The following changes since commit 5a67d7735d4162630769ef495cf813244fc850df: Merge remote-tracking branch 'remotes/berrange-gitlab/tags/tls-deps-pull-request' into staging (2021-07-02 08:22:39 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210702 for you to fetch changes up to 04ea4d3cfd0a21b248ece8eb7a9436a3d9898dd8: target/arm: Implement MVE shifts by register (2021-07-02 11:48:38 +0100) ---------------------------------------------------------------- target-arm queue: * more MVE instructions * hw/gpio/gpio_pwr: use shutdown function for reboot * target/arm: Check NaN mode before silencing NaN * tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine * hw/arm: Add basic power management to raspi. * docs/system/arm: Add quanta-gbs-bmc, quanta-q7l1-bmc ---------------------------------------------------------------- Joe Komlodi (1): target/arm: Check NaN mode before silencing NaN Maxim Uvarov (1): hw/gpio/gpio_pwr: use shutdown function for reboot Nolan Leake (1): hw/arm: Add basic power management to raspi. Patrick Venture (2): docs/system/arm: Add quanta-q7l1-bmc reference docs/system/arm: Add quanta-gbs-bmc reference Peter Maydell (18): target/arm: Fix MVE widening/narrowing VLDR/VSTR offset calculation target/arm: Fix bugs in MVE VRMLALDAVH, VRMLSLDAVH target/arm: Make asimd_imm_const() public target/arm: Use asimd_imm_const for A64 decode target/arm: Use dup_const() instead of bitfield_replicate() target/arm: Implement MVE logical immediate insns target/arm: Implement MVE vector shift left by immediate insns target/arm: Implement MVE vector shift right by immediate insns target/arm: Implement MVE VSHLL target/arm: Implement MVE VSRI, VSLI target/arm: Implement MVE VSHRN, VRSHRN target/arm: Implement MVE saturating narrowing shifts target/arm: Implement MVE VSHLC target/arm: Implement MVE VADDLV target/arm: Implement MVE long shifts by immediate target/arm: Implement MVE long shifts by register target/arm: Implement MVE shifts by immediate target/arm: Implement MVE shifts by register Philippe Mathieu-Daudé (1): tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine docs/system/arm/aspeed.rst | 1 + docs/system/arm/nuvoton.rst | 5 +- include/hw/arm/bcm2835_peripherals.h | 3 +- include/hw/misc/bcm2835_powermgt.h | 29 ++ target/arm/helper-mve.h | 108 +++++++ target/arm/translate.h | 41 +++ target/arm/mve.decode | 177 ++++++++++- target/arm/t32.decode | 71 ++++- hw/arm/bcm2835_peripherals.c | 13 +- hw/gpio/gpio_pwr.c | 2 +- hw/misc/bcm2835_powermgt.c | 160 ++++++++++ target/arm/helper-a64.c | 12 +- target/arm/mve_helper.c | 524 +++++++++++++++++++++++++++++++-- target/arm/translate-a64.c | 86 +----- target/arm/translate-mve.c | 261 +++++++++++++++- target/arm/translate-neon.c | 81 ----- target/arm/translate.c | 327 +++++++++++++++++++- target/arm/vfp_helper.c | 24 +- hw/misc/meson.build | 1 + tests/acceptance/boot_linux_console.py | 43 +++ 20 files changed, 1760 insertions(+), 209 deletions(-) create mode 100644 include/hw/misc/bcm2835_powermgt.h create mode 100644 hw/misc/bcm2835_powermgt.c From: Patrick Venture <venture@google.com> Adds a line-item reference to the supported quanta-q71l-bmc aspeed entry. Signed-off-by: Patrick Venture <venture@google.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Message-id: 20210615192848.1065297-2-venture@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/aspeed.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/aspeed.rst +++ b/docs/system/arm/aspeed.rst @@ -XXX,XX +XXX,XX @@ etc. AST2400 SoC based machines : - ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC +- ``quanta-q71l-bmc`` OpenBMC Quanta BMC AST2500 SoC based machines : -- 2.20.1 From: Patrick Venture <venture@google.com> Add line item reference to quanta-gbs-bmc machine. Signed-off-by: Patrick Venture <venture@google.