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 First arm pullreq for 7.1. The bulk of this is the qemu_split_irq removal. I have enough stuff in my to-review queue that I expect to do another pullreq early next week, but 31 patches is enough to not hang on to. thanks -- PMM The following changes since commit 9c125d17e9402c232c46610802e5931b3639d77b: Merge tag 'pull-tcg-20220420' of https://gitlab.com/rth7680/qemu into staging (2022-04-20 16:43:11 -0700) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20220421 for you to fetch changes up to 5b415dd61bdbf61fb4be0e9f1a7172b8bce682c6: hw/arm: Use bit fields for NPCM7XX PWRON STRAPs (2022-04-21 11:37:05 +0100) ---------------------------------------------------------------- target-arm queue: * hw/arm/virt: Check for attempt to use TrustZone with KVM or HVF * versal: Add the Cortex-R5s in the Real-Time Processing Unit (RPU) subsystem * versal: model enough of the Clock/Reset Low-power domain (CRL) to allow control of the Cortex-R5s * xlnx-zynqmp: Connect 4 TTC timers * exynos4210: Refactor GIC/combiner code to stop using qemu_split_irq * realview: replace 'qemu_split_irq' with 'TYPE_SPLIT_IRQ' * stellaris: replace 'qemu_split_irq' with 'TYPE_SPLIT_IRQ' * hw/core/irq: remove unused 'qemu_irq_split' function * npcm7xx: use symbolic constants for PWRON STRAP bit fields * virt: document impact of gic-version on max CPUs ---------------------------------------------------------------- Edgar E. Iglesias (6): timer: cadence_ttc: Break out header file to allow embedding hw/arm/xlnx-zynqmp: Connect 4 TTC timers hw/arm: versal: Create an APU CPU Cluster hw/arm: versal: Add the Cortex-R5Fs hw/misc: Add a model of the Xilinx Versal CRL hw/arm: versal: Connect the CRL Hao Wu (2): hw/misc: Add PWRON STRAP bit fields in GCR module hw/arm: Use bit fields for NPCM7XX PWRON STRAPs Heinrich Schuchardt (1): hw/arm/virt: impact of gic-version on max CPUs Peter Maydell (19): hw/arm/virt: Check for attempt to use TrustZone with KVM or HVF hw/arm/exynos4210: Use TYPE_OR_IRQ instead of custom OR-gate device hw/intc/exynos4210_gic: Remove unused TYPE_EXYNOS4210_IRQ_GATE hw/arm/exynos4210: Put a9mpcore device into state struct hw/arm/exynos4210: Drop int_gic_irq[] from Exynos4210Irq struct hw/arm/exynos4210: Coalesce board_irqs and irq_table hw/arm/exynos4210: Fix code style nit in combiner_grp_to_gic_id[] hw/arm/exynos4210: Move exynos4210_init_board_irqs() into exynos4210.c hw/arm/exynos4210: Put external GIC into state struct hw/arm/exynos4210: Drop ext_gic_irq[] from Exynos4210Irq struct hw/arm/exynos4210: Move exynos4210_combiner_get_gpioin() into exynos4210.c hw/arm/exynos4210: Delete unused macro definitions hw/arm/exynos4210: Use TYPE_SPLIT_IRQ in exynos4210_init_board_irqs() hw/arm/exynos4210: Fill in irq_table[] for internal-combiner-only IRQ lines hw/arm/exynos4210: Connect MCT_G0 and MCT_G1 to both combiners hw/arm/exynos4210: Don't connect multiple lines to external GIC inputs hw/arm/exynos4210: Fold combiner splits into exynos4210_init_board_irqs() hw/arm/exynos4210: Put combiners into state struct hw/arm/exynos4210: Drop Exynos4210Irq struct Zongyuan Li (3): hw/arm/realview: replace 'qemu_split_irq' with 'TYPE_SPLIT_IRQ' hw/arm/stellaris: replace 'qemu_split_irq' with 'TYPE_SPLIT_IRQ' hw/core/irq: remove unused 'qemu_irq_split' function docs/system/arm/virt.rst | 4 +- include/hw/arm/exynos4210.h | 50 ++-- include/hw/arm/xlnx-versal.h | 16 ++ include/hw/arm/xlnx-zynqmp.h | 4 + include/hw/intc/exynos4210_combiner.h | 57 +++++ include/hw/intc/exynos4210_gic.h | 43 ++++ include/hw/irq.h | 5 - include/hw/misc/npcm7xx_gcr.h | 30 +++ include/hw/misc/xlnx-versal-crl.h | 235 +++++++++++++++++++ include/hw/timer/cadence_ttc.h | 54 +++++ hw/arm/exynos4210.c | 430 ++++++++++++++++++++++++++++++---- hw/arm/npcm7xx_boards.c | 24 +- hw/arm/realview.c | 33 ++- hw/arm/stellaris.c | 15 +- hw/arm/virt.c | 7 + hw/arm/xlnx-versal-virt.c | 6 +- hw/arm/xlnx-versal.c | 99 +++++++- hw/arm/xlnx-zynqmp.c | 22 ++ hw/core/irq.c | 15 -- hw/intc/exynos4210_combiner.c | 108 +-------- hw/intc/exynos4210_gic.c | 344 +-------------------------- hw/misc/xlnx-versal-crl.c | 421 +++++++++++++++++++++++++++++++++ hw/timer/cadence_ttc.c | 32 +-- MAINTAINERS | 2 +- hw/misc/meson.build | 1 + 25 files changed, 1457 insertions(+), 600 deletions(-) create mode 100644 include/hw/intc/exynos4210_combiner.h create mode 100644 include/hw/intc/exynos4210_gic.h create mode 100644 include/hw/misc/xlnx-versal-crl.h create mode 100644 include/hw/timer/cadence_ttc.h create mode 100644 hw/misc/xlnx-versal-crl.c It's not possible to provide the guest with the Security extensions (TrustZone) when using KVM or HVF, because the hardware virtualization extensions don't permit running EL3 guest code. However, we weren't checking for this combination, with the result that QEMU would assert if you tried it: $ qemu-system-aarch64 -enable-kvm -machine virt,secure=on -cpu host -display none Unexpected error in object_property_find_err() at ../../qom/object.c:1304: qemu-system-aarch64: Property 'host-arm-cpu.secure-memory' not found Aborted Check for this combination of options and report an error, in the same way we already do for attempts to give a KVM or HVF guest the Virtualization or MTE extensions. Now we will report: qemu-system-aarch64: mach-virt: KVM does not support providing Security extensions (TrustZone) to the guest CPU Resolves: https://gitlab.com/qemu-project/qemu/-/issues/961 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404155301.566542-1-peter.maydell@linaro.org --- hw/arm/virt.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) exit(1); } + if (vms->secure && (kvm_enabled() || hvf_enabled())) { + error_report("mach-virt: %s does not support providing " + "Security extensions (TrustZone) to the guest CPU", + kvm_enabled() ? "KVM" : "HVF"); + exit(1); + } + if (vms->virt && (kvm_enabled() || hvf_enabled())) { error_report("mach-virt: %s does not support providing " "Virtualization extensions to the guest CPU", -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Break out header file to allow embedding of the the TTC. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Message-id: 20220331222017.2914409-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/timer/cadence_ttc.h | 54 ++++++++++++++++++++++++++++++++++ hw/timer/cadence_ttc.c | 32 ++------------------ 2 files changed, 56 insertions(+), 30 deletions(-) create mode 100644 include/hw/timer/cadence_ttc.h diff --git a/include/hw/timer/cadence_ttc.h b/include/hw/timer/cadence_ttc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/cadence_ttc.h @@ -XXX,XX +XXX,XX @@ +/* + * Xilinx Zynq cadence TTC model + * + * Copyright (c) 2011 Xilinx Inc. + * Copyright (c) 2012 Peter A.G. Crosthwaite (peter.crosthwaite@petalogix.com) + * Copyright (c) 2012 PetaLogix Pty Ltd. + * Written By Haibing Ma + * M. Habib + * + * 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. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ +#ifndef HW_TIMER_CADENCE_TTC_H +#define HW_TIMER_CADENCE_TTC_H + +#include "hw/sysbus.h" +#include "qemu/timer.h" + +typedef struct { + QEMUTimer *timer; + int freq; + + uint32_t reg_clock; + uint32_t reg_count; + uint32_t reg_value; + uint16_t reg_interval; + uint16_t reg_match[3]; + uint32_t reg_intr; + uint32_t reg_intr_en; + uint32_t reg_event_ctrl; + uint32_t reg_event; + + uint64_t cpu_time; + unsigned int cpu_time_valid; + + qemu_irq irq; +} CadenceTimerState; + +#define TYPE_CADENCE_TTC "cadence_ttc" +OBJECT_DECLARE_SIMPLE_TYPE(CadenceTTCState, CADENCE_TTC) + +struct CadenceTTCState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + CadenceTimerState timer[3]; +}; + +#endif diff --git a/hw/timer/cadence_ttc.c b/hw/timer/cadence_ttc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/cadence_ttc.c +++ b/hw/timer/cadence_ttc.c @@ -XXX,XX +XXX,XX @@ #include "qemu/timer.h" #include "qom/object.h" +#include "hw/timer/cadence_ttc.h" + #ifdef CADENCE_TTC_ERR_DEBUG #define DB_PRINT(...) do { \ fprintf(stderr, ": %s: ", __func__); \ @@ -XXX,XX +XXX,XX @@ #define CLOCK_CTRL_PS_EN 0x00000001 #define CLOCK_CTRL_PS_V 0x0000001e -typedef struct { - QEMUTimer *timer; - int freq; - - uint32_t reg_clock; - uint32_t reg_count; - uint32_t reg_value; - uint16_t reg_interval; - uint16_t reg_match[3]; - uint32_t reg_intr; - uint32_t reg_intr_en; - uint32_t reg_event_ctrl; - uint32_t reg_event; - - uint64_t cpu_time; - unsigned int cpu_time_valid; - - qemu_irq irq; -} CadenceTimerState; - -#define TYPE_CADENCE_TTC "cadence_ttc" -OBJECT_DECLARE_SIMPLE_TYPE(CadenceTTCState, CADENCE_TTC) - -struct CadenceTTCState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - CadenceTimerState timer[3]; -}; - static void cadence_timer_update(CadenceTimerState *s) { qemu_set_irq(s->irq, !!(s->reg_intr & s->reg_intr_en)); -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Connect the 4 TTC timers on the ZynqMP. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Message-id: 20220331222017.2914409-3-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 4 ++++ hw/arm/xlnx-zynqmp.c | 22 ++++++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/misc/xlnx-zynqmp-apu-ctrl.h" #include "hw/misc/xlnx-zynqmp-crf.h" +#include "hw/timer/cadence_ttc.h" #define TYPE_XLNX_ZYNQMP "xlnx-zynqmp" OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) #define XLNX_ZYNQMP_MAX_RAM_SIZE (XLNX_ZYNQMP_MAX_LOW_RAM_SIZE + \ XLNX_ZYNQMP_MAX_HIGH_RAM_SIZE) +#define XLNX_ZYNQMP_NUM_TTC 4 + /* * Unimplemented mmio regions needed to boot some images. */ @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { qemu_or_irq qspi_irq_orgate; XlnxZynqMPAPUCtrl apu_ctrl; XlnxZynqMPCRF crf; + CadenceTTCState ttc[XLNX_ZYNQMP_NUM_TTC]; char *boot_cpu; ARMCPU *boot_cpu_ptr; diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zynqmp.c +++ b/hw/arm/xlnx-zynqmp.c @@ -XXX,XX +XXX,XX @@ #define APU_ADDR 0xfd5c0000 #define APU_IRQ 153 +#define TTC0_ADDR 0xFF110000 +#define TTC0_IRQ 36 + #define IPI_ADDR 0xFF300000 #define IPI_IRQ 64 @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_create_crf(XlnxZynqMPState *s, qemu_irq *gic) sysbus_connect_irq(sbd, 0, gic[CRF_IRQ]); } +static void xlnx_zynqmp_create_ttc(XlnxZynqMPState *s, qemu_irq *gic) +{ + SysBusDevice *sbd; + int i, irq; + + for (i = 0; i < XLNX_ZYNQMP_NUM_TTC; i++) { + object_initialize_child(OBJECT(s), "ttc[*]", &s->ttc[i], + TYPE_CADENCE_TTC); + sbd = SYS_BUS_DEVICE(&s->ttc[i]); + + sysbus_realize(sbd, &error_fatal); + sysbus_mmio_map(sbd, 0, TTC0_ADDR + i * 0x10000); + for (irq = 0; irq < 3; irq++) { + sysbus_connect_irq(sbd, irq, gic[TTC0_IRQ + i * 3 + irq]); + } + } +} + static void xlnx_zynqmp_create_unimp_mmio(XlnxZynqMPState *s) { static const struct UnimpInfo { @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) xlnx_zynqmp_create_efuse(s, gic_spi); xlnx_zynqmp_create_apu_ctrl(s, gic_spi); xlnx_zynqmp_create_crf(s, gic_spi); + xlnx_zynqmp_create_ttc(s, gic_spi); xlnx_zynqmp_create_unimp_mmio(s); for (i = 0; i < XLNX_ZYNQMP_NUM_GDMA_CH; i++) { -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Create an APU CPU Cluster. This is in preparation to add the RPU. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20220406174303.2022038-2-edgar.iglesias@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 2 ++ hw/arm/xlnx-versal.c | 9 ++++++++- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/arm/boot.h" +#include "hw/cpu/cluster.h" #include "hw/or-irq.h" #include "hw/sd/sdhci.h" #include "hw/intc/arm_gicv3.h" @@ -XXX,XX +XXX,XX @@ struct Versal { struct { struct { MemoryRegion mr; + CPUClusterState cluster; ARMCPU cpu[XLNX_VERSAL_NR_ACPUS]; GICv3State gic; } apu; diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) { int i; + object_initialize_child(OBJECT(s), "apu-cluster", &s->fpd.apu.cluster, + TYPE_CPU_CLUSTER); + qdev_prop_set_uint32(DEVICE(&s->fpd.apu.cluster), "cluster-id", 0); + for (i = 0; i < ARRAY_SIZE(s->fpd.apu.cpu); i++) { Object *obj; - object_initialize_child(OBJECT(s), "apu-cpu[*]", &s->fpd.apu.cpu[i], + object_initialize_child(OBJECT(&s->fpd.apu.cluster), + "apu-cpu[*]", &s->fpd.apu.cpu[i], XLNX_VERSAL_ACPU_TYPE); obj = OBJECT(&s->fpd.apu.cpu[i]); if (i) { @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) &error_abort); qdev_realize(DEVICE(obj), NULL, &error_fatal); } + + qdev_realize(DEVICE(&s->fpd.apu.cluster), NULL, &error_fatal); } static void versal_create_apu_gic(Versal *s, qemu_irq *pic) -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Add the Cortex-R5Fs of the Versal RPU (Real-time Processing Unit) subsystem. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20220406174303.2022038-3-edgar.iglesias@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 10 ++++++++++ hw/arm/xlnx-versal-virt.c | 6 +++--- hw/arm/xlnx-versal.c | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 49 insertions(+), 3 deletions(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) #define XLNX_VERSAL_NR_ACPUS 2 +#define XLNX_VERSAL_NR_RCPUS 2 #define XLNX_VERSAL_NR_UARTS 2 #define XLNX_VERSAL_NR_GEMS 2 #define XLNX_VERSAL_NR_ADMAS 8 @@ -XXX,XX +XXX,XX @@ struct Versal { VersalUsb2 usb; } iou; + /* Real-time Processing Unit. */ + struct { + MemoryRegion mr; + MemoryRegion mr_ps_alias; + + CPUClusterState cluster; + ARMCPU cpu[XLNX_VERSAL_NR_RCPUS]; + } rpu; + struct { qemu_or_irq irq_orgate; XlnxXramCtrl ctrl[XLNX_VERSAL_NR_XRAM]; diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ static void versal_virt_machine_class_init(ObjectClass *oc, void *data) mc->desc = "Xilinx Versal Virtual development board"; mc->init = versal_virt_init; - mc->min_cpus = XLNX_VERSAL_NR_ACPUS; - mc->max_cpus = XLNX_VERSAL_NR_ACPUS; - mc->default_cpus = XLNX_VERSAL_NR_ACPUS; + mc->min_cpus = XLNX_VERSAL_NR_ACPUS + XLNX_VERSAL_NR_RCPUS; + mc->max_cpus = XLNX_VERSAL_NR_ACPUS + XLNX_VERSAL_NR_RCPUS; + mc->default_cpus = XLNX_VERSAL_NR_ACPUS + XLNX_VERSAL_NR_RCPUS; mc->no_cdrom = true; mc->default_ram_id = "ddr"; } diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #define XLNX_VERSAL_ACPU_TYPE ARM_CPU_TYPE_NAME("cortex-a72") +#define XLNX_VERSAL_RCPU_TYPE ARM_CPU_TYPE_NAME("cortex-r5f") #define GEM_REVISION 0x40070106 #define VERSAL_NUM_PMC_APB_IRQS 3 @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_gic(Versal *s, qemu_irq *pic) } } +static void versal_create_rpu_cpus(Versal *s) +{ + int i; + + object_initialize_child(OBJECT(s), "rpu-cluster", &s->lpd.rpu.cluster, + TYPE_CPU_CLUSTER); + qdev_prop_set_uint32(DEVICE(&s->lpd.rpu.cluster), "cluster-id", 1); + + for (i = 0; i < ARRAY_SIZE(s->lpd.rpu.cpu); i++) { + Object *obj; + + object_initialize_child(OBJECT(&s->lpd.rpu.cluster), + "rpu-cpu[*]", &s->lpd.rpu.cpu[i], + XLNX_VERSAL_RCPU_TYPE); + obj = OBJECT(&s->lpd.rpu.cpu[i]); + object_property_set_bool(obj, "start-powered-off", true, + &error_abort); + + object_property_set_int(obj, "mp-affinity", 0x100 | i, &error_abort); + object_property_set_int(obj, "core-count", ARRAY_SIZE(s->lpd.rpu.cpu), + &error_abort); + object_property_set_link(obj, "memory", OBJECT(&s->lpd.rpu.mr), + &error_abort); + qdev_realize(DEVICE(obj), NULL, &error_fatal); + } + + qdev_realize(DEVICE(&s->lpd.rpu.cluster), NULL, &error_fatal); +} + static void versal_create_uarts(Versal *s, qemu_irq *pic) { int i; @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_apu_cpus(s); versal_create_apu_gic(s, pic); + versal_create_rpu_cpus(s); versal_create_uarts(s, pic); versal_create_usbs(s, pic); versal_create_gems(s, pic); @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) memory_region_add_subregion_overlap(&s->mr_ps, MM_OCM, &s->lpd.mr_ocm, 0); memory_region_add_subregion_overlap(&s->fpd.apu.mr, 0, &s->mr_ps, 0); + memory_region_add_subregion_overlap(&s->lpd.rpu.mr, 0, + &s->lpd.rpu.mr_ps_alias, 0); } static void versal_init(Object *obj) @@ -XXX,XX +XXX,XX @@ static void versal_init(Object *obj) Versal *s = XLNX_VERSAL(obj); memory_region_init(&s->fpd.apu.mr, obj, "mr-apu", UINT64_MAX); + memory_region_init(&s->lpd.rpu.mr, obj, "mr-rpu", UINT64_MAX); memory_region_init(&s->mr_ps, obj, "mr-ps-switch", UINT64_MAX); + memory_region_init_alias(&s->lpd.rpu.mr_ps_alias, OBJECT(s), + "mr-rpu-ps-alias", &s->mr_ps, 0, UINT64_MAX); } static Property versal_properties[] = { -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Add a model of the Xilinx Versal CRL. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Frederic Konrad <fkonrad@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20220406174303.2022038-4-edgar.iglesias@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/xlnx-versal-crl.h | 235 +++++++++++++++++ hw/misc/xlnx-versal-crl.c | 421 ++++++++++++++++++++++++++++++ hw/misc/meson.build | 1 + 3 files changed, 657 insertions(+) create mode 100644 include/hw/misc/xlnx-versal-crl.h create mode 100644 hw/misc/xlnx-versal-crl.c diff --git a/include/hw/misc/xlnx-versal-crl.h b/include/hw/misc/xlnx-versal-crl.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/xlnx-versal-crl.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Clock-Reset-LPD (CRL). + * + * Copyright (c) 2022 Xilinx Inc. + * SPDX-License-Identifier: GPL-2.0-or-later + * + * Written by Edgar E. Iglesias <edgar.iglesias@xilinx.com> + */ +#ifndef HW_MISC_XLNX_VERSAL_CRL_H +#define HW_MISC_XLNX_VERSAL_CRL_H + +#include "hw/sysbus.h" +#include "hw/register.h" +#include "target/arm/cpu.h" + +#define TYPE_XLNX_VERSAL_CRL "xlnx,versal-crl" +OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCRL, XLNX_VERSAL_CRL) + +REG32(ERR_CTRL, 0x0) + FIELD(ERR_CTRL, SLVERR_ENABLE, 0, 1) +REG32(IR_STATUS, 0x4) + FIELD(IR_STATUS, ADDR_DECODE_ERR, 0, 1) +REG32(IR_MASK, 0x8) + FIELD(IR_MASK, ADDR_DECODE_ERR, 0, 1) +REG32(IR_ENABLE, 0xc) + FIELD(IR_ENABLE, ADDR_DECODE_ERR, 0, 1) +REG32(IR_DISABLE, 0x10) + FIELD(IR_DISABLE, ADDR_DECODE_ERR, 0, 1) +REG32(WPROT, 0x1c) + FIELD(WPROT, ACTIVE, 0, 1) +REG32(PLL_CLK_OTHER_DMN, 0x20) + FIELD(PLL_CLK_OTHER_DMN, APLL_BYPASS, 0, 1) +REG32(RPLL_CTRL, 0x40) + FIELD(RPLL_CTRL, POST_SRC, 24, 3) + FIELD(RPLL_CTRL, PRE_SRC, 20, 3) + FIELD(RPLL_CTRL, CLKOUTDIV, 16, 2) + FIELD(RPLL_CTRL, FBDIV, 8, 8) + FIELD(RPLL_CTRL, BYPASS, 3, 1) + FIELD(RPLL_CTRL, RESET, 0, 1) +REG32(RPLL_CFG, 0x44) + FIELD(RPLL_CFG, LOCK_DLY, 25, 7) + FIELD(RPLL_CFG, LOCK_CNT, 13, 10) + FIELD(RPLL_CFG, LFHF, 10, 2) + FIELD(RPLL_CFG, CP, 5, 4) + FIELD(RPLL_CFG, RES, 0, 4) +REG32(RPLL_FRAC_CFG, 0x48) + FIELD(RPLL_FRAC_CFG, ENABLED, 31, 1) + FIELD(RPLL_FRAC_CFG, SEED, 22, 3) + FIELD(RPLL_FRAC_CFG, ALGRTHM, 19, 1) + FIELD(RPLL_FRAC_CFG, ORDER, 18, 1) + FIELD(RPLL_FRAC_CFG, DATA, 0, 16) +REG32(PLL_STATUS, 0x50) + FIELD(PLL_STATUS, RPLL_STABLE, 2, 1) + FIELD(PLL_STATUS, RPLL_LOCK, 0, 1) +REG32(RPLL_TO_XPD_CTRL, 0x100) + FIELD(RPLL_TO_XPD_CTRL, CLKACT, 25, 1) + FIELD(RPLL_TO_XPD_CTRL, DIVISOR0, 8, 10) +REG32(LPD_TOP_SWITCH_CTRL, 0x104) + FIELD(LPD_TOP_SWITCH_CTRL, CLKACT_ADMA, 26, 1) + FIELD(LPD_TOP_SWITCH_CTRL, CLKACT, 25, 1) + FIELD(LPD_TOP_SWITCH_CTRL, DIVISOR0, 8, 10) + FIELD(LPD_TOP_SWITCH_CTRL, SRCSEL, 0, 3) +REG32(LPD_LSBUS_CTRL, 0x108) + FIELD(LPD_LSBUS_CTRL, CLKACT, 25, 1) + FIELD(LPD_LSBUS_CTRL, DIVISOR0, 8, 10) + FIELD(LPD_LSBUS_CTRL, SRCSEL, 0, 3) +REG32(CPU_R5_CTRL, 0x10c) + FIELD(CPU_R5_CTRL, CLKACT_OCM2, 28, 1) + FIELD(CPU_R5_CTRL, CLKACT_OCM, 27, 1) + FIELD(CPU_R5_CTRL, CLKACT_CORE, 26, 1) + FIELD(CPU_R5_CTRL, CLKACT, 25, 1) + FIELD(CPU_R5_CTRL, DIVISOR0, 8, 10) + FIELD(CPU_R5_CTRL, SRCSEL, 0, 3) +REG32(IOU_SWITCH_CTRL, 0x114) + FIELD(IOU_SWITCH_CTRL, CLKACT, 25, 1) + FIELD(IOU_SWITCH_CTRL, DIVISOR0, 8, 10) + FIELD(IOU_SWITCH_CTRL, SRCSEL, 0, 3) +REG32(GEM0_REF_CTRL, 0x118) + FIELD(GEM0_REF_CTRL, CLKACT_RX, 27, 1) + FIELD(GEM0_REF_CTRL, CLKACT_TX, 26, 1) + FIELD(GEM0_REF_CTRL, CLKACT, 25, 1) + FIELD(GEM0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(GEM0_REF_CTRL, SRCSEL, 0, 3) +REG32(GEM1_REF_CTRL, 0x11c) + FIELD(GEM1_REF_CTRL, CLKACT_RX, 27, 1) + FIELD(GEM1_REF_CTRL, CLKACT_TX, 26, 1) + FIELD(GEM1_REF_CTRL, CLKACT, 25, 1) + FIELD(GEM1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(GEM1_REF_CTRL, SRCSEL, 0, 3) +REG32(GEM_TSU_REF_CTRL, 0x120) + FIELD(GEM_TSU_REF_CTRL, CLKACT, 25, 1) + FIELD(GEM_TSU_REF_CTRL, DIVISOR0, 8, 10) + FIELD(GEM_TSU_REF_CTRL, SRCSEL, 0, 3) +REG32(USB0_BUS_REF_CTRL, 0x124) + FIELD(USB0_BUS_REF_CTRL, CLKACT, 25, 1) + FIELD(USB0_BUS_REF_CTRL, DIVISOR0, 8, 10) + FIELD(USB0_BUS_REF_CTRL, SRCSEL, 0, 3) +REG32(UART0_REF_CTRL, 0x128) + FIELD(UART0_REF_CTRL, CLKACT, 25, 1) + FIELD(UART0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(UART0_REF_CTRL, SRCSEL, 0, 3) +REG32(UART1_REF_CTRL, 0x12c) + FIELD(UART1_REF_CTRL, CLKACT, 25, 1) + FIELD(UART1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(UART1_REF_CTRL, SRCSEL, 0, 3) +REG32(SPI0_REF_CTRL, 0x130) + FIELD(SPI0_REF_CTRL, CLKACT, 25, 1) + FIELD(SPI0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(SPI0_REF_CTRL, SRCSEL, 0, 3) +REG32(SPI1_REF_CTRL, 0x134) + FIELD(SPI1_REF_CTRL, CLKACT, 25, 1) + FIELD(SPI1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(SPI1_REF_CTRL, SRCSEL, 0, 3) +REG32(CAN0_REF_CTRL, 0x138) + FIELD(CAN0_REF_CTRL, CLKACT, 25, 1) + FIELD(CAN0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(CAN0_REF_CTRL, SRCSEL, 0, 3) +REG32(CAN1_REF_CTRL, 0x13c) + FIELD(CAN1_REF_CTRL, CLKACT, 25, 1) + FIELD(CAN1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(CAN1_REF_CTRL, SRCSEL, 0, 3) +REG32(I2C0_REF_CTRL, 0x140) + FIELD(I2C0_REF_CTRL, CLKACT, 25, 1) + FIELD(I2C0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(I2C0_REF_CTRL, SRCSEL, 0, 3) +REG32(I2C1_REF_CTRL, 0x144) + FIELD(I2C1_REF_CTRL, CLKACT, 25, 1) + FIELD(I2C1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(I2C1_REF_CTRL, SRCSEL, 0, 3) +REG32(DBG_LPD_CTRL, 0x148) + FIELD(DBG_LPD_CTRL, CLKACT, 25, 1) + FIELD(DBG_LPD_CTRL, DIVISOR0, 8, 10) + FIELD(DBG_LPD_CTRL, SRCSEL, 0, 3) +REG32(TIMESTAMP_REF_CTRL, 0x14c) + FIELD(TIMESTAMP_REF_CTRL, CLKACT, 25, 1) + FIELD(TIMESTAMP_REF_CTRL, DIVISOR0, 8, 10) + FIELD(TIMESTAMP_REF_CTRL, SRCSEL, 0, 3) +REG32(CRL_SAFETY_CHK, 0x150) +REG32(PSM_REF_CTRL, 0x154) + FIELD(PSM_REF_CTRL, DIVISOR0, 8, 10) + FIELD(PSM_REF_CTRL, SRCSEL, 0, 3) +REG32(DBG_TSTMP_CTRL, 0x158) + FIELD(DBG_TSTMP_CTRL, CLKACT, 25, 1) + FIELD(DBG_TSTMP_CTRL, DIVISOR0, 8, 10) + FIELD(DBG_TSTMP_CTRL, SRCSEL, 0, 3) +REG32(CPM_TOPSW_REF_CTRL, 0x15c) + FIELD(CPM_TOPSW_REF_CTRL, CLKACT, 25, 1) + FIELD(CPM_TOPSW_REF_CTRL, DIVISOR0, 8, 10) + FIELD(CPM_TOPSW_REF_CTRL, SRCSEL, 0, 3) +REG32(USB3_DUAL_REF_CTRL, 0x160) + FIELD(USB3_DUAL_REF_CTRL, CLKACT, 25, 1) + FIELD(USB3_DUAL_REF_CTRL, DIVISOR0, 8, 10) + FIELD(USB3_DUAL_REF_CTRL, SRCSEL, 0, 3) +REG32(RST_CPU_R5, 0x300) + FIELD(RST_CPU_R5, RESET_PGE, 4, 1) + FIELD(RST_CPU_R5, RESET_AMBA, 2, 1) + FIELD(RST_CPU_R5, RESET_CPU1, 1, 1) + FIELD(RST_CPU_R5, RESET_CPU0, 0, 1) +REG32(RST_ADMA, 0x304) + FIELD(RST_ADMA, RESET, 0, 1) +REG32(RST_GEM0, 0x308) + FIELD(RST_GEM0, RESET, 0, 1) +REG32(RST_GEM1, 0x30c) + FIELD(RST_GEM1, RESET, 0, 1) +REG32(RST_SPARE, 0x310) + FIELD(RST_SPARE, RESET, 0, 1) +REG32(RST_USB0, 0x314) + FIELD(RST_USB0, RESET, 0, 1) +REG32(RST_UART0, 0x318) + FIELD(RST_UART0, RESET, 0, 1) +REG32(RST_UART1, 0x31c) + FIELD(RST_UART1, RESET, 0, 1) +REG32(RST_SPI0, 0x320) + FIELD(RST_SPI0, RESET, 0, 1) +REG32(RST_SPI1, 0x324) + FIELD(RST_SPI1, RESET, 0, 1) +REG32(RST_CAN0, 0x328) + FIELD(RST_CAN0, RESET, 0, 1) +REG32(RST_CAN1, 0x32c) + FIELD(RST_CAN1, RESET, 0, 1) +REG32(RST_I2C0, 0x330) + FIELD(RST_I2C0, RESET, 0, 1) +REG32(RST_I2C1, 0x334) + FIELD(RST_I2C1, RESET, 0, 1) +REG32(RST_DBG_LPD, 0x338) + FIELD(RST_DBG_LPD, RPU_DBG1_RESET, 5, 1) + FIELD(RST_DBG_LPD, RPU_DBG0_RESET, 4, 1) + FIELD(RST_DBG_LPD, RESET_HSDP, 1, 1) + FIELD(RST_DBG_LPD, RESET, 0, 1) +REG32(RST_GPIO, 0x33c) + FIELD(RST_GPIO, RESET, 0, 1) +REG32(RST_TTC, 0x344) + FIELD(RST_TTC, TTC3_RESET, 3, 1) + FIELD(RST_TTC, TTC2_RESET, 2, 1) + FIELD(RST_TTC, TTC1_RESET, 1, 1) + FIELD(RST_TTC, TTC0_RESET, 0, 1) +REG32(RST_TIMESTAMP, 0x348) + FIELD(RST_TIMESTAMP, RESET, 0, 1) +REG32(RST_SWDT, 0x34c) + FIELD(RST_SWDT, RESET, 0, 1) +REG32(RST_OCM, 0x350) + FIELD(RST_OCM, RESET, 0, 1) +REG32(RST_IPI, 0x354) + FIELD(RST_IPI, RESET, 0, 1) +REG32(RST_SYSMON, 0x358) + FIELD(RST_SYSMON, SEQ_RST, 1, 1) + FIELD(RST_SYSMON, CFG_RST, 0, 1) +REG32(RST_FPD, 0x360) + FIELD(RST_FPD, SRST, 1, 1) + FIELD(RST_FPD, POR, 0, 1) +REG32(PSM_RST_MODE, 0x370) + FIELD(PSM_RST_MODE, WAKEUP, 2, 1) + FIELD(PSM_RST_MODE, RST_MODE, 0, 2) + +#define CRL_R_MAX (R_PSM_RST_MODE + 1) + +#define RPU_MAX_CPU 2 + +struct XlnxVersalCRL { + SysBusDevice parent_obj; + qemu_irq irq; + + struct { + ARMCPU *cpu_r5[RPU_MAX_CPU]; + DeviceState *adma[8]; + DeviceState *uart[2]; + DeviceState *gem[2]; + DeviceState *usb; + } cfg; + + RegisterInfoArray *reg_array; + uint32_t regs[CRL_R_MAX]; + RegisterInfo regs_info[CRL_R_MAX]; +}; +#endif diff --git a/hw/misc/xlnx-versal-crl.c b/hw/misc/xlnx-versal-crl.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/xlnx-versal-crl.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Clock-Reset-LPD (CRL). + * + * Copyright (c) 2022 Advanced Micro Devices, Inc. + * SPDX-License-Identifier: GPL-2.0-or-later + * + * Written by Edgar E. Iglesias <edgar.iglesias@amd.com> + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/log.h" +#include "qemu/bitops.h" +#include "migration/vmstate.h" +#include "hw/qdev-properties.h" +#include "hw/sysbus.h" +#include "hw/irq.h" +#include "hw/register.h" +#include "hw/resettable.h" + +#include "target/arm/arm-powerctl.h" +#include "hw/misc/xlnx-versal-crl.h" + +#ifndef XLNX_VERSAL_CRL_ERR_DEBUG +#define XLNX_VERSAL_CRL_ERR_DEBUG 0 +#endif + +static void crl_update_irq(XlnxVersalCRL *s) +{ + bool pending = s->regs[R_IR_STATUS] & ~s->regs[R_IR_MASK]; + qemu_set_irq(s->irq, pending); +} + +static void crl_status_postw(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + crl_update_irq(s); +} + +static uint64_t crl_enable_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + uint32_t val = val64; + + s->regs[R_IR_MASK] &= ~val; + crl_update_irq(s); + return 0; +} + +static uint64_t crl_disable_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + uint32_t val = val64; + + s->regs[R_IR_MASK] |= val; + crl_update_irq(s); + return 0; +} + +static void crl_reset_dev(XlnxVersalCRL *s, DeviceState *dev, + bool rst_old, bool rst_new) +{ + device_cold_reset(dev); +} + +static void crl_reset_cpu(XlnxVersalCRL *s, ARMCPU *armcpu, + bool rst_old, bool rst_new) +{ + if (rst_new) { + arm_set_cpu_off(armcpu->mp_affinity); + } else { + arm_set_cpu_on_and_reset(armcpu->mp_affinity); + } +} + +#define REGFIELD_RESET(type, s, reg, f, new_val, dev) { \ + bool old_f = ARRAY_FIELD_EX32((s)->regs, reg, f); \ + bool new_f = FIELD_EX32(new_val, reg, f); \ + \ + /* Detect edges. */ \ + if (dev && old_f != new_f) { \ + crl_reset_ ## type(s, dev, old_f, new_f); \ + } \ +} + +static uint64_t crl_rst_r5_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(cpu, s, RST_CPU_R5, RESET_CPU0, val64, s->cfg.cpu_r5[0]); + REGFIELD_RESET(cpu, s, RST_CPU_R5, RESET_CPU1, val64, s->cfg.cpu_r5[1]); + return val64; +} + +static uint64_t crl_rst_adma_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + int i; + + /* A single register fans out to all ADMA reset inputs. */ + for (i = 0; i < ARRAY_SIZE(s->cfg.adma); i++) { + REGFIELD_RESET(dev, s, RST_ADMA, RESET, val64, s->cfg.adma[i]); + } + return val64; +} + +static uint64_t crl_rst_uart0_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_UART0, RESET, val64, s->cfg.uart[0]); + return val64; +} + +static uint64_t crl_rst_uart1_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_UART1, RESET, val64, s->cfg.uart[1]); + return val64; +} + +static uint64_t crl_rst_gem0_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_GEM0, RESET, val64, s->cfg.gem[0]); + return val64; +} + +static uint64_t crl_rst_gem1_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_GEM1, RESET, val64, s->cfg.gem[1]); + return val64; +} + +static uint64_t crl_rst_usb_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_USB0, RESET, val64, s->cfg.usb); + return val64; +} + +static const RegisterAccessInfo crl_regs_info[] = { + { .name = "ERR_CTRL", .addr = A_ERR_CTRL, + },{ .name = "IR_STATUS", .addr = A_IR_STATUS, + .w1c = 0x1, + .post_write = crl_status_postw, + },{ .name = "IR_MASK", .addr = A_IR_MASK, + .reset = 0x1, + .ro = 0x1, + },{ .name = "IR_ENABLE", .addr = A_IR_ENABLE, + .pre_write = crl_enable_prew, + },{ .name = "IR_DISABLE", .addr = A_IR_DISABLE, + .pre_write = crl_disable_prew, + },{ .name = "WPROT", .addr = A_WPROT, + },{ .name = "PLL_CLK_OTHER_DMN", .addr = A_PLL_CLK_OTHER_DMN, + .reset = 0x1, + .rsvd = 0xe, + },{ .name = "RPLL_CTRL", .addr = A_RPLL_CTRL, + .reset = 0x24809, + .rsvd = 0xf88c00f6, + },{ .name = "RPLL_CFG", .addr = A_RPLL_CFG, + .reset = 0x2000000, + .rsvd = 0x1801210, + },{ .name = "RPLL_FRAC_CFG", .addr = A_RPLL_FRAC_CFG, + .rsvd = 0x7e330000, + },{ .name = "PLL_STATUS", .addr = A_PLL_STATUS, + .reset = R_PLL_STATUS_RPLL_STABLE_MASK | + R_PLL_STATUS_RPLL_LOCK_MASK, + .rsvd = 0xfa, + .ro = 0x5, + },{ .name = "RPLL_TO_XPD_CTRL", .addr = A_RPLL_TO_XPD_CTRL, + .reset = 0x2000100, + .rsvd = 0xfdfc00ff, + },{ .name = "LPD_TOP_SWITCH_CTRL", .addr = A_LPD_TOP_SWITCH_CTRL, + .reset = 0x6000300, + .rsvd = 0xf9fc00f8, + },{ .name = "LPD_LSBUS_CTRL", .addr = A_LPD_LSBUS_CTRL, + .reset = 0x2000800, + .rsvd = 0xfdfc00f8, + },{ .name = "CPU_R5_CTRL", .addr = A_CPU_R5_CTRL, + .reset = 0xe000300, + .rsvd = 0xe1fc00f8, + },{ .name = "IOU_SWITCH_CTRL", .addr = A_IOU_SWITCH_CTRL, + .reset = 0x2000500, + .rsvd = 0xfdfc00f8, + },{ .name = "GEM0_REF_CTRL", .addr = A_GEM0_REF_CTRL, + .reset = 0xe000a00, + .rsvd = 0xf1fc00f8, + },{ .name = "GEM1_REF_CTRL", .addr = A_GEM1_REF_CTRL, + .reset = 0xe000a00, + .rsvd = 0xf1fc00f8, + },{ .name = "GEM_TSU_REF_CTRL", .addr = A_GEM_TSU_REF_CTRL, + .reset = 0x300, + .rsvd = 0xfdfc00f8, + },{ .name = "USB0_BUS_REF_CTRL", .addr = A_USB0_BUS_REF_CTRL, + .reset = 0x2001900, + .rsvd = 0xfdfc00f8, + },{ .name = "UART0_REF_CTRL", .addr = A_UART0_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "UART1_REF_CTRL", .addr = A_UART1_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "SPI0_REF_CTRL", .addr = A_SPI0_REF_CTRL, + .reset = 0x600, + .rsvd = 0xfdfc00f8, + },{ .name = "SPI1_REF_CTRL", .addr = A_SPI1_REF_CTRL, + .reset = 0x600, + .rsvd = 0xfdfc00f8, + },{ .name = "CAN0_REF_CTRL", .addr = A_CAN0_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "CAN1_REF_CTRL", .addr = A_CAN1_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "I2C0_REF_CTRL", .addr = A_I2C0_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "I2C1_REF_CTRL", .addr = A_I2C1_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "DBG_LPD_CTRL", .addr = A_DBG_LPD_CTRL, + .reset = 0x300, + .rsvd = 0xfdfc00f8, + },{ .name = "TIMESTAMP_REF_CTRL", .addr = A_TIMESTAMP_REF_CTRL, + .reset = 0x2000c00, + .rsvd = 0xfdfc00f8, + },{ .name = "CRL_SAFETY_CHK", .addr = A_CRL_SAFETY_CHK, + },{ .name = "PSM_REF_CTRL", .addr = A_PSM_REF_CTRL, + .reset = 0xf04, + .rsvd = 0xfffc00f8, + },{ .name = "DBG_TSTMP_CTRL", .addr = A_DBG_TSTMP_CTRL, + .reset = 0x300, + .rsvd = 0xfdfc00f8, + },{ .name = "CPM_TOPSW_REF_CTRL", .addr = A_CPM_TOPSW_REF_CTRL, + .reset = 0x300, + .rsvd = 0xfdfc00f8, + },{ .name = "USB3_DUAL_REF_CTRL", .addr = A_USB3_DUAL_REF_CTRL, + .reset = 0x3c00, + .rsvd = 0xfdfc00f8, + },{ .name = "RST_CPU_R5", .addr = A_RST_CPU_R5, + .reset = 0x17, + .rsvd = 0x8, + .pre_write = crl_rst_r5_prew, + },{ .name = "RST_ADMA", .addr = A_RST_ADMA, + .reset = 0x1, + .pre_write = crl_rst_adma_prew, + },{ .name = "RST_GEM0", .addr = A_RST_GEM0, + .reset = 0x1, + .pre_write = crl_rst_gem0_prew, + },{ .name = "RST_GEM1", .addr = A_RST_GEM1, + .reset = 0x1, + .pre_write = crl_rst_gem1_prew, + },{ .name = "RST_SPARE", .addr = A_RST_SPARE, + .reset = 0x1, + },{ .name = "RST_USB0", .addr = A_RST_USB0, + .reset = 0x1, + .pre_write = crl_rst_usb_prew, + },{ .name = "RST_UART0", .addr = A_RST_UART0, + .reset = 0x1, + .pre_write = crl_rst_uart0_prew, + },{ .name = "RST_UART1", .addr = A_RST_UART1, + .reset = 0x1, + .pre_write = crl_rst_uart1_prew, + },{ .name = "RST_SPI0", .addr = A_RST_SPI0, + .reset = 0x1, + },{ .name = "RST_SPI1", .addr = A_RST_SPI1, + .reset = 0x1, + },{ .name = "RST_CAN0", .addr = A_RST_CAN0, + .reset = 0x1, + },{ .name = "RST_CAN1", .addr = A_RST_CAN1, + .reset = 0x1, + },{ .name = "RST_I2C0", .addr = A_RST_I2C0, + .reset = 0x1, + },{ .name = "RST_I2C1", .addr = A_RST_I2C1, + .reset = 0x1, + },{ .name = "RST_DBG_LPD", .addr = A_RST_DBG_LPD, + .reset = 0x33, + .rsvd = 0xcc, + },{ .name = "RST_GPIO", .addr = A_RST_GPIO, + .reset = 0x1, + },{ .name = "RST_TTC", .addr = A_RST_TTC, + .reset = 0xf, + },{ .name = "RST_TIMESTAMP", .addr = A_RST_TIMESTAMP, + .reset = 0x1, + },{ .name = "RST_SWDT", .addr = A_RST_SWDT, + .reset = 0x1, + },{ .name = "RST_OCM", .addr = A_RST_OCM, + },{ .name = "RST_IPI", .addr = A_RST_IPI, + },{ .name = "RST_FPD", .addr = A_RST_FPD, + .reset = 0x3, + },{ .name = "PSM_RST_MODE", .addr = A_PSM_RST_MODE, + .reset = 0x1, + .rsvd = 0xf8, + } +}; + +static void crl_reset_enter(Object *obj, ResetType type) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(obj); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { + register_reset(&s->regs_info[i]); + } +} + +static void crl_reset_hold(Object *obj) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(obj); + + crl_update_irq(s); +} + +static const MemoryRegionOps crl_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void crl_init(Object *obj) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + int i; + + s->reg_array = + register_init_block32(DEVICE(obj), crl_regs_info, + ARRAY_SIZE(crl_regs_info), + s->regs_info, s->regs, + &crl_ops, + XLNX_VERSAL_CRL_ERR_DEBUG, + CRL_R_MAX * 4); + sysbus_init_mmio(sbd, &s->reg_array->mem); + sysbus_init_irq(sbd, &s->irq); + + for (i = 0; i < ARRAY_SIZE(s->cfg.cpu_r5); ++i) { + object_property_add_link(obj, "cpu_r5[*]", TYPE_ARM_CPU, + (Object **)&s->cfg.cpu_r5[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); + } + + for (i = 0; i < ARRAY_SIZE(s->cfg.adma); ++i) { + object_property_add_link(obj, "adma[*]", TYPE_DEVICE, + (Object **)&s->cfg.adma[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); + } + + for (i = 0; i < ARRAY_SIZE(s->cfg.uart); ++i) { + object_property_add_link(obj, "uart[*]", TYPE_DEVICE, + (Object **)&s->cfg.uart[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); + } + + for (i = 0; i < ARRAY_SIZE(s->cfg.gem); ++i) { + object_property_add_link(obj, "gem[*]", TYPE_DEVICE, + (Object **)&s->cfg.gem[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); + } + + object_property_add_link(obj, "usb", TYPE_DEVICE, + (Object **)&s->cfg.gem[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); +} + +static void crl_finalize(Object *obj) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(obj); + register_finalize_block(s->reg_array); +} + +static const VMStateDescription vmstate_crl = { + .name = TYPE_XLNX_VERSAL_CRL, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, XlnxVersalCRL, CRL_R_MAX), + VMSTATE_END_OF_LIST(), + } +}; + +static void crl_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_crl; + + rc->phases.enter = crl_reset_enter; + rc->phases.hold = crl_reset_hold; +} + +static const TypeInfo crl_info = { + .name = TYPE_XLNX_VERSAL_CRL, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxVersalCRL), + .class_init = crl_class_init, + .instance_init = crl_init, + .instance_finalize = crl_finalize, +}; + +static void crl_register_types(void) +{ + type_register_static(&crl_info); +} + +type_init(crl_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_SLAVIO', if_true: files('slavio_misc.c')) softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c')) specific_ss.add(when: 'CONFIG_XLNX_ZYNQMP_ARM', if_true: files('xlnx-zynqmp-crf.c')) specific_ss.add(when: 'CONFIG_XLNX_ZYNQMP_ARM', if_true: files('xlnx-zynqmp-apu-ctrl.c')) +specific_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-crl.c')) softmmu_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files( 'xlnx-versal-xramc.c', 'xlnx-versal-pmc-iou-slcr.c', -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Connect the CRL (Clock Reset LPD) to the Versal SoC. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Frederic Konrad <fkonrad@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20220406174303.2022038-5-edgar.iglesias@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 4 +++ hw/arm/xlnx-versal.c | 54 ++++++++++++++++++++++++++++++++++-- 2 files changed, 56 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/nvram/xlnx-versal-efuse.h" #include "hw/ssi/xlnx-versal-ospi.h" #include "hw/dma/xlnx_csu_dma.h" +#include "hw/misc/xlnx-versal-crl.h" #include "hw/misc/xlnx-versal-pmc-iou-slcr.h" #define TYPE_XLNX_VERSAL "xlnx-versal" @@ -XXX,XX +XXX,XX @@ struct Versal { qemu_or_irq irq_orgate; XlnxXramCtrl ctrl[XLNX_VERSAL_NR_XRAM]; } xram; + + XlnxVersalCRL crl; } lpd; /* The Platform Management Controller subsystem. */ @@ -XXX,XX +XXX,XX @@ struct Versal { #define VERSAL_TIMER_NS_EL1_IRQ 14 #define VERSAL_TIMER_NS_EL2_IRQ 10 +#define VERSAL_CRL_IRQ 10 #define VERSAL_UART0_IRQ_0 18 #define VERSAL_UART1_IRQ_0 19 #define VERSAL_USB0_IRQ_0 22 diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_ospi(Versal *s, qemu_irq *pic) qdev_connect_gpio_out(orgate, 0, pic[VERSAL_OSPI_IRQ]); } +static void versal_create_crl(Versal *s, qemu_irq *pic) +{ + SysBusDevice *sbd; + int i; + + object_initialize_child(OBJECT(s), "crl", &s->lpd.crl, + TYPE_XLNX_VERSAL_CRL); + sbd = SYS_BUS_DEVICE(&s->lpd.crl); + + for (i = 0; i < ARRAY_SIZE(s->lpd.rpu.cpu); i++) { + g_autofree gchar *name = g_strdup_printf("cpu_r5[%d]", i); + + object_property_set_link(OBJECT(&s->lpd.crl), + name, OBJECT(&s->lpd.rpu.cpu[i]), + &error_abort); + } + + for (i = 0; i < ARRAY_SIZE(s->lpd.iou.gem); i++) { + g_autofree gchar *name = g_strdup_printf("gem[%d]", i); + + object_property_set_link(OBJECT(&s->lpd.crl), + name, OBJECT(&s->lpd.iou.gem[i]), + &error_abort); + } + + for (i = 0; i < ARRAY_SIZE(s->lpd.iou.adma); i++) { + g_autofree gchar *name = g_strdup_printf("adma[%d]", i); + + object_property_set_link(OBJECT(&s->lpd.crl), + name, OBJECT(&s->lpd.iou.adma[i]), + &error_abort); + } + + for (i = 0; i < ARRAY_SIZE(s->lpd.iou.uart); i++) { + g_autofree gchar *name = g_strdup_printf("uart[%d]", i); + + object_property_set_link(OBJECT(&s->lpd.crl), + name, OBJECT(&s->lpd.iou.uart[i]), + &error_abort); + } + + object_property_set_link(OBJECT(&s->lpd.crl), + "usb", OBJECT(&s->lpd.iou.usb), + &error_abort); + + sysbus_realize(sbd, &error_fatal); + memory_region_add_subregion(&s->mr_ps, MM_CRL, + sysbus_mmio_get_region(sbd, 0)); + sysbus_connect_irq(sbd, 0, pic[VERSAL_CRL_IRQ]); +} + /* This takes the board allocated linear DDR memory and creates aliases * for each split DDR range/aperture on the Versal address map. */ @@ -XXX,XX +XXX,XX @@ static void versal_unimp(Versal *s) versal_unimp_area(s, "psm", &s->mr_ps, MM_PSM_START, MM_PSM_END - MM_PSM_START); - versal_unimp_area(s, "crl", &s->mr_ps, - MM_CRL, MM_CRL_SIZE); versal_unimp_area(s, "crf", &s->mr_ps, MM_FPD_CRF, MM_FPD_CRF_SIZE); versal_unimp_area(s, "apu", &s->mr_ps, @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_efuse(s, pic); versal_create_pmc_iou_slcr(s, pic); versal_create_ospi(s, pic); + versal_create_crl(s, pic); versal_map_ddr(s); versal_unimp(s); -- 2.25.1 The Exynos4210 SoC device currently uses a custom device "exynos4210.irq_gate" to model the OR gate that feeds each CPU's IRQ line. We have a standard TYPE_OR_IRQ device for this now, so use that instead. (This is a migration compatibility break, but that is OK for this machine type.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-2-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 1 + hw/arm/exynos4210.c | 31 ++++++++++++++++--------------- 2 files changed, 17 insertions(+), 15 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { MemoryRegion bootreg_mem; I2CBus *i2c_if[EXYNOS4210_I2C_NUMBER]; qemu_or_irq pl330_irq_orgate[EXYNOS4210_NUM_DMA]; + qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; }; #define TYPE_EXYNOS4210_SOC "exynos4210" diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) { Exynos4210State *s = EXYNOS4210_SOC(socdev); MemoryRegion *system_mem = get_system_memory(); - qemu_irq gate_irq[EXYNOS4210_NCPUS][EXYNOS4210_IRQ_GATE_NINPUTS]; SysBusDevice *busdev; DeviceState *dev, *uart[4], *pl330[3]; int i, n; @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) /* IRQ Gate */ for (i = 0; i < EXYNOS4210_NCPUS; i++) { - dev = qdev_new("exynos4210.irq_gate"); - qdev_prop_set_uint32(dev, "n_in", EXYNOS4210_IRQ_GATE_NINPUTS); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - /* Get IRQ Gate input in gate_irq */ - for (n = 0; n < EXYNOS4210_IRQ_GATE_NINPUTS; n++) { - gate_irq[i][n] = qdev_get_gpio_in(dev, n); - } - busdev = SYS_BUS_DEVICE(dev); - - /* Connect IRQ Gate output to CPU's IRQ line */ - sysbus_connect_irq(busdev, 0, - qdev_get_gpio_in(DEVICE(s->cpu[i]), ARM_CPU_IRQ)); + DeviceState *orgate = DEVICE(&s->cpu_irq_orgate[i]); + object_property_set_int(OBJECT(orgate), "num-lines", + EXYNOS4210_IRQ_GATE_NINPUTS, + &error_abort); + qdev_realize(orgate, NULL, &error_abort); + qdev_connect_gpio_out(orgate, 0, + qdev_get_gpio_in(DEVICE(s->cpu[i]), ARM_CPU_IRQ)); } /* Private memory region and Internal GIC */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_realize_and_unref(busdev, &error_fatal); sysbus_mmio_map(busdev, 0, EXYNOS4210_SMP_PRIVATE_BASE_ADDR); for (n = 0; n < EXYNOS4210_NCPUS; n++) { - sysbus_connect_irq(busdev, n, gate_irq[n][0]); + sysbus_connect_irq(busdev, n, + qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 0)); } for (n = 0; n < EXYNOS4210_INT_GIC_NIRQ; n++) { s->irqs.int_gic_irq[n] = qdev_get_gpio_in(dev, n); @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) /* Map Distributer interface */ sysbus_mmio_map(busdev, 1, EXYNOS4210_EXT_GIC_DIST_BASE_ADDR); for (n = 0; n < EXYNOS4210_NCPUS; n++) { - sysbus_connect_irq(busdev, n, gate_irq[n][1]); + sysbus_connect_irq(busdev, n, + qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 1)); } for (n = 0; n < EXYNOS4210_EXT_GIC_NIRQ; n++) { s->irqs.ext_gic_irq[n] = qdev_get_gpio_in(dev, n); @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) object_initialize_child(obj, name, orgate, TYPE_OR_IRQ); g_free(name); } + + for (i = 0; i < ARRAY_SIZE(s->cpu_irq_orgate); i++) { + g_autofree char *name = g_strdup_printf("cpu-irq-orgate%d", i); + object_initialize_child(obj, name, &s->cpu_irq_orgate[i], TYPE_OR_IRQ); + } } static void exynos4210_class_init(ObjectClass *klass, void *data) -- 2.25.1 Now we have removed the only use of TYPE_EXYNOS4210_IRQ_GATE we can delete the device entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Message-id: 20220404154658.565020-3-peter.maydell@linaro.org --- hw/intc/exynos4210_gic.c | 107 --------------------------------------- 1 file changed, 107 deletions(-) diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_gic_register_types(void) } type_init(exynos4210_gic_register_types) - -/* IRQ OR Gate struct. - * - * This device models an OR gate. There are n_in input qdev gpio lines and one - * output sysbus IRQ line. The output IRQ level is formed as OR between all - * gpio inputs. - */ - -#define TYPE_EXYNOS4210_IRQ_GATE "exynos4210.irq_gate" -OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210IRQGateState, EXYNOS4210_IRQ_GATE) - -struct Exynos4210IRQGateState { - SysBusDevice parent_obj; - - uint32_t n_in; /* inputs amount */ - uint32_t *level; /* input levels */ - qemu_irq out; /* output IRQ */ -}; - -static Property exynos4210_irq_gate_properties[] = { - DEFINE_PROP_UINT32("n_in", Exynos4210IRQGateState, n_in, 1), - DEFINE_PROP_END_OF_LIST(), -}; - -static const VMStateDescription vmstate_exynos4210_irq_gate = { - .name = "exynos4210.irq_gate", - .version_id = 2, - .minimum_version_id = 2, - .fields = (VMStateField[]) { - VMSTATE_VBUFFER_UINT32(level, Exynos4210IRQGateState, 1, NULL, n_in), - VMSTATE_END_OF_LIST() - } -}; - -/* Process a change in IRQ input. */ -static void exynos4210_irq_gate_handler(void *opaque, int irq, int level) -{ - Exynos4210IRQGateState *s = (Exynos4210IRQGateState *)opaque; - uint32_t i; - - assert(irq < s->n_in); - - s->level[irq] = level; - - for (i = 0; i < s->n_in; i++) { - if (s->level[i] >= 1) { - qemu_irq_raise(s->out); - return; - } - } - - qemu_irq_lower(s->out); -} - -static void exynos4210_irq_gate_reset(DeviceState *d) -{ - Exynos4210IRQGateState *s = EXYNOS4210_IRQ_GATE(d); - - memset(s->level, 0, s->n_in * sizeof(*s->level)); -} - -/* - * IRQ Gate initialization. - */ -static void exynos4210_irq_gate_init(Object *obj) -{ - Exynos4210IRQGateState *s = EXYNOS4210_IRQ_GATE(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - sysbus_init_irq(sbd, &s->out); -} - -static void exynos4210_irq_gate_realize(DeviceState *dev, Error **errp) -{ - Exynos4210IRQGateState *s = EXYNOS4210_IRQ_GATE(dev); - - /* Allocate general purpose input signals and connect a handler to each of - * them */ - qdev_init_gpio_in(dev, exynos4210_irq_gate_handler, s->n_in); - - s->level = g_malloc0(s->n_in * sizeof(*s->level)); -} - -static void exynos4210_irq_gate_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->reset = exynos4210_irq_gate_reset; - dc->vmsd = &vmstate_exynos4210_irq_gate; - device_class_set_props(dc, exynos4210_irq_gate_properties); - dc->realize = exynos4210_irq_gate_realize; -} - -static const TypeInfo exynos4210_irq_gate_info = { - .name = TYPE_EXYNOS4210_IRQ_GATE, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(Exynos4210IRQGateState), - .instance_init = exynos4210_irq_gate_init, - .class_init = exynos4210_irq_gate_class_init, -}; - -static void exynos4210_irq_gate_register_types(void) -{ - type_register_static(&exynos4210_irq_gate_info); -} - -type_init(exynos4210_irq_gate_register_types) -- 2.25.1 The exynos4210 SoC mostly creates its child devices as if it were board code. This includes the a9mpcore object. Switch that to a new-style "embedded in the state struct" creation, because in the next commit we're going to want to refer to the object again further down in the exynos4210_realize() function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-4-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 2 ++ hw/arm/exynos4210.c | 11 ++++++----- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/sysbus.h" +#include "hw/cpu/a9mpcore.h" #include "target/arm/cpu-qom.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { I2CBus *i2c_if[EXYNOS4210_I2C_NUMBER]; qemu_or_irq pl330_irq_orgate[EXYNOS4210_NUM_DMA]; qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; + A9MPPrivState a9mpcore; }; #define TYPE_EXYNOS4210_SOC "exynos4210" diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) } /* Private memory region and Internal GIC */ - dev = qdev_new(TYPE_A9MPCORE_PRIV); - qdev_prop_set_uint32(dev, "num-cpu", EXYNOS4210_NCPUS); - busdev = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(busdev, &error_fatal); + qdev_prop_set_uint32(DEVICE(&s->a9mpcore), "num-cpu", EXYNOS4210_NCPUS); + busdev = SYS_BUS_DEVICE(&s->a9mpcore); + sysbus_realize(busdev, &error_fatal); sysbus_mmio_map(busdev, 0, EXYNOS4210_SMP_PRIVATE_BASE_ADDR); for (n = 0; n < EXYNOS4210_NCPUS; n++) { sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 0)); } for (n = 0; n < EXYNOS4210_INT_GIC_NIRQ; n++) { - s->irqs.int_gic_irq[n] = qdev_get_gpio_in(dev, n); + s->irqs.int_gic_irq[n] = qdev_get_gpio_in(DEVICE(&s->a9mpcore), n); } /* Cache controller */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) g_autofree char *name = g_strdup_printf("cpu-irq-orgate%d", i); object_initialize_child(obj, name, &s->cpu_irq_orgate[i], TYPE_OR_IRQ); } + + object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); } static void exynos4210_class_init(ObjectClass *klass, void *data) -- 2.25.1 The only time we use the int_gic_irq[] array in the Exynos4210Irq struct is in the exynos4210_realize() function: we initialize it with the GPIO inputs of the a9mpcore device, and then a bit later on we connect those to the outputs of the internal combiner. Now that the a9mpcore object is easily accessible as s->a9mpcore we can make the connection directly from one device to the other without going via this array. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-5-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 1 - hw/arm/exynos4210.c | 6 ++---- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; - qemu_irq int_gic_irq[EXYNOS4210_INT_GIC_NIRQ]; qemu_irq ext_gic_irq[EXYNOS4210_EXT_GIC_NIRQ]; qemu_irq board_irqs[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; } Exynos4210Irq; diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 0)); } - for (n = 0; n < EXYNOS4210_INT_GIC_NIRQ; n++) { - s->irqs.int_gic_irq[n] = qdev_get_gpio_in(DEVICE(&s->a9mpcore), n); - } /* Cache controller */ sysbus_create_simple("l2x0", EXYNOS4210_L2X0_BASE_ADDR, NULL); @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) busdev = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(busdev, &error_fatal); for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { - sysbus_connect_irq(busdev, n, s->irqs.int_gic_irq[n]); + sysbus_connect_irq(busdev, n, + qdev_get_gpio_in(DEVICE(&s->a9mpcore), n)); } exynos4210_combiner_get_gpioin(&s->irqs, dev, 0); sysbus_mmio_map(busdev, 0, EXYNOS4210_INT_COMBINER_BASE_ADDR); -- 2.25.1 The exynos4210 code currently has two very similar arrays of IRQs: * board_irqs is a field of the Exynos4210Irq struct which is filled in by exynos4210_init_board_irqs() with the appropriate qemu_irqs for each IRQ the board/SoC can assert * irq_table is a set of qemu_irqs pointed to from the Exynos4210State struct. It's allocated in exynos4210_init_irq, and the only behaviour these irqs have is that they pass on the level to the equivalent board_irqs[] irq The extra indirection through irq_table is unnecessary, so coalesce these into a single irq_table[] array as a direct field in Exynos4210State which exynos4210_init_board_irqs() fills in. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-6-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 8 ++------ hw/arm/exynos4210.c | 6 +----- hw/intc/exynos4210_gic.c | 32 ++++++++------------------------ 3 files changed, 11 insertions(+), 35 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; qemu_irq ext_gic_irq[EXYNOS4210_EXT_GIC_NIRQ]; - qemu_irq board_irqs[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; } Exynos4210Irq; struct Exynos4210State { @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { /*< public >*/ ARMCPU *cpu[EXYNOS4210_NCPUS]; Exynos4210Irq irqs; - qemu_irq *irq_table; + qemu_irq irq_table[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; MemoryRegion chipid_mem; MemoryRegion iram_mem; @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210State, EXYNOS4210_SOC) void exynos4210_write_secondary(ARMCPU *cpu, const struct arm_boot_info *info); -/* Initialize exynos4210 IRQ subsystem stub */ -qemu_irq *exynos4210_init_irq(Exynos4210Irq *env); - /* Initialize board IRQs. * These IRQs contain splitted Int/External Combiner and External Gic IRQs */ -void exynos4210_init_board_irqs(Exynos4210Irq *s); +void exynos4210_init_board_irqs(Exynos4210State *s); /* Get IRQ number from exynos4210 IRQ subsystem stub. * To identify IRQ source use internal combiner group and bit number diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) qdev_realize(DEVICE(cpuobj), NULL, &error_fatal); } - /*** IRQs ***/ - - s->irq_table = exynos4210_init_irq(&s->irqs); - /* IRQ Gate */ for (i = 0; i < EXYNOS4210_NCPUS; i++) { DeviceState *orgate = DEVICE(&s->cpu_irq_orgate[i]); @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_COMBINER_BASE_ADDR); /* Initialize board IRQs. */ - exynos4210_init_board_irqs(&s->irqs); + exynos4210_init_board_irqs(s); /*** Memory ***/ diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ combiner_grp_to_gic_id[64-EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { #define EXYNOS4210_GIC_CPU_REGION_SIZE 0x100 #define EXYNOS4210_GIC_DIST_REGION_SIZE 0x1000 -static void exynos4210_irq_handler(void *opaque, int irq, int level) -{ - Exynos4210Irq *s = (Exynos4210Irq *)opaque; - - /* Bypass */ - qemu_set_irq(s->board_irqs[irq], level); -} - -/* - * Initialize exynos4210 IRQ subsystem stub. - */ -qemu_irq *exynos4210_init_irq(Exynos4210Irq *s) -{ - return qemu_allocate_irqs(exynos4210_irq_handler, s, - EXYNOS4210_MAX_INT_COMBINER_IN_IRQ); -} - /* * Initialize board IRQs. * These IRQs contain splitted Int/External Combiner and External Gic IRQs. */ -void exynos4210_init_board_irqs(Exynos4210Irq *s) +void exynos4210_init_board_irqs(Exynos4210State *s) { uint32_t grp, bit, irq_id, n; + Exynos4210Irq *is = &s->irqs; for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; @@ -XXX,XX +XXX,XX @@ void exynos4210_init_board_irqs(Exynos4210Irq *s) irq_id = EXT_GIC_ID_MCT_G1; } if (irq_id) { - s->board_irqs[n] = qemu_irq_split(s->int_combiner_irq[n], - s->ext_gic_irq[irq_id-32]); + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_gic_irq[irq_id - 32]); } else { - s->board_irqs[n] = qemu_irq_split(s->int_combiner_irq[n], - s->ext_combiner_irq[n]); + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_combiner_irq[n]); } } for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { @@ -XXX,XX +XXX,XX @@ void exynos4210_init_board_irqs(Exynos4210Irq *s) EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; if (irq_id) { - s->board_irqs[n] = qemu_irq_split(s->int_combiner_irq[n], - s->ext_gic_irq[irq_id-32]); + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_gic_irq[irq_id - 32]); } } } -- 2.25.1 Fix a missing set of spaces around '-' in the definition of combiner_grp_to_gic_id[]. We're about to move this code, so fix the style issue first to keep checkpatch happy with the code-motion patch. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-7-peter.maydell@linaro.org --- hw/intc/exynos4210_gic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ enum ExtInt { */ static const uint32_t -combiner_grp_to_gic_id[64-EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { +combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { /* int combiner groups 16-19 */ { }, { }, { }, { }, /* int combiner group 20 */ -- 2.25.1 The function exynos4210_init_board_irqs() currently lives in exynos4210_gic.c, but it isn't really part of the exynos4210.gic device -- it is a function that implements (some of) the wiring up of interrupts between the SoC's GIC and combiner components. This means it fits better in exynos4210.c, which is the SoC-level code. Move it there. Similarly, exynos4210_git_irq() is used almost only in the SoC-level code, so move it too. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-8-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 4 - hw/arm/exynos4210.c | 202 +++++++++++++++++++++++++++++++++++ hw/intc/exynos4210_gic.c | 204 ------------------------------------ 3 files changed, 202 insertions(+), 208 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210State, EXYNOS4210_SOC) void exynos4210_write_secondary(ARMCPU *cpu, const struct arm_boot_info *info); -/* Initialize board IRQs. - * These IRQs contain splitted Int/External Combiner and External Gic IRQs */ -void exynos4210_init_board_irqs(Exynos4210State *s); - /* Get IRQ number from exynos4210 IRQ subsystem stub. * To identify IRQ source use internal combiner group and bit number * grp - group number diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ #define EXYNOS4210_PL330_BASE1_ADDR 0x12690000 #define EXYNOS4210_PL330_BASE2_ADDR 0x12850000 +enum ExtGicId { + EXT_GIC_ID_MDMA_LCD0 = 66, + EXT_GIC_ID_PDMA0, + EXT_GIC_ID_PDMA1, + EXT_GIC_ID_TIMER0, + EXT_GIC_ID_TIMER1, + EXT_GIC_ID_TIMER2, + EXT_GIC_ID_TIMER3, + EXT_GIC_ID_TIMER4, + EXT_GIC_ID_MCT_L0, + EXT_GIC_ID_WDT, + EXT_GIC_ID_RTC_ALARM, + EXT_GIC_ID_RTC_TIC, + EXT_GIC_ID_GPIO_XB, + EXT_GIC_ID_GPIO_XA, + EXT_GIC_ID_MCT_L1, + EXT_GIC_ID_IEM_APC, + EXT_GIC_ID_IEM_IEC, + EXT_GIC_ID_NFC, + EXT_GIC_ID_UART0, + EXT_GIC_ID_UART1, + EXT_GIC_ID_UART2, + EXT_GIC_ID_UART3, + EXT_GIC_ID_UART4, + EXT_GIC_ID_MCT_G0, + EXT_GIC_ID_I2C0, + EXT_GIC_ID_I2C1, + EXT_GIC_ID_I2C2, + EXT_GIC_ID_I2C3, + EXT_GIC_ID_I2C4, + EXT_GIC_ID_I2C5, + EXT_GIC_ID_I2C6, + EXT_GIC_ID_I2C7, + EXT_GIC_ID_SPI0, + EXT_GIC_ID_SPI1, + EXT_GIC_ID_SPI2, + EXT_GIC_ID_MCT_G1, + EXT_GIC_ID_USB_HOST, + EXT_GIC_ID_USB_DEVICE, + EXT_GIC_ID_MODEMIF, + EXT_GIC_ID_HSMMC0, + EXT_GIC_ID_HSMMC1, + EXT_GIC_ID_HSMMC2, + EXT_GIC_ID_HSMMC3, + EXT_GIC_ID_SDMMC, + EXT_GIC_ID_MIPI_CSI_4LANE, + EXT_GIC_ID_MIPI_DSI_4LANE, + EXT_GIC_ID_MIPI_CSI_2LANE, + EXT_GIC_ID_MIPI_DSI_2LANE, + EXT_GIC_ID_ONENAND_AUDI, + EXT_GIC_ID_ROTATOR, + EXT_GIC_ID_FIMC0, + EXT_GIC_ID_FIMC1, + EXT_GIC_ID_FIMC2, + EXT_GIC_ID_FIMC3, + EXT_GIC_ID_JPEG, + EXT_GIC_ID_2D, + EXT_GIC_ID_PCIe, + EXT_GIC_ID_MIXER, + EXT_GIC_ID_HDMI, + EXT_GIC_ID_HDMI_I2C, + EXT_GIC_ID_MFC, + EXT_GIC_ID_TVENC, +}; + +enum ExtInt { + EXT_GIC_ID_EXTINT0 = 48, + EXT_GIC_ID_EXTINT1, + EXT_GIC_ID_EXTINT2, + EXT_GIC_ID_EXTINT3, + EXT_GIC_ID_EXTINT4, + EXT_GIC_ID_EXTINT5, + EXT_GIC_ID_EXTINT6, + EXT_GIC_ID_EXTINT7, + EXT_GIC_ID_EXTINT8, + EXT_GIC_ID_EXTINT9, + EXT_GIC_ID_EXTINT10, + EXT_GIC_ID_EXTINT11, + EXT_GIC_ID_EXTINT12, + EXT_GIC_ID_EXTINT13, + EXT_GIC_ID_EXTINT14, + EXT_GIC_ID_EXTINT15 +}; + +/* + * External GIC sources which are not from External Interrupt Combiner or + * External Interrupts are starting from EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ, + * which is INTG16 in Internal Interrupt Combiner. + */ + +static const uint32_t +combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { + /* int combiner groups 16-19 */ + { }, { }, { }, { }, + /* int combiner group 20 */ + { 0, EXT_GIC_ID_MDMA_LCD0 }, + /* int combiner group 21 */ + { EXT_GIC_ID_PDMA0, EXT_GIC_ID_PDMA1 }, + /* int combiner group 22 */ + { EXT_GIC_ID_TIMER0, EXT_GIC_ID_TIMER1, EXT_GIC_ID_TIMER2, + EXT_GIC_ID_TIMER3, EXT_GIC_ID_TIMER4 }, + /* int combiner group 23 */ + { EXT_GIC_ID_RTC_ALARM, EXT_GIC_ID_RTC_TIC }, + /* int combiner group 24 */ + { EXT_GIC_ID_GPIO_XB, EXT_GIC_ID_GPIO_XA }, + /* int combiner group 25 */ + { EXT_GIC_ID_IEM_APC, EXT_GIC_ID_IEM_IEC }, + /* int combiner group 26 */ + { EXT_GIC_ID_UART0, EXT_GIC_ID_UART1, EXT_GIC_ID_UART2, EXT_GIC_ID_UART3, + EXT_GIC_ID_UART4 }, + /* int combiner group 27 */ + { EXT_GIC_ID_I2C0, EXT_GIC_ID_I2C1, EXT_GIC_ID_I2C2, EXT_GIC_ID_I2C3, + EXT_GIC_ID_I2C4, EXT_GIC_ID_I2C5, EXT_GIC_ID_I2C6, + EXT_GIC_ID_I2C7 }, + /* int combiner group 28 */ + { EXT_GIC_ID_SPI0, EXT_GIC_ID_SPI1, EXT_GIC_ID_SPI2 , EXT_GIC_ID_USB_HOST}, + /* int combiner group 29 */ + { EXT_GIC_ID_HSMMC0, EXT_GIC_ID_HSMMC1, EXT_GIC_ID_HSMMC2, + EXT_GIC_ID_HSMMC3, EXT_GIC_ID_SDMMC }, + /* int combiner group 30 */ + { EXT_GIC_ID_MIPI_CSI_4LANE, EXT_GIC_ID_MIPI_CSI_2LANE }, + /* int combiner group 31 */ + { EXT_GIC_ID_MIPI_DSI_4LANE, EXT_GIC_ID_MIPI_DSI_2LANE }, + /* int