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 The following changes since commit 64ada298b98a51eb2512607f6e6180cb330c47b1: Merge remote-tracking branch 'remotes/legoater/tags/pull-ppc-20220302' into staging (2022-03-02 12:38:46 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20220302 for you to fetch changes up to 268c11984e67867c22f53beb3c7f8b98900d66b2: ui/cocoa.m: Remove unnecessary NSAutoreleasePools (2022-03-02 19:27:37 +0000) ---------------------------------------------------------------- target-arm queue: * mps3-an547: Add missing user ahb interfaces * hw/arm/mps2-tz.c: Update AN547 documentation URL * hw/input/tsc210x: Don't abort on bad SPI word widths * hw/i2c: flatten pca954x mux device * target/arm: Support PSCI 1.1 and SMCCC 1.0 * target/arm: Fix early free of TCG temp in handle_simd_shift_fpint_conv() * tests/qtest: add qtests for npcm7xx sdhci * Implement FEAT_LVA * Implement FEAT_LPA * Implement FEAT_LPA2 (but do not enable it yet) * Report KVM's actual PSCI version to guest in dtb * ui/cocoa.m: Fix updateUIInfo threading issues * ui/cocoa.m: Remove unnecessary NSAutoreleasePools ---------------------------------------------------------------- Akihiko Odaki (1): target/arm: Support PSCI 1.1 and SMCCC 1.0 Jimmy Brisson (1): mps3-an547: Add missing user ahb interfaces Patrick Venture (1): hw/i2c: flatten pca954x mux device Peter Maydell (5): hw/arm/mps2-tz.c: Update AN547 documentation URL hw/input/tsc210x: Don't abort on bad SPI word widths target/arm: Report KVM's actual PSCI version to guest in dtb ui/cocoa.m: Fix updateUIInfo threading issues ui/cocoa.m: Remove unnecessary NSAutoreleasePools Richard Henderson (16): hw/registerfields: Add FIELD_SEX<N> and FIELD_SDP<N> target/arm: Set TCR_EL1.TSZ for user-only target/arm: Fault on invalid TCR_ELx.TxSZ target/arm: Move arm_pamax out of line target/arm: Pass outputsize down to check_s2_mmu_setup target/arm: Use MAKE_64BIT_MASK to compute indexmask target/arm: Honor TCR_ELx.{I}PS target/arm: Prepare DBGBVR and DBGWVR for FEAT_LVA target/arm: Implement FEAT_LVA target/arm: Implement FEAT_LPA target/arm: Extend arm_fi_to_lfsc to level -1 target/arm: Introduce tlbi_aa64_get_range target/arm: Fix TLBIRange.base for 16k and 64k pages target/arm: Validate tlbi TG matches translation granule in use target/arm: Advertise all page sizes for -cpu max target/arm: Implement FEAT_LPA2 Shengtan Mao (1): tests/qtest: add qtests for npcm7xx sdhci Wentao_Liang (1): target/arm: Fix early free of TCG temp in handle_simd_shift_fpint_conv() docs/system/arm/emulation.rst | 3 + include/hw/registerfields.h | 48 +++++- target/arm/cpu-param.h | 4 +- target/arm/cpu.h | 27 ++++ target/arm/internals.h | 58 ++++--- target/arm/kvm-consts.h | 14 +- hw/arm/boot.c | 11 +- hw/arm/mps2-tz.c | 6 +- hw/i2c/i2c_mux_pca954x.c | 77 ++------- hw/input/tsc210x.c | 8 +- target/arm/cpu.c | 8 +- target/arm/cpu64.c | 7 +- target/arm/helper.c | 332 ++++++++++++++++++++++++++++++--------- target/arm/hvf/hvf.c | 27 +++- target/arm/kvm64.c | 14 +- target/arm/psci.c | 35 ++++- target/arm/translate-a64.c | 2 +- tests/qtest/npcm7xx_sdhci-test.c | 215 +++++++++++++++++++++++++ tests/qtest/meson.build | 1 + ui/cocoa.m | 31 ++-- 20 files changed, 736 insertions(+), 192 deletions(-) create mode 100644 tests/qtest/npcm7xx_sdhci-test.c From: Jimmy Brisson <jimmy.brisson@linaro.org> With these interfaces missing, TFM would delegate peripherals 0, 1, 2, 3 and 8, and qemu would ignore the delegation of interface 8, as it thought interface 4 was eth & USB. This patch corrects this behavior and allows TFM to delegate the eth & USB peripheral to NS mode. (The old QEMU behaviour was based on revision B of the AN547 appnote; revision C corrects this error in the documentation, and this commit brings QEMU in to line with how the FPGA image really behaves.) Signed-off-by: Jimmy Brisson <jimmy.brisson@linaro.org> Message-id: 20220210210227.3203883-1-jimmy.brisson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: added commit message note clarifying that the old behaviour was a docs issue, not because there were two different versions of the FPGA image] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/mps2-tz.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) { "gpio1", make_unimp_dev, &mms->gpio[1], 0x41101000, 0x1000 }, { "gpio2", make_unimp_dev, &mms->gpio[2], 0x41102000, 0x1000 }, { "gpio3", make_unimp_dev, &mms->gpio[3], 0x41103000, 0x1000 }, + { /* port 4 USER AHB interface 0 */ }, + { /* port 5 USER AHB interface 1 */ }, + { /* port 6 USER AHB interface 2 */ }, + { /* port 7 USER AHB interface 3 */ }, { "eth-usb", make_eth_usb, NULL, 0x41400000, 0x200000, { 49 } }, }, }, -- 2.25.1 The AN547 application note URL has changed: update our comment accordingly. (Rev B is still downloadable from the old URL, but there is a new Rev C of the document now.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20220221094144.426191-1-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ * Application Note AN524: * https://developer.arm.com/documentation/dai0524/latest/ * Application Note AN547: - * https://developer.arm.com/-/media/Arm%20Developer%20Community/PDF/DAI0547B_SSE300_PLUS_U55_FPGA_for_mps3.pdf + * https://developer.arm.com/documentation/dai0547/latest/ * * The AN505 defers to the Cortex-M33 processor ARMv8M IoT Kit FVP User Guide * (ARM ECM0601256) for the details of some of the device layout: -- 2.25.1 The tsc210x doesn't support anything other than 16-bit reads on the SPI bus, but the guest can program the SPI controller to attempt them anyway. If this happens, don't abort QEMU, just log this as a guest error. This fixes our machine_arm_n8x0.py:N8x0Machine.test_n800 acceptance test, which hits this assertion. The reason we hit the assertion is because the guest kernel thinks there is a TSC2005 on this SPI bus address, not a TSC210x. (The n810 *does* have a TSC2005 at this address.) The TSC2005 supports the 24-bit accesses which the guest driver makes, and the TSC210x does not (that is, our TSC210x emulation is not missing support for a word width the hardware can handle). It's not clear whether the problem here is that the guest kernel incorrectly thinks the n800 has the same device at this SPI bus address as the n810, or that QEMU's n810 board model doesn't get the SPI devices right. At this late date there no longer appears to be any reliable information on the web about the hardware behaviour, but I am inclined to think this is a guest kernel bug. In any case, we prefer not to abort QEMU for guest-triggerable conditions, so logging the error is the right thing to do. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/736 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20220221140750.514557-1-peter.maydell@linaro.org --- hw/input/tsc210x.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/hw/input/tsc210x.c b/hw/input/tsc210x.c index XXXXXXX..XXXXXXX 100644 --- a/hw/input/tsc210x.c +++ b/hw/input/tsc210x.c @@ -XXX,XX +XXX,XX @@ #include "hw/hw.h" #include "audio/audio.h" #include "qemu/timer.h" +#include "qemu/log.h" #include "sysemu/reset.h" #include "ui/console.h" #include "hw/arm/omap.h" /* For I2SCodec */ @@ -XXX,XX +XXX,XX @@ uint32_t tsc210x_txrx(void *opaque, uint32_t value, int len) TSC210xState *s = opaque; uint32_t ret = 0; - if (len != 16) - hw_error("%s: FIXME: bad SPI word width %i\n", __func__, len); + if (len != 16) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: bad SPI word width %i\n", __func__, len); + return 0; + } /* TODO: sequential reads etc - how do we make sure the host doesn't * unintentionally read out a conversion result from a register while -- 2.25.1 From: Patrick Venture <venture@google.com> Previously this device created N subdevices which each owned an i2c bus. Now this device simply owns the N i2c busses directly. Tested: Verified devices behind mux are still accessible via qmp and i2c from within an arm32 SoC. Reviewed-by: Hao Wu <wuhaotsh@google.com> Signed-off-by: Patrick Venture <venture@google.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20220202164533.1283668-1-venture@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/i2c_mux_pca954x.c | 77 +++++++--------------------------------- 1 file changed, 13 insertions(+), 64 deletions(-) diff --git a/hw/i2c/i2c_mux_pca954x.c b/hw/i2c/i2c_mux_pca954x.