0; i < s->num_priority_queues; i++) { - s->regs_rtc[GEM_INT_Q1_STATUS + i] = 0x00000CE6; + s->regs_rtc[R_INT_Q1_STATUS + i] = 0x00000CE6; } /* Mask of register bits which are write 1 to clear */ memset(&s->regs_w1c[0], 0, sizeof(s->regs_w1c)); - s->regs_w1c[GEM_TXSTATUS] = 0x000001F7; - s->regs_w1c[GEM_RXSTATUS] = 0x0000000F; + s->regs_w1c[R_TXSTATUS] = 0x000001F7; + s->regs_w1c[R_RXSTATUS] = 0x0000000F; /* Mask of register bits which are write only */ memset(&s->regs_wo[0], 0, sizeof(s->regs_wo)); - s->regs_wo[GEM_NWCTRL] = 0x00073E60; - s->regs_wo[GEM_IER] = 0x07FFFFFF; - s->regs_wo[GEM_IDR] = 0x07FFFFFF; + s->regs_wo[R_NWCTRL] = 0x00073E60; + s->regs_wo[R_IER] = 0x07FFFFFF; + s->regs_wo[R_IDR] = 0x07FFFFFF; for (i = 0; i < s->num_priority_queues; i++) { - s->regs_wo[GEM_INT_Q1_ENABLE + i] = 0x00000CE6; - s->regs_wo[GEM_INT_Q1_DISABLE + i] = 0x00000CE6; + s->regs_wo[R_INT_Q1_ENABLE + i] = 0x00000CE6; + s->regs_wo[R_INT_Q1_DISABLE + i] = 0x00000CE6; } } @@ -XXX,XX +XXX,XX @@ static bool gem_can_receive(NetClientState *nc) s = qemu_get_nic_opaque(nc); /* Do nothing if receive is not enabled. */ - if (!(s->regs[GEM_NWCTRL] & GEM_NWCTRL_RXENA)) { + if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_RXENA)) { if (s->can_rx_state != 1) { s->can_rx_state = 1; DB_PRINT("can't receive - no enable\n"); @@ -XXX,XX +XXX,XX @@ static void gem_update_int_status(CadenceGEMState *s) { int i; - qemu_set_irq(s->irq[0], !!s->regs[GEM_ISR]); + qemu_set_irq(s->irq[0], !!s->regs[R_ISR]); for (i = 1; i < s->num_priority_queues; ++i) { - qemu_set_irq(s->irq[i], !!s->regs[GEM_INT_Q1_STATUS + i - 1]); + qemu_set_irq(s->irq[i], !!s->regs[R_INT_Q1_STATUS + i - 1]); } } @@ -XXX,XX +XXX,XX @@ static void gem_receive_updatestats(CadenceGEMState *s, const uint8_t *packet, uint64_t octets; /* Total octets (bytes) received */ - octets = ((uint64_t)(s->regs[GEM_OCTRXLO]) << 32) | - s->regs[GEM_OCTRXHI]; + octets = ((uint64_t)(s->regs[R_OCTRXLO]) << 32) | + s->regs[R_OCTRXHI]; octets += bytes; - s->regs[GEM_OCTRXLO] = octets >> 32; - s->regs[GEM_OCTRXHI] = octets; + s->regs[R_OCTRXLO] = octets >> 32; + s->regs[R_OCTRXHI] = octets; /* Error-free Frames received */ - s->regs[GEM_RXCNT]++; + s->regs[R_RXCNT]++; /* Error-free Broadcast Frames counter */ if (!memcmp(packet, broadcast_addr, 6)) { - s->regs[GEM_RXBROADCNT]++; + s->regs[R_RXBROADCNT]++; } /* Error-free Multicast Frames counter */ if (packet[0] == 0x01) { - s->regs[GEM_RXMULTICNT]++; + s->regs[R_RXMULTICNT]++; } if (bytes <= 64) { - s->regs[GEM_RX64CNT]++; + s->regs[R_RX64CNT]++; } else if (bytes <= 127) { - s->regs[GEM_RX65CNT]++; + s->regs[R_RX65CNT]++; } else if (bytes <= 255) { - s->regs[GEM_RX128CNT]++; + s->regs[R_RX128CNT]++; } else if (bytes <= 511) { - s->regs[GEM_RX256CNT]++; + s->regs[R_RX256CNT]++; } else if (bytes <= 1023) { - s->regs[GEM_RX512CNT]++; + s->regs[R_RX512CNT]++; } else if (bytes <= 1518) { - s->regs[GEM_RX1024CNT]++; + s->regs[R_RX1024CNT]++; } else { - s->regs[GEM_RX1519CNT]++; + s->regs[R_RX1519CNT]++; } } @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) int i, is_mc; /* Promiscuous mode? */ - if (s->regs[GEM_NWCFG] & GEM_NWCFG_PROMISC) { + if (s->regs[R_NWCFG] & GEM_NWCFG_PROMISC) { return GEM_RX_PROMISCUOUS_ACCEPT; } if (!memcmp(packet, broadcast_addr, 6)) { /* Reject broadcast packets? */ - if (s->regs[GEM_NWCFG] & GEM_NWCFG_BCAST_REJ) { + if (s->regs[R_NWCFG] & GEM_NWCFG_BCAST_REJ) { return GEM_RX_REJECT; } return GEM_RX_BROADCAST_ACCEPT; @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) /* Accept packets -w- hash match? */ is_mc = is_multicast_ether_addr(packet); - if ((is_mc && (s->regs[GEM_NWCFG] & GEM_NWCFG_MCAST_HASH)) || - (!is_mc && (s->regs[GEM_NWCFG] & GEM_NWCFG_UCAST_HASH))) { + if ((is_mc && (s->regs[R_NWCFG] & GEM_NWCFG_MCAST_HASH)) || + (!is_mc && (s->regs[R_NWCFG] & GEM_NWCFG_UCAST_HASH))) { uint64_t buckets; unsigned hash_index; hash_index = calc_mac_hash(packet); - buckets = ((uint64_t)s->regs[GEM_HASHHI] << 32) | s->regs[GEM_HASHLO]; + buckets = ((uint64_t)s->regs[R_HASHHI] << 32) | s->regs[R_HASHLO]; if ((buckets >> hash_index) & 1) { return is_mc ? GEM_RX_MULTICAST_HASH_ACCEPT : GEM_RX_UNICAST_HASH_ACCEPT; @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) } /* Check all 4 specific addresses */ - gem_spaddr = (uint8_t *)&(s->regs[GEM_SPADDR1LO]); + gem_spaddr = (uint8_t *)&(s->regs[R_SPADDR1LO]); for (i = 3; i >= 0; i--) { if (s->sar_active[i] && !memcmp(packet, gem_spaddr + 8 * i, 6)) { return GEM_RX_SAR_ACCEPT + i; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, int i, j; for (i = 0; i < s->num_type1_screeners; i++) { - reg = s->regs[GEM_SCREENING_TYPE1_REGISTER_0 + i]; + reg = s->regs[R_SCREENING_TYPE1_REG0 + i]; matched = false; mismatched = false; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } for (i = 0; i < s->num_type2_screeners; i++) { - reg = s->regs[GEM_SCREENING_TYPE2_REGISTER_0 + i]; + reg = s->regs[R_SCREENING_TYPE2_REG0 + i]; matched = false; mismatched = false; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, qemu_log_mask(LOG_GUEST_ERROR, "Out of range ethertype " "register index: %d\n", et_idx); } - if (type == s->regs[GEM_SCREENING_TYPE2_ETHERTYPE_REG_0 + + if (type == s->regs[R_SCREENING_TYPE2_ETHERTYPE_REG0 + et_idx]) { matched = true; } else { @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, "register index: %d\n", cr_idx); } - cr0 = s->regs[GEM_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2]; - cr1 = s->regs[GEM_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2 + 1]; + cr0 = s->regs[R_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2]; + cr1 = s->regs[R_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2 + 1]; offset = extract32(cr1, GEM_T2CW1_OFFSET_VALUE_SHIFT, GEM_T2CW1_OFFSET_VALUE_WIDTH); @@ -XXX,XX +XXX,XX @@ static uint32_t gem_get_queue_base_addr(CadenceGEMState *s, bool tx, int q) switch (q) { case 0: - base_addr = s->regs[tx ? GEM_TXQBASE : GEM_RXQBASE]; + base_addr = s->regs[tx ? R_TXQBASE : R_RXQBASE]; break; case 1 ... (MAX_PRIORITY_QUEUES - 1): - base_addr = s->regs[(tx ? GEM_TRANSMIT_Q1_PTR : - GEM_RECEIVE_Q1_PTR) + q - 1]; + base_addr = s->regs[(tx ? R_TRANSMIT_Q1_PTR : + R_RECEIVE_Q1_PTR) + q - 1]; break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static hwaddr gem_get_desc_addr(CadenceGEMState *s, bool tx, int q) { hwaddr desc_addr = 0; - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { - desc_addr = s->regs[tx ? GEM_TBQPH : GEM_RBQPH]; + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + desc_addr = s->regs[tx ? R_TBQPH : R_RBQPH]; } desc_addr <<= 32; desc_addr |= tx ? s->tx_desc_addr[q] : s->rx_desc_addr[q]; @@ -XXX,XX +XXX,XX @@ static void gem_get_rx_desc(CadenceGEMState *s, int q) /* Descriptor owned by software ? */ if (rx_desc_get_ownership(s->rx_desc[q]) == 1) { DB_PRINT("descriptor 0x%" HWADDR_PRIx " owned by sw.