combiner group 32 */ + { EXT_GIC_ID_FIMC0, EXT_GIC_ID_FIMC1 }, + /* int combiner group 33 */ + { EXT_GIC_ID_FIMC2, EXT_GIC_ID_FIMC3 }, + /* int combiner group 34 */ + { EXT_GIC_ID_ONENAND_AUDI, EXT_GIC_ID_NFC }, + /* int combiner group 35 */ + { 0, 0, 0, EXT_GIC_ID_MCT_L1, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + /* int combiner group 36 */ + { EXT_GIC_ID_MIXER }, + /* int combiner group 37 */ + { EXT_GIC_ID_EXTINT4, EXT_GIC_ID_EXTINT5, EXT_GIC_ID_EXTINT6, + EXT_GIC_ID_EXTINT7 }, + /* groups 38-50 */ + { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, + /* int combiner group 51 */ + { EXT_GIC_ID_MCT_L0, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + /* group 52 */ + { }, + /* int combiner group 53 */ + { EXT_GIC_ID_WDT, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + /* groups 54-63 */ + { }, { }, { }, { }, { }, { }, { }, { }, { }, { } +}; + +/* + * Initialize board IRQs. + * These IRQs contain splitted Int/External Combiner and External Gic IRQs. + */ +static void exynos4210_init_board_irqs(Exynos4210State *s) +{ + uint32_t grp, bit, irq_id, n; + Exynos4210Irq *is = &s->irqs; + + for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { + irq_id = 0; + if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 4) || + n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4)) { + /* MCT_G0 is passed to External GIC */ + irq_id = EXT_GIC_ID_MCT_G0; + } + if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 5) || + n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 5)) { + /* MCT_G1 is passed to External and GIC */ + irq_id = EXT_GIC_ID_MCT_G1; + } + if (irq_id) { + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_gic_irq[irq_id - 32]); + } else { + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_combiner_irq[n]); + } + } + for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { + /* these IDs are passed to Internal Combiner and External GIC */ + grp = EXYNOS4210_COMBINER_GET_GRP_NUM(n); + bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); + irq_id = combiner_grp_to_gic_id[grp - + EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; + + if (irq_id) { + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_gic_irq[irq_id - 32]); + } + } +} + +/* + * Get IRQ number from exynos4210 IRQ subsystem stub. + * To identify IRQ source use internal combiner group and bit number + * grp - group number + * bit - bit number inside group + */ +uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit) +{ + return EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit); +} + static uint8_t chipid_and_omr[] = { 0x11, 0x02, 0x21, 0x43, 0x09, 0x00, 0x00, 0x00 }; diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/exynos4210.h" #include "qom/object.h" -enum ExtGicId { - EXT_GIC_ID_MDMA_LCD0 = 66, - EXT_GIC_ID_PDMA0, - EXT_GIC_ID_PDMA1, - EXT_GIC_ID_TIMER0, - EXT_GIC_ID_TIMER1, - EXT_GIC_ID_TIMER2, - EXT_GIC_ID_TIMER3, - EXT_GIC_ID_TIMER4, - EXT_GIC_ID_MCT_L0, - EXT_GIC_ID_WDT, - EXT_GIC_ID_RTC_ALARM, - EXT_GIC_ID_RTC_TIC, - EXT_GIC_ID_GPIO_XB, - EXT_GIC_ID_GPIO_XA, - EXT_GIC_ID_MCT_L1, - EXT_GIC_ID_IEM_APC, - EXT_GIC_ID_IEM_IEC, - EXT_GIC_ID_NFC, - EXT_GIC_ID_UART0, - EXT_GIC_ID_UART1, - EXT_GIC_ID_UART2, - EXT_GIC_ID_UART3, - EXT_GIC_ID_UART4, - EXT_GIC_ID_MCT_G0, - EXT_GIC_ID_I2C0, - EXT_GIC_ID_I2C1, - EXT_GIC_ID_I2C2, - EXT_GIC_ID_I2C3, - EXT_GIC_ID_I2C4, - EXT_GIC_ID_I2C5, - EXT_GIC_ID_I2C6, - EXT_GIC_ID_I2C7, - EXT_GIC_ID_SPI0, - EXT_GIC_ID_SPI1, - EXT_GIC_ID_SPI2, - EXT_GIC_ID_MCT_G1, - EXT_GIC_ID_USB_HOST, - EXT_GIC_ID_USB_DEVICE, - EXT_GIC_ID_MODEMIF, - EXT_GIC_ID_HSMMC0, - EXT_GIC_ID_HSMMC1, - EXT_GIC_ID_HSMMC2, - EXT_GIC_ID_HSMMC3, - EXT_GIC_ID_SDMMC, - EXT_GIC_ID_MIPI_CSI_4LANE, - EXT_GIC_ID_MIPI_DSI_4LANE, - EXT_GIC_ID_MIPI_CSI_2LANE, - EXT_GIC_ID_MIPI_DSI_2LANE, - EXT_GIC_ID_ONENAND_AUDI, - EXT_GIC_ID_ROTATOR, - EXT_GIC_ID_FIMC0, - EXT_GIC_ID_FIMC1, - EXT_GIC_ID_FIMC2, - EXT_GIC_ID_FIMC3, - EXT_GIC_ID_JPEG, - EXT_GIC_ID_2D, - EXT_GIC_ID_PCIe, - EXT_GIC_ID_MIXER, - EXT_GIC_ID_HDMI, - EXT_GIC_ID_HDMI_I2C, - EXT_GIC_ID_MFC, - EXT_GIC_ID_TVENC, -}; - -enum ExtInt { - EXT_GIC_ID_EXTINT0 = 48, - EXT_GIC_ID_EXTINT1, - EXT_GIC_ID_EXTINT2, - EXT_GIC_ID_EXTINT3, - EXT_GIC_ID_EXTINT4, - EXT_GIC_ID_EXTINT5, - EXT_GIC_ID_EXTINT6, - EXT_GIC_ID_EXTINT7, - EXT_GIC_ID_EXTINT8, - EXT_GIC_ID_EXTINT9, - EXT_GIC_ID_EXTINT10, - EXT_GIC_ID_EXTINT11, - EXT_GIC_ID_EXTINT12, - EXT_GIC_ID_EXTINT13, - EXT_GIC_ID_EXTINT14, - EXT_GIC_ID_EXTINT15 -}; - -/* - * External GIC sources which are not from External Interrupt Combiner or - * External Interrupts are starting from EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ, - * which is INTG16 in Internal Interrupt Combiner. - */ - -static const uint32_t -combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { - /* int combiner groups 16-19 */ - { }, { }, { }, { }, - /* int combiner group 20 */ - { 0, EXT_GIC_ID_MDMA_LCD0 }, - /* int combiner group 21 */ - { EXT_GIC_ID_PDMA0, EXT_GIC_ID_PDMA1 }, - /* int combiner group 22 */ - { EXT_GIC_ID_TIMER0, EXT_GIC_ID_TIMER1, EXT_GIC_ID_TIMER2, - EXT_GIC_ID_TIMER3, EXT_GIC_ID_TIMER4 }, - /* int combiner group 23 */ - { EXT_GIC_ID_RTC_ALARM, EXT_GIC_ID_RTC_TIC }, - /* int combiner group 24 */ - { EXT_GIC_ID_GPIO_XB, EXT_GIC_ID_GPIO_XA }, - /* int combiner group 25 */ - { EXT_GIC_ID_IEM_APC, EXT_GIC_ID_IEM_IEC }, - /* int combiner group 26 */ - { EXT_GIC_ID_UART0, EXT_GIC_ID_UART1, EXT_GIC_ID_UART2, EXT_GIC_ID_UART3, - EXT_GIC_ID_UART4 }, - /* int combiner group 27 */ - { EXT_GIC_ID_I2C0, EXT_GIC_ID_I2C1, EXT_GIC_ID_I2C2, EXT_GIC_ID_I2C3, - EXT_GIC_ID_I2C4, EXT_GIC_ID_I2C5, EXT_GIC_ID_I2C6, - EXT_GIC_ID_I2C7 }, - /* int combiner group 28 */ - { EXT_GIC_ID_SPI0, EXT_GIC_ID_SPI1, EXT_GIC_ID_SPI2 , EXT_GIC_ID_USB_HOST}, - /* int combiner group 29 */ - { EXT_GIC_ID_HSMMC0, EXT_GIC_ID_HSMMC1, EXT_GIC_ID_HSMMC2, - EXT_GIC_ID_HSMMC3, EXT_GIC_ID_SDMMC }, - /* int combiner group 30 */ - { EXT_GIC_ID_MIPI_CSI_4LANE, EXT_GIC_ID_MIPI_CSI_2LANE }, - /* int combiner group 31 */ - { EXT_GIC_ID_MIPI_DSI_4LANE, EXT_GIC_ID_MIPI_DSI_2LANE }, - /* int combiner group 32 */ - { EXT_GIC_ID_FIMC0, EXT_GIC_ID_FIMC1 }, - /* int combiner group 33 */ - { EXT_GIC_ID_FIMC2, EXT_GIC_ID_FIMC3 }, - /* int combiner group 34 */ - { EXT_GIC_ID_ONENAND_AUDI, EXT_GIC_ID_NFC }, - /* int combiner group 35 */ - { 0, 0, 0, EXT_GIC_ID_MCT_L1, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, - /* int combiner group 36 */ - { EXT_GIC_ID_MIXER }, - /* int combiner group 37 */ - { EXT_GIC_ID_EXTINT4, EXT_GIC_ID_EXTINT5, EXT_GIC_ID_EXTINT6, - EXT_GIC_ID_EXTINT7 }, - /* groups 38-50 */ - { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, - /* int combiner group 51 */ - { EXT_GIC_ID_MCT_L0, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, - /* group 52 */ - { }, - /* int combiner group 53 */ - { EXT_GIC_ID_WDT, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, - /* groups 54-63 */ - { }, { }, { }, { }, { }, { }, { }, { }, { }, { } -}; - #define EXYNOS4210_GIC_NIRQ 160 #define EXYNOS4210_EXT_GIC_CPU_REGION_SIZE 0x10000 @@ -XXX,XX +XXX,XX @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { #define EXYNOS4210_GIC_CPU_REGION_SIZE 0x100 #define EXYNOS4210_GIC_DIST_REGION_SIZE 0x1000 -/* - * Initialize board IRQs. - * These IRQs contain splitted Int/External Combiner and External Gic IRQs. - */ -void exynos4210_init_board_irqs(Exynos4210State *s) -{ - uint32_t grp, bit, irq_id, n; - Exynos4210Irq *is = &s->irqs; - - for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { - irq_id = 0; - if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 4) || - n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4)) { - /* MCT_G0 is passed to External GIC */ - irq_id = EXT_GIC_ID_MCT_G0; - } - if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 5) || - n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 5)) { - /* MCT_G1 is passed to External and GIC */ - irq_id = EXT_GIC_ID_MCT_G1; - } - if (irq_id) { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_gic_irq[irq_id - 32]); - } else { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_combiner_irq[n]); - } - } - for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { - /* these IDs are passed to Internal Combiner and External GIC */ - grp = EXYNOS4210_COMBINER_GET_GRP_NUM(n); - bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); - irq_id = combiner_grp_to_gic_id[grp - - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; - - if (irq_id) { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_gic_irq[irq_id - 32]); - } - } -} - -/* - * Get IRQ number from exynos4210 IRQ subsystem stub. - * To identify IRQ source use internal combiner group and bit number - * grp - group number - * bit - bit number inside group - */ -uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit) -{ - return EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit); -} - -/********* GIC part *********/ - #define TYPE_EXYNOS4210_GIC "exynos4210.gic" OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210GicState, EXYNOS4210_GIC) -- 2.25.1 Switch the creation of the external GIC to the new-style "embedded in state struct" approach, so we can easily refer to the object elsewhere during realize. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-9-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 2 ++ include/hw/intc/exynos4210_gic.h | 43 ++++++++++++++++++++++++++++++++ hw/arm/exynos4210.c | 10 ++++---- hw/intc/exynos4210_gic.c | 17 ++----------- MAINTAINERS | 2 +- 5 files changed, 53 insertions(+), 21 deletions(-) create mode 100644 include/hw/intc/exynos4210_gic.h diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/sysbus.h" #include "hw/cpu/a9mpcore.h" +#include "hw/intc/exynos4210_gic.h" #include "target/arm/cpu-qom.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { qemu_or_irq pl330_irq_orgate[EXYNOS4210_NUM_DMA]; qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; A9MPPrivState a9mpcore; + Exynos4210GicState ext_gic; }; #define TYPE_EXYNOS4210_SOC "exynos4210" diff --git a/include/hw/intc/exynos4210_gic.h b/include/hw/intc/exynos4210_gic.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/intc/exynos4210_gic.h @@ -XXX,XX +XXX,XX @@ +/* + * Samsung exynos4210 GIC implementation. Based on hw/arm_gic.c + * + * Copyright (c) 2000 - 2011 Samsung Electronics Co., Ltd. + * All rights reserved. + * + * Evgeny Voevodin <e.voevodin@samsung.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 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. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ +#ifndef HW_INTC_EXYNOS4210_GIC_H +#define HW_INTC_EXYNOS4210_GIC_H + +#include "hw/sysbus.h" + +#define TYPE_EXYNOS4210_GIC "exynos4210.gic" +OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210GicState, EXYNOS4210_GIC) + +#define EXYNOS4210_GIC_NCPUS 2 + +struct Exynos4210GicState { + SysBusDevice parent_obj; + + MemoryRegion cpu_container; + MemoryRegion dist_container; + MemoryRegion cpu_alias[EXYNOS4210_GIC_NCPUS]; + MemoryRegion dist_alias[EXYNOS4210_GIC_NCPUS]; + uint32_t num_cpu; + DeviceState *gic; +}; + +#endif diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_create_simple("l2x0", EXYNOS4210_L2X0_BASE_ADDR, NULL); /* External GIC */ - dev = qdev_new("exynos4210.gic"); - qdev_prop_set_uint32(dev, "num-cpu", EXYNOS4210_NCPUS); - busdev = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(busdev, &error_fatal); + qdev_prop_set_uint32(DEVICE(&s->ext_gic), "num-cpu", EXYNOS4210_NCPUS); + busdev = SYS_BUS_DEVICE(&s->ext_gic); + sysbus_realize(busdev, &error_fatal); /* Map CPU interface */ sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_GIC_CPU_BASE_ADDR); /* Map Distributer interface */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 1)); } for (n = 0; n < EXYNOS4210_EXT_GIC_NIRQ; n++) { - s->irqs.ext_gic_irq[n] = qdev_get_gpio_in(dev, n); + s->irqs.ext_gic_irq[n] = qdev_get_gpio_in(DEVICE(&s->ext_gic), n); } /* Internal Interrupt Combiner */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) } object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); + object_initialize_child(obj, "ext-gic", &s->ext_gic, TYPE_EXYNOS4210_GIC); } static void exynos4210_class_init(ObjectClass *klass, void *data) diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "hw/irq.h" #include "hw/qdev-properties.h" +#include "hw/intc/exynos4210_gic.h" #include "hw/arm/exynos4210.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ #define EXYNOS4210_GIC_CPU_REGION_SIZE 0x100 #define EXYNOS4210_GIC_DIST_REGION_SIZE 0x1000 -#define TYPE_EXYNOS4210_GIC "exynos4210.gic" -OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210GicState, EXYNOS4210_GIC) - -struct Exynos4210GicState { - SysBusDevice parent_obj; - - MemoryRegion cpu_container; - MemoryRegion dist_container; - MemoryRegion cpu_alias[EXYNOS4210_NCPUS]; - MemoryRegion dist_alias[EXYNOS4210_NCPUS]; - uint32_t num_cpu; - DeviceState *gic; -}; - static void exynos4210_gic_set_irq(void *opaque, int irq, int level) { Exynos4210GicState *s = (Exynos4210GicState *)opaque; @@ -XXX,XX +XXX,XX @@ static void exynos4210_gic_realize(DeviceState *dev, Error **errp) * enough room for the cpu numbers. gcc 9.2.1 on 32-bit x86 * doesn't figure this out, otherwise and gives spurious warnings. */ - assert(n <= EXYNOS4210_NCPUS); + assert(n <= EXYNOS4210_GIC_NCPUS); for (i = 0; i < n; i++) { /* Map CPU interface per SMP Core */ sprintf(cpu_alias_name, "%s%x", cpu_prefix, i); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes F: hw/*/exynos* -F: include/hw/arm/exynos4210.h +F: include/hw/*/exynos* Calxeda Highbank M: Rob Herring <robh@kernel.org> -- 2.25.1 The only time we use the ext_gic_irq[] array in the Exynos4210Irq struct is during realize of the SoC -- we initialize it with the input IRQs of the external GIC device, and then connect those to outputs of other devices further on in realize (including in the exynos4210_init_board_irqs() function). Now that the ext_gic object is easily accessible as s->ext_gic we can make the connections directly from one device to the other without going via this array. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-10-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 1 - hw/arm/exynos4210.c | 12 ++++++------ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; - qemu_irq ext_gic_irq[EXYNOS4210_EXT_GIC_NIRQ]; } Exynos4210Irq; struct Exynos4210State { diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) { uint32_t grp, bit, irq_id, n; Exynos4210Irq *is = &s->irqs; + DeviceState *extgicdev = DEVICE(&s->ext_gic); for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) } if (irq_id) { s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_gic_irq[irq_id - 32]); + qdev_get_gpio_in(extgicdev, + irq_id - 32)); } else { s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], is->ext_combiner_irq[n]); @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) if (irq_id) { s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_gic_irq[irq_id - 32]); + qdev_get_gpio_in(extgicdev, + irq_id - 32)); } } } @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 1)); } - for (n = 0; n < EXYNOS4210_EXT_GIC_NIRQ; n++) { - s->irqs.ext_gic_irq[n] = qdev_get_gpio_in(DEVICE(&s->ext_gic), n); - } /* Internal Interrupt Combiner */ dev = qdev_new("exynos4210.combiner"); @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) busdev = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(busdev, &error_fatal); for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { - sysbus_connect_irq(busdev, n, s->irqs.ext_gic_irq[n]); + sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->ext_gic), n)); } exynos4210_combiner_get_gpioin(&s->irqs, dev, 1); sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_COMBINER_BASE_ADDR); -- 2.25.1 The function exynos4210_combiner_get_gpioin() currently lives in exynos4210_combiner.c, but it isn't really part of the combiner device itself -- it is a function that implements the wiring up of some interrupt sources to multiple combiner inputs. Move it to live with the other SoC-level code in exynos4210.c, along with a few macros previously defined in exynos4210.h which are now used only in exynos4210.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-11-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 11 ----- hw/arm/exynos4210.c | 82 +++++++++++++++++++++++++++++++++++ hw/intc/exynos4210_combiner.c | 77 -------------------------------- 3 files changed, 82 insertions(+), 88 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #define EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ \ (EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ * 8) -#define EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit) ((grp)*8 + (bit)) -#define EXYNOS4210_COMBINER_GET_GRP_NUM(irq) ((irq) / 8) -#define EXYNOS4210_COMBINER_GET_BIT_NUM(irq) \ - ((irq) - 8 * EXYNOS4210_COMBINER_GET_GRP_NUM(irq)) - /* IRQs number for external and internal GIC */ #define EXYNOS4210_EXT_GIC_NIRQ (160-32) #define EXYNOS4210_INT_GIC_NIRQ 64 @@ -XXX,XX +XXX,XX @@ void exynos4210_write_secondary(ARMCPU *cpu, * bit - bit number inside group */ uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit); -/* - * Get Combiner input GPIO into irqs structure - */ -void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, DeviceState *dev, - int ext); - /* * exynos4210 UART */ diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { { }, { }, { }, { }, { }, { }, { }, { }, { }, { } }; +#define EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit) ((grp) * 8 + (bit)) +#define EXYNOS4210_COMBINER_GET_GRP_NUM(irq) ((irq) / 8) +#define EXYNOS4210_COMBINER_GET_BIT_NUM(irq) \ + ((irq) - 8 * EXYNOS4210_COMBINER_GET_GRP_NUM(irq)) + /* * Initialize board IRQs. * These IRQs contain splitted Int/External Combiner and External Gic IRQs. @@ -XXX,XX +XXX,XX @@ uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit) return EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit); } +/* + * Get Combiner input GPIO into irqs structure + */ +static void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, + DeviceState *dev, int ext) +{ + int n; + int bit; + int max; + qemu_irq *irq; + + max = ext ? EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ : + EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; + irq = ext ? irqs->ext_combiner_irq : irqs->int_combiner_irq; + + /* + * Some IRQs of Int/External Combiner are going to two Combiners groups, + * so let split them. + */ + for (n = 0; n < max; n++) { + + bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); + + switch (n) { + /* MDNIE_LCD1 INTG1 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 0) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 3): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(0, bit + 4)]); + continue; + + /* TMU INTG3 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(3, 4): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(2, bit)]); + continue; + + /* LCD1 INTG12 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 0) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 3): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(11, bit + 4)]); + continue; + + /* Multi-Core Timer INTG12 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 8): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); + continue; + + /* Multi-Core Timer INTG35 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 4) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 8): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); + continue; + + /* Multi-Core Timer INTG51 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 4) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 8): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); + continue; + + /* Multi-Core Timer INTG53 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 4) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 8): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); + continue; + } + + irq[n] = qdev_get_gpio_in(dev, n); + } +} + static uint8_t chipid_and_omr[] = { 0x11, 0x02, 0x21, 0x43, 0x09, 0x00, 0x00, 0x00 }; diff --git a/hw/intc/exynos4210_combiner.c b/hw/intc/exynos4210_combiner.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_combiner.c +++ b/hw/intc/exynos4210_combiner.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_exynos4210_combiner = { } }; -/* - * Get Combiner input GPIO into irqs structure - */ -void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, DeviceState *dev, - int ext) -{ - int n; - int bit; - int max; - qemu_irq *irq; - - max = ext ? EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ : - EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; - irq = ext ? irqs->ext_combiner_irq : irqs->int_combiner_irq; - - /* - * Some IRQs of Int/External Combiner are going to two Combiners groups, - * so let split them. - */ - for (n = 0; n < max; n++) { - - bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); - - switch (n) { - /* MDNIE_LCD1 INTG1 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 0) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 3): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(0, bit + 4)]); - continue; - - /* TMU INTG3 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(3, 4): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(2, bit)]); - continue; - - /* LCD1 INTG12 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 0) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 3): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(11, bit + 4)]); - continue; - - /* Multi-Core Timer INTG12 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG35 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG51 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG53 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - } - - irq[n] = qdev_get_gpio_in(dev, n); - } -} - static uint64_t exynos4210_combiner_read(void *opaque, hwaddr offset, unsigned size) { -- 2.25.1 Delete a couple of #defines which are never used. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-12-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #define EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ \ (EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ * 8) -/* IRQs number for external and internal GIC */ -#define EXYNOS4210_EXT_GIC_NIRQ (160-32) -#define EXYNOS4210_INT_GIC_NIRQ 64 - #define EXYNOS4210_I2C_NUMBER 9 #define EXYNOS4210_NUM_DMA 3 -- 2.25.1 In exynos4210_init_board_irqs(), use the TYPE_SPLIT_IRQ device instead of qemu_irq_split(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-13-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 9 ++++++++ hw/arm/exynos4210.c | 41 +++++++++++++++++++++++++++++-------- 2 files changed, 42 insertions(+), 8 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/cpu/a9mpcore.h" #include "hw/intc/exynos4210_gic.h" +#include "hw/core/split-irq.h" #include "target/arm/cpu-qom.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ #define EXYNOS4210_NUM_DMA 3 +/* + * We need one splitter for every external combiner input, plus + * one for every non-zero entry in combiner_grp_to_gic_id[]. + * We'll assert in exynos4210_init_board_irqs() if this is wrong. + */ +#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 60) + typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; A9MPPrivState a9mpcore; Exynos4210GicState ext_gic; + SplitIRQ splitter[EXYNOS4210_NUM_SPLITTERS]; }; #define TYPE_EXYNOS4210_SOC "exynos4210" diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) uint32_t grp, bit, irq_id, n; Exynos4210Irq *is = &s->irqs; DeviceState *extgicdev = DEVICE(&s->ext_gic); + int splitcount = 0; + DeviceState *splitter; for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) /* MCT_G1 is passed to External and GIC */ irq_id = EXT_GIC_ID_MCT_G1; } + + assert(splitcount < EXYNOS4210_NUM_SPLITTERS); + splitter = DEVICE(&s->splitter[splitcount]); + qdev_prop_set_uint16(splitter, "num-lines", 2); + qdev_realize(splitter, NULL, &error_abort); + splitcount++; + s->irq_table[n] = qdev_get_gpio_in(splitter, 0); + qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); if (irq_id) { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - qdev_get_gpio_in(extgicdev, - irq_id - 32)); + qdev_connect_gpio_out(splitter, 1, + qdev_get_gpio_in(extgicdev, irq_id - 32)); } else { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_combiner_irq[n]); + qdev_connect_gpio_out(splitter, 1, is->ext_combiner_irq[n]); } } for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; if (irq_id) { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - qdev_get_gpio_in(extgicdev, - irq_id - 32)); + assert(splitcount < EXYNOS4210_NUM_SPLITTERS); + splitter = DEVICE(&s->splitter[splitcount]); + qdev_prop_set_uint16(splitter, "num-lines", 2); + qdev_realize(splitter, NULL, &error_abort); + splitcount++; + s->irq_table[n] = qdev_get_gpio_in(splitter, 0); + qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); + qdev_connect_gpio_out(splitter, 1, + qdev_get_gpio_in(extgicdev, irq_id - 32)); } } + /* + * We check this here to avoid a more obscure assert later when + * qdev_assert_realized_properly() checks that we realized every + * child object we initialized. + */ + assert(splitcount == EXYNOS4210_NUM_SPLITTERS); } /* @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) object_initialize_child(obj, name, &s->cpu_irq_orgate[i], TYPE_OR_IRQ); } + for (i = 0; i < ARRAY_SIZE(s->splitter); i++) { + g_autofree char *name = g_strdup_printf("irq-splitter%d", i); + object_initialize_child(obj, name, &s->splitter[i], TYPE_SPLIT_IRQ); + } + object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); object_initialize_child(obj, "ext-gic", &s->ext_gic, TYPE_EXYNOS4210_GIC); } -- 2.25.1 In exynos4210_init_board_irqs(), the loop that handles IRQ lines that are in a range that applies to the internal combiner only creates a splitter for those interrupts which go to both the internal combiner and to the external GIC, but it does nothing at all for the interrupts which don't go to the external GIC, leaving the irq_table[] array element empty for those. (This will result in those interrupts simply being lost, not in a QEMU crash.) I don't have a reliable datasheet for this SoC, but since we do wire up one interrupt line in this category (the HDMI I2C device on interrupt 16,1), this seems like it must be a bug in the existing QEMU code. Fill in the irq_table[] entries where we're not splitting the IRQ to both the internal combiner and the external GIC with the IRQ line of the internal combiner. (That is, these IRQ lines go to just one device, not multiple.) This bug didn't have any visible guest effects because the only implemented device that was affected was the HDMI I2C controller, and we never connect any I2C devices to that bus. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-14-peter.maydell@linaro.org --- hw/arm/exynos4210.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); qdev_connect_gpio_out(splitter, 1, qdev_get_gpio_in(extgicdev, irq_id - 32)); + } else { + s->irq_table[n] = is->int_combiner_irq[n]; } } /* -- 2.25.1 Currently for the interrupts MCT_G0 and MCT_G1 which are the only ones in the input range of the external combiner and which are also wired to the external GIC, we connect them only to the internal combiner and the external GIC. This seems likely to be a bug, as all other interrupts which are in the input range of both combiners are connected to both combiners. (The fact that the code in exynos4210_combiner_get_gpioin() is also trying to wire up these inputs on both combiners also suggests this.) Wire these interrupts up to both combiners, like the rest. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-15-peter.maydell@linaro.org --- hw/arm/exynos4210.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) assert(splitcount < EXYNOS4210_NUM_SPLITTERS); splitter = DEVICE(&s->splitter[splitcount]); - qdev_prop_set_uint16(splitter, "num-lines", 2); + qdev_prop_set_uint16(splitter, "num-lines", irq_id ? 3 : 2); qdev_realize(splitter, NULL, &error_abort); splitcount++; s->irq_table[n] = qdev_get_gpio_in(splitter, 0); qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); + qdev_connect_gpio_out(splitter, 1, is->ext_combiner_irq[n]); if (irq_id) { - qdev_connect_gpio_out(splitter, 1, + qdev_connect_gpio_out(splitter, 2, qdev_get_gpio_in(extgicdev, irq_id - 32)); - } else { - qdev_connect_gpio_out(splitter, 1, is->ext_combiner_irq[n]); } } for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { -- 2.25.1 The combiner_grp_to_gic_id[] array includes the EXT_GIC_ID_MCT_G0 and EXT_GIC_ID_MCT_G1 multiple times. This means that we will connect multiple IRQs up to the same external GIC input, which is not permitted. We do the same thing in the code in exynos4210_init_board_irqs() because the conditionals selecting an irq_id in the first loop match multiple interrupt IDs. Overall we do this for interrupt IDs (1, 4), (12, 4), (35, 4), (51, 4), (53, 4) for EXT_GIC_ID_MCT_G0 and (1, 5), (12, 5), (35, 5), (51, 5), (53, 5) for EXT_GIC_ID_MCT_G1 These correspond to the cases for the multi-core timer that we are wiring up to multiple inputs on the combiner in exynos4210_combiner_get_gpioin(). That code already deals with all these interrupt IDs being the same input source, so we don't need to connect the external GIC interrupt for any of them except the first (1, 4) and (1, 5). Remove the array entries and conditionals which were incorrectly causing us to wire up extra lines. This bug didn't cause any visible effects, because we only connect up a device to the "primary" ID values (1, 4) and (1, 5), so the extra lines would never be set to a level. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-16-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 2 +- hw/arm/exynos4210.c | 12 +++++------- 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ * one for every non-zero entry in combiner_grp_to_gic_id[]. * We'll assert in exynos4210_init_board_irqs() if this is wrong. */ -#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 60) +#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 54) typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { /* int combiner group 34 */ { EXT_GIC_ID_ONENAND_AUDI, EXT_GIC_ID_NFC }, /* int combiner group 35 */ - { 0, 0, 0, EXT_GIC_ID_MCT_L1, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + { 0, 0, 0, EXT_GIC_ID_MCT_L1 }, /* int combiner group 36 */ { EXT_GIC_ID_MIXER }, /* int combiner group 37 */ @@ -XXX,XX +XXX,XX @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { /* groups 38-50 */ { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, /* int combiner group 51 */ - { EXT_GIC_ID_MCT_L0, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + { EXT_GIC_ID_MCT_L0 }, /* group 52 */ { }, /* int combiner group 53 */ - { EXT_GIC_ID_WDT, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + { EXT_GIC_ID_WDT }, /* groups 54-63 */ { }, { }, { }, { }, { }, { }, { }, { }, { }, { } }; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; - if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 4) || - n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4)) { + if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 4)) { /* MCT_G0 is passed to External GIC */ irq_id = EXT_GIC_ID_MCT_G0; } - if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 5) || - n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 5)) { + if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 5)) { /* MCT_G1 is passed to External and GIC */ irq_id = EXT_GIC_ID_MCT_G1; } -- 2.25.1 At this point, the function exynos4210_init_board_irqs() splits input IRQ lines to connect them to the input combiner, output combiner and external GIC. The function exynos4210_combiner_get_gpioin() splits some of the combiner input lines further to connect them to multiple different inputs on the combiner. Because (unlike qemu_irq_split()) the TYPE_SPLIT_IRQ device has a configurable number of outputs, we can do all this in one place, by making exynos4210_init_board_irqs() add extra outputs to the splitter device when it must be connected to more than one input on each combiner. We do this with a new data structure, the combinermap, which is an array each of whose elements is a list of the interrupt IDs on the combiner which must be tied together. As we loop through each interrupt ID, if we find that it is the first one in one of these lists, we configure the splitter device with eonugh extra outputs and wire them up to the other interrupt IDs in the list. Conveniently, for all the cases where this is necessary, the lowest-numbered interrupt ID in each group is in the range of the external combiner, so we only need to code for this in the first of the two loops in exynos4210_init_board_irqs(). The old code in exynos4210_combiner_get_gpioin() which is being deleted here had several problems which don't exist in the new code in its handling of the multi-core timer interrupts: (1) the case labels specified bits 4 ... 8, but bit '8' doesn't exist; these should have been 4 ... 7 (2) it used the input irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)] multiple times as the input of several different splitters, which isn't allowed (3) in an apparent cut-and-paste error, the cases for all the multi-core timer inputs used "bit + 4" even though the bit range for the case was (intended to be) 4 ... 7, which meant it was looking at non-existent bits 8 ... 11. None of these exist in the new code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-17-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 6 +- hw/arm/exynos4210.c | 178 +++++++++++++++++++++++------------- 2 files changed, 119 insertions(+), 65 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ /* * We need one splitter for every external combiner input, plus - * one for every non-zero entry in combiner_grp_to_gic_id[]. + * one for every non-zero entry in combiner_grp_to_gic_id[], + * minus one for every external combiner ID in second or later + * places in a combinermap[] line. * We'll assert in exynos4210_init_board_irqs() if this is wrong. */ -#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 54) +#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 38) typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { #define EXYNOS4210_COMBINER_GET_BIT_NUM(irq) \ ((irq) - 8 * EXYNOS4210_COMBINER_GET_GRP_NUM(irq)) +/* + * Some interrupt lines go to multiple combiner inputs. + * This data structure defines those: each array element is + * a list of combiner inputs which are connected together; + * the one with the smallest interrupt ID value must be first. + * As with combiner_grp_to_gic_id[], we rely on (0, 0) not being + * wired to anything so we can use 0 as a terminator. + */ +#define IRQNO(G, B) EXYNOS4210_COMBINER_GET_IRQ_NUM(G, B) +#define IRQNONE 0 + +#define COMBINERMAP_SIZE 16 + +static const int combinermap[COMBINERMAP_SIZE][6] = { + /* MDNIE_LCD1 */ + { IRQNO(0, 4), IRQNO(1, 0), IRQNONE }, + { IRQNO(0, 5), IRQNO(1, 1), IRQNONE }, + { IRQNO(0, 6), IRQNO(1, 2), IRQNONE }, + { IRQNO(0, 7), IRQNO(1, 3), IRQNONE }, + /* TMU */ + { IRQNO(2, 4), IRQNO(3, 4), IRQNONE }, + { IRQNO(2, 5), IRQNO(3, 5), IRQNONE }, + { IRQNO(2, 6), IRQNO(3, 6), IRQNONE }, + { IRQNO(2, 7), IRQNO(3, 7), IRQNONE }, + /* LCD1 */ + { IRQNO(11, 4), IRQNO(12, 0), IRQNONE }, + { IRQNO(11, 5), IRQNO(12, 1), IRQNONE }, + { IRQNO(11, 6), IRQNO(12, 2), IRQNONE }, + { IRQNO(11, 7), IRQNO(12, 3), IRQNONE }, + /* Multi-core timer */ + { IRQNO(1, 4), IRQNO(12, 4), IRQNO(35, 4), IRQNO(51, 4), IRQNO(53, 4), IRQNONE }, + { IRQNO(1, 5), IRQNO(12, 5), IRQNO(35, 5), IRQNO(51, 5), IRQNO(53, 5), IRQNONE }, + { IRQNO(1, 6), IRQNO(12, 6), IRQNO(35, 6), IRQNO(51, 6), IRQNO(53, 6), IRQNONE }, + { IRQNO(1, 7), IRQNO(12, 7), IRQNO(35, 7), IRQNO(51, 7), IRQNO(53, 7), IRQNONE }, +}; + +#undef IRQNO + +static const int *combinermap_entry(int irq) +{ + /* + * If the interrupt number passed in is the first entry in some + * line of the combinermap, return a pointer to that line; + * otherwise return NULL. + */ + int i; + for (i = 0; i < COMBINERMAP_SIZE; i++) { + if (combinermap[i][0] == irq) { + return combinermap[i]; + } + } + return NULL; +} + +static int mapline_size(const int *mapline) +{ + /* Return number of entries in this mapline in total */ + int i = 0; + + if (!mapline) { + /* Not in the map? IRQ goes to exactly one combiner input */ + return 1; + } + while (*mapline != IRQNONE) { + mapline++; + i++; + } + return i; +} + /* * Initialize board IRQs. * These IRQs contain splitted Int/External Combiner and External Gic IRQs. @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) DeviceState *extgicdev = DEVICE(&s->ext_gic); int splitcount = 0; DeviceState *splitter; + const int *mapline; + int numlines, splitin, in; for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) irq_id = EXT_GIC_ID_MCT_G1; } + if (s->irq_table[n]) { + /* + * This must be some non-first entry in a combinermap line, + * and we've already filled it in. + */ + continue; + } + mapline = combinermap_entry(n); + /* + * We need to connect the IRQ to multiple inputs on both combiners + * and possibly also to the external GIC. + */ + numlines = 2 * mapline_size(mapline); + if (irq_id) { + numlines++; + } assert(splitcount < EXYNOS4210_NUM_SPLITTERS); splitter = DEVICE(&s->splitter[splitcount]); - qdev_prop_set_uint16(splitter, "num-lines", irq_id ? 3 : 2); + qdev_prop_set_uint16(splitter, "num-lines", numlines); qdev_realize(splitter, NULL, &error_abort); splitcount++; - s->irq_table[n] = qdev_get_gpio_in(splitter, 0); - qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); - qdev_connect_gpio_out(splitter, 1, is->ext_combiner_irq[n]); + + in = n; + splitin = 0; + for (;;) { + s->irq_table[in] = qdev_get_gpio_in(splitter, 0); + qdev_connect_gpio_out(splitter, splitin, is->int_combiner_irq[in]); + qdev_connect_gpio_out(splitter, splitin + 1, is->ext_combiner_irq[in]); + splitin += 2; + if (!mapline) { + break; + } + mapline++; + in = *mapline; + if (in == IRQNONE) { + break; + } + } if (irq_id) { - qdev_connect_gpio_out(splitter, 2, + qdev_connect_gpio_out(splitter, splitin, qdev_get_gpio_in(extgicdev, irq_id - 32)); } } @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) irq_id = combiner_grp_to_gic_id[grp - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; + if (s->irq_table[n]) { + /* + * This must be some non-first entry in a combinermap line, + * and we've already filled it in. + */ + continue; + } + if (irq_id) { assert(splitcount < EXYNOS4210_NUM_SPLITTERS); splitter = DEVICE(&s->splitter[splitcount]); @@ -XXX,XX +XXX,XX @@ static void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, DeviceState *dev, int ext) { int n; - int bit; int max; qemu_irq *irq; @@ -XXX,XX +XXX,XX @@ static void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; irq = ext ? irqs->ext_combiner_irq : irqs->int_combiner_irq; - /* - * Some IRQs of Int/External Combiner are going to two Combiners groups, - * so let split them. - */ for (n = 0; n < max; n++) { - - bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); - - switch (n) { - /* MDNIE_LCD1 INTG1 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 0) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 3): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(0, bit + 4)]); - continue; - - /* TMU INTG3 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(3, 4): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(2, bit)]); - continue; - - /* LCD1 INTG12 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 0) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 3): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(11, bit + 4)]); - continue; - - /* Multi-Core Timer INTG12 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG35 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG51 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG53 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - } - irq[n] = qdev_get_gpio_in(dev, n); } } -- 2.25.1 Switch the creation of the combiner devices to the new-style "embedded in state struct" approach, so we can easily refer to the object elsewhere during realize. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-18-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 3 ++ include/hw/intc/exynos4210_combiner.h | 57 +++++++++++++++++++++++++++ hw/arm/exynos4210.c | 20 +++++----- hw/intc/exynos4210_combiner.c | 31 +-------------- 4 files changed, 72 insertions(+), 39 deletions(-) create mode 100644 include/hw/intc/exynos4210_combiner.h diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/cpu/a9mpcore.h" #include "hw/intc/exynos4210_gic.h" +#include "hw/intc/exynos4210_combiner.h" #include "hw/core/split-irq.h" #include "target/arm/cpu-qom.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; A9MPPrivState a9mpcore; Exynos4210GicState ext_gic; + Exynos4210CombinerState int_combiner; + Exynos4210CombinerState ext_combiner; SplitIRQ splitter[EXYNOS4210_NUM_SPLITTERS]; }; diff --git a/include/hw/intc/exynos4210_combiner.h b/include/hw/intc/exynos4210_combiner.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/intc/exynos4210_combiner.h @@ -XXX,XX +XXX,XX @@ +/* + * Samsung exynos4210 Interrupt Combiner + * + * Copyright (c) 2000 - 2011 Samsung Electronics Co., Ltd. + * All rights reserved. + * + * Evgeny Voevodin <e.voevodin@samsung.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 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. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_INTC_EXYNOS4210_COMBINER +#define HW_INTC_EXYNOS4210_COMBINER + +#include "hw/sysbus.h" + +/* + * State for each output signal of internal combiner + */ +typedef struct CombinerGroupState { + uint8_t src_mask; /* 1 - source enabled, 0 - disabled */ + uint8_t src_pending; /* Pending source interrupts before masking */ +} CombinerGroupState; + +#define TYPE_EXYNOS4210_COMBINER "exynos4210.combiner" +OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210CombinerState, EXYNOS4210_COMBINER) + +/* Number of groups and total number of interrupts for the internal combiner */ +#define IIC_NGRP 64 +#define IIC_NIRQ (IIC_NGRP * 8) +#define IIC_REGSET_SIZE 0x41 + +struct Exynos4210CombinerState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + + struct CombinerGroupState group[IIC_NGRP]; + uint32_t reg_set[IIC_REGSET_SIZE]; + uint32_t icipsr[2]; + uint32_t external; /* 1 means that this combiner is external */ + + qemu_irq output_irq[IIC_NGRP]; +}; + +#endif diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) } /* Internal Interrupt Combiner */ - dev = qdev_new("exynos4210.combiner"); - busdev = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(busdev, &error_fatal); + busdev = SYS_BUS_DEVICE(&s->int_combiner); + sysbus_realize(busdev, &error_fatal); for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->a9mpcore), n)); } - exynos4210_combiner_get_gpioin(&s->irqs, dev, 0); + exynos4210_combiner_get_gpioin(&s->irqs, DEVICE(&s->int_combiner), 0); sysbus_mmio_map(busdev, 0, EXYNOS4210_INT_COMBINER_BASE_ADDR); /* External Interrupt Combiner */ - dev = qdev_new("exynos4210.combiner"); - qdev_prop_set_uint32(dev, "external", 1); - busdev = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(busdev, &error_fatal); + qdev_prop_set_uint32(DEVICE(&s->ext_combiner), "external", 1); + busdev = SYS_BUS_DEVICE(&s->ext_combiner); + sysbus_realize(busdev, &error_fatal); for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->ext_gic), n)); } - exynos4210_combiner_get_gpioin(&s->irqs, dev, 1); + exynos4210_combiner_get_gpioin(&s->irqs, DEVICE(&s->ext_combiner), 1); sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_COMBINER_BASE_ADDR); /* Initialize board IRQs. */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); object_initialize_child(obj, "ext-gic", &s->ext_gic, TYPE_EXYNOS4210_GIC); + object_initialize_child(obj, "int-combiner", &s->int_combiner, + TYPE_EXYNOS4210_COMBINER); + object_initialize_child(obj, "ext-combiner", &s->ext_combiner, + TYPE_EXYNOS4210_COMBINER); } static void exynos4210_class_init(ObjectClass *klass, void *data) diff --git a/hw/intc/exynos4210_combiner.c b/hw/intc/exynos4210_combiner.