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/i2c_mux_pca954x.c +++ b/hw/i2c/i2c_mux_pca954x.c @@ -XXX,XX +XXX,XX @@ #define PCA9548_CHANNEL_COUNT 8 #define PCA9546_CHANNEL_COUNT 4 -/* - * struct Pca954xChannel - The i2c mux device will have N of these states - * that own the i2c channel bus. - * @bus: The owned channel bus. - * @enabled: Is this channel active? - */ -typedef struct Pca954xChannel { - SysBusDevice parent; - - I2CBus *bus; - - bool enabled; -} Pca954xChannel; - -#define TYPE_PCA954X_CHANNEL "pca954x-channel" -#define PCA954X_CHANNEL(obj) \ - OBJECT_CHECK(Pca954xChannel, (obj), TYPE_PCA954X_CHANNEL) - /* * struct Pca954xState - The pca954x state object. * @control: The value written to the mux control. @@ -XXX,XX +XXX,XX @@ typedef struct Pca954xState { uint8_t control; - /* The channel i2c buses. */ - Pca954xChannel channel[PCA9548_CHANNEL_COUNT]; + bool enabled[PCA9548_CHANNEL_COUNT]; + I2CBus *bus[PCA9548_CHANNEL_COUNT]; } Pca954xState; /* @@ -XXX,XX +XXX,XX @@ static bool pca954x_match(I2CSlave *candidate, uint8_t address, } for (i = 0; i < mc->nchans; i++) { - if (!mux->channel[i].enabled) { + if (!mux->enabled[i]) { continue; } - if (i2c_scan_bus(mux->channel[i].bus, address, broadcast, + if (i2c_scan_bus(mux->bus[i], address, broadcast, current_devs)) { if (!broadcast) { return true; @@ -XXX,XX +XXX,XX @@ static void pca954x_enable_channel(Pca954xState *s, uint8_t enable_mask) */ for (i = 0; i < mc->nchans; i++) { if (enable_mask & (1 << i)) { - s->channel[i].enabled = true; + s->enabled[i] = true; } else { - s->channel[i].enabled = false; + s->enabled[i] = false; } } } @@ -XXX,XX +XXX,XX @@ I2CBus *pca954x_i2c_get_bus(I2CSlave *mux, uint8_t channel) Pca954xState *pca954x = PCA954X(mux); g_assert(channel < pc->nchans); - return I2C_BUS(qdev_get_child_bus(DEVICE(&pca954x->channel[channel]), - "i2c-bus")); -} - -static void pca954x_channel_init(Object *obj) -{ - Pca954xChannel *s = PCA954X_CHANNEL(obj); - s->bus = i2c_init_bus(DEVICE(s), "i2c-bus"); - - /* Start all channels as disabled. */ - s->enabled = false; -} - -static void pca954x_channel_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - dc->desc = "Pca954x Channel"; + return pca954x->bus[channel]; } static void pca9546_class_init(ObjectClass *klass, void *data) @@ -XXX,XX +XXX,XX @@ static void pca9548_class_init(ObjectClass *klass, void *data) s->nchans = PCA9548_CHANNEL_COUNT; } -static void pca954x_realize(DeviceState *dev, Error **errp) -{ - Pca954xState *s = PCA954X(dev); - Pca954xClass *c = PCA954X_GET_CLASS(s); - int i; - - /* SMBus modules. Cannot fail. */ - for (i = 0; i < c->nchans; i++) { - sysbus_realize(SYS_BUS_DEVICE(&s->channel[i]), &error_abort); - } -} - static void pca954x_init(Object *obj) { Pca954xState *s = PCA954X(obj); Pca954xClass *c = PCA954X_GET_CLASS(obj); int i; - /* Only initialize the children we expect. */ + /* SMBus modules. Cannot fail. */ for (i = 0; i < c->nchans; i++) { - object_initialize_child(obj, "channel[*]", &s->channel[i], - TYPE_PCA954X_CHANNEL); + g_autofree gchar *bus_name = g_strdup_printf("i2c.%d", i); + + /* start all channels as disabled. */ + s->enabled[i] = false; + s->bus[i] = i2c_init_bus(DEVICE(s), bus_name); } } @@ -XXX,XX +XXX,XX @@ static void pca954x_class_init(ObjectClass *klass, void *data) rc->phases.enter = pca954x_enter_reset; dc->desc = "Pca954x i2c-mux"; - dc->realize = pca954x_realize; k->write_data = pca954x_write_data; k->receive_byte = pca954x_read_byte; @@ -XXX,XX +XXX,XX @@ static const TypeInfo pca954x_info[] = { .parent = TYPE_PCA954X, .class_init = pca9548_class_init, }, - { - .name = TYPE_PCA954X_CHANNEL, - .parent = TYPE_SYS_BUS_DEVICE, - .class_init = pca954x_channel_class_init, - .instance_size = sizeof(Pca954xChannel), - .instance_init = pca954x_channel_init, - } }; DEFINE_TYPES(pca954x_info) -- 2.25.1 From: Akihiko Odaki <akihiko.odaki@gmail.com> Support the latest PSCI on TCG and HVF. A 64-bit function called from AArch32 now returns NOT_SUPPORTED, which is necessary to adhere to SMC Calling Convention 1.0. It is still not compliant with SMCCC 1.3 since they do not implement mandatory functions. Signed-off-by: Akihiko Odaki <akihiko.odaki@gmail.com> Message-id: 20220213035753.34577-1-akihiko.odaki@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: update MISMATCH_CHECK checks on PSCI_VERSION macros to match] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm-consts.h | 13 +++++++++---- hw/arm/boot.c | 12 +++++++++--- target/arm/cpu.c | 5 +++-- target/arm/hvf/hvf.c | 27 ++++++++++++++++++++++++++- target/arm/kvm64.c | 2 +- target/arm/psci.c | 35 ++++++++++++++++++++++++++++++++--- 6 files changed, 80 insertions(+), 14 deletions(-) diff --git a/target/arm/kvm-consts.h b/target/arm/kvm-consts.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm-consts.h +++ b/target/arm/kvm-consts.h @@ -XXX,XX +XXX,XX @@ MISMATCH_CHECK(QEMU_PSCI_0_1_FN_MIGRATE, KVM_PSCI_FN_MIGRATE); #define QEMU_PSCI_0_2_FN64_AFFINITY_INFO QEMU_PSCI_0_2_FN64(4) #define QEMU_PSCI_0_2_FN64_MIGRATE QEMU_PSCI_0_2_FN64(5) +#define QEMU_PSCI_1_0_FN_PSCI_FEATURES QEMU_PSCI_0_2_FN(10) + MISMATCH_CHECK(QEMU_PSCI_0_2_FN_CPU_SUSPEND, PSCI_0_2_FN_CPU_SUSPEND); MISMATCH_CHECK(QEMU_PSCI_0_2_FN_CPU_OFF, PSCI_0_2_FN_CPU_OFF); MISMATCH_CHECK(QEMU_PSCI_0_2_FN_CPU_ON, PSCI_0_2_FN_CPU_ON); @@ -XXX,XX +XXX,XX @@ MISMATCH_CHECK(QEMU_PSCI_0_2_FN_MIGRATE, PSCI_0_2_FN_MIGRATE); MISMATCH_CHECK(QEMU_PSCI_0_2_FN64_CPU_SUSPEND, PSCI_0_2_FN64_CPU_SUSPEND); MISMATCH_CHECK(QEMU_PSCI_0_2_FN64_CPU_ON, PSCI_0_2_FN64_CPU_ON); MISMATCH_CHECK(QEMU_PSCI_0_2_FN64_MIGRATE, PSCI_0_2_FN64_MIGRATE); +MISMATCH_CHECK(QEMU_PSCI_1_0_FN_PSCI_FEATURES, PSCI_1_0_FN_PSCI_FEATURES); /* PSCI v0.2 return values used by TCG emulation of PSCI */ /* No Trusted OS migration to worry about when offlining CPUs */ #define QEMU_PSCI_0_2_RET_TOS_MIGRATION_NOT_REQUIRED 2 -/* We implement version 0.2 only */ -#define QEMU_PSCI_0_2_RET_VERSION_0_2 2 +#define QEMU_PSCI_VERSION_0_1 0x00001 +#define QEMU_PSCI_VERSION_0_2 0x00002 +#define QEMU_PSCI_VERSION_1_1 0x10001 MISMATCH_CHECK(QEMU_PSCI_0_2_RET_TOS_MIGRATION_NOT_REQUIRED, PSCI_0_2_TOS_MP); -MISMATCH_CHECK(QEMU_PSCI_0_2_RET_VERSION_0_2, - (PSCI_VERSION_MAJOR(0) | PSCI_VERSION_MINOR(2))); +/* We don't bother to check every possible version value */ +MISMATCH_CHECK(QEMU_PSCI_VERSION_0_2, PSCI_VERSION(0, 2)); +MISMATCH_CHECK(QEMU_PSCI_VERSION_1_1, PSCI_VERSION(1, 1)); /* PSCI return values (inclusive of all PSCI versions) */ #define QEMU_PSCI_RET_SUCCESS 0 diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void fdt_add_psci_node(void *fdt) } qemu_fdt_add_subnode(fdt, "/psci"); - if (armcpu->psci_version == 2) { - const char comp[] = "arm,psci-0.2\0arm,psci"; - qemu_fdt_setprop(fdt, "/psci", "compatible", comp, sizeof(comp)); + if (armcpu->psci_version == QEMU_PSCI_VERSION_0_2 || + armcpu->psci_version == QEMU_PSCI_VERSION_1_1) { + if (armcpu->psci_version == QEMU_PSCI_VERSION_0_2) { + const char comp[] = "arm,psci-0.2\0arm,psci"; + qemu_fdt_setprop(fdt, "/psci", "compatible", comp, sizeof(comp)); + } else { + const char comp[] = "arm,psci-1.0\0arm,psci-0.2\0arm,psci"; + qemu_fdt_setprop(fdt, "/psci", "compatible", comp, sizeof(comp)); + } cpu_off_fn = QEMU_PSCI_0_2_FN_CPU_OFF; if (arm_feature(&armcpu->env, ARM_FEATURE_AARCH64)) { diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_initfn(Object *obj) * picky DTB consumer will also provide a helpful error message. */ cpu->dtb_compatible = "qemu,unknown"; - cpu->psci_version = 1; /* By default assume PSCI v0.1 */ + cpu->psci_version = QEMU_PSCI_VERSION_0_1; /* By default assume PSCI v0.1 */ cpu->kvm_target = QEMU_KVM_ARM_TARGET_NONE; if (tcg_enabled() || hvf_enabled()) { - cpu->psci_version = 2; /* TCG and HVF implement PSCI 0.2 */ + /* TCG and HVF implement PSCI 1.1 */ + cpu->psci_version = QEMU_PSCI_VERSION_1_1; } } diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ static bool hvf_handle_psci_call(CPUState *cpu) switch (param[0]) { case QEMU_PSCI_0_2_FN_PSCI_VERSION: - ret = QEMU_PSCI_0_2_RET_VERSION_0_2; + ret = QEMU_PSCI_VERSION_1_1; break; case QEMU_PSCI_0_2_FN_MIGRATE_INFO_TYPE: ret = QEMU_PSCI_0_2_RET_TOS_MIGRATION_NOT_REQUIRED; /* No trusted OS */ @@ -XXX,XX +XXX,XX @@ static bool hvf_handle_psci_call(CPUState *cpu) case QEMU_PSCI_0_2_FN_MIGRATE: ret = QEMU_PSCI_RET_NOT_SUPPORTED; break; + case QEMU_PSCI_1_0_FN_PSCI_FEATURES: + switch (param[1]) { + case QEMU_PSCI_0_2_FN_PSCI_VERSION: + case QEMU_PSCI_0_2_FN_MIGRATE_INFO_TYPE: + case QEMU_PSCI_0_2_FN_AFFINITY_INFO: + case QEMU_PSCI_0_2_FN64_AFFINITY_INFO: + case QEMU_PSCI_0_2_FN_SYSTEM_RESET: + case QEMU_PSCI_0_2_FN_SYSTEM_OFF: + case QEMU_PSCI_0_1_FN_CPU_ON: + case QEMU_PSCI_0_2_FN_CPU_ON: + case QEMU_PSCI_0_2_FN64_CPU_ON: + case QEMU_PSCI_0_1_FN_CPU_OFF: + case QEMU_PSCI_0_2_FN_CPU_OFF: + case QEMU_PSCI_0_1_FN_CPU_SUSPEND: + case QEMU_PSCI_0_2_FN_CPU_SUSPEND: + case QEMU_PSCI_0_2_FN64_CPU_SUSPEND: + case QEMU_PSCI_1_0_FN_PSCI_FEATURES: + ret = 0; + break; + case QEMU_PSCI_0_1_FN_MIGRATE: + case QEMU_PSCI_0_2_FN_MIGRATE: + default: + ret = QEMU_PSCI_RET_NOT_SUPPORTED; + } + break; default: return false; } 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 @@ int kvm_arch_init_vcpu(CPUState *cs) cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_POWER_OFF; } if (kvm_check_extension(cs->kvm_state, KVM_CAP_ARM_PSCI_0_2)) { - cpu->psci_version = 2; + cpu->psci_version = QEMU_PSCI_VERSION_0_2; cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PSCI_0_2; } if (!arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { diff --git a/target/arm/psci.c b/target/arm/psci.