\n", desc_addr); - s->regs[GEM_RXSTATUS] |= GEM_RXSTATUS_NOBUF; + s->regs[R_RXSTATUS] |= GEM_RXSTATUS_NOBUF; gem_set_isr(s, q, GEM_INT_RXUSED); /* Handle interrupt consequences */ gem_update_int_status(s); @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) } /* Discard packets with receive length error enabled ? */ - if (s->regs[GEM_NWCFG] & GEM_NWCFG_LERR_DISC) { + if (s->regs[R_NWCFG] & GEM_NWCFG_LERR_DISC) { unsigned type_len; /* Fish the ethertype / length field out of the RX packet */ @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* * Determine configured receive buffer offset (probably 0) */ - rxbuf_offset = (s->regs[GEM_NWCFG] & GEM_NWCFG_BUFF_OFST_M) >> + rxbuf_offset = (s->regs[R_NWCFG] & GEM_NWCFG_BUFF_OFST_M) >> GEM_NWCFG_BUFF_OFST_S; /* The configure size of each receive buffer. Determines how many * buffers needed to hold this packet. */ - rxbufsize = ((s->regs[GEM_DMACFG] & GEM_DMACFG_RBUFSZ_M) >> + rxbufsize = ((s->regs[R_DMACFG] & GEM_DMACFG_RBUFSZ_M) >> GEM_DMACFG_RBUFSZ_S) * GEM_DMACFG_RBUFSZ_MUL; bytes_to_copy = size; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) } /* Strip of FCS field ? (usually yes) */ - if (s->regs[GEM_NWCFG] & GEM_NWCFG_STRIP_FCS) { + if (s->regs[R_NWCFG] & GEM_NWCFG_STRIP_FCS) { rxbuf_ptr = (void *)buf; } else { unsigned crc_val; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* Count it */ gem_receive_updatestats(s, buf, size); - s->regs[GEM_RXSTATUS] |= GEM_RXSTATUS_FRMRCVD; + s->regs[R_RXSTATUS] |= GEM_RXSTATUS_FRMRCVD; gem_set_isr(s, q, GEM_INT_RXCMPL); /* Handle interrupt consequences */ @@ -XXX,XX +XXX,XX @@ static void gem_transmit_updatestats(CadenceGEMState *s, const uint8_t *packet, uint64_t octets; /* Total octets (bytes) transmitted */ - octets = ((uint64_t)(s->regs[GEM_OCTTXLO]) << 32) | - s->regs[GEM_OCTTXHI]; + octets = ((uint64_t)(s->regs[R_OCTTXLO]) << 32) | + s->regs[R_OCTTXHI]; octets += bytes; - s->regs[GEM_OCTTXLO] = octets >> 32; - s->regs[GEM_OCTTXHI] = octets; + s->regs[R_OCTTXLO] = octets >> 32; + s->regs[R_OCTTXHI] = octets; /* Error-free Frames transmitted */ - s->regs[GEM_TXCNT]++; + s->regs[R_TXCNT]++; /* Error-free Broadcast Frames counter */ if (!memcmp(packet, broadcast_addr, 6)) { - s->regs[GEM_TXBCNT]++; + s->regs[R_TXBCNT]++; } /* Error-free Multicast Frames counter */ if (packet[0] == 0x01) { - s->regs[GEM_TXMCNT]++; + s->regs[R_TXMCNT]++; } if (bytes <= 64) { - s->regs[GEM_TX64CNT]++; + s->regs[R_TX64CNT]++; } else if (bytes <= 127) { - s->regs[GEM_TX65CNT]++; + s->regs[R_TX65CNT]++; } else if (bytes <= 255) { - s->regs[GEM_TX128CNT]++; + s->regs[R_TX128CNT]++; } else if (bytes <= 511) { - s->regs[GEM_TX256CNT]++; + s->regs[R_TX256CNT]++; } else if (bytes <= 1023) { - s->regs[GEM_TX512CNT]++; + s->regs[R_TX512CNT]++; } else if (bytes <= 1518) { - s->regs[GEM_TX1024CNT]++; + s->regs[R_TX1024CNT]++; } else { - s->regs[GEM_TX1519CNT]++; + s->regs[R_TX1519CNT]++; } } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) int q = 0; /* Do nothing if transmit is not enabled. */ - if (!(s->regs[GEM_NWCTRL] & GEM_NWCTRL_TXENA)) { + if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_TXENA)) { return; } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) while (tx_desc_get_used(desc) == 0) { /* Do nothing if transmit is not enabled. */ - if (!(s->regs[GEM_NWCTRL] & GEM_NWCTRL_TXENA)) { + if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_TXENA)) { return; } print_gem_tx_desc(desc, q); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) } DB_PRINT("TX descriptor next: 0x%08x\n", s->tx_desc_addr[q]); - s->regs[GEM_TXSTATUS] |= GEM_TXSTATUS_TXCMPL; + s->regs[R_TXSTATUS] |= GEM_TXSTATUS_TXCMPL; gem_set_isr(s, q, GEM_INT_TXCMPL); /* Handle interrupt consequences */ gem_update_int_status(s); /* Is checksum offload enabled? */ - if (s->regs[GEM_DMACFG] & GEM_DMACFG_TXCSUM_OFFL) { + if (s->regs[R_DMACFG] & GEM_DMACFG_TXCSUM_OFFL) { net_checksum_calculate(s->tx_packet, total_bytes, CSUM_ALL); } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) gem_transmit_updatestats(s, s->tx_packet, total_bytes); /* Send the packet somewhere */ - if (s->phy_loop || (s->regs[GEM_NWCTRL] & + if (s->phy_loop || (s->regs[R_NWCTRL] & GEM_NWCTRL_LOCALLOOP)) { qemu_receive_packet(qemu_get_queue(s->nic), s->tx_packet, total_bytes); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) /* read next descriptor */ if (tx_desc_get_wrap(desc)) { - - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { - packet_desc_addr = s->regs[GEM_TBQPH]; + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + packet_desc_addr = s->regs[R_TBQPH]; packet_desc_addr <<= 32; } else { packet_desc_addr = 0; @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) } if (tx_desc_get_used(desc)) { - s->regs[GEM_TXSTATUS] |= GEM_TXSTATUS_USED; + s->regs[R_TXSTATUS] |= GEM_TXSTATUS_USED; /* IRQ TXUSED is defined only for queue 0 */ if (q == 0) { gem_set_isr(s, 0, GEM_INT_TXUSED); @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) /* Set post reset register values */ memset(&s->regs[0], 0, sizeof(s->regs)); - s->regs[GEM_NWCFG] = 0x00080000; - s->regs[GEM_NWSTATUS] = 0x00000006; - s->regs[GEM_DMACFG] = 0x00020784; - s->regs[GEM_IMR] = 0x07ffffff; - s->regs[GEM_TXPAUSE] = 0x0000ffff; - s->regs[GEM_TXPARTIALSF] = 0x000003ff; - s->regs[GEM_RXPARTIALSF] = 0x000003ff; - s->regs[GEM_MODID] = s->revision; - s->regs[GEM_DESCONF] = 0x02D00111; - s->regs[GEM_DESCONF2] = 0x2ab10000 | s->jumbo_max_len; - s->regs[GEM_DESCONF5] = 0x002f2045; - s->regs[GEM_DESCONF6] = GEM_DESCONF6_64B_MASK; - s->regs[GEM_INT_Q1_MASK] = 0x00000CE6; - s->regs[GEM_JUMBO_MAX_LEN] = s->jumbo_max_len; + s->regs[R_NWCFG] = 0x00080000; + s->regs[R_NWSTATUS] = 0x00000006; + s->regs[R_DMACFG] = 0x00020784; + s->regs[R_IMR] = 0x07ffffff; + s->regs[R_TXPAUSE] = 