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_combiner.c +++ b/hw/intc/exynos4210_combiner.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "migration/vmstate.h" #include "qemu/module.h" - +#include "hw/intc/exynos4210_combiner.h" #include "hw/arm/exynos4210.h" #include "hw/hw.h" #include "hw/irq.h" @@ -XXX,XX +XXX,XX @@ #define DPRINTF(fmt, ...) do {} while (0) #endif -#define IIC_NGRP 64 /* Internal Interrupt Combiner - Groups number */ -#define IIC_NIRQ (IIC_NGRP * 8)/* Internal Interrupt Combiner - Interrupts number */ #define IIC_REGION_SIZE 0x108 /* Size of memory mapped region */ -#define IIC_REGSET_SIZE 0x41 - -/* - * State for each output signal of internal combiner - */ -typedef struct CombinerGroupState { - uint8_t src_mask; /* 1 - source enabled, 0 - disabled */ - uint8_t src_pending; /* Pending source interrupts before masking */ -} CombinerGroupState; - -#define TYPE_EXYNOS4210_COMBINER "exynos4210.combiner" -OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210CombinerState, EXYNOS4210_COMBINER) - -struct Exynos4210CombinerState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - - struct CombinerGroupState group[IIC_NGRP]; - uint32_t reg_set[IIC_REGSET_SIZE]; - uint32_t icipsr[2]; - uint32_t external; /* 1 means that this combiner is external */ - - qemu_irq output_irq[IIC_NGRP]; -}; static const VMStateDescription vmstate_exynos4210_combiner_group_state = { .name = "exynos4210.combiner.groupstate", -- 2.25.1 The only time we use the int_combiner_irq[] and ext_combiner_irq[] arrays in the Exynos4210Irq struct is during realize of the SoC -- we initialize them with the input IRQs of the combiner devices, and then connect those to outputs of other devices in exynos4210_init_board_irqs(). Now that the combiner objects are easily accessible as s->int_combiner and s->ext_combiner we can make the connections directly from one device to the other without going via these arrays. Since these are the only two remaining elements of Exynos4210Irq, we can remove that struct entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-19-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 6 ------ hw/arm/exynos4210.c | 34 ++++++++-------------------------- 2 files changed, 8 insertions(+), 32 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ */ #define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 38) -typedef struct Exynos4210Irq { - qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; - qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; -} Exynos4210Irq; - struct Exynos4210State { /*< private >*/ SysBusDevice parent_obj; /*< public >*/ ARMCPU *cpu[EXYNOS4210_NCPUS]; - Exynos4210Irq irqs; qemu_irq irq_table[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; MemoryRegion chipid_mem; diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static int mapline_size(const int *mapline) static void exynos4210_init_board_irqs(Exynos4210State *s) { uint32_t grp, bit, irq_id, n; - Exynos4210Irq *is = &s->irqs; DeviceState *extgicdev = DEVICE(&s->ext_gic); + DeviceState *intcdev = DEVICE(&s->int_combiner); + DeviceState *extcdev = DEVICE(&s->ext_combiner); int splitcount = 0; DeviceState *splitter; const int *mapline; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) splitin = 0; for (;;) { s->irq_table[in] = qdev_get_gpio_in(splitter, 0); - qdev_connect_gpio_out(splitter, splitin, is->int_combiner_irq[in]); - qdev_connect_gpio_out(splitter, splitin + 1, is->ext_combiner_irq[in]); + qdev_connect_gpio_out(splitter, splitin, + qdev_get_gpio_in(intcdev, in)); + qdev_connect_gpio_out(splitter, splitin + 1, + qdev_get_gpio_in(extcdev, in)); splitin += 2; if (!mapline) { break; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) qdev_realize(splitter, NULL, &error_abort); splitcount++; s->irq_table[n] = qdev_get_gpio_in(splitter, 0); - qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); + qdev_connect_gpio_out(splitter, 0, qdev_get_gpio_in(intcdev, n)); qdev_connect_gpio_out(splitter, 1, qdev_get_gpio_in(extgicdev, irq_id - 32)); } else { - s->irq_table[n] = is->int_combiner_irq[n]; + s->irq_table[n] = qdev_get_gpio_in(intcdev, n); } } /* @@ -XXX,XX +XXX,XX @@ uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit) return EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit); } -/* - * Get Combiner input GPIO into irqs structure - */ -static void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, - DeviceState *dev, int ext) -{ - int n; - int max; - qemu_irq *irq; - - max = ext ? EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ : - EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; - irq = ext ? irqs->ext_combiner_irq : irqs->int_combiner_irq; - - for (n = 0; n < max; n++) { - irq[n] = qdev_get_gpio_in(dev, n); - } -} - static uint8_t chipid_and_omr[] = { 0x11, 0x02, 0x21, 0x43, 0x09, 0x00, 0x00, 0x00 }; @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->a9mpcore), n)); } - exynos4210_combiner_get_gpioin(&s->irqs, DEVICE(&s->int_combiner), 0); sysbus_mmio_map(busdev, 0, EXYNOS4210_INT_COMBINER_BASE_ADDR); /* External Interrupt Combiner */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->ext_gic), n)); } - exynos4210_combiner_get_gpioin(&s->irqs, DEVICE(&s->ext_combiner), 1); sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_COMBINER_BASE_ADDR); /* Initialize board IRQs. */ -- 2.25.1 From: Zongyuan Li <zongyuan.li@smartx.com> Signed-off-by: Zongyuan Li <zongyuan.li@smartx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20220324181557.203805-2-zongyuan.li@smartx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/realview.c | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/hw/arm/realview.c b/hw/arm/realview.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/realview.c +++ b/hw/arm/realview.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/arm/boot.h" #include "hw/arm/primecell.h" +#include "hw/core/split-irq.h" #include "hw/net/lan9118.h" #include "hw/net/smc91c111.h" #include "hw/pci/pci.h" +#include "hw/qdev-core.h" #include "net/net.h" #include "sysemu/sysemu.h" #include "hw/boards.h" @@ -XXX,XX +XXX,XX @@ static const int realview_board_id[] = { 0x76d }; +static void split_irq_from_named(DeviceState *src, const char* outname, + qemu_irq out1, qemu_irq out2) { + DeviceState *splitter = qdev_new(TYPE_SPLIT_IRQ); + + qdev_prop_set_uint32(splitter, "num-lines", 2); + + qdev_realize_and_unref(splitter, NULL, &error_fatal); + + qdev_connect_gpio_out(splitter, 0, out1); + qdev_connect_gpio_out(splitter, 1, out2); + qdev_connect_gpio_out_named(src, outname, 0, + qdev_get_gpio_in(splitter, 0)); +} + static void realview_init(MachineState *machine, enum realview_board_type board_type) { @@ -XXX,XX +XXX,XX @@ static void realview_init(MachineState *machine, DeviceState *dev, *sysctl, *gpio2, *pl041; SysBusDevice *busdev; qemu_irq pic[64]; - qemu_irq mmc_irq[2]; PCIBus *pci_bus = NULL; NICInfo *nd; DriveInfo *dinfo; @@ -XXX,XX +XXX,XX @@ static void realview_init(MachineState *machine, * and the PL061 has them the other way about. Also the card * detect line is inverted. */ - mmc_irq[0] = qemu_irq_split( - qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_WPROT), - qdev_get_gpio_in(gpio2, 1)); - mmc_irq[1] = qemu_irq_split( - qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_CARDIN), - qemu_irq_invert(qdev_get_gpio_in(gpio2, 0))); - qdev_connect_gpio_out_named(dev, "card-read-only", 0, mmc_irq[0]); - qdev_connect_gpio_out_named(dev, "card-inserted", 0, mmc_irq[1]); + split_irq_from_named(dev, "card-read-only", + qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_WPROT), + qdev_get_gpio_in(gpio2, 1)); + + split_irq_from_named(dev, "card-inserted", + qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_CARDIN), + qemu_irq_invert(qdev_get_gpio_in(gpio2, 0))); + dinfo = drive_get(IF_SD, 0, 0); if (dinfo) { DeviceState *card; -- 2.25.1 From: Zongyuan Li <zongyuan.li@smartx.com> Signed-off-by: Zongyuan Li <zongyuan.li@smartx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20220324181557.203805-3-zongyuan.li@smartx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" +#include "hw/core/split-irq.h" #include "hw/sysbus.h" #include "hw/sd/sd.h" #include "hw/ssi/ssi.h" @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) DeviceState *ssddev; DriveInfo *dinfo; DeviceState *carddev; + DeviceState *gpio_d_splitter; BlockBackend *blk; /* @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) &error_fatal); ssddev = ssi_create_peripheral(bus, "ssd0323"); - gpio_out[GPIO_D][0] = qemu_irq_split( - qdev_get_gpio_in_named(sddev, SSI_GPIO_CS, 0), + + gpio_d_splitter = qdev_new(TYPE_SPLIT_IRQ); + qdev_prop_set_uint32(gpio_d_splitter, "num-lines", 2); + qdev_realize_and_unref(gpio_d_splitter, NULL, &error_fatal); + qdev_connect_gpio_out( + gpio_d_splitter, 0, + qdev_get_gpio_in_named(sddev, SSI_GPIO_CS, 0)); + qdev_connect_gpio_out( + gpio_d_splitter, 1, qdev_get_gpio_in_named(ssddev, SSI_GPIO_CS, 0)); + gpio_out[GPIO_D][0] = qdev_get_gpio_in(gpio_d_splitter, 0); + gpio_out[GPIO_C][7] = qdev_get_gpio_in(ssddev, 0); /* Make sure the select pin is high. */ -- 2.25.1 From: Zongyuan Li <zongyuan.li@smartx.com> Signed-off-by: Zongyuan Li <zongyuan.li@smartx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20220324181557.203805-5-zongyuan.li@smartx.com Resolves: https://gitlab.com/qemu-project/qemu/-/issues/811 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/irq.h | 5 ----- hw/core/irq.c | 15 --------------- 2 files changed, 20 deletions(-) diff --git a/include/hw/irq.h b/include/hw/irq.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/irq.h +++ b/include/hw/irq.h @@ -XXX,XX +XXX,XX @@ void qemu_free_irq(qemu_irq irq); /* Returns a new IRQ with opposite polarity. */ qemu_irq qemu_irq_invert(qemu_irq irq); -/* Returns a new IRQ which feeds into both the passed IRQs. - * It's probably better to use the TYPE_SPLIT_IRQ device instead. - */ -qemu_irq qemu_irq_split(qemu_irq irq1, qemu_irq irq2); - /* For internal use in qtest. Similar to qemu_irq_split, but operating on an existing vector of qemu_irq. */ void qemu_irq_intercept_in(qemu_irq *gpio_in, qemu_irq_handler handler, int n); diff --git a/hw/core/irq.c b/hw/core/irq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/irq.c +++ b/hw/core/irq.c @@ -XXX,XX +XXX,XX @@ qemu_irq qemu_irq_invert(qemu_irq irq) return qemu_allocate_irq(qemu_notirq, irq, 0); } -static void qemu_splitirq(void *opaque, int line, int level) -{ - struct IRQState **irq = opaque; - irq[0]->handler(irq[0]->opaque, irq[0]->n, level); - irq[1]->handler(irq[1]->opaque, irq[1]->n, level); -} - -qemu_irq qemu_irq_split(qemu_irq irq1, qemu_irq irq2) -{ - qemu_irq *s = g_new0(qemu_irq, 2); - s[0] = irq1; - s[1] = irq2; - return qemu_allocate_irq(qemu_splitirq, s, 0); -} - void qemu_irq_intercept_in(qemu_irq *gpio_in, qemu_irq_handler handler, int n) { int i; -- 2.25.1 From: Heinrich Schuchardt <heinrich.schuchardt@canonical.com> Describe that the gic-version influences the maximum number of CPUs. Signed-off-by: Heinrich Schuchardt <heinrich.schuchardt@canonical.com> Message-id: 20220413231456.35811-1-heinrich.schuchardt@canonical.com [PMM: minor punctuation tweaks] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/virt.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -XXX,XX +XXX,XX @@ gic-version Valid values are: ``2`` - GICv2 + GICv2. Note that this limits the number of CPUs to 8. ``3`` - GICv3 + GICv3. This allows up to 512 CPUs. ``host`` Use the same GIC version the host provides, when using KVM ``max`` -- 2.25.1 From: Hao Wu <wuhaotsh@google.com> Similar to the Aspeed code in include/misc/aspeed_scu.h, we define the PWRON STRAP fields in their corresponding module for NPCM7XX. Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Patrick Venture <venture@google.com> Message-id: 20220411165842.3912945-2-wuhaotsh@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_gcr.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/include/hw/misc/npcm7xx_gcr.h b/include/hw/misc/npcm7xx_gcr.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_gcr.h +++ b/include/hw/misc/npcm7xx_gcr.h @@ -XXX,XX +XXX,XX @@ #include "exec/memory.h" #include "hw/sysbus.h" +/* + * NPCM7XX PWRON STRAP bit fields + * 12: SPI0 powered by VSBV3 at 1.8V + * 11: System flash attached to BMC + * 10: BSP alternative pins. + * 9:8: Flash UART command route enabled. + * 7: Security enabled. + * 6: HI-Z state control. + * 5: ECC disabled. + * 4: Reserved + * 3: JTAG2 enabled. + * 2:0: CPU and DRAM clock frequency. + */ +#define NPCM7XX_PWRON_STRAP_SPI0F18 BIT(12) +#define NPCM7XX_PWRON_STRAP_SFAB BIT(11) +#define NPCM7XX_PWRON_STRAP_BSPA BIT(10) +#define NPCM7XX_PWRON_STRAP_FUP(x) ((x) << 8) +#define FUP_NORM_UART2 3 +#define FUP_PROG_UART3 2 +#define FUP_PROG_UART2 1 +#define FUP_NORM_UART3 0 +#define NPCM7XX_PWRON_STRAP_SECEN BIT(7) +#define NPCM7XX_PWRON_STRAP_HIZ BIT(6) +#define NPCM7XX_PWRON_STRAP_ECC BIT(5) +#define NPCM7XX_PWRON_STRAP_RESERVE1 BIT(4) +#define NPCM7XX_PWRON_STRAP_J2EN BIT(3) +#define NPCM7XX_PWRON_STRAP_CKFRQ(x) (x) +#define CKFRQ_SKIPINIT 0x000 +#define CKFRQ_DEFAULT 0x111 + /* * Number of registers in our device state structure. Don't change this without * incrementing the version_id in the vmstate. -- 2.25.1 From: Hao Wu <wuhaotsh@google.com> This patch uses the defined fields to describe PWRON STRAPs for better readability. Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Patrick Venture <venture@google.com> Message-id: 20220411165842.3912945-3-wuhaotsh@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/npcm7xx_boards.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "sysemu/block-backend.h" -#define NPCM750_EVB_POWER_ON_STRAPS 0x00001ff7 -#define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff -#define QUANTA_GBS_POWER_ON_STRAPS 0x000017ff -#define KUDO_BMC_POWER_ON_STRAPS 0x00001fff -#define MORI_BMC_POWER_ON_STRAPS 0x00001fff +#define NPCM7XX_POWER_ON_STRAPS_DEFAULT ( \ + NPCM7XX_PWRON_STRAP_SPI0F18 | \ + NPCM7XX_PWRON_STRAP_SFAB | \ + NPCM7XX_PWRON_STRAP_BSPA | \ + NPCM7XX_PWRON_STRAP_FUP(FUP_NORM_UART2) | \ + NPCM7XX_PWRON_STRAP_SECEN | \ + NPCM7XX_PWRON_STRAP_HIZ | \ + NPCM7XX_PWRON_STRAP_ECC | \ + NPCM7XX_PWRON_STRAP_RESERVE1 | \ + NPCM7XX_PWRON_STRAP_J2EN | \ + NPCM7XX_PWRON_STRAP_CKFRQ(CKFRQ_DEFAULT)) + +#define NPCM750_EVB_POWER_ON_STRAPS ( \ + NPCM7XX_POWER_ON_STRAPS_DEFAULT & ~NPCM7XX_PWRON_STRAP_J2EN) +#define QUANTA_GSJ_POWER_ON_STRAPS NPCM7XX_POWER_ON_STRAPS_DEFAULT +#define QUANTA_GBS_POWER_ON_STRAPS ( \ + NPCM7XX_POWER_ON_STRAPS_DEFAULT & ~NPCM7XX_PWRON_STRAP_SFAB) +#define KUDO_BMC_POWER_ON_STRAPS NPCM7XX_POWER_ON_STRAPS_DEFAULT +#define MORI_BMC_POWER_ON_STRAPS NPCM7XX_POWER_ON_STRAPS_DEFAULT static const char npcm7xx_default_bootrom[] = "npcm7xx_bootrom.bin"; -- 2.25.1