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Message-id: 20210615192848.1065297-3-venture@google.com [PMM: fixed underline Sphinx warning] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ -Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``) -===================================================== +Nuvoton iBMC boards (``*-bmc``, ``npcm750-evb``, ``quanta-gsj``) +================================================================ The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are designed to be used as Baseboard Management Controllers (BMCs) in various @@ -XXX,XX +XXX,XX @@ segment. The following machines are based on this chip : The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and Hyperscale applications. The following machines are based on this chip : +- ``quanta-gbs-bmc`` Quanta GBS server BMC - ``quanta-gsj`` Quanta GSJ server BMC There are also two more SoCs, NPCM710 and NPCM705, which are single-core -- 2.20.1 From: Nolan Leake <nolan@sigbus.net> This is just enough to make reboot and poweroff work. Works for linux, u-boot, and the arm trusted firmware. Not tested, but should work for plan9, and bare-metal/hobby OSes, since they seem to generally do what linux does for reset. The watchdog timer functionality is not yet implemented. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/64 Signed-off-by: Nolan Leake <nolan@sigbus.net> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210625210209.1870217-1-nolan@sigbus.net [PMM: tweaked commit title; fixed region size to 0x200; moved header file to include/] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 3 +- include/hw/misc/bcm2835_powermgt.h | 29 +++++ hw/arm/bcm2835_peripherals.c | 13 ++- hw/misc/bcm2835_powermgt.c | 160 +++++++++++++++++++++++++++ hw/misc/meson.build | 1 + 5 files changed, 204 insertions(+), 2 deletions(-) create mode 100644 include/hw/misc/bcm2835_powermgt.h create mode 100644 hw/misc/bcm2835_powermgt.c diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/bcm2835_mphi.h" #include "hw/misc/bcm2835_thermal.h" #include "hw/misc/bcm2835_cprman.h" +#include "hw/misc/bcm2835_powermgt.h" #include "hw/sd/sdhci.h" #include "hw/sd/bcm2835_sdhost.h" #include "hw/gpio/bcm2835_gpio.h" @@ -XXX,XX +XXX,XX @@ struct BCM2835PeripheralState { BCM2835MphiState mphi; UnimplementedDeviceState txp; UnimplementedDeviceState armtmr; - UnimplementedDeviceState powermgt; + BCM2835PowerMgtState powermgt; BCM2835CprmanState cprman; PL011State uart0; BCM2835AuxState aux; diff --git a/include/hw/misc/bcm2835_powermgt.h b/include/hw/misc/bcm2835_powermgt.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/bcm2835_powermgt.h @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 Power Management emulation + * + * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com> + * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef BCM2835_POWERMGT_H +#define BCM2835_POWERMGT_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_BCM2835_POWERMGT "bcm2835-powermgt" +OBJECT_DECLARE_SIMPLE_TYPE(BCM2835PowerMgtState, BCM2835_POWERMGT) + +struct BCM2835PowerMgtState { + SysBusDevice busdev; + MemoryRegion iomem; + + uint32_t rstc; + uint32_t rsts; + uint32_t wdog; +}; + +#endif diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr", OBJECT(&s->gpu_bus_mr)); + + /* Power Management */ + object_initialize_child(obj, "powermgt", &s->powermgt, + TYPE_BCM2835_POWERMGT); } static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, INTERRUPT_USB)); + /* Power Management */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->powermgt), errp)) { + return; + } + + memory_region_add_subregion(&s->peri_mr, PM_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->powermgt), 0)); + create_unimp(s, &s->txp, "bcm2835-txp", TXP_OFFSET, 0x1000); create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); - create_unimp(s, &s->powermgt, "bcm2835-powermgt", PM_OFFSET, 0x114); create_unimp(s, &s->i2s, "bcm2835-i2s", I2S_OFFSET, 0x100); create_unimp(s, &s->smi, "bcm2835-smi", SMI_OFFSET, 0x100); create_unimp(s, &s->spi[0], "bcm2835-spi0", SPI0_OFFSET, 0x20); diff --git a/hw/misc/bcm2835_powermgt.c b/hw/misc/bcm2835_powermgt.