0x0000ffff; + s->regs[R_TXPARTIALSF] = 0x000003ff; + s->regs[R_RXPARTIALSF] = 0x000003ff; + s->regs[R_MODID] = s->revision; + s->regs[R_DESCONF] = 0x02D00111; + s->regs[R_DESCONF2] = 0x2ab10000 | s->jumbo_max_len; + s->regs[R_DESCONF5] = 0x002f2045; + s->regs[R_DESCONF6] = GEM_DESCONF6_64B_MASK; + s->regs[R_INT_Q1_MASK] = 0x00000CE6; + s->regs[R_JUMBO_MAX_LEN] = s->jumbo_max_len; if (s->num_priority_queues > 1) { queues_mask = MAKE_64BIT_MASK(1, s->num_priority_queues - 1); - s->regs[GEM_DESCONF6] |= queues_mask; + s->regs[R_DESCONF6] |= queues_mask; } /* Set MAC address */ a = &s->conf.macaddr.a[0]; - s->regs[GEM_SPADDR1LO] = a[0] | (a[1] << 8) | (a[2] << 16) | (a[3] << 24); - s->regs[GEM_SPADDR1HI] = a[4] | (a[5] << 8); + s->regs[R_SPADDR1LO] = a[0] | (a[1] << 8) | (a[2] << 16) | (a[3] << 24); + s->regs[R_SPADDR1HI] = a[4] | (a[5] << 8); for (i = 0; i < 4; i++) { s->sar_active[i] = false; @@ -XXX,XX +XXX,XX @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size) DB_PRINT("offset: 0x%04x read: 0x%08x\n", (unsigned)offset*4, retval); switch (offset) { - case GEM_ISR: + case R_ISR: DB_PRINT("lowering irqs on ISR read\n"); /* The interrupts get updated at the end of the function. */ break; - case GEM_PHYMNTNC: + case R_PHYMNTNC: if (retval & GEM_PHYMNTNC_OP_R) { uint32_t phy_addr, reg_num; @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, /* Handle register write side effects */ switch (offset) { - case GEM_NWCTRL: + case R_NWCTRL: if (val & GEM_NWCTRL_RXENA) { for (i = 0; i < s->num_priority_queues; ++i) { gem_get_rx_desc(s, i); @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, } break; - case GEM_TXSTATUS: + case R_TXSTATUS: gem_update_int_status(s); break; - case GEM_RXQBASE: + case R_RXQBASE: s->rx_desc_addr[0] = val; break; - case GEM_RECEIVE_Q1_PTR ... GEM_RECEIVE_Q7_PTR: - s->rx_desc_addr[offset - GEM_RECEIVE_Q1_PTR + 1] = val; + case R_RECEIVE_Q1_PTR ... R_RECEIVE_Q7_PTR: + s->rx_desc_addr[offset - R_RECEIVE_Q1_PTR + 1] = val; break; - case GEM_TXQBASE: + case R_TXQBASE: s->tx_desc_addr[0] = val; break; - case GEM_TRANSMIT_Q1_PTR ... GEM_TRANSMIT_Q7_PTR: - s->tx_desc_addr[offset - GEM_TRANSMIT_Q1_PTR + 1] = val; + case R_TRANSMIT_Q1_PTR ... R_TRANSMIT_Q7_PTR: + s->tx_desc_addr[offset - R_TRANSMIT_Q1_PTR + 1] = val; break; - case GEM_RXSTATUS: + case R_RXSTATUS: gem_update_int_status(s); break; - case GEM_IER: - s->regs[GEM_IMR] &= ~val; + case R_IER: + s->regs[R_IMR] &= ~val; gem_update_int_status(s); break; - case GEM_JUMBO_MAX_LEN: - s->regs[GEM_JUMBO_MAX_LEN] = val & MAX_JUMBO_FRAME_SIZE_MASK; + case R_JUMBO_MAX_LEN: + s->regs[R_JUMBO_MAX_LEN] = val & MAX_JUMBO_FRAME_SIZE_MASK; break; - case GEM_INT_Q1_ENABLE ... GEM_INT_Q7_ENABLE: - s->regs[GEM_INT_Q1_MASK + offset - GEM_INT_Q1_ENABLE] &= ~val; + case R_INT_Q1_ENABLE ... R_INT_Q7_ENABLE: + s->regs[R_INT_Q1_MASK + offset - R_INT_Q1_ENABLE] &= ~val; gem_update_int_status(s); break; - case GEM_IDR: - s->regs[GEM_IMR] |= val; + case R_IDR: + s->regs[R_IMR] |= val; gem_update_int_status(s); break; - case GEM_INT_Q1_DISABLE ... GEM_INT_Q7_DISABLE: - s->regs[GEM_INT_Q1_MASK + offset - GEM_INT_Q1_DISABLE] |= val; + case R_INT_Q1_DISABLE ... R_INT_Q7_DISABLE: + s->regs[R_INT_Q1_MASK + offset - R_INT_Q1_DISABLE] |= val; gem_update_int_status(s); break; - case GEM_SPADDR1LO: - case GEM_SPADDR2LO: - case GEM_SPADDR3LO: - case GEM_SPADDR4LO: - s->sar_active[(offset - GEM_SPADDR1LO) / 2] = false; + case R_SPADDR1LO: + case R_SPADDR2LO: + case R_SPADDR3LO: + case R_SPADDR4LO: + s->sar_active[(offset - R_SPADDR1LO) / 2] = false; break; - case GEM_SPADDR1HI: - case GEM_SPADDR2HI: - case GEM_SPADDR3HI: - case GEM_SPADDR4HI: - s->sar_active[(offset - GEM_SPADDR1HI) / 2] = true; + case R_SPADDR1HI: + case R_SPADDR2HI: + case R_SPADDR3HI: + case R_SPADDR4HI: + s->sar_active[(offset - R_SPADDR1HI) / 2] = true; break; - case GEM_PHYMNTNC: + case R_PHYMNTNC: if (val & GEM_PHYMNTNC_OP_W) { uint32_t phy_addr, reg_num; -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Describe screening registers fields using the FIELD macros. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-3-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 94 ++++++++++++++++++++++---------------------- 1 file changed, 48 insertions(+), 46 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(INT_Q1_DISABLE, 0x620) REG32(INT_Q7_DISABLE, 0x638) REG32(SCREENING_TYPE1_REG0, 0x500) - -#define GEM_ST1R_UDP_PORT_MATCH_ENABLE (1 << 29) -#define GEM_ST1R_DSTC_ENABLE (1 << 28) -#define GEM_ST1R_UDP_PORT_MATCH_SHIFT (12) -#define GEM_ST1R_UDP_PORT_MATCH_WIDTH (27 - GEM_ST1R_UDP_PORT_MATCH_SHIFT + 1) -#define GEM_ST1R_DSTC_MATCH_SHIFT (4) -#define GEM_ST1R_DSTC_MATCH_WIDTH (11 - GEM_ST1R_DSTC_MATCH_SHIFT + 1) -#define GEM_ST1R_QUEUE_SHIFT (0) -#define GEM_ST1R_QUEUE_WIDTH (3 - GEM_ST1R_QUEUE_SHIFT + 1) + FIELD(SCREENING_TYPE1_REG0, QUEUE_NUM, 0, 4) + FIELD(SCREENING_TYPE1_REG0, DSTC_MATCH, 4, 8) + FIELD(SCREENING_TYPE1_REG0, UDP_PORT_MATCH, 12, 16) + FIELD(SCREENING_TYPE1_REG0, DSTC_ENABLE, 28, 1) + FIELD(SCREENING_TYPE1_REG0, UDP_PORT_MATCH_EN, 29, 1) + FIELD(SCREENING_TYPE1_REG0, DROP_ON_MATCH, 30, 1) REG32(SCREENING_TYPE2_REG0, 0x540) - -#define GEM_ST2R_COMPARE_A_ENABLE (1 << 18) -#define GEM_ST2R_COMPARE_A_SHIFT (13) -#define GEM_ST2R_COMPARE_WIDTH (17 - GEM_ST2R_COMPARE_A_SHIFT + 1) -#define GEM_ST2R_ETHERTYPE_ENABLE (1 << 12) -#define GEM_ST2R_ETHERTYPE_INDEX_SHIFT (9) -#define GEM_ST2R_ETHERTYPE_INDEX_WIDTH (11 - GEM_ST2R_ETHERTYPE_INDEX_SHIFT \ - + 1) -#define GEM_ST2R_QUEUE_SHIFT (0) -#define GEM_ST2R_QUEUE_WIDTH (3 - GEM_ST2R_QUEUE_SHIFT + 1) + FIELD(SCREENING_TYPE2_REG0, QUEUE_NUM, 0, 4) + FIELD(SCREENING_TYPE2_REG0, VLAN_PRIORITY, 4, 3) + FIELD(SCREENING_TYPE2_REG0, VLAN_ENABLE, 8, 1) + FIELD(SCREENING_TYPE2_REG0, ETHERTYPE_REG_INDEX, 9, 3) + FIELD(SCREENING_TYPE2_REG0, ETHERTYPE_ENABLE, 12, 1) + FIELD(SCREENING_TYPE2_REG0, COMPARE_A, 13, 5) + FIELD(SCREENING_TYPE2_REG0, COMPARE_A_ENABLE, 18, 1) + FIELD(SCREENING_TYPE2_REG0, COMPARE_B, 19, 5) + FIELD(SCREENING_TYPE2_REG0, COMPARE_B_ENABLE, 24, 1) + FIELD(SCREENING_TYPE2_REG0, COMPARE_C, 25, 5) + FIELD(SCREENING_TYPE2_REG0, COMPARE_C_ENABLE, 30, 1) + FIELD(SCREENING_TYPE2_REG0, DROP_ON_MATCH, 31, 1) REG32(SCREENING_TYPE2_ETHERTYPE_REG0, 0x6e0) -REG32(TYPE2_COMPARE_0_WORD_0, 0x700) -#define GEM_T2CW1_COMPARE_OFFSET_SHIFT (7) -#define GEM_T2CW1_COMPARE_OFFSET_WIDTH (8 - GEM_T2CW1_COMPARE_OFFSET_SHIFT + 1) -#define GEM_T2CW1_OFFSET_VALUE_SHIFT (0) -#define GEM_T2CW1_OFFSET_VALUE_WIDTH (6 - GEM_T2CW1_OFFSET_VALUE_SHIFT + 1) +REG32(TYPE2_COMPARE_0_WORD_0, 0x700) + FIELD(TYPE2_COMPARE_0_WORD_0, MASK_VALUE, 0, 16) + FIELD(TYPE2_COMPARE_0_WORD_0, COMPARE_VALUE, 16, 16) + +REG32(TYPE2_COMPARE_0_WORD_1, 0x704) + FIELD(TYPE2_COMPARE_0_WORD_1, OFFSET_VALUE, 0, 7) + FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_OFFSET, 7, 2) + FIELD(TYPE2_COMPARE_0_WORD_1, DISABLE_MASK, 9, 1) + FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_VLAN_ID, 10, 1) /*****************************************/ #define GEM_NWCTRL_TXSTART 0x00000200 /* Transmit Enable */ @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, mismatched = false; /* Screening is based on UDP Port */ - if (reg & GEM_ST1R_UDP_PORT_MATCH_ENABLE) { + if (FIELD_EX32(reg, SCREENING_TYPE1_REG0, UDP_PORT_MATCH_EN)) { uint16_t udp_port = rxbuf_ptr[14 + 22] << 8 | rxbuf_ptr[14 + 23]; - if (udp_port == extract32(reg, GEM_ST1R_UDP_PORT_MATCH_SHIFT, - GEM_ST1R_UDP_PORT_MATCH_WIDTH)) { + if (udp_port == FIELD_EX32(reg, SCREENING_TYPE1_REG0, UDP_PORT_MATCH)) { matched = true; } else { mismatched = true; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } /* Screening is based on DS/TC */ - if (reg & GEM_ST1R_DSTC_ENABLE) { + if (FIELD_EX32(reg, SCREENING_TYPE1_REG0, DSTC_ENABLE)) { uint8_t dscp = rxbuf_ptr[14 + 1]; - if (dscp == extract32(reg, GEM_ST1R_DSTC_MATCH_SHIFT, - GEM_ST1R_DSTC_MATCH_WIDTH)) { + if (dscp == FIELD_EX32(reg, SCREENING_TYPE1_REG0, DSTC_MATCH)) { matched = true; } else { mismatched = true; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } if (matched && !mismatched) { - return extract32(reg, GEM_ST1R_QUEUE_SHIFT, GEM_ST1R_QUEUE_WIDTH); + return FIELD_EX32(reg, SCREENING_TYPE1_REG0, QUEUE_NUM); } } @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, matched = false; mismatched = false; - if (reg & GEM_ST2R_ETHERTYPE_ENABLE) { + if (FIELD_EX32(reg, SCREENING_TYPE2_REG0, ETHERTYPE_ENABLE)) { uint16_t type = rxbuf_ptr[12] << 8 | rxbuf_ptr[13]; - int et_idx = extract32(reg, GEM_ST2R_ETHERTYPE_INDEX_SHIFT, - GEM_ST2R_ETHERTYPE_INDEX_WIDTH); + int et_idx = FIELD_EX32(reg, SCREENING_TYPE2_REG0, + ETHERTYPE_REG_INDEX); if (et_idx > s->num_type2_screeners) { qemu_log_mask(LOG_GUEST_ERROR, "Out of range ethertype " @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, /* Compare A, B, C */ for (j = 0; j < 3; j++) { - uint32_t cr0, cr1, mask; + uint32_t cr0, cr1, mask, compare; uint16_t rx_cmp; int offset; - int cr_idx = extract32(reg, GEM_ST2R_COMPARE_A_SHIFT + j * 6, - GEM_ST2R_COMPARE_WIDTH); + int cr_idx = extract32(reg, R_SCREENING_TYPE2_REG0_COMPARE_A_SHIFT + j * 6, + R_SCREENING_TYPE2_REG0_COMPARE_A_LENGTH); - if (!(reg & (GEM_ST2R_COMPARE_A_ENABLE << (j * 6)))) { + if (!extract32(reg, R_SCREENING_TYPE2_REG0_COMPARE_A_ENABLE_SHIFT + j * 6, + R_SCREENING_TYPE2_REG0_COMPARE_A_ENABLE_LENGTH)) { continue; } + if (cr_idx > s->num_type2_screeners) { qemu_log_mask(LOG_GUEST_ERROR, "Out of range compare " "register index: %d\n", cr_idx); } cr0 = s->regs[R_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2]; - cr1 = s->regs[R_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2 + 1]; - offset = extract32(cr1, GEM_T2CW1_OFFSET_VALUE_SHIFT, - GEM_T2CW1_OFFSET_VALUE_WIDTH); + cr1 = s->regs[R_TYPE2_COMPARE_0_WORD_1 + cr_idx * 2]; + offset = FIELD_EX32(cr1, TYPE2_COMPARE_0_WORD_1, OFFSET_VALUE); - switch (extract32(cr1, GEM_T2CW1_COMPARE_OFFSET_SHIFT, - GEM_T2CW1_COMPARE_OFFSET_WIDTH)) { + switch (FIELD_EX32(cr1, TYPE2_COMPARE_0_WORD_1, COMPARE_OFFSET)) { case 3: /* Skip UDP header */ qemu_log_mask(LOG_UNIMP, "TCP compare offsets" "unimplemented - assuming UDP\n"); @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } rx_cmp = rxbuf_ptr[offset] << 8 | rxbuf_ptr[offset]; - mask = extract32(cr0, 0, 16); + mask = FIELD_EX32(cr0, TYPE2_COMPARE_0_WORD_0, MASK_VALUE); + compare = FIELD_EX32(cr0, TYPE2_COMPARE_0_WORD_0, COMPARE_VALUE); - if ((rx_cmp & mask) == (extract32(cr0, 16, 16) & mask)) { + if ((rx_cmp & mask) == (compare & mask)) { matched = true; } else { mismatched = true; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } if (matched && !mismatched) { - return extract32(reg, GEM_ST2R_QUEUE_SHIFT, GEM_ST2R_QUEUE_WIDTH); + return FIELD_EX32(reg, SCREENING_TYPE2_REG0, QUEUE_NUM); } } -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use the FIELD macro to describe the NWCTRL register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-4-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 53 +++++++++++++++++++++++++++++++++----------- 1 file changed, 40 insertions(+), 13 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ } while (0) REG32(NWCTRL, 0x0) /* Network Control reg */ + FIELD(NWCTRL, LOOPBACK , 0, 1) + FIELD(NWCTRL, LOOPBACK_LOCAL , 1, 1) + FIELD(NWCTRL, ENABLE_RECEIVE, 2, 1) + FIELD(NWCTRL, ENABLE_TRANSMIT, 3, 1) + FIELD(NWCTRL, MAN_PORT_EN , 4, 1) + FIELD(NWCTRL, CLEAR_ALL_STATS_REGS , 5, 1) + FIELD(NWCTRL, INC_ALL_STATS_REGS, 6, 1) + FIELD(NWCTRL, STATS_WRITE_EN, 7, 1) + FIELD(NWCTRL, BACK_PRESSURE, 8, 1) + FIELD(NWCTRL, TRANSMIT_START , 9, 1) + FIELD(NWCTRL, TRANSMIT_HALT, 10, 1) + FIELD(NWCTRL, TX_PAUSE_FRAME_RE, 11, 1) + FIELD(NWCTRL, TX_PAUSE_FRAME_ZE, 12, 1) + FIELD(NWCTRL, STATS_TAKE_SNAP, 13, 1) + FIELD(NWCTRL, STATS_READ_SNAP, 14, 1) + FIELD(NWCTRL, STORE_RX_TS, 15, 1) + FIELD(NWCTRL, PFC_ENABLE, 16, 1) + FIELD(NWCTRL, PFC_PRIO_BASED, 17, 1) + FIELD(NWCTRL, FLUSH_RX_PKT_PCLK , 18, 1) + FIELD(NWCTRL, TX_LPI_EN, 19, 1) + FIELD(NWCTRL, PTP_UNICAST_ENA, 20, 1) + FIELD(NWCTRL, ALT_SGMII_MODE, 21, 1) + FIELD(NWCTRL, STORE_UDP_OFFSET, 22, 1) + FIELD(NWCTRL, EXT_TSU_PORT_EN, 23, 1) + FIELD(NWCTRL, ONE_STEP_SYNC_MO, 24, 1) + FIELD(NWCTRL, PFC_CTRL , 25, 1) + FIELD(NWCTRL, EXT_RXQ_SEL_EN , 26, 1) + FIELD(NWCTRL, OSS_CORRECTION_FIELD, 27, 1) + FIELD(NWCTRL, SEL_MII_ON_RGMII, 28, 1) + FIELD(NWCTRL, TWO_PT_FIVE_GIG, 29, 1) + FIELD(NWCTRL, IFG_EATS_QAV_CREDIT, 30, 1) + REG32(NWCFG, 0x4) /* Network Config reg */ REG32(NWSTATUS, 0x8) /* Network Status reg */ REG32(USERIO, 0xc) /* User IO reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_VLAN_ID, 10, 1) /*****************************************/ -#define