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/psci.c +++ b/target/arm/psci.c @@ -XXX,XX +XXX,XX @@ void arm_handle_psci_call(ARMCPU *cpu) { /* * This function partially implements the logic for dispatching Power State - * Coordination Interface (PSCI) calls (as described in ARM DEN 0022B.b), + * Coordination Interface (PSCI) calls (as described in ARM DEN 0022D.b), * to the extent required for bringing up and taking down secondary cores, * and for handling reset and poweroff requests. * Additional information about the calling convention used is available in @@ -XXX,XX +XXX,XX @@ void arm_handle_psci_call(ARMCPU *cpu) } if ((param[0] & QEMU_PSCI_0_2_64BIT) && !is_a64(env)) { - ret = QEMU_PSCI_RET_INVALID_PARAMS; + ret = QEMU_PSCI_RET_NOT_SUPPORTED; goto err; } @@ -XXX,XX +XXX,XX @@ void arm_handle_psci_call(ARMCPU *cpu) ARMCPU *target_cpu; case QEMU_PSCI_0_2_FN_PSCI_VERSION: - ret = QEMU_PSCI_0_2_RET_VERSION_0_2; + ret = QEMU_PSCI_VERSION_1_1; break; case QEMU_PSCI_0_2_FN_MIGRATE_INFO_TYPE: ret = QEMU_PSCI_0_2_RET_TOS_MIGRATION_NOT_REQUIRED; /* No trusted OS */ @@ -XXX,XX +XXX,XX @@ void arm_handle_psci_call(ARMCPU *cpu) } helper_wfi(env, 4); break; + case QEMU_PSCI_1_0_FN_PSCI_FEATURES: + switch (param[1]) { + case QEMU_PSCI_0_2_FN_PSCI_VERSION: + case QEMU_PSCI_0_2_FN_MIGRATE_INFO_TYPE: + case QEMU_PSCI_0_2_FN_AFFINITY_INFO: + case QEMU_PSCI_0_2_FN64_AFFINITY_INFO: + case QEMU_PSCI_0_2_FN_SYSTEM_RESET: + case QEMU_PSCI_0_2_FN_SYSTEM_OFF: + case QEMU_PSCI_0_1_FN_CPU_ON: + case QEMU_PSCI_0_2_FN_CPU_ON: + case QEMU_PSCI_0_2_FN64_CPU_ON: + case QEMU_PSCI_0_1_FN_CPU_OFF: + case QEMU_PSCI_0_2_FN_CPU_OFF: + case QEMU_PSCI_0_1_FN_CPU_SUSPEND: + case QEMU_PSCI_0_2_FN_CPU_SUSPEND: + case QEMU_PSCI_0_2_FN64_CPU_SUSPEND: + case QEMU_PSCI_1_0_FN_PSCI_FEATURES: + if (!(param[1] & QEMU_PSCI_0_2_64BIT) || is_a64(env)) { + ret = 0; + break; + } + /* fallthrough */ + case QEMU_PSCI_0_1_FN_MIGRATE: + case QEMU_PSCI_0_2_FN_MIGRATE: + default: + ret = QEMU_PSCI_RET_NOT_SUPPORTED; + break; + } + break; case QEMU_PSCI_0_1_FN_MIGRATE: case QEMU_PSCI_0_2_FN_MIGRATE: default: -- 2.25.1 From: Wentao_Liang <Wentao_Liang_g@163.com> handle_simd_shift_fpint_conv() was accidentally freeing the TCG temporary tcg_fpstatus too early, before the last use of it. Move the free down to where it belongs. Signed-off-by: Wentao_Liang <Wentao_Liang_g@163.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> [PMM: cleaned up commit message] Signed-off-by: Peter Maydell <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 handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, } } - tcg_temp_free_ptr(tcg_fpstatus); tcg_temp_free_i32(tcg_shift); gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); + tcg_temp_free_ptr(tcg_fpstatus); tcg_temp_free_i32(tcg_rmode); } -- 2.25.1 From: Shengtan Mao <stmao@google.com> Reviewed-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Chris Rauer <crauer@google.com> Signed-off-by: Shengtan Mao <stmao@google.com> Signed-off-by: Patrick Venture <venture@google.com> Message-id: 20220225174451.192304-1-wuhaotsh@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/npcm7xx_sdhci-test.c | 215 +++++++++++++++++++++++++++++++ tests/qtest/meson.build | 1 + 2 files changed, 216 insertions(+) create mode 100644 tests/qtest/npcm7xx_sdhci-test.c diff --git a/tests/qtest/npcm7xx_sdhci-test.c b/tests/qtest/npcm7xx_sdhci-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/npcm7xx_sdhci-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTests for NPCM7xx SD-3.0 / MMC-4.51 Host Controller + * + * Copyright (c) 2022 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" +#include "hw/sd/npcm7xx_sdhci.h" + +#include "libqos/libqtest.h" +#include "libqtest-single.h" +#include "libqos/sdhci-cmd.h" + +#define NPCM7XX_REG_SIZE 0x100 +#define NPCM7XX_MMC_BA 0xF0842000 +#define NPCM7XX_BLK_SIZE 512 +#define NPCM7XX_TEST_IMAGE_SIZE (1 << 30) + +char *sd_path; + +static QTestState *setup_sd_card(void) +{ + QTestState *qts = qtest_initf( + "-machine kudo-bmc " + "-device sd-card,drive=drive0 " + "-drive id=drive0,if=none,file=%s,format=raw,auto-read-only=off", + sd_path); + + qtest_writew(qts, NPCM7XX_MMC_BA + SDHC_SWRST, SDHC_RESET_ALL); + qtest_writew(qts, NPCM7XX_MMC_BA + SDHC_CLKCON, + SDHC_CLOCK_SDCLK_EN | SDHC_CLOCK_INT_STABLE | + SDHC_CLOCK_INT_EN); + sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0, 0, SDHC_APP_CMD); + sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0x41200000, 0, (41 << 8)); + sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0, 0, SDHC_ALL_SEND_CID); + sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0, 0, SDHC_SEND_RELATIVE_ADDR); + sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0x45670000, 0, + SDHC_SELECT_DESELECT_CARD); + + return qts; +} + +static void write_sdread(QTestState *qts, const char *msg) +{ + int fd, ret; + size_t len = strlen(msg); + char *rmsg = g_malloc(len); + + /* write message to sd */ + fd = open(sd_path, O_WRONLY); + g_assert(fd >= 0); + ret = write(fd, msg, len); + close(fd); + g_assert(ret == len); + + /* read message using sdhci */ + ret = sdhci_read_cmd(qts, NPCM7XX_MMC_BA, rmsg, len); + g_assert(ret == len); + g_assert(!memcmp(rmsg, msg, len)); + + g_free(rmsg); +} + +/* Check MMC can read values from sd */ +static void test_read_sd(void) +{ + QTestState *qts = setup_sd_card(); + + write_sdread(qts, "hello world"); + write_sdread(qts, "goodbye"); + + qtest_quit(qts); +} + +static void sdwrite_read(QTestState *qts, const char *msg) +{ + int fd, ret; + size_t len = strlen(msg); + char *rmsg = g_malloc(len); + + /* write message using sdhci */ + sdhci_write_cmd(qts, NPCM7XX_MMC_BA, msg, len, NPCM7XX_BLK_SIZE); + + /* read message from sd */ + fd = open(sd_path, O_RDONLY); + g_assert(fd >= 0); + ret = read(fd, rmsg, len); + close(fd); + g_assert(ret == len); + + g_assert(!memcmp(rmsg, msg, len)); + + g_free(rmsg); +} + +/* Check MMC can write values to sd */ +static void test_write_sd(void) +{ + QTestState *qts = setup_sd_card(); + + sdwrite_read(qts, "hello world"); + sdwrite_read(qts, "goodbye"); + + qtest_quit(qts); +} + +/* Check SDHCI has correct default values. */ +static void test_reset(void) +{ + QTestState *qts = qtest_init("-machine kudo-bmc"); + uint64_t addr = NPCM7XX_MMC_BA; + uint64_t end_addr = addr + NPCM7XX_REG_SIZE; + uint16_t prstvals_resets[] = {NPCM7XX_PRSTVALS_0_RESET, + NPCM7XX_PRSTVALS_1_RESET, + 0, + NPCM7XX_PRSTVALS_3_RESET, + 0, + 0}; + int i; + uint32_t mask; + + while (addr < end_addr) { + switch (addr - NPCM7XX_MMC_BA) { + case SDHC_PRNSTS: + /* + * ignores bits 20 to 24: they are changed when reading registers + */ + mask = 0x1f00000; + g_assert_cmphex(qtest_readl(qts, addr) | mask, ==, + NPCM7XX_PRSNTS_RESET | mask); + addr += 4; + break; + case SDHC_BLKGAP: + g_assert_cmphex(qtest_readb(qts, addr), ==, NPCM7XX_BLKGAP_RESET); + addr += 1; + break; + case SDHC_CAPAB: + g_assert_cmphex(qtest_readq(qts, addr), ==, NPCM7XX_CAPAB_RESET); + addr += 8; + break; + case SDHC_MAXCURR: + g_assert_cmphex(qtest_readq(qts, addr), ==, NPCM7XX_MAXCURR_RESET); + addr += 8; + break; + case SDHC_HCVER: + g_assert_cmphex(qtest_readw(qts, addr), ==, NPCM7XX_HCVER_RESET); + addr += 2; + break; + case NPCM7XX_PRSTVALS: + for (i = 0; i < NPCM7XX_PRSTVALS_SIZE; ++i) { + g_assert_cmphex(qtest_readw(qts, addr + 2 * i), ==, + prstvals_resets[i]); + } + addr += NPCM7XX_PRSTVALS_SIZE * 2; + break; + default: + g_assert_cmphex(qtest_readb(qts, addr), ==, 0); + addr += 1; + } + } + + qtest_quit(qts); +} + +static void drive_destroy(void) +{ + unlink(sd_path); + g_free(sd_path); +} + +static void drive_create(void) +{ + int fd, ret; + GError *error = NULL; + + /* Create a temporary raw image */ + fd = g_file_open_tmp("sdhci_XXXXXX", &sd_path, &error); + if (fd == -1) { + fprintf(stderr, "unable to create sdhci file: %s\n", error->message); + g_error_free(error); + } + g_assert(sd_path != NULL); + + ret = ftruncate(fd, NPCM7XX_TEST_IMAGE_SIZE); + g_assert_cmpint(ret, ==, 0); + g_message("%s", sd_path); + close(fd); +} + +int main(int argc, char **argv) +{ + int ret; + + drive_create(); + + g_test_init(&argc, &argv, NULL); + + qtest_add_func("npcm7xx_sdhci/reset", test_reset); + qtest_add_func("npcm7xx_sdhci/write_sd", test_write_sd); + qtest_add_func("npcm7xx_sdhci/read_sd", test_read_sd); + + ret = g_test_run(); + drive_destroy(); + return ret; +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_npcm7xx = \ 'npcm7xx_gpio-test', 'npcm7xx_pwm-test', 'npcm7xx_rng-test', + 'npcm7xx_sdhci-test', 'npcm7xx_smbus-test', 'npcm7xx_timer-test', 'npcm7xx_watchdog_timer-test'] + \ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Add new macros to manipulate signed fields within the register. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-2-richard.henderson@linaro.org Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/registerfields.h | 48 ++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) diff --git a/include/hw/registerfields.h b/include/hw/registerfields.