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/bcm2835_powermgt.c @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 Power Management emulation + * + * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com> + * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/bcm2835_powermgt.h" +#include "migration/vmstate.h" +#include "sysemu/runstate.h" + +#define PASSWORD 0x5a000000 +#define PASSWORD_MASK 0xff000000 + +#define R_RSTC 0x1c +#define V_RSTC_RESET 0x20 +#define R_RSTS 0x20 +#define V_RSTS_POWEROFF 0x555 /* Linux uses partition 63 to indicate halt. */ +#define R_WDOG 0x24 + +static uint64_t bcm2835_powermgt_read(void *opaque, hwaddr offset, + unsigned size) +{ + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; + uint32_t res = 0; + + switch (offset) { + case R_RSTC: + res = s->rstc; + break; + case R_RSTS: + res = s->rsts; + break; + case R_WDOG: + res = s->wdog; + break; + + default: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_read: Unknown offset 0x%08"HWADDR_PRIx + "\n", offset); + res = 0; + break; + } + + return res; +} + +static void bcm2835_powermgt_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; + + if ((value & PASSWORD_MASK) != PASSWORD) { + qemu_log_mask(LOG_GUEST_ERROR, + "bcm2835_powermgt_write: Bad password 0x%"PRIx64 + " at offset 0x%08"HWADDR_PRIx"\n", + value, offset); + return; + } + + value = value & ~PASSWORD_MASK; + + switch (offset) { + case R_RSTC: + s->rstc = value; + if (value & V_RSTC_RESET) { + if ((s->rsts & 0xfff) == V_RSTS_POWEROFF) { + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + } else { + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); + } + } + break; + case R_RSTS: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_write: RSTS\n"); + s->rsts = value; + break; + case R_WDOG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_write: WDOG\n"); + s->wdog = value; + break; + + default: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_write: Unknown offset 0x%08"HWADDR_PRIx + "\n", offset); + break; + } +} + +static const MemoryRegionOps bcm2835_powermgt_ops = { + .read = bcm2835_powermgt_read, + .write = bcm2835_powermgt_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl.min_access_size = 4, + .impl.max_access_size = 4, +}; + +static const VMStateDescription vmstate_bcm2835_powermgt = { + .name = TYPE_BCM2835_POWERMGT, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(rstc, BCM2835PowerMgtState), + VMSTATE_UINT32(rsts, BCM2835PowerMgtState), + VMSTATE_UINT32(wdog, BCM2835PowerMgtState), + VMSTATE_END_OF_LIST() + } +}; + +static void bcm2835_powermgt_init(Object *obj) +{ + BCM2835PowerMgtState *s = BCM2835_POWERMGT(obj); + + memory_region_init_io(&s->iomem, obj, &bcm2835_powermgt_ops, s, + TYPE_BCM2835_POWERMGT, 0x200); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); +} + +static void bcm2835_powermgt_reset(DeviceState *dev) +{ + BCM2835PowerMgtState *s = BCM2835_POWERMGT(dev); + + /* https://elinux.org/BCM2835_registers#PM */ + s->rstc = 0x00000102; + s->rsts = 0x00001000; + s->wdog = 0x00000000; +} + +static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = bcm2835_powermgt_reset; + dc->vmsd = &vmstate_bcm2835_powermgt; +} + +static TypeInfo bcm2835_powermgt_info = { + .name = TYPE_BCM2835_POWERMGT, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(BCM2835PowerMgtState), + .class_init = bcm2835_powermgt_class_init, + .instance_init = bcm2835_powermgt_init, +}; + +static void bcm2835_powermgt_register_types(void) +{ + type_register_static(&bcm2835_powermgt_info); +} + +type_init(bcm2835_powermgt_register_types) diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files( 