GEM_NWCTRL_TXSTART 0x00000200 /* Transmit Enable */ -#define GEM_NWCTRL_TXENA 0x00000008 /* Transmit Enable */ -#define GEM_NWCTRL_RXENA 0x00000004 /* Receive Enable */ -#define GEM_NWCTRL_LOCALLOOP 0x00000002 /* Local Loopback */ - #define GEM_NWCFG_STRIP_FCS 0x00020000 /* Strip FCS field */ #define GEM_NWCFG_LERR_DISC 0x00010000 /* Discard RX frames with len err */ #define GEM_NWCFG_BUFF_OFST_M 0x0000C000 /* Receive buffer offset mask */ @@ -XXX,XX +XXX,XX @@ static bool gem_can_receive(NetClientState *nc) s = qemu_get_nic_opaque(nc); /* Do nothing if receive is not enabled. */ - if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_RXENA)) { + if (!FIELD_EX32(s->regs[R_NWCTRL], NWCTRL, ENABLE_RECEIVE)) { if (s->can_rx_state != 1) { s->can_rx_state = 1; DB_PRINT("can't receive - no enable\n"); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) int q = 0; /* Do nothing if transmit is not enabled. */ - if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_TXENA)) { + if (!FIELD_EX32(s->regs[R_NWCTRL], NWCTRL, ENABLE_TRANSMIT)) { return; } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) while (tx_desc_get_used(desc) == 0) { /* Do nothing if transmit is not enabled. */ - if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_TXENA)) { + if (!FIELD_EX32(s->regs[R_NWCTRL], NWCTRL, ENABLE_TRANSMIT)) { return; } print_gem_tx_desc(desc, q); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) gem_transmit_updatestats(s, s->tx_packet, total_bytes); /* Send the packet somewhere */ - if (s->phy_loop || (s->regs[R_NWCTRL] & - GEM_NWCTRL_LOCALLOOP)) { + if (s->phy_loop || FIELD_EX32(s->regs[R_NWCTRL], NWCTRL, + LOOPBACK_LOCAL)) { qemu_receive_packet(qemu_get_queue(s->nic), s->tx_packet, total_bytes); } else { @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, /* Handle register write side effects */ switch (offset) { case R_NWCTRL: - if (val & GEM_NWCTRL_RXENA) { + if (FIELD_EX32(val, NWCTRL, ENABLE_RECEIVE)) { for (i = 0; i < s->num_priority_queues; ++i) { gem_get_rx_desc(s, i); } } - if (val & GEM_NWCTRL_TXSTART) { + if (FIELD_EX32(val, NWCTRL, TRANSMIT_START)) { gem_transmit(s); } - if (!(val & GEM_NWCTRL_TXENA)) { + if (!(FIELD_EX32(val, NWCTRL, ENABLE_TRANSMIT))) { /* Reset to start of Q when transmit disabled. */ for (i = 0; i < s->num_priority_queues; i++) { s->tx_desc_addr[i] = gem_get_tx_queue_base_addr(s, i); -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use de FIELD macro to describe the NWCFG register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-5-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 60 ++++++++++++++++++++++++++++---------------- 1 file changed, 39 insertions(+), 21 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(NWCTRL, 0x0) /* Network Control reg */ FIELD(NWCTRL, IFG_EATS_QAV_CREDIT, 30, 1) REG32(NWCFG, 0x4) /* Network Config reg */ + FIELD(NWCFG, SPEED, 0, 1) + FIELD(NWCFG, FULL_DUPLEX, 1, 1) + FIELD(NWCFG, DISCARD_NON_VLAN_FRAMES, 2, 1) + FIELD(NWCFG, JUMBO_FRAMES, 3, 1) + FIELD(NWCFG, PROMISC, 4, 1) + FIELD(NWCFG, NO_BROADCAST, 5, 1) + FIELD(NWCFG, MULTICAST_HASH_EN, 6, 1) + FIELD(NWCFG, UNICAST_HASH_EN, 7, 1) + FIELD(NWCFG, RECV_1536_BYTE_FRAMES, 8, 1) + FIELD(NWCFG, EXTERNAL_ADDR_MATCH_EN, 9, 1) + FIELD(NWCFG, GIGABIT_MODE_ENABLE, 10, 1) + FIELD(NWCFG, PCS_SELECT, 11, 1) + FIELD(NWCFG, RETRY_TEST, 12, 1) + FIELD(NWCFG, PAUSE_ENABLE, 13, 1) + FIELD(NWCFG, RECV_BUF_OFFSET, 14, 2) + FIELD(NWCFG, LEN_ERR_DISCARD, 16, 1) + FIELD(NWCFG, FCS_REMOVE, 17, 1) + FIELD(NWCFG, MDC_CLOCK_DIV, 18, 3) + FIELD(NWCFG, DATA_BUS_WIDTH, 21, 2) + FIELD(NWCFG, DISABLE_COPY_PAUSE_FRAMES, 23, 1) + FIELD(NWCFG, RECV_CSUM_OFFLOAD_EN, 24, 1) + FIELD(NWCFG, EN_HALF_DUPLEX_RX, 25, 1) + FIELD(NWCFG, IGNORE_RX_FCS, 26, 1) + FIELD(NWCFG, SGMII_MODE_ENABLE, 27, 1) + FIELD(NWCFG, IPG_STRETCH_ENABLE, 28, 1) + FIELD(NWCFG, NSP_ACCEPT, 29, 1) + FIELD(NWCFG, IGNORE_IPG_RX_ER, 30, 1) + FIELD(NWCFG, UNI_DIRECTION_ENABLE, 31, 1) + REG32(NWSTATUS, 0x8) /* Network Status reg */ REG32(USERIO, 0xc) /* User IO reg */ REG32(DMACFG, 0x10) /* DMA Control reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_VLAN_ID, 10, 1) /*****************************************/ -#define GEM_NWCFG_STRIP_FCS 0x00020000 /* Strip FCS field */ -#define GEM_NWCFG_LERR_DISC 0x00010000 /* Discard RX frames with len err */ -#define GEM_NWCFG_BUFF_OFST_M 0x0000C000 /* Receive buffer offset mask */ -#define GEM_NWCFG_BUFF_OFST_S 14 /* Receive buffer offset shift */ -#define GEM_NWCFG_RCV_1538 0x00000100 /* Receive 1538 bytes frame */ -#define GEM_NWCFG_UCAST_HASH 0x00000080 /* accept unicast if hash match */ -#define GEM_NWCFG_MCAST_HASH 0x00000040 /* accept multicast if hash match */ -#define GEM_NWCFG_BCAST_REJ 0x00000020 /* Reject broadcast packets */ -#define GEM_NWCFG_PROMISC 0x00000010 /* Accept all packets */ -#define GEM_NWCFG_JUMBO_FRAME 0x00000008 /* Jumbo Frames enable */ - #define GEM_DMACFG_ADDR_64B (1U << 30) #define GEM_DMACFG_TX_BD_EXT (1U << 29) #define GEM_DMACFG_RX_BD_EXT (1U << 28) @@ -XXX,XX +XXX,XX @@ static const uint8_t broadcast_addr[] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) { uint32_t size; - if (s->regs[R_NWCFG] & GEM_NWCFG_JUMBO_FRAME) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, JUMBO_FRAMES)) { size = s->regs[R_JUMBO_MAX_LEN]; if (size > s->jumbo_max_len) { size = s->jumbo_max_len; @@ -XXX,XX +XXX,XX @@ static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) } else if (tx) { size = 1518; } else { - size = s->regs[R_NWCFG] & GEM_NWCFG_RCV_1538 ? 1538 : 1518; + size = FIELD_EX32(s->regs[R_NWCFG], + NWCFG, RECV_1536_BYTE_FRAMES) ? 