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/registerfields.h +++ b/include/hw/registerfields.h @@ -XXX,XX +XXX,XX @@ extract64((storage), R_ ## reg ## _ ## field ## _SHIFT, \ R_ ## reg ## _ ## field ## _LENGTH) +#define FIELD_SEX8(storage, reg, field) \ + sextract8((storage), R_ ## reg ## _ ## field ## _SHIFT, \ + R_ ## reg ## _ ## field ## _LENGTH) +#define FIELD_SEX16(storage, reg, field) \ + sextract16((storage), R_ ## reg ## _ ## field ## _SHIFT, \ + R_ ## reg ## _ ## field ## _LENGTH) +#define FIELD_SEX32(storage, reg, field) \ + sextract32((storage), R_ ## reg ## _ ## field ## _SHIFT, \ + R_ ## reg ## _ ## field ## _LENGTH) +#define FIELD_SEX64(storage, reg, field) \ + sextract64((storage), R_ ## reg ## _ ## field ## _SHIFT, \ + R_ ## reg ## _ ## field ## _LENGTH) + /* Extract a field from an array of registers */ #define ARRAY_FIELD_EX32(regs, reg, field) \ FIELD_EX32((regs)[R_ ## reg], reg, field) @@ -XXX,XX +XXX,XX @@ _d; }) #define FIELD_DP64(storage, reg, field, val) ({ \ struct { \ - uint64_t v:R_ ## reg ## _ ## field ## _LENGTH; \ + uint64_t v:R_ ## reg ## _ ## field ## _LENGTH; \ + } _v = { .v = val }; \ + uint64_t _d; \ + _d = deposit64((storage), R_ ## reg ## _ ## field ## _SHIFT, \ + R_ ## reg ## _ ## field ## _LENGTH, _v.v); \ + _d; }) + +#define FIELD_SDP8(storage, reg, field, val) ({ \ + struct { \ + signed int v:R_ ## reg ## _ ## field ## _LENGTH; \ + } _v = { .v = val }; \ + uint8_t _d; \ + _d = deposit32((storage), R_ ## reg ## _ ## field ## _SHIFT, \ + R_ ## reg ## _ ## field ## _LENGTH, _v.v); \ + _d; }) +#define FIELD_SDP16(storage, reg, field, val) ({ \ + struct { \ + signed int v:R_ ## reg ## _ ## field ## _LENGTH; \ + } _v = { .v = val }; \ + uint16_t _d; \ + _d = deposit32((storage), R_ ## reg ## _ ## field ## _SHIFT, \ + R_ ## reg ## _ ## field ## _LENGTH, _v.v); \ + _d; }) +#define FIELD_SDP32(storage, reg, field, val) ({ \ + struct { \ + signed int v:R_ ## reg ## _ ## field ## _LENGTH; \ + } _v = { .v = val }; \ + uint32_t _d; \ + _d = deposit32((storage), R_ ## reg ## _ ## field ## _SHIFT, \ + R_ ## reg ## _ ## field ## _LENGTH, _v.v); \ + _d; }) +#define FIELD_SDP64(storage, reg, field, val) ({ \ + struct { \ + int64_t v:R_ ## reg ## _ ## field ## _LENGTH; \ } _v = { .v = val }; \ uint64_t _d; \ _d = deposit64((storage), R_ ## reg ## _ ## field ## _SHIFT, \ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Set this as the kernel would, to 48 bits, to keep the computation of the address space correct for PAuth. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) aarch64_sve_zcr_get_valid_len(cpu, cpu->sve_default_vq - 1); } /* + * Enable 48-bit address space (TODO: take reserved_va into account). * Enable TBI0 but not TBI1. * Note that this must match useronly_clean_ptr. */ - env->cp15.tcr_el[1].raw_tcr = (1ULL << 37); + env->cp15.tcr_el[1].raw_tcr = 5 | (1ULL << 37); /* Enable MTE */ if (cpu_isar_feature(aa64_mte, cpu)) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Without FEAT_LVA, the behaviour of programming an invalid value is IMPLEMENTATION DEFINED. With FEAT_LVA, programming an invalid minimum value requires a Translation fault. It is most self-consistent to choose to generate the fault always. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 1 + target/arm/helper.c | 32 ++++++++++++++++++++++++++++---- 2 files changed, 29 insertions(+), 4 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ typedef struct ARMVAParameters { bool hpd : 1; bool using16k : 1; bool using64k : 1; + bool tsz_oob : 1; /* tsz has been clamped to legal range */ } ARMVAParameters; ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, 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 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, ARMMMUIdx mmu_idx, bool data) { uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; - bool epd, hpd, using16k, using64k; - int select, tsz, tbi, max_tsz; + bool epd, hpd, using16k, using64k, tsz_oob; + int select, tsz, tbi, max_tsz, min_tsz; if (!regime_has_2_ranges(mmu_idx)) { select = 0; @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, } else { max_tsz = 39; } + min_tsz = 16; /* TODO: ARMv8.2-LVA */ - tsz = MIN(tsz, max_tsz); - tsz = MAX(tsz, 16); /* TODO: ARMv8.2-LVA */ + if (tsz > max_tsz) { + tsz = max_tsz; + tsz_oob = true; + } else if (tsz < min_tsz) { + tsz = min_tsz; + tsz_oob = true; + } else { + tsz_oob = false; + } /* Present TBI as a composite with TBID. */ tbi = aa64_va_parameter_tbi(tcr, mmu_idx); @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, .hpd = hpd, .using16k = using16k, .using64k = using64k, + .tsz_oob = tsz_oob, }; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, param = aa64_va_parameters(env, address, mmu_idx, access_type != MMU_INST_FETCH); level = 0; + + /* + * If TxSZ is programmed to a value larger than the maximum, + * or smaller than the effective minimum, it is IMPLEMENTATION + * DEFINED whether we behave as if the field were programmed + * within bounds, or if a level 0 Translation fault is generated. + * + * With FEAT_LVA, fault on less than minimum becomes required, + * so our choice is to always raise the fault. + */ + if (param.tsz_oob) { + fault_type = ARMFault_Translation; + goto do_fault; + } + addrsize = 64 - 8 * param.tbi; inputsize = 64 - param.tsz; } else { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We will shortly share parts of this function with other portions of address translation. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 19 +------------------ target/arm/helper.c | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+), 18 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline void update_spsel(CPUARMState *env, uint32_t imm) * Returns the implementation defined bit-width of physical addresses. * The ARMv8 reference manuals refer to this as PAMax(). */ -static inline unsigned int arm_pamax(ARMCPU *cpu) -{ - static const unsigned int pamax_map[] = { - [0] = 32, - [1] = 36, - [2] = 40, - [3] = 42, - [4] = 44, - [5] = 48, - }; - unsigned int parange = - FIELD_EX64(cpu->isar.id_aa64mmfr0, ID_AA64MMFR0, PARANGE); - - /* id_aa64mmfr0 is a read-only register so values outside of the - * supported mappings can be considered an implementation error. */ - assert(parange < ARRAY_SIZE(pamax_map)); - return pamax_map[parange]; -} +unsigned int arm_pamax(ARMCPU *cpu); /* Return true if extended addresses are enabled. * This is always the case if our translation regime is 64 bit, diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs) } #endif /* !CONFIG_USER_ONLY */ +/* The cpu-specific constant value of PAMax; also used by hw/arm/virt. */ +unsigned int arm_pamax(ARMCPU *cpu) +{ + static const unsigned int pamax_map[] = { + [0] = 32, + [1] = 36, + [2] = 40, + [3] = 42, + [4] = 44, + [5] = 48, + }; + unsigned int parange = + FIELD_EX64(cpu->isar.id_aa64mmfr0, ID_AA64MMFR0, PARANGE); + + /* + * id_aa64mmfr0 is a read-only register so values outside of the + * supported mappings can be considered an implementation error. + */ + assert(parange < ARRAY_SIZE(pamax_map)); + return pamax_map[parange]; +} + static int aa64_va_parameter_tbi(uint64_t tcr, ARMMMUIdx mmu_idx) { if (regime_has_2_ranges(mmu_idx)) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Pass down the width of the output address from translation. For now this is still just PAMax, but a subsequent patch will compute the correct value from TCR_ELx.{I}PS. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) 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 @@ do_fault: * false otherwise. */ static bool check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, int level, - int inputsize, int stride) + int inputsize, int stride, int outputsize) { const int grainsize = stride + 3; int startsizecheck; @@ -XXX,XX +XXX,XX @@ static bool check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, int level, } if (is_aa64) { - CPUARMState *env = &cpu->env; - unsigned int pamax = arm_pamax(cpu); - switch (stride) { case 13: /* 64KB Pages. */ - if (level == 0 || (level == 1 && pamax <= 42)) { + if (level == 0 || (level == 1 && outputsize <= 42)) { return false; } break; case 11: /* 16KB Pages. */ - if (level == 0 || (level == 1 && pamax <= 40)) { + if (level == 0 || (level == 1 && outputsize <= 40)) { return false; } break; case 9: /* 4KB Pages. */ - if (level == 0 && pamax <= 42) { + if (level == 0 && outputsize <= 42) { return false; } break; @@ -XXX,XX +XXX,XX @@ static bool check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, int level, } /* Inputsize checks. */ - if (inputsize > pamax && - (arm_el_is_aa64(env, 1) || inputsize > 40)) { + if (inputsize > outputsize && + (arm_el_is_aa64(&cpu->env, 1) || inputsize > 40)) { /* This is CONSTRAINED UNPREDICTABLE and we choose to fault. */ return false; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, target_ulong page_size; uint32_t attrs; int32_t stride; - int addrsize, inputsize; + int addrsize, inputsize, outputsize; TCR *tcr = regime_tcr(env, mmu_idx); int ap, ns, xn, pxn; uint32_t el = regime_el(env, mmu_idx); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, addrsize = 64 - 8 * param.tbi; inputsize = 64 - param.tsz; + outputsize = arm_pamax(cpu); } else { param = aa32_va_parameters(env, address, mmu_idx); level = 1; addrsize = (mmu_idx == ARMMMUIdx_Stage2 ? 40 : 32); inputsize = addrsize - param.tsz; + outputsize = 40; } /* @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, /* Check that the starting level is valid. */ ok = check_s2_mmu_setup(cpu, aarch64, startlevel, - inputsize, stride); + inputsize, stride, outputsize); if (!ok) { fault_type = ARMFault_Translation; goto do_fault; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The macro is a bit more readable than the inlined computation. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, level = startlevel; } - indexmask_grainsize = (1ULL << (stride + 3)) - 1; - indexmask = (1ULL << (inputsize - (stride * (4 - level)))) - 1; + indexmask_grainsize = MAKE_64BIT_MASK(0, stride + 3); + indexmask = MAKE_64BIT_MASK(0, inputsize - (stride * (4 - level))); /* Now we can extract the actual base address from the TTBR */ descaddr = extract64(ttbr, 0, 48); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This field controls the output (intermediate) physical address size of the translation process. V8 requires to raise an AddressSize fault if the page tables are programmed incorrectly, such that any intermediate descriptor address, or the final translated address, is out of range. Add a PS field to ARMVAParameters, and properly compute outputsize in get_phys_addr_lpae. Test the descaddr as extracted from TTBR and from page table entries. Restrict descaddrmask so that we won't raise the fault for v7. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 1 + target/arm/helper.c | 72 ++++++++++++++++++++++++++++++++---------- 2 files changed, 57 insertions(+), 16 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t aarch64_pstate_valid_mask(const ARMISARegisters *id) */ typedef struct ARMVAParameters { unsigned tsz : 8; + unsigned ps : 3; unsigned select : 1; bool tbi : 1; bool epd : 1; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs) } #endif /* !CONFIG_USER_ONLY */ +/* This mapping is common between ID_AA64MMFR0.PARANGE and TCR_ELx.{I}PS. */ +static const uint8_t pamax_map[] = { + [0] = 32, + [1] = 36, + [2] = 40, + [3] = 42, + [4] = 44, + [5] = 48, +}; + /* The cpu-specific constant value of PAMax; also used by hw/arm/virt. */ unsigned int arm_pamax(ARMCPU *cpu) { - static const unsigned int pamax_map[] = { - [0] = 32, - [1] = 36, - [2] = 40, - [3] = 42, - [4] = 44, - [5] = 48, - }; unsigned int parange = FIELD_EX64(cpu->isar.id_aa64mmfr0, ID_AA64MMFR0, PARANGE); @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, { uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; bool epd, hpd, using16k, using64k, tsz_oob; - int select, tsz, tbi, max_tsz, min_tsz; + int select, tsz, tbi, max_tsz, min_tsz, ps; if (!regime_has_2_ranges(mmu_idx)) { select = 0; @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, hpd = extract32(tcr, 24, 1); } epd = false; + ps = extract32(tcr, 16, 3); } else { /* * Bit 55 is always between the two regions, and is canonical for @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, epd = extract32(tcr, 23, 1); hpd = extract64(tcr, 42, 1); } + ps = extract64(tcr, 32, 3); } if (cpu_isar_feature(aa64_st, env_archcpu(env))) { @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, return (ARMVAParameters) { .tsz = tsz, + .ps = ps, .select = select, .tbi = tbi, .epd = epd, @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, /* TODO: This code does not support shareability levels. */ if (aarch64) { + int ps; + param = aa64_va_parameters(env, address, mmu_idx, access_type != MMU_INST_FETCH); level = 0; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, addrsize = 64 - 8 * param.tbi; inputsize = 64 - param.tsz; - outputsize = arm_pamax(cpu); + + /* + * Bound PS by PARANGE to find the effective output address size. + * ID_AA64MMFR0 is a read-only register so values outside of the + * supported mappings can be considered an implementation error. + */ + ps = FIELD_EX64(cpu->isar.id_aa64mmfr0, ID_AA64MMFR0, PARANGE); + ps = MIN(ps, param.ps); + assert(ps < ARRAY_SIZE(pamax_map)); + outputsize = pamax_map[ps]; } else { param = aa32_va_parameters(env, address, mmu_idx); level = 1; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, /* Now we can extract the actual base address from the TTBR */ descaddr = extract64(ttbr, 0, 48); + + /* + * If the base address is out of range, raise AddressSizeFault. + * In the pseudocode, this is !IsZero(baseregister<47:outputsize>), + * but we've just cleared the bits above 47, so simplify the test. + */ + if (descaddr >> outputsize) { + level = 0; + fault_type = ARMFault_AddressSize; + goto do_fault; + } + /* * We rely on this masking to clear the RES0 bits at the bottom of the TTBR * and also to mask out CnP (bit 0) which could validly be non-zero. */ descaddr &= ~indexmask; - /* The address field in the descriptor goes up to bit 39 for ARMv7 - * but up to bit 47 for ARMv8, but we use the descaddrmask - * up to bit 39 for AArch32, because we don't need other bits in that case - * to construct next descriptor address (anyway they should be all zeroes). + /* + * For AArch32, the address field in the descriptor goes up to bit 39 + * for both v7 and v8. However, for v8 the SBZ bits [47:40] must be 0 + * or an AddressSize fault is raised. So for v8 we extract those SBZ + * bits as part of the address, which will be checked via outputsize. + * For AArch64, the address field always goes up to bit 47 (with extra + * bits for FEAT_LPA placed elsewhere). AArch64 implies v8. */ - descaddrmask = ((1ull << (aarch64 ? 48 : 40)) - 1) & - ~indexmask_grainsize; + if (arm_feature(env, ARM_FEATURE_V8)) { + descaddrmask = MAKE_64BIT_MASK(0, 48); + } else { + descaddrmask = MAKE_64BIT_MASK(0, 40); + } + descaddrmask &= ~indexmask_grainsize; /* Secure accesses start with the page table in secure memory and * can be downgraded to non-secure at any step. Non-secure accesses @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, /* Invalid, or the Reserved level 3 encoding */ goto do_fault; } + descaddr = descriptor & descaddrmask; + if (descaddr >> outputsize) { + fault_type = ARMFault_AddressSize; + goto do_fault; + } if ((descriptor & 2) && (level < 3)) { /* Table entry. The top five bits are attributes which may -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The original A.a revision of the AArch64 ARM required that we force-extend the addresses in these registers from 49 bits. This language has been loosened via a combination of IMPLEMENTATION DEFINED and CONSTRAINTED UNPREDICTABLE to allow consideration of the entire aligned address. This means that we do not have to consider whether or not FEAT_LVA is enabled, and decide from which bit an address might need to be extended. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void dbgwvr_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMCPU *cpu = env_archcpu(env); int i = ri->crm; - /* Bits [63:49] are hardwired to the value of bit [48]; that is, the - * register reads and behaves as if values written are sign extended. + /* * Bits [1:0] are RES0. + * + * It is IMPLEMENTATION DEFINED whether [63:49] ([63:53] with FEAT_LVA) + * are hardwired to the value of bit [48] ([52] with FEAT_LVA), or if + * they contain the value written. It is CONSTRAINED UNPREDICTABLE + * whether the RESS bits are ignored when comparing an address. + * + * Therefore we are allowed to compare the entire register, which lets + * us avoid considering whether or not FEAT_LVA is actually enabled. */ - value = sextract64(value, 0, 49) & ~3ULL; + value &= ~3ULL; raw_write(env, ri, value); hw_watchpoint_update(cpu, i); @@ -XXX,XX +XXX,XX @@ void hw_breakpoint_update(ARMCPU *cpu, int n) case 0: /* unlinked address match */ case 1: /* linked address match */ { - /* Bits [63:49] are hardwired to the value of bit [48]; that is, - * we behave as if the register was sign extended. Bits [1:0] are - * RES0. The BAS field is used to allow setting breakpoints on 16 - * bit wide instructions; it is CONSTRAINED UNPREDICTABLE whether + /* + * Bits [1:0] are RES0. + * + * It is IMPLEMENTATION DEFINED whether bits [63:49] + * ([63:53] for FEAT_LVA) are hardwired to a copy of the sign bit + * of the VA field ([48] or [52] for FEAT_LVA), or whether the + * value is read as written. It is CONSTRAINED UNPREDICTABLE + * whether the RESS bits are ignored when comparing an address. + * Therefore we are allowed to compare the entire register, which + * lets us avoid considering whether FEAT_LVA is actually enabled. + * + * The BAS field is used to allow setting breakpoints on 16-bit + * wide instructions; it is CONSTRAINED UNPREDICTABLE whether * a bp will fire if the addresses covered by the bp and the addresses * covered by the insn overlap but the insn doesn't start at the * start of the bp address range. We choose to require the insn and @@ -XXX,XX +XXX,XX @@ void hw_breakpoint_update(ARMCPU *cpu, int n) * See also figure D2-3 in the v8 ARM ARM (DDI0487A.c). */ int bas = extract64(bcr, 5, 4); - addr = sextract64(bvr, 0, 49) & ~3ULL; + addr = bvr & ~3ULL; if (bas == 0) { return; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This feature is relatively small, as it applies only to 64k pages and thus requires no additional changes to the table descriptor walking algorithm, only a change to the minimum TSZ (which is the inverse of the maximum virtual address space size). Note that this feature widens VBAR_ELx, but we already treat the register as being 64 bits wide. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu-param.h | 2 +- target/arm/cpu.h | 5 +++++ target/arm/cpu64.c | 1 + target/arm/helper.c | 9 ++++++++- 5 files changed, 16 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_LRCPC (Load-acquire RCpc instructions) - FEAT_LRCPC2 (Load-acquire RCpc instructions v2) - FEAT_LSE (Large System Extensions) +- FEAT_LVA (Large Virtual Address space) - FEAT_MTE (Memory Tagging Extension) - FEAT_MTE2 (Memory Tagging Extension) - FEAT_MTE3 (MTE Asymmetric Fault Handling) diff --git a/target/arm/cpu-param.h b/target/arm/cpu-param.