'bcm2835_rng.c', 'bcm2835_thermal.c', 'bcm2835_cprman.c', + 'bcm2835_powermgt.c', )) softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c')) softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c')) -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Add a test booting and quickly shutdown a raspi2 machine, to test the power management model: (1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_raspi2_initrd: console: [ 0.000000] Booting Linux on physical CPU 0xf00 console: [ 0.000000] Linux version 4.14.98-v7+ (dom@dom-XPS-13-9370) (gcc version 4.9.3 (crosstool-NG crosstool-ng-1.22.0-88-g8460611)) #1200 SMP Tue Feb 12 20:27:48 GMT 2019 console: [ 0.000000] CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=10c5387d console: [ 0.000000] CPU: div instructions available: patching division code console: [ 0.000000] CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache console: [ 0.000000] OF: fdt: Machine model: Raspberry Pi 2 Model B ... console: Boot successful. console: cat /proc/cpuinfo console: / # cat /proc/cpuinfo ... console: processor : 3 console: model name : ARMv7 Processor rev 5 (v7l) console: BogoMIPS : 125.00 console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm console: CPU implementer : 0x41 console: CPU architecture: 7 console: CPU variant : 0x0 console: CPU part : 0xc07 console: CPU revision : 5 console: Hardware : BCM2835 console: Revision : 0000 console: Serial : 0000000000000000 console: cat /proc/iomem console: / # cat /proc/iomem console: 00000000-3bffffff : System RAM console: 00008000-00afffff : Kernel code console: 00c00000-00d468ef : Kernel data console: 3f006000-3f006fff : dwc_otg console: 3f007000-3f007eff : /soc/dma@7e007000 console: 3f00b880-3f00b8bf : /soc/mailbox@7e00b880 console: 3f100000-3f100027 : /soc/watchdog@7e100000 console: 3f101000-3f102fff : /soc/cprman@7e101000 console: 3f200000-3f2000b3 : /soc/gpio@7e200000 PASS (24.59 s) RESULTS : PASS 1 | ERROR 0 | FAIL 0 | SKIP 0 | WARN 0 | INTERRUPT 0 | CANCEL 0 JOB TIME : 25.02 s Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Message-id: 20210531113837.1689775-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 43 ++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ from avocado import skip from avocado import skipUnless from avocado_qemu import Test +from avocado_qemu import exec_command from avocado_qemu import exec_command_and_wait_for_pattern from avocado_qemu import interrupt_interactive_console_until_pattern from avocado_qemu import wait_for_console_pattern @@ -XXX,XX +XXX,XX @@ def test_arm_raspi2_uart0(self): """ self.do_test_arm_raspi2(0) + def test_arm_raspi2_initrd(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:raspi2 + """ + deb_url = ('http://archive.raspberrypi.org/debian/' + 'pool/main/r/raspberrypi-firmware/' + 'raspberrypi-kernel_1.20190215-1_armhf.deb') + deb_hash = 'cd284220b32128c5084037553db3c482426f3972' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, '/boot/kernel7.img') + dtb_path = self.extract_from_deb(deb_path, '/boot/bcm2709-rpi-2-b.dtb') + + initrd_url = ('https://github.com/groeck/linux-build-test/raw/' + '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' + 'arm/rootfs-armv7a.cpio.gz') + initrd_hash = '604b2e45cdf35045846b8bbfbf2129b1891bdc9c' + initrd_path_gz = self.fetch_asset(initrd_url, asset_hash=initrd_hash) + initrd_path = os.path.join(self.workdir, 'rootfs.cpio') + archive.gzip_uncompress(initrd_path_gz, initrd_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'earlycon=pl011,0x3f201000 console=ttyAMA0 ' + 'panic=-1 noreboot ' + + 'dwc_otg.fiq_fsm_enable=0') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-initrd', initrd_path, + '-append', kernel_command_line, + '-no-reboot') + self.vm.launch() + self.wait_for_console_pattern('Boot successful.') + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'BCM2835') + exec_command_and_wait_for_pattern(self, 