1538 : 1518; } return size; } @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) int i, is_mc; /* Promiscuous mode? */ - if (s->regs[R_NWCFG] & GEM_NWCFG_PROMISC) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, PROMISC)) { return GEM_RX_PROMISCUOUS_ACCEPT; } if (!memcmp(packet, broadcast_addr, 6)) { /* Reject broadcast packets? */ - if (s->regs[R_NWCFG] & GEM_NWCFG_BCAST_REJ) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, NO_BROADCAST)) { return GEM_RX_REJECT; } return GEM_RX_BROADCAST_ACCEPT; @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) /* Accept packets -w- hash match? */ is_mc = is_multicast_ether_addr(packet); - if ((is_mc && (s->regs[R_NWCFG] & GEM_NWCFG_MCAST_HASH)) || - (!is_mc && (s->regs[R_NWCFG] & GEM_NWCFG_UCAST_HASH))) { + if ((is_mc && (FIELD_EX32(s->regs[R_NWCFG], NWCFG, MULTICAST_HASH_EN))) || + (!is_mc && FIELD_EX32(s->regs[R_NWCFG], NWCFG, UNICAST_HASH_EN))) { uint64_t buckets; unsigned hash_index; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) } /* Discard packets with receive length error enabled ? */ - if (s->regs[R_NWCFG] & GEM_NWCFG_LERR_DISC) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, LEN_ERR_DISCARD)) { unsigned type_len; /* Fish the ethertype / length field out of the RX packet */ @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* * Determine configured receive buffer offset (probably 0) */ - rxbuf_offset = (s->regs[R_NWCFG] & GEM_NWCFG_BUFF_OFST_M) >> - GEM_NWCFG_BUFF_OFST_S; + rxbuf_offset = FIELD_EX32(s->regs[R_NWCFG], NWCFG, RECV_BUF_OFFSET); /* The configure size of each receive buffer. Determines how many * buffers needed to hold this packet. @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) } /* Strip of FCS field ? (usually yes) */ - if (s->regs[R_NWCFG] & GEM_NWCFG_STRIP_FCS) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, FCS_REMOVE)) { rxbuf_ptr = (void *)buf; } else { unsigned crc_val; -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use de FIELD macro to describe the DMACFG register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-6-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 48 ++++++++++++++++++++++++++++---------------- 1 file changed, 31 insertions(+), 17 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(NWCFG, 0x4) /* Network Config reg */ REG32(NWSTATUS, 0x8) /* Network Status reg */ REG32(USERIO, 0xc) /* User IO reg */ + REG32(DMACFG, 0x10) /* DMA Control reg */ + FIELD(DMACFG, SEND_BCAST_TO_ALL_QS, 31, 1) + FIELD(DMACFG, DMA_ADDR_BUS_WIDTH, 30, 1) + FIELD(DMACFG, TX_BD_EXT_MODE_EN , 29, 1) + FIELD(DMACFG, RX_BD_EXT_MODE_EN , 28, 1) + FIELD(DMACFG, FORCE_MAX_AMBA_BURST_TX, 26, 1) + FIELD(DMACFG, FORCE_MAX_AMBA_BURST_RX, 25, 1) + FIELD(DMACFG, FORCE_DISCARD_ON_ERR, 24, 1) + FIELD(DMACFG, RX_BUF_SIZE, 16, 8) + FIELD(DMACFG, CRC_ERROR_REPORT, 13, 1) + FIELD(DMACFG, INF_LAST_DBUF_SIZE_EN, 12, 1) + FIELD(DMACFG, TX_PBUF_CSUM_OFFLOAD, 11, 1) + FIELD(DMACFG, TX_PBUF_SIZE, 10, 1) + FIELD(DMACFG, RX_PBUF_SIZE, 8, 2) + FIELD(DMACFG, ENDIAN_SWAP_PACKET, 7, 1) + FIELD(DMACFG, ENDIAN_SWAP_MGNT, 6, 1) + FIELD(DMACFG, HDR_DATA_SPLIT_EN, 5, 1) + FIELD(DMACFG, AMBA_BURST_LEN , 0, 5) +#define GEM_DMACFG_RBUFSZ_MUL 64 /* DMA RX Buffer Size multiplier */ + REG32(TXSTATUS, 0x14) /* TX Status reg */ REG32(RXQBASE, 0x18) /* RX Q Base address reg */ REG32(TXQBASE, 0x1c) /* TX Q Base address reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_VLAN_ID, 10, 1) /*****************************************/ -#define GEM_DMACFG_ADDR_64B (1U << 30) -#define GEM_DMACFG_TX_BD_EXT (1U << 29) -#define GEM_DMACFG_RX_BD_EXT (1U << 28) -#define GEM_DMACFG_RBUFSZ_M 0x00FF0000 /* DMA RX Buffer Size mask */ -#define GEM_DMACFG_RBUFSZ_S 16 /* DMA RX Buffer Size shift */ -#define GEM_DMACFG_RBUFSZ_MUL 64 /* DMA RX Buffer Size multiplier */ -#define GEM_DMACFG_TXCSUM_OFFL 0x00000800 /* Transmit checksum offload */ #define GEM_TXSTATUS_TXCMPL 0x00000020 /* Transmit Complete */ #define GEM_TXSTATUS_USED 0x00000001 /* sw owned descriptor encountered */ @@ -XXX,XX +XXX,XX @@ static inline uint64_t tx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc) { uint64_t ret = desc[0]; - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { ret |= (uint64_t)desc[2] << 32; } return ret; @@ -XXX,XX +XXX,XX @@ static inline uint64_t rx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc) { uint64_t ret = desc[0] & ~0x3UL; - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { ret |= (uint64_t)desc[2] << 32; } return ret; @@ -XXX,XX +XXX,XX @@ static inline int gem_get_desc_len(CadenceGEMState *s, bool rx_n_tx) { int ret = 2; - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { ret += 2; } - if (s->regs[R_DMACFG] & (rx_n_tx ? GEM_DMACFG_RX_BD_EXT - : GEM_DMACFG_TX_BD_EXT)) { + if (s->regs[R_DMACFG] & (rx_n_tx ? R_DMACFG_RX_BD_EXT_MODE_EN_MASK + : R_DMACFG_TX_BD_EXT_MODE_EN_MASK)) { ret += 2; } @@ -XXX,XX +XXX,XX @@ static hwaddr gem_get_desc_addr(CadenceGEMState *s, bool tx, int q) { hwaddr desc_addr = 0; - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { desc_addr = s->regs[tx ? R_TBQPH : R_RBQPH]; } desc_addr <<= 32; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* The configure size of each receive buffer. Determines how many * buffers needed to hold this packet. */ - rxbufsize = ((s->regs[R_DMACFG] & GEM_DMACFG_RBUFSZ_M) >> - GEM_DMACFG_RBUFSZ_S) * GEM_DMACFG_RBUFSZ_MUL; + rxbufsize = FIELD_EX32(s->regs[R_DMACFG], DMACFG, RX_BUF_SIZE); + rxbufsize *= GEM_DMACFG_RBUFSZ_MUL; + bytes_to_copy = size; /* Hardware allows a zero value here but warns against it. To avoid QEMU @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) gem_update_int_status(s); /* Is checksum offload enabled? */ - if (s->regs[R_DMACFG] & GEM_DMACFG_TXCSUM_OFFL) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, TX_PBUF_CSUM_OFFLOAD)) { net_checksum_calculate(s->tx_packet, total_bytes, CSUM_ALL); } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) /* read next descriptor */ if (tx_desc_get_wrap(desc)) { - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { packet_desc_addr = s->regs[R_TBQPH]; packet_desc_addr <<= 32; } else { -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use de FIELD macro to describe the TXSTATUS and RXSTATUS register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-7-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 34 +++++++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 9 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(DMACFG, 0x10) /* DMA Control reg */ #define GEM_DMACFG_RBUFSZ_MUL 64 /* DMA RX Buffer Size multiplier */ REG32(TXSTATUS, 0x14) /* TX Status reg */ + FIELD(TXSTATUS, TX_USED_BIT_READ_MIDFRAME, 12, 1) + FIELD(TXSTATUS, TX_FRAME_TOO_LARGE, 11, 1) + FIELD(TXSTATUS, TX_DMA_LOCKUP, 10, 1) + FIELD(TXSTATUS, TX_MAC_LOCKUP, 9, 1) + FIELD(TXSTATUS, RESP_NOT_OK, 8, 1) + FIELD(TXSTATUS, LATE_COLLISION, 7, 1) + FIELD(TXSTATUS, TRANSMIT_UNDER_RUN, 6, 1) + FIELD(TXSTATUS, TRANSMIT_COMPLETE, 5, 1) + FIELD(TXSTATUS, AMBA_ERROR, 4, 1) + FIELD(TXSTATUS, TRANSMIT_GO, 3, 1) + FIELD(TXSTATUS, RETRY_LIMIT, 2, 1) + FIELD(TXSTATUS, COLLISION, 1, 1) + FIELD(TXSTATUS, USED_BIT_READ, 0, 1) + REG32(RXQBASE, 0x18) /* RX Q Base address reg */ REG32(TXQBASE, 0x1c) /* TX Q Base address reg */ REG32(RXSTATUS, 0x20) /* RX Status reg */ + FIELD(RXSTATUS, RX_DMA_LOCKUP, 5, 1) + FIELD(RXSTATUS, RX_MAC_LOCKUP, 4, 1) + FIELD(RXSTATUS, RESP_NOT_OK, 3, 1) + FIELD(RXSTATUS, RECEIVE_OVERRUN, 2, 1) + FIELD(RXSTATUS, FRAME_RECEIVED, 1, 1) + FIELD(RXSTATUS, BUF_NOT_AVAILABLE, 0, 1) + REG32(ISR, 0x24) /* Interrupt Status reg */ REG32(IER, 0x28) /* Interrupt Enable reg */ REG32(IDR, 0x2c) /* Interrupt Disable reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) /*****************************************/ -#define GEM_TXSTATUS_TXCMPL 0x00000020 /* Transmit Complete */ -#define GEM_TXSTATUS_USED 0x00000001 /* sw owned descriptor encountered */ - -#define GEM_RXSTATUS_FRMRCVD 0x00000002 /* Frame received */ -#define GEM_RXSTATUS_NOBUF 0x00000001 /* Buffer unavailable */ /* GEM_ISR GEM_IER GEM_IDR GEM_IMR */ #define GEM_INT_TXCMPL 0x00000080 /* Transmit Complete */ @@ -XXX,XX +XXX,XX @@ static void gem_get_rx_desc(CadenceGEMState *s, int q) /* Descriptor owned by software ? */ if (rx_desc_get_ownership(s->rx_desc[q]) == 1) { DB_PRINT("descriptor 0x%" HWADDR_PRIx " owned by sw.\n", desc_addr); - s->regs[R_RXSTATUS] |= GEM_RXSTATUS_NOBUF; + s->regs[R_RXSTATUS] |= R_RXSTATUS_BUF_NOT_AVAILABLE_MASK; gem_set_isr(s, q, GEM_INT_RXUSED); /* Handle interrupt consequences */ gem_update_int_status(s); @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* Count it */ gem_receive_updatestats(s, buf, size); - s->regs[R_RXSTATUS] |= GEM_RXSTATUS_FRMRCVD; + s->regs[R_RXSTATUS] |= R_RXSTATUS_FRAME_RECEIVED_MASK; gem_set_isr(s, q, GEM_INT_RXCMPL); /* Handle interrupt consequences */ @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) } DB_PRINT("TX descriptor next: 0x%08x\n", s->tx_desc_addr[q]); - s->regs[R_TXSTATUS] |= GEM_TXSTATUS_TXCMPL; + s->regs[R_TXSTATUS] |= R_TXSTATUS_TRANSMIT_COMPLETE_MASK; gem_set_isr(s, q, GEM_INT_TXCMPL); /* Handle interrupt consequences */ @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) } if (tx_desc_get_used(desc)) { - s->regs[R_TXSTATUS] |= GEM_TXSTATUS_USED; + s->regs[R_TXSTATUS] |= R_TXSTATUS_USED_BIT_READ_MASK; /* IRQ TXUSED is defined only for queue 0 */ if (q == 0) { gem_set_isr(s, 0, GEM_INT_TXUSED); -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use de FIELD macro to describe the IRQ related register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-8-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 51 +++++++++++++++++++++++++++++++++----------- 1 file changed, 39 insertions(+), 12 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(RXSTATUS, 0x20) /* RX Status reg */ FIELD(RXSTATUS, BUF_NOT_AVAILABLE, 0, 1) REG32(ISR, 0x24) /* Interrupt Status reg */ + FIELD(ISR, TX_LOCKUP, 31, 1) + FIELD(ISR, RX_LOCKUP, 30, 1) + FIELD(ISR, TSU_TIMER, 29, 1) + FIELD(ISR, WOL, 28, 1) + FIELD(ISR, RECV_LPI, 27, 1) + FIELD(ISR, TSU_SEC_INCR, 26, 1) + FIELD(ISR, PTP_PDELAY_RESP_XMIT, 25, 1) + FIELD(ISR, PTP_PDELAY_REQ_XMIT, 24, 1) + FIELD(ISR, PTP_PDELAY_RESP_RECV, 23, 1) + FIELD(ISR, PTP_PDELAY_REQ_RECV, 22, 1) + FIELD(ISR, PTP_SYNC_XMIT, 21, 1) + FIELD(ISR, PTP_DELAY_REQ_XMIT, 20, 1) + FIELD(ISR, PTP_SYNC_RECV, 19, 1) + FIELD(ISR, PTP_DELAY_REQ_RECV, 18, 1) + FIELD(ISR, PCS_LP_PAGE_RECV, 17, 1) + FIELD(ISR, PCS_AN_COMPLETE, 16, 1) + FIELD(ISR, EXT_IRQ, 15, 1) + FIELD(ISR, PAUSE_FRAME_XMIT, 14, 1) + FIELD(ISR, PAUSE_TIME_ELAPSED, 13, 1) + FIELD(ISR, PAUSE_FRAME_RECV, 12, 1) + FIELD(ISR, RESP_NOT_OK, 11, 1) + FIELD(ISR, RECV_OVERRUN, 10, 1) + FIELD(ISR, LINK_CHANGE, 9, 1) + FIELD(ISR, USXGMII_INT, 8, 1) + FIELD(ISR, XMIT_COMPLETE, 7, 1) + FIELD(ISR, AMBA_ERROR, 6, 1) + FIELD(ISR, RETRY_EXCEEDED, 5, 1) + FIELD(ISR, XMIT_UNDER_RUN, 4, 1) + FIELD(ISR, TX_USED, 3, 1) + FIELD(ISR, RX_USED, 2, 1) + FIELD(ISR, RECV_COMPLETE, 1, 1) + FIELD(ISR, MGNT_FRAME_SENT, 0, 1) REG32(IER, 0x28) /* Interrupt Enable reg */ REG32(IDR, 0x2c) /* Interrupt Disable reg */ REG32(IMR, 0x30) /* Interrupt Mask reg */ + REG32(PHYMNTNC, 0x34) /* Phy Maintenance reg */ REG32(RXPAUSE, 0x38) /* RX Pause Time reg */ REG32(TXPAUSE, 0x3c) /* TX Pause Time reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) /*****************************************/ -/* GEM_ISR GEM_IER GEM_IDR GEM_IMR */ -#define GEM_INT_TXCMPL 0x00000080 /* Transmit Complete */ -#define GEM_INT_AMBA_ERR 0x00000040 -#define GEM_INT_TXUSED 0x00000008 -#define GEM_INT_RXUSED 0x00000004 -#define GEM_INT_RXCMPL 0x00000002 #define GEM_PHYMNTNC_OP_R 0x20000000 /* read operation */ #define GEM_PHYMNTNC_OP_W 0x10000000 /* write operation */ @@ -XXX,XX +XXX,XX @@ static void gem_get_rx_desc(CadenceGEMState *s, int q) if (rx_desc_get_ownership(s->rx_desc[q]) == 1) { DB_PRINT("descriptor 0x%" HWADDR_PRIx " owned by sw.\n", desc_addr); s->regs[R_RXSTATUS] |= R_RXSTATUS_BUF_NOT_AVAILABLE_MASK; - gem_set_isr(s, q, GEM_INT_RXUSED); + gem_set_isr(s, q, R_ISR_RX_USED_MASK); /* Handle interrupt consequences */ gem_update_int_status(s); } @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) if (size > gem_get_max_buf_len(s, false)) { qemu_log_mask(LOG_GUEST_ERROR, "rx frame too long\n"); - gem_set_isr(s, q, GEM_INT_AMBA_ERR); + gem_set_isr(s, q, R_ISR_AMBA_ERROR_MASK); return -1; } @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) gem_receive_updatestats(s, buf, size); s->regs[R_RXSTATUS] |= R_RXSTATUS_FRAME_RECEIVED_MASK; - gem_set_isr(s, q, GEM_INT_RXCMPL); + gem_set_isr(s, q, R_ISR_RECV_COMPLETE_MASK); /* Handle interrupt consequences */ gem_update_int_status(s); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) HWADDR_PRIx " too large: size 0x%x space 0x%zx\n", packet_desc_addr, tx_desc_get_length(desc), gem_get_max_buf_len(s, true) - (p - s->tx_packet)); - gem_set_isr(s, q, GEM_INT_AMBA_ERR); + gem_set_isr(s, q, R_ISR_AMBA_ERROR_MASK); break; } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) DB_PRINT("TX descriptor next: 0x%08x\n", s->tx_desc_addr[q]); s->regs[R_TXSTATUS] |= R_TXSTATUS_TRANSMIT_COMPLETE_MASK; - gem_set_isr(s, q, GEM_INT_TXCMPL); + gem_set_isr(s, q, R_ISR_XMIT_COMPLETE_MASK); /* Handle interrupt consequences */ gem_update_int_status(s); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) s->regs[R_TXSTATUS] |= R_TXSTATUS_USED_BIT_READ_MASK; /* IRQ TXUSED is defined only for queue 0 */ if (q == 0) { - gem_set_isr(s, 0, GEM_INT_TXUSED); + gem_set_isr(s, 0, R_ISR_TX_USED_MASK); } gem_update_int_status(s); } -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use the FIELD macro to describe the DESCONF6 register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20231017194422.4124691-9-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(DESCONF3, 0x288) REG32(DESCONF4, 0x28c) REG32(DESCONF5, 0x290) REG32(DESCONF6, 0x294) -#define GEM_DESCONF6_64B_MASK (1U << 23) + FIELD(DESCONF6, DMA_ADDR_64B, 23, 1) REG32(DESCONF7, 0x298) REG32(INT_Q1_STATUS, 0x400) @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) s->regs[R_DESCONF] = 0x02D00111; s->regs[R_DESCONF2] = 0x2ab10000 | s->jumbo_max_len; s->regs[R_DESCONF5] = 0x002f2045; - s->regs[R_DESCONF6] = GEM_DESCONF6_64B_MASK; + s->regs[R_DESCONF6] = R_DESCONF6_DMA_ADDR_64B_MASK; s->regs[R_INT_Q1_MASK] = 0x00000CE6; s->regs[R_JUMBO_MAX_LEN] = s->jumbo_max_len; -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use the FIELD macro to describe the PHYMNTNC register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-10-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(IDR, 0x2c) /* Interrupt Disable reg */ REG32(IMR, 0x30) /* Interrupt Mask reg */ REG32(PHYMNTNC, 0x34) /* Phy Maintenance reg */ + FIELD(PHYMNTNC, DATA, 0, 16) + FIELD(PHYMNTNC, REG_ADDR, 18, 5) + FIELD(PHYMNTNC, PHY_ADDR, 23, 5) + FIELD(PHYMNTNC, OP, 28, 2) + FIELD(PHYMNTNC, ST, 30, 2) +#define MDIO_OP_READ 0x3 +#define MDIO_OP_WRITE 0x2 + REG32(RXPAUSE, 0x38) /* RX Pause Time reg */ REG32(TXPAUSE, 0x3c) /* TX Pause Time reg */ REG32(TXPARTIALSF, 0x40) /* TX Partial Store and Forward */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) -#define GEM_PHYMNTNC_OP_R 0x20000000 /* read operation */ -#define GEM_PHYMNTNC_OP_W 0x10000000 /* write operation */ -#define GEM_PHYMNTNC_ADDR 0x0F800000 /* Address bits */ -#define GEM_PHYMNTNC_ADDR_SHFT 23 -#define GEM_PHYMNTNC_REG 0x007C0000 /* register bits */ -#define GEM_PHYMNTNC_REG_SHIFT 18 - /* Marvell PHY definitions */ #define BOARD_PHY_ADDRESS 0 /* PHY address we will emulate a device at */ @@ -XXX,XX +XXX,XX @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size) /* The interrupts get updated at the end of the function. */ break; case R_PHYMNTNC: - if (retval & GEM_PHYMNTNC_OP_R) { + if (FIELD_EX32(retval, PHYMNTNC, OP) == MDIO_OP_READ) { uint32_t phy_addr, reg_num; - phy_addr = (retval & GEM_PHYMNTNC_ADDR) >> GEM_PHYMNTNC_ADDR_SHFT; + phy_addr = FIELD_EX32(retval, PHYMNTNC, PHY_ADDR); if (phy_addr == s->phy_addr) { - reg_num = (retval & GEM_PHYMNTNC_REG) >> GEM_PHYMNTNC_REG_SHIFT; + reg_num = FIELD_EX32(retval, PHYMNTNC, REG_ADDR); retval &= 0xFFFF0000; retval |= gem_phy_read(s, reg_num); } else { @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, s->sar_active[(offset - R_SPADDR1HI) / 2] = true; break; case R_PHYMNTNC: - if (val & GEM_PHYMNTNC_OP_W) { + if (FIELD_EX32(val, PHYMNTNC, OP) == MDIO_OP_WRITE) { uint32_t phy_addr, reg_num; - phy_addr = (val & GEM_PHYMNTNC_ADDR) >> GEM_PHYMNTNC_ADDR_SHFT; + phy_addr = FIELD_EX32(val, PHYMNTNC, PHY_ADDR); if (phy_addr == s->phy_addr) { - reg_num = (val & GEM_PHYMNTNC_REG) >> GEM_PHYMNTNC_REG_SHIFT; + reg_num = FIELD_EX32(val, PHYMNTNC, REG_ADDR); gem_phy_write(s, reg_num, val); } } -- 2.34.1 From: Luc Michel <luc.michel@amd.com> The MDIO access is done only on a write to the PHYMNTNC register. A subsequent read is used to retrieve the result but does not trigger an MDIO access by itself. Refactor the PHY access logic to perform all accesses (MDIO reads and writes) at PHYMNTNC write time. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-11-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 56 ++++++++++++++++++++++++++------------------ 1 file changed, 33 insertions(+), 23 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static void gem_phy_write(CadenceGEMState *s, unsigned reg_num, uint16_t val) s->phy_regs[reg_num] = val; } +static void gem_handle_phy_access(CadenceGEMState *s) +{ + uint32_t val = s->regs[R_PHYMNTNC]; + uint32_t phy_addr, reg_num; + + phy_addr = FIELD_EX32(val, PHYMNTNC, PHY_ADDR); + + if (phy_addr != s->phy_addr) { + /* no phy at this address */ + if (FIELD_EX32(val, PHYMNTNC, OP) == MDIO_OP_READ) { + s->regs[R_PHYMNTNC] = FIELD_DP32(val, PHYMNTNC, DATA, 0xffff); + } + return; + } + + reg_num = FIELD_EX32(val, PHYMNTNC, REG_ADDR); + + switch (FIELD_EX32(val, PHYMNTNC, OP)) { + case MDIO_OP_READ: + s->regs[R_PHYMNTNC] = FIELD_DP32(val, PHYMNTNC, DATA, + gem_phy_read(s, reg_num)); + break; + + case MDIO_OP_WRITE: + gem_phy_write(s, reg_num, val); + break; + + default: + break; /* only clause 22 operations are supported */ + } +} + /* * gem_read32: * Read a GEM register. @@ -XXX,XX +XXX,XX @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size) DB_PRINT("lowering irqs on ISR read\n"); /* The interrupts get updated at the end of the function. */ break; - case R_PHYMNTNC: - if (FIELD_EX32(retval, PHYMNTNC, OP) == MDIO_OP_READ) { - uint32_t phy_addr, reg_num; - - phy_addr = FIELD_EX32(retval, PHYMNTNC, PHY_ADDR); - if (phy_addr == s->phy_addr) { - reg_num = FIELD_EX32(retval, PHYMNTNC, REG_ADDR); - retval &= 0xFFFF0000; - retval |= gem_phy_read(s, reg_num); - } else { - retval |= 0xFFFF; /* No device at this address */ - } - } - break; } /* Squash read to clear bits */ @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, s->sar_active[(offset - R_SPADDR1HI) / 2] = true; break; case R_PHYMNTNC: - if (FIELD_EX32(val, PHYMNTNC, OP) == MDIO_OP_WRITE) { - uint32_t phy_addr, reg_num; - - phy_addr = FIELD_EX32(val, PHYMNTNC, PHY_ADDR); - if (phy_addr == s->phy_addr) { - reg_num = FIELD_EX32(val, PHYMNTNC, REG_ADDR); - gem_phy_write(s, reg_num, val); - } - } + gem_handle_phy_access(s); break; } -- 2.34.1 From: Luc Michel <luc.michel@amd.com> The CRC was stored in an unsigned variable in gem_receive. Change it for a uint32_t to ensure we have the correct variable size here. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-12-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, FCS_REMOVE)) { rxbuf_ptr = (void *)buf; } else { - unsigned crc_val; + uint32_t crc_val; if (size > MAX_FRAME_SIZE - sizeof(crc_val)) { size = MAX_FRAME_SIZE - sizeof(crc_val); -- 2.34.1