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-param.h +++ b/target/arm/cpu-param.h @@ -XXX,XX +XXX,XX @@ #ifdef TARGET_AARCH64 # define TARGET_LONG_BITS 64 # define TARGET_PHYS_ADDR_SPACE_BITS 48 -# define TARGET_VIRT_ADDR_SPACE_BITS 48 +# define TARGET_VIRT_ADDR_SPACE_BITS 52 #else # define TARGET_LONG_BITS 32 # define TARGET_PHYS_ADDR_SPACE_BITS 40 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 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_tts2uxn(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; 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 @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64MMFR2, UAO, 1); t = FIELD_DP64(t, ID_AA64MMFR2, CNP, 1); /* TTCNP */ t = FIELD_DP64(t, ID_AA64MMFR2, ST, 1); /* TTST */ + t = FIELD_DP64(t, ID_AA64MMFR2, VARANGE, 1); /* FEAT_LVA */ cpu->isar.id_aa64mmfr2 = t; t = cpu->isar.id_aa64zfr0; 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 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, } else { max_tsz = 39; } - min_tsz = 16; /* TODO: ARMv8.2-LVA */ + + min_tsz = 16; + if (using64k) { + if (cpu_isar_feature(aa64_lva, env_archcpu(env))) { + min_tsz = 12; + } + } + /* TODO: FEAT_LPA2 */ if (tsz > max_tsz) { tsz = max_tsz; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This feature widens physical addresses (and intermediate physical addresses for 2-stage translation) from 48 to 52 bits, when using 64k pages. The only thing left at this point is to handle the extra bits in the TTBR and in the table descriptors. Note that PAR_EL1 and HPFAR_EL2 are nominally extended, but we don't mask out the high bits when writing to those registers, so no changes are required there. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu-param.h | 2 +- target/arm/cpu64.c | 2 +- target/arm/helper.c | 19 ++++++++++++++++--- 4 files changed, 19 insertions(+), 5 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_I8MM (AArch64 Int8 matrix multiplication instructions) - FEAT_JSCVT (JavaScript conversion instructions) - FEAT_LOR (Limited ordering regions) +- FEAT_LPA (Large Physical Address space) - FEAT_LRCPC (Load-acquire RCpc instructions) - FEAT_LRCPC2 (Load-acquire RCpc instructions v2) - FEAT_LSE (Large System Extensions) diff --git a/target/arm/cpu-param.h b/target/arm/cpu-param.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-param.h +++ b/target/arm/cpu-param.h @@ -XXX,XX +XXX,XX @@ #ifdef TARGET_AARCH64 # define TARGET_LONG_BITS 64 -# define TARGET_PHYS_ADDR_SPACE_BITS 48 +# define TARGET_PHYS_ADDR_SPACE_BITS 52 # define TARGET_VIRT_ADDR_SPACE_BITS 52 #else # define TARGET_LONG_BITS 32 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 @@ static void aarch64_max_initfn(Object *obj) cpu->isar.id_aa64pfr1 = t; t = cpu->isar.id_aa64mmfr0; - t = FIELD_DP64(t, ID_AA64MMFR0, PARANGE, 5); /* PARange: 48 bits */ + t = FIELD_DP64(t, ID_AA64MMFR0, PARANGE, 6); /* FEAT_LPA: 52 bits */ cpu->isar.id_aa64mmfr0 = t; t = cpu->isar.id_aa64mmfr1; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const uint8_t pamax_map[] = { [3] = 42, [4] = 44, [5] = 48, + [6] = 52, }; /* The cpu-specific constant value of PAMax; also used by hw/arm/virt. */ @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, descaddr = extract64(ttbr, 0, 48); /* - * If the base address is out of range, raise AddressSizeFault. + * For FEAT_LPA and PS=6, bits [51:48] of descaddr are in [5:2] of TTBR. + * + * Otherwise, if the base address is out of range, raise AddressSizeFault. * In the pseudocode, this is !IsZero(baseregister<47:outputsize>), * but we've just cleared the bits above 47, so simplify the test. */ - if (descaddr >> outputsize) { + if (outputsize > 48) { + descaddr |= extract64(ttbr, 2, 4) << 48; + } else if (descaddr >> outputsize) { level = 0; fault_type = ARMFault_AddressSize; goto do_fault; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, } descaddr = descriptor & descaddrmask; - if (descaddr >> outputsize) { + + /* + * For FEAT_LPA and PS=6, bits [51:48] of descaddr are in [15:12] + * of descriptor. Otherwise, if descaddr is out of range, raise + * AddressSizeFault. + */ + if (outputsize > 48) { + descaddr |= extract64(descriptor, 12, 4) << 48; + } else if (descaddr >> outputsize) { fault_type = ARMFault_AddressSize; goto do_fault; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> With FEAT_LPA2, rather than introducing translation level 4, we introduce level -1, below the current level 0. Extend arm_fi_to_lfsc to handle these faults. Assert that this new translation level does not leak into fault types for which it is not defined, which allows some masking of fi->level to be removed. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 35 +++++++++++++++++++++++++++++------ 1 file changed, 29 insertions(+), 6 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t arm_fi_to_lfsc(ARMMMUFaultInfo *fi) case ARMFault_None: return 0; case ARMFault_AddressSize: - fsc = fi->level & 3; + assert(fi->level >= -1 && fi->level <= 3); + if (fi->level < 0) { + fsc = 0b101001; + } else { + fsc = fi->level; + } break; case ARMFault_AccessFlag: - fsc = (fi->level & 3) | (0x2 << 2); + assert(fi->level >= 0 && fi->level <= 3); + fsc = 0b001000 | fi->level; break; case ARMFault_Permission: - fsc = (fi->level & 3) | (0x3 << 2); + assert(fi->level >= 0 && fi->level <= 3); + fsc = 0b001100 | fi->level; break; case ARMFault_Translation: - fsc = (fi->level & 3) | (0x1 << 2); + assert(fi->level >= -1 && fi->level <= 3); + if (fi->level < 0) { + fsc = 0b101011; + } else { + fsc = 0b000100 | fi->level; + } break; case ARMFault_SyncExternal: fsc = 0x10 | (fi->ea << 12); break; case ARMFault_SyncExternalOnWalk: - fsc = (fi->level & 3) | (0x5 << 2) | (fi->ea << 12); + assert(fi->level >= -1 && fi->level <= 3); + if (fi->level < 0) { + fsc = 0b010011; + } else { + fsc = 0b010100 | fi->level; + } + fsc |= fi->ea << 12; break; case ARMFault_SyncParity: fsc = 0x18; break; case ARMFault_SyncParityOnWalk: - fsc = (fi->level & 3) | (0x7 << 2); + assert(fi->level >= -1 && fi->level <= 3); + if (fi->level < 0) { + fsc = 0b011011; + } else { + fsc = 0b011100 | fi->level; + } break; case ARMFault_AsyncParity: fsc = 0x19; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Merge tlbi_aa64_range_get_length and tlbi_aa64_range_get_base, returning a structure containing both results. Pass in the ARMMMUIdx, rather than the digested two_ranges boolean. This is in preparation for FEAT_LPA2, where the interpretation of 'value' depends on the effective value of DS for the regime. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 58 +++++++++++++++++++-------------------------- 1 file changed, 24 insertions(+), 34 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, } #ifdef TARGET_AARCH64 -static uint64_t tlbi_aa64_range_get_length(CPUARMState *env, - uint64_t value) -{ - unsigned int page_shift; - unsigned int page_size_granule; - uint64_t num; - uint64_t scale; - uint64_t exponent; +typedef struct { + uint64_t base; uint64_t length; +} TLBIRange; + +static TLBIRange tlbi_aa64_get_range(CPUARMState *env, ARMMMUIdx mmuidx, + uint64_t value) +{ + unsigned int page_size_granule, page_shift, num, scale, exponent; + TLBIRange ret = { }; - num = extract64(value, 39, 5); - scale = extract64(value, 44, 2); page_size_granule = extract64(value, 46, 2); if (page_size_granule == 0) { qemu_log_mask(LOG_GUEST_ERROR, "Invalid page size granule %d\n", page_size_granule); - return 0; + return ret; } page_shift = (page_size_granule - 1) * 2 + 12; - + num = extract64(value, 39, 5); + scale = extract64(value, 44, 2); exponent = (5 * scale) + 1; - length = (num + 1) << (exponent + page_shift); - return length; -} + ret.length = (num + 1) << (exponent + page_shift); -static uint64_t tlbi_aa64_range_get_base(CPUARMState *env, uint64_t value, - bool two_ranges) -{ - /* TODO: ARMv8.7 FEAT_LPA2 */ - uint64_t pageaddr; - - if (two_ranges) { - pageaddr = sextract64(value, 0, 37) << TARGET_PAGE_BITS; + if (regime_has_2_ranges(mmuidx)) { + ret.base = sextract64(value, 0, 37) << TARGET_PAGE_BITS; } else { - pageaddr = extract64(value, 0, 37) << TARGET_PAGE_BITS; + ret.base = extract64(value, 0, 37) << TARGET_PAGE_BITS; } - return pageaddr; + return ret; } static void do_rvae_write(CPUARMState *env, uint64_t value, int idxmap, bool synced) { ARMMMUIdx one_idx = ARM_MMU_IDX_A | ctz32(idxmap); - bool two_ranges = regime_has_2_ranges(one_idx); - uint64_t baseaddr, length; + TLBIRange range; int bits; - baseaddr = tlbi_aa64_range_get_base(env, value, two_ranges); - length = tlbi_aa64_range_get_length(env, value); - bits = tlbbits_for_regime(env, one_idx, baseaddr); + range = tlbi_aa64_get_range(env, one_idx, value); + bits = tlbbits_for_regime(env, one_idx, range.base); if (synced) { tlb_flush_range_by_mmuidx_all_cpus_synced(env_cpu(env), - baseaddr, - length, + range.base, + range.length, idxmap, bits); } else { - tlb_flush_range_by_mmuidx(env_cpu(env), baseaddr, - length, idxmap, bits); + tlb_flush_range_by_mmuidx(env_cpu(env), range.base, + range.length, idxmap, bits); } } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The shift of the BaseADDR field depends on the translation granule in use. Fixes: 84940ed8255 ("target/arm: Add support for FEAT_TLBIRANGE") Reported-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static TLBIRange tlbi_aa64_get_range(CPUARMState *env, ARMMMUIdx mmuidx, ret.length = (num + 1) << (exponent + page_shift); if (regime_has_2_ranges(mmuidx)) { - ret.base = sextract64(value, 0, 37) << TARGET_PAGE_BITS; + ret.base = sextract64(value, 0, 37); } else { - ret.base = extract64(value, 0, 37) << TARGET_PAGE_BITS; + ret.base = extract64(value, 0, 37); } + ret.base <<= page_shift; return ret; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> For FEAT_LPA2, we will need other ARMVAParameters, which themselves depend on the translation granule in use. We might as well validate that the given TG matches; the architecture "does not require that the instruction invalidates any entries" if this is not true. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static TLBIRange tlbi_aa64_get_range(CPUARMState *env, ARMMMUIdx mmuidx, uint64_t value) { unsigned int page_size_granule, page_shift, num, scale, exponent; + /* Extract one bit to represent the va selector in use. */ + uint64_t select = sextract64(value, 36, 1); + ARMVAParameters param = aa64_va_parameters(env, select, mmuidx, true); TLBIRange ret = { }; page_size_granule = extract64(value, 46, 2); - if (page_size_granule == 0) { - qemu_log_mask(LOG_GUEST_ERROR, "Invalid page size granule %d\n", + /* The granule encoded in value must match the granule in use. */ + if (page_size_granule != (param.using64k ? 3 : param.using16k ? 2 : 1)) { + qemu_log_mask(LOG_GUEST_ERROR, "Invalid tlbi page size granule %d\n", page_size_granule); return ret; } @@ -XXX,XX +XXX,XX @@ static TLBIRange tlbi_aa64_get_range(CPUARMState *env, ARMMMUIdx mmuidx, ret.length = (num + 1) << (exponent + page_shift); - if (regime_has_2_ranges(mmuidx)) { + if (param.select) { ret.base = sextract64(value, 0, 37); } else { ret.base = extract64(value, 0, 37); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We support 16k pages, but do not advertize that in ID_AA64MMFR0. The value 0 in the TGRAN*_2 fields indicates that stage2 lookups defer to the same support as stage1 lookups. This setting is deprecated, so indicate support for all stage2 page sizes directly. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20220301215958.157011-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = cpu->isar.id_aa64mmfr0; t = FIELD_DP64(t, ID_AA64MMFR0, PARANGE, 6); /* FEAT_LPA: 52 bits */ + t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN16, 1); /* 16k pages supported */ + t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN16_2, 2); /* 16k stage2 supported */ + t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN64_2, 2); /* 64k stage2 supported */ + t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN4_2, 2); /* 4k stage2 supported */ cpu->isar.id_aa64mmfr0 = t; t = cpu->isar.id_aa64mmfr1; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This feature widens physical addresses (and intermediate physical addresses for 2-stage translation) from 48 to 52 bits, when using 4k or 16k pages. This introduces the DS bit to TCR_ELx, which is RES0 unless the page size is enabled and supports LPA2, resulting in the effective value of DS for a given table walk. The DS bit changes the format of the page table descriptor slightly, moving the PS field out to TCR so that all pages have the same sharability and repurposing those bits of the page table descriptor for the highest bits of the output address. Do not yet enable FEAT_LPA2; we need extra plumbing to avoid tickling an old kernel bug. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220301215958.157011-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu.h | 22 ++++++++ target/arm/internals.h | 2 + target/arm/helper.c | 102 +++++++++++++++++++++++++++++----- 4 files changed, 112 insertions(+), 15 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_JSCVT (JavaScript conversion instructions) - FEAT_LOR (Limited ordering regions) - FEAT_LPA (Large Physical Address space) +- FEAT_LPA2 (Large Physical and virtual Address space v2) - FEAT_LRCPC (Load-acquire RCpc instructions) - FEAT_LRCPC2 (Load-acquire RCpc instructions v2) - FEAT_LSE (Large System Extensions) 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 bool isar_feature_aa64_i8mm(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 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_ccidx(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; 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 @@ static inline uint32_t aarch64_pstate_valid_mask(const ARMISARegisters *id) typedef struct ARMVAParameters { unsigned tsz : 8; unsigned ps : 3; + unsigned sh : 2; unsigned select : 1; bool tbi : 1; bool epd : 1; @@ -XXX,XX +XXX,XX @@ typedef struct ARMVAParameters { bool using16k : 1; bool using64k : 1; bool tsz_oob : 1; /* tsz has been clamped to legal range */ + bool ds : 1; } ARMVAParameters; ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static TLBIRange tlbi_aa64_get_range(CPUARMState *env, ARMMMUIdx mmuidx, } else { ret.base = extract64(value, 0, 37); } + if (param.ds) { + /* + * With DS=1, BaseADDR is always shifted 16 so that it is able + * to address all 52 va bits. The input address is perforce + * aligned on a 64k boundary regardless of translation granule. + */ + page_shift = 16; + } ret.base <<= page_shift; return ret; @@ -XXX,XX +XXX,XX @@ static bool check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, int level, const int grainsize = stride + 3; int startsizecheck; - /* Negative levels are never allowed. */ - if (level < 0) { + /* + * Negative levels are usually not allowed... + * Except for FEAT_LPA2, 4k page table, 52-bit address space, which + * begins with level -1. Note that previous feature tests will have + * eliminated this combination if it is not enabled. + */ + if (level < (inputsize == 52 && stride == 9 ? -1 : 0)) { return false; } @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, ARMMMUIdx mmu_idx, bool data) { uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; - bool epd, hpd, using16k, using64k, tsz_oob; - int select, tsz, tbi, max_tsz, min_tsz, ps; + bool epd, hpd, using16k, using64k, tsz_oob, ds; + int select, tsz, tbi, max_tsz, min_tsz, ps, sh; + ARMCPU *cpu = env_archcpu(env); if (!regime_has_2_ranges(mmu_idx)) { select = 0; @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, hpd = extract32(tcr, 24, 1); } epd = false; + sh = extract32(tcr, 12, 2); ps = extract32(tcr, 16, 3); + ds = extract64(tcr, 32, 1); } else { /* * Bit 55 is always between the two regions, and is canonical for @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, if (!select) { tsz = extract32(tcr, 0, 6); epd = extract32(tcr, 7, 1); + sh = extract32(tcr, 12, 2); using64k = extract32(tcr, 14, 1); using16k = extract32(tcr, 15, 1); hpd = extract64(tcr, 41, 1); @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, using64k = tg == 3; tsz = extract32(tcr, 16, 6); epd = extract32(tcr, 23, 1); + sh = extract32(tcr, 28, 2); hpd = extract64(tcr, 42, 1); } ps = extract64(tcr, 32, 3); + ds = extract64(tcr, 59, 1); } - if (cpu_isar_feature(aa64_st, env_archcpu(env))) { + if (cpu_isar_feature(aa64_st, cpu)) { max_tsz = 48 - using64k; } else { max_tsz = 39; } + /* + * DS is RES0 unless FEAT_LPA2 is supported for the given page size; + * adjust the effective value of DS, as documented. + */ min_tsz = 16; if (using64k) { - if (cpu_isar_feature(aa64_lva, env_archcpu(env))) { + if (cpu_isar_feature(aa64_lva, cpu)) { + min_tsz = 12; + } + ds = false; + } else if (ds) { + switch (mmu_idx) { + case ARMMMUIdx_Stage2: + case ARMMMUIdx_Stage2_S: + if (using16k) { + ds = cpu_isar_feature(aa64_tgran16_2_lpa2, cpu); + } else { + ds = cpu_isar_feature(aa64_tgran4_2_lpa2, cpu); + } + break; + default: + if (using16k) { + ds = cpu_isar_feature(aa64_tgran16_lpa2, cpu); + } else { + ds = cpu_isar_feature(aa64_tgran4_lpa2, cpu); + } + break; + } + if (ds) { min_tsz = 12; } } - /* TODO: FEAT_LPA2 */ if (tsz > max_tsz) { tsz = max_tsz; @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, return (ARMVAParameters) { .tsz = tsz, .ps = ps, + .sh = sh, .select = select, .tbi = tbi, .epd = epd, @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, .using16k = using16k, .using64k = using64k, .tsz_oob = tsz_oob, + .ds = ds, }; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, * VTCR_EL2.SL0 field (whose interpretation depends on the page size) */ uint32_t sl0 = extract32(tcr->raw_tcr, 6, 2); + uint32_t sl2 = extract64(tcr->raw_tcr, 33, 1); uint32_t startlevel; bool ok; - if (!aarch64 || stride == 9) { + /* SL2 is RES0 unless DS=1 & 4kb granule. */ + if (param.ds && stride == 9 && sl2) { + if (sl0 != 0) { + level = 0; + fault_type = ARMFault_Translation; + goto do_fault; + } + startlevel = -1; + } else if (!aarch64 || stride == 9) { /* AArch32 or 4KB pages */ startlevel = 2 - sl0; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, * for both v7 and v8. However, for v8 the SBZ bits [47:40] must be 0 * or an AddressSize fault is raised. So for v8 we extract those SBZ * bits as part of the address, which will be checked via outputsize. - * For AArch64, the address field always goes up to bit 47 (with extra - * bits for FEAT_LPA placed elsewhere). AArch64 implies v8. + * For AArch64, the address field goes up to bit 47, or 49 with FEAT_LPA2; + * the highest bits of a 52-bit output are placed elsewhere. */ - if (arm_feature(env, ARM_FEATURE_V8)) { + if (param.ds) { + descaddrmask = MAKE_64BIT_MASK(0, 50); + } else if (arm_feature(env, ARM_FEATURE_V8)) { descaddrmask = MAKE_64BIT_MASK(0, 48); } else { descaddrmask = MAKE_64BIT_MASK(0, 40); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, /* * For FEAT_LPA and PS=6, bits [51:48] of descaddr are in [15:12] - * of descriptor. Otherwise, if descaddr is out of range, raise - * AddressSizeFault. + * of descriptor. For FEAT_LPA2 and effective DS, bits [51:50] of + * descaddr are in [9:8]. Otherwise, if descaddr is out of range, + * raise AddressSizeFault. */ if (outputsize > 48) { - descaddr |= extract64(descriptor, 12, 4) << 48; + if (param.ds) { + descaddr |= extract64(descriptor, 8, 2) << 50; + } else { + descaddr |= extract64(descriptor, 12, 4) << 48; + } } else if (descaddr >> outputsize) { fault_type = ARMFault_AddressSize; goto do_fault; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, assert(attrindx <= 7); cacheattrs->attrs = extract64(mair, attrindx * 8, 8); } - cacheattrs->shareability = extract32(attrs, 6, 2); + + /* + * For FEAT_LPA2 and effective DS, the SH field in the attributes + * was re-purposed for output address bits. The SH attribute in + * that case comes from TCR_ELx, which we extracted earlier. + */ + if (param.ds) { + cacheattrs->shareability = param.sh; + } else { + cacheattrs->shareability = extract32(attrs, 6, 2); + } *phys_ptr = descaddr; *page_size_ptr = page_size; -- 2.25.1 When we're using KVM, the PSCI implementation is provided by the kernel, but QEMU has to tell the guest about it via the device tree. Currently we look at the KVM_CAP_ARM_PSCI_0_2 capability to determine if the kernel is providing at least PSCI 0.2, but if the kernel provides a newer version than that we will still only tell the guest it has PSCI 0.2. (This is fairly harmless; it just means the guest won't use newer parts of the PSCI API.) The kernel exposes the specific PSCI version it is implementing via the ONE_REG API; use this to report in the dtb that the PSCI implementation is 1.0-compatible if appropriate. (The device tree binding currently only distinguishes "pre-0.2", "0.2-compatible" and "1.0-compatible".) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Marc Zyngier <maz@kernel.org> Reviewed-by: Akihiko Odaki <akihiko.odaki@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20220224134655.1207865-1-peter.maydell@linaro.org --- target/arm/kvm-consts.h | 1 + hw/arm/boot.c | 5 ++--- target/arm/kvm64.c | 12 ++++++++++++ 3 files changed, 15 insertions(+), 3 deletions(-) diff --git a/target/arm/kvm-consts.h b/target/arm/kvm-consts.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm-consts.h +++ b/target/arm/kvm-consts.h @@ -XXX,XX +XXX,XX @@ MISMATCH_CHECK(QEMU_PSCI_1_0_FN_PSCI_FEATURES, PSCI_1_0_FN_PSCI_FEATURES); #define QEMU_PSCI_VERSION_0_1 0x00001 #define QEMU_PSCI_VERSION_0_2 0x00002 +#define QEMU_PSCI_VERSION_1_0 0x10000 #define QEMU_PSCI_VERSION_1_1 0x10001 MISMATCH_CHECK(QEMU_PSCI_0_2_RET_TOS_MIGRATION_NOT_REQUIRED, PSCI_0_2_TOS_MP); diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void fdt_add_psci_node(void *fdt) } qemu_fdt_add_subnode(fdt, "/psci"); - if (armcpu->psci_version == QEMU_PSCI_VERSION_0_2 || - armcpu->psci_version == QEMU_PSCI_VERSION_1_1) { - if (armcpu->psci_version == QEMU_PSCI_VERSION_0_2) { + if (armcpu->psci_version >= QEMU_PSCI_VERSION_0_2) { + if (armcpu->psci_version < QEMU_PSCI_VERSION_1_0) { const char comp[] = "arm,psci-0.2\0arm,psci"; qemu_fdt_setprop(fdt, "/psci", "compatible", comp, sizeof(comp)); } else { 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 @@ int kvm_arch_init_vcpu(CPUState *cs) uint64_t mpidr; ARMCPU *cpu = ARM_CPU(cs); CPUARMState *env = &cpu->env; + uint64_t psciver; if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE || !object_dynamic_cast(OBJECT(cpu), TYPE_AARCH64_CPU)) { @@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs) } } + /* + * KVM reports the exact PSCI version it is implementing via a + * special sysreg. If it is present, use its contents to determine + * what to report to the guest in the dtb (it is the PSCI version, + * in the same 15-bits major 16-bits minor format that PSCI_VERSION + * returns). + */ + if (!kvm_get_one_reg(cs, KVM_REG_ARM_PSCI_VERSION, &psciver)) { + cpu->psci_version = psciver; + } + /* * When KVM is in use, PSCI is emulated in-kernel and not by qemu. * Currently KVM has its own idea about MPIDR assignment, so we -- 2.25.1 The updateUIInfo method makes Cocoa API calls. It also calls back into QEMU functions like dpy_set_ui_info(). To do this safely, we need to follow two rules: * Cocoa API calls are made on the Cocoa UI thread * When calling back into QEMU we must hold the iothread lock Fix the places where we got this wrong, by taking the iothread lock while executing updateUIInfo, and moving the call in cocoa_switch() inside the dispatch_async block. Some of the Cocoa UI methods which call updateUIInfo are invoked as part of the initial application startup, while we're still doing the little cross-thread dance described in the comment just above call_qemu_main(). This meant they were calling back into the QEMU UI layer before we'd actually finished initializing our display and registered the DisplayChangeListener, which isn't really valid. Once updateUIInfo takes the iothread lock, we no longer get away with this, because during this startup phase the iothread lock is held by the QEMU main-loop thread which is waiting for us to finish our display initialization. So we must suppress updateUIInfo until applicationDidFinishLaunching allows the QEMU main-loop thread to continue. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Akihiko Odaki <akihiko.odaki@gmail.com> Tested-by: Akihiko Odaki <akihiko.odaki@gmail.com> Message-id: 20220224101330.967429-2-peter.maydell@linaro.org --- ui/cocoa.m | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/ui/cocoa.m b/ui/cocoa.m index XXXXXXX..XXXXXXX 100644 --- a/ui/cocoa.m +++ b/ui/cocoa.m @@ -XXX,XX +XXX,XX @@ QemuCocoaView *cocoaView; } } -- (void) updateUIInfo +- (void) updateUIInfoLocked { + /* Must be called with the iothread lock, i.e. via updateUIInfo */ NSSize frameSize; QemuUIInfo info; @@ -XXX,XX +XXX,XX @@ QemuCocoaView *cocoaView; dpy_set_ui_info(dcl.con, &info, TRUE); } +- (void) updateUIInfo +{ + if (!allow_events) { + /* + * Don't try to tell QEMU about UI information in the application + * startup phase -- we haven't yet registered dcl with the QEMU UI + * layer, and also trying to take the iothread lock would deadlock. + * When cocoa_display_init() does register the dcl, the UI layer + * will call cocoa_switch(), which will call updateUIInfo, so + * we don't lose any information here. + */ + return; + } + + with_iothread_lock(^{ + [self updateUIInfoLocked]; + }); +} + - (void)viewDidMoveToWindow { [self updateUIInfo]; @@ -XXX,XX +XXX,XX @@ static void cocoa_switch(DisplayChangeListener *dcl, COCOA_DEBUG("qemu_cocoa: cocoa_switch\n"); - [cocoaView updateUIInfo]; - // The DisplaySurface will be freed as soon as this callback returns. // We take a reference to the underlying pixman image here so it does // not disappear from under our feet; the switchSurface method will @@ -XXX,XX +XXX,XX @@ static void cocoa_switch(DisplayChangeListener *dcl, pixman_image_ref(image); dispatch_async(dispatch_get_main_queue(), ^{ + [cocoaView updateUIInfo]; [cocoaView switchSurface:image]; }); [pool release]; -- 2.25.1 In commit 6e657e64cdc478 in 2013 we added some autorelease pools to deal with complaints from macOS when we made calls into Cocoa from threads that didn't have automatically created autorelease pools. Later on, macOS got stricter about forbidding cross-thread Cocoa calls, and in commit 5588840ff77800e839d8 we restructured the code to avoid them. This left the autorelease pool creation in several functions without any purpose; delete it. We still need the pool in cocoa_refresh() for the clipboard related code which is called directly there. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Akihiko Odaki <akihiko.odaki@gmail.com> Tested-by: Akihiko Odaki <akihiko.odaki@gmail.com> Message-id: 20220224101330.967429-3-peter.maydell@linaro.org --- ui/cocoa.m | 6 ------ 1 file changed, 6 deletions(-) diff --git a/ui/cocoa.m b/ui/cocoa.m index XXXXXXX..XXXXXXX 100644 --- a/ui/cocoa.m +++ b/ui/cocoa.m @@ -XXX,XX +XXX,XX @@ int main (int argc, char **argv) { static void cocoa_update(DisplayChangeListener *dcl, int x, int y, int w, int h) { - NSAutoreleasePool * pool = [[NSAutoreleasePool alloc] init]; - COCOA_DEBUG("qemu_cocoa: cocoa_update\n"); dispatch_async(dispatch_get_main_queue(), ^{ @@ -XXX,XX +XXX,XX @@ static void cocoa_update(DisplayChangeListener *dcl, } [cocoaView setNeedsDisplayInRect:rect]; }); - - [pool release]; } static void cocoa_switch(DisplayChangeListener *dcl, DisplaySurface *surface) { - NSAutoreleasePool * pool = [[NSAutoreleasePool alloc] init]; pixman_image_t *image = surface->image; COCOA_DEBUG("qemu_cocoa: cocoa_switch\n"); @@ -XXX,XX +XXX,XX @@ static void cocoa_switch(DisplayChangeListener *dcl, [cocoaView updateUIInfo]; [cocoaView switchSurface:image]; }); - [pool release]; } static void cocoa_refresh(DisplayChangeListener *dcl) -- 2.25.1