'cat /proc/iomem', + '/soc/cprman@7e101000') + exec_command(self, 'halt') + # Wait for VM to shut down gracefully + self.vm.wait() + def test_arm_exynos4210_initrd(self): """ :avocado: tags=arch:arm -- 2.20.1 From: Joe Komlodi <joe.komlodi@xilinx.com> If the CPU is running in default NaN mode (FPCR.DN == 1) and we execute FRSQRTE, FRECPE, or FRECPX with a signaling NaN, parts_silence_nan_frac() will assert due to fpst->default_nan_mode being set. To avoid this, we check to see what NaN mode we're running in before we call floatxx_silence_nan(). Signed-off-by: Joe Komlodi <joe.komlodi@xilinx.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1624662174-175828-2-git-send-email-joe.komlodi@xilinx.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.c | 12 +++++++++--- target/arm/vfp_helper.c | 24 ++++++++++++++++++------ 2 files changed, 27 insertions(+), 9 deletions(-) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) float16 nan = a; if (float16_is_signaling_nan(a, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float16_silence_nan(a, fpst); + if (!fpst->default_nan_mode) { + nan = float16_silence_nan(a, fpst); + } } if (fpst->default_nan_mode) { nan = float16_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ float32 HELPER(frecpx_f32)(float32 a, void *fpstp) float32 nan = a; if (float32_is_signaling_nan(a, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float32_silence_nan(a, fpst); + if (!fpst->default_nan_mode) { + nan = float32_silence_nan(a, fpst); + } } if (fpst->default_nan_mode) { nan = float32_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ float64 HELPER(frecpx_f64)(float64 a, void *fpstp) float64 nan = a; if (float64_is_signaling_nan(a, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float64_silence_nan(a, fpst); + if (!fpst->default_nan_mode) { + nan = float64_silence_nan(a, fpst); + } } if (fpst->default_nan_mode) { nan = float64_default_nan(fpst); diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp) float16 nan = f16; if (float16_is_signaling_nan(f16, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float16_silence_nan(f16, fpst); + if (!fpst->default_nan_mode) { + nan = float16_silence_nan(f16, fpst); + } } if (fpst->default_nan_mode) { nan = float16_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ float32 HELPER(recpe_f32)(float32 input, void *fpstp) float32 nan = f32; if (float32_is_signaling_nan(f32, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float32_silence_nan(f32, fpst); + if (!fpst->default_nan_mode) { + nan = float32_silence_nan(f32, fpst); + } } if (fpst->default_nan_mode) { nan = float32_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp) float64 nan = f64; if (float64_is_signaling_nan(f64, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float64_silence_nan(f64, fpst); + if (!fpst->default_nan_mode) { + nan = float64_silence_nan(f64, fpst); + } } if (fpst->default_nan_mode) { nan = float64_default_nan(fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp) float16 nan = f16; if (float16_is_signaling_nan(f16, s)) { float_raise(float_flag_invalid, s); - nan = float16_silence_nan(f16, s); + if (!s->default_nan_mode) { + nan = float16_silence_nan(f16, fpstp); + } } if (s->default_nan_mode) { nan = float16_default_nan(s); @@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) float32 nan = f32; if (float32_is_signaling_nan(f32, s)) { float_raise(float_flag_invalid, s); - nan = float32_silence_nan(f32, s); + if (!s->default_nan_mode) { + nan = float32_silence_nan(f32, fpstp); + } } if (s->default_nan_mode) { nan = float32_default_nan(s); @@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) float64 nan = f64; if (float64_is_signaling_nan(f64, s)) { float_raise(float_flag_invalid, s); - nan = float64_silence_nan(f64, s); + if (!s->default_nan_mode) { + nan = float64_silence_nan(f64, fpstp); + } } if (s->default_nan_mode) { nan = float64_default_nan(s); -- 2.20.1 From: Maxim Uvarov <maxim.uvarov@linaro.org> qemu has 2 type of functions: shutdown and reboot. Shutdown function has to be used for machine shutdown. Otherwise we cause a reset with a bogus "cause" value, when we intended a shutdown. Signed-off-by: Maxim Uvarov <maxim.uvarov@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210625111842.3790-3-maxim.uvarov@linaro.org [PMM: tweaked commit message] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/gpio/gpio_pwr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/gpio/gpio_pwr.c b/hw/gpio/gpio_pwr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/gpio_pwr.c +++ b/hw/gpio/gpio_pwr.c @@ -XXX,XX +XXX,XX @@ static void gpio_pwr_reset(void *opaque, int n, int level) static void gpio_pwr_shutdown(void *opaque, int n, int level) { if (level) { - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); } } -- 2.20.1 In do_ldst(), the calculation of the offset needs to be based on the size of the memory access, not the size of the elements in the vector. This meant we were getting it wrong for the widening and narrowing variants of the various VLDR and VSTR insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-2-peter.maydell@linaro.org --- target/arm/translate-mve.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool mve_skip_first_beat(DisasContext *s) } } -static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) +static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn, + unsigned msize) { TCGv_i32 addr; uint32_t offset; @@ -XXX,XX +XXX,XX @@ static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) return true; } - offset = a->imm << a->size; + offset = a->imm << msize; if (!a->a) { offset = -offset; } @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a) { gen_helper_mve_vstrw, gen_helper_mve_vldrw }, { NULL, NULL } }; - return do_ldst(s, a, ldstfns[a->size][a->l]); + return do_ldst(s, a, ldstfns[a->size][a->l], a->size); } -#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST) \ +#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST, MSIZE) \ static bool trans_##OP(DisasContext *s, arg_VLDR_VSTR *a) \ { \ static MVEGenLdStFn * const ldstfns[2][2] = { \ { gen_helper_mve_##ST, gen_helper_mve_##SLD }, \ { NULL, gen_helper_mve_##ULD }, \ }; \ - return do_ldst(s, a, ldstfns[a->u][a->l]); \ + return do_ldst(s, a, ldstfns[a->u][a->l], MSIZE); \ } -DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h) -DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w) -DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w) +DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8) +DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8) +DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16) static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { -- 2.20.1 The initial implementation of the MVE VRMLALDAVH and VRMLSLDAVH insns had some bugs: * the 32x32 multiply of elements was being done as 32x32->32, not 32x32->64 * we were incorrectly maintaining the accumulator in its full 72-bit form across all 4 beats of the insn; in the pseudocode it is squashed back into the 64 bits of the RdaHi:RdaLo registers after each beat In particular, fixing the second of these allows us to recast the implementation to avoid 128-bit arithmetic entirely. Since the element size here is always 4, we can also drop the parameterization of ESIZE to make the code a little more readable. Suggested-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-3-peter.maydell@linaro.org --- target/arm/mve_helper.c | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "qemu/int128.h" #include "cpu.h" #include "internals.h" #include "vec_internal.h" @@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=) DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=) /* - * Rounding multiply add long dual accumulate high: we must keep - * a 72-bit internal accumulator value and return the top 64 bits. + * Rounding multiply add long dual accumulate high. In the pseudocode + * this is implemented with a 72-bit internal accumulator value of which + * the top 64 bits are returned. We optimize this to avoid having to + * use 128-bit arithmetic -- we can do this because the 74-bit accumulator + * is squashed back into 64-bits after each beat. */ -#define DO_LDAVH(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC, TO128) \ +#define DO_LDAVH(OP, TYPE, LTYPE, XCHG, SUB) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ void *vm, uint64_t a) \ { \ uint16_t mask = mve_element_mask(env); \ unsigned e; \ TYPE *n = vn, *m = vm; \ - Int128 acc = int128_lshift(TO128(a), 8); \ - for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ if (mask & 1) { \ + LTYPE mul; \ if (e & 1) { \ - acc = ODDACC(acc, TO128(n[H##ESIZE(e - 1 * XCHG)] * \ - m[H##ESIZE(e)])); \ + mul = (LTYPE)n[H4(e - 1 * XCHG)] * m[H4(e)]; \ + if (SUB) { \ + mul = -mul; \ + } \ } else { \ - acc = EVENACC(acc, TO128(n[H##ESIZE(e + 1 * XCHG)] * \ - m[H##ESIZE(e)])); \ + mul = (LTYPE)n[H4(e + 1 * XCHG)] * m[H4(e)]; \ } \ - acc = int128_add(acc, int128_make64(1 << 7)); \ + mul = (mul >> 8) + ((mul >> 7) & 1); \ + a += mul; \ } \ } \ mve_advance_vpt(env); \ - return int128_getlo(int128_rshift(acc, 8)); \ + return a; \ } -DO_LDAVH(vrmlaldavhsw, 4, int32_t, false, int128_add, int128_add, int128_makes64) -DO_LDAVH(vrmlaldavhxsw, 4, int32_t, true, int128_add, int128_add, int128_makes64) +DO_LDAVH(vrmlaldavhsw, int32_t, int64_t, false, false) +DO_LDAVH(vrmlaldavhxsw, int32_t, int64_t, true, false) -DO_LDAVH(vrmlaldavhuw, 4, uint32_t, false, int128_add, int128_add, int128_make64) +DO_LDAVH(vrmlaldavhuw, uint32_t, uint64_t, false, false) -DO_LDAVH(vrmlsldavhsw, 4, int32_t, false, int128_add, int128_sub, int128_makes64) -DO_LDAVH(vrmlsldavhxsw, 4, int32_t, true, int128_add, int128_sub, int128_makes64) +DO_LDAVH(vrmlsldavhsw, int32_t, int64_t, false, true) +DO_LDAVH(vrmlsldavhxsw, int32_t, int64_t, true, true) /* Vector add across vector */ #define DO_VADDV(OP, ESIZE, TYPE) \ -- 2.20.1 The function asimd_imm_const() in translate-neon.c is an implementation of the pseudocode AdvSIMDExpandImm(), which we will also want for MVE. Move the implementation to translate.c, with a prototype in translate.h. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-4-peter.maydell@linaro.org --- target/arm/translate.h | 16 ++++++++++ target/arm/translate-neon.c | 63 ------------------------------------- target/arm/translate.c | 57 +++++++++++++++++++++++++++++++++ 3 files changed, 73 insertions(+), 63 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) return opc | s->be_data; } +/** + * asimd_imm_const: Expand an encoded SIMD constant value + * + * Expand a SIMD constant value. This is essentially the pseudocode + * AdvSIMDExpandImm, except that we also perform the boolean NOT needed for + * VMVN and VBIC (when cmode < 14 && op == 1). + * + * The combination cmode == 15 op == 1 is a reserved encoding for AArch32; + * callers must catch this. + * + * cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 was UNPREDICTABLE in v7A but + * is either not unpredictable or merely CONSTRAINED UNPREDICTABLE in v8A; + * we produce an immediate constant value of 0 in these cases. + */ +uint64_t asimd_imm_const(uint32_t imm, int cmode, int op); + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh) DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs) DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu) -static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) -{ - /* - * Expand the encoded constant. - * Note that cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE. - * We choose to not special-case this and will behave as if a - * valid constant encoding of 0 had been given. - * cmode = 15 op = 1 must UNDEF; we assume decode has handled that. - */ - switch (cmode) { - case 0: case 1: - /* no-op */ - break; - case 2: case 3: - imm <<= 8; - break; - case 4: case 5: - imm <<= 16; - break; - case 6: case 7: - imm <<= 24; - break; - case 8: case 9: - imm |= imm << 16; - break; - case 10: case 11: - imm = (imm << 8) | (imm << 24); - break; - case 12: - imm = (imm << 8) | 0xff; - break; - case 13: - imm = (imm << 16) | 0xffff; - break; - case 14: - if (op) { - /* - * This is the only case where the top and bottom 32 bits - * of the encoded constant differ. - */ - uint64_t imm64 = 0; - int n; - - for (n = 0; n < 8; n++) { - if (imm & (1 << n)) { - imm64 |= (0xffULL << (n * 8)); - } - } - return imm64; - } - imm |= (imm << 8) | (imm << 16) | (imm << 24); - break; - case 15: - imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) - | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); - break; - } - if (op) { - imm = ~imm; - } - return dup_const(MO_32, imm); -} - static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a, GVecGen2iFn *fn) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void arm_translate_init(void) a64_translate_init(); } +uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) +{ + /* Expand the encoded constant as per AdvSIMDExpandImm pseudocode */ + switch (cmode) { + case 0: case 1: + /* no-op */ + break; + case 2: case 3: + imm <<= 8; + break; + case 4: case 5: + imm <<= 16; + break; + case 6: case 7: + imm <<= 24; + break; + case 8: case 9: + imm |= imm << 16; + break; + case 10: case 11: + imm = (imm << 8) | (imm << 24); + break; + case 12: + imm = (imm << 8) | 0xff; + break; + case 13: + imm = (imm << 16) | 0xffff; + break; + case 14: + if (op) { + /* + * This is the only case where the top and bottom 32 bits + * of the encoded constant differ. + */ + uint64_t imm64 = 0; + int n; + + for (n = 0; n < 8; n++) { + if (imm & (1 << n)) { + imm64 |= (0xffULL << (n * 8)); + } + } + return imm64; + } + imm |= (imm << 8) | (imm << 16) | (imm << 24); + break; + case 15: + imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) + | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); + break; + } + if (op) { + imm = ~imm; + } + return dup_const(MO_32, imm); +} + /* Generate a label used for skipping this instruction */ void arm_gen_condlabel(DisasContext *s) { -- 2.20.1 The A64 AdvSIMD modified-immediate grouping uses almost the same constant encoding that A32 Neon does; reuse asimd_imm_const() (to which we add the AArch64-specific case for cmode 15 op 1) instead of reimplementing it all. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-5-peter.maydell@linaro.org --- target/arm/translate.h | 3 +- target/arm/translate-a64.c | 86 ++++---------------------------------- target/arm/translate.c | 17 +++++++- 3 files changed, 24 insertions(+), 82 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) * VMVN and VBIC (when cmode < 14 && op == 1). * * The combination cmode == 15 op == 1 is a reserved encoding for AArch32; - * callers must catch this. + * callers must catch this; we return the 64-bit constant value defined + * for AArch64. * * cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 was UNPREDICTABLE in v7A but * is either not unpredictable or merely CONSTRAINED UNPREDICTABLE in v8A; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) { int rd = extract32(insn, 0, 5); int cmode = extract32(insn, 12, 4); - int cmode_3_1 = extract32(cmode, 1, 3); - int cmode_0 = extract32(cmode, 0, 1); int o2 = extract32(insn, 11, 1); uint64_t abcdefgh = extract32(insn, 5, 5) | (extract32(insn, 16, 3) << 5); bool is_neg = extract32(insn, 29, 1); @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) return; } - /* See AdvSIMDExpandImm() in ARM ARM */ - switch (cmode_3_1) { - case 0: /* Replicate(Zeros(24):imm8, 2) */ - case 1: /* Replicate(Zeros(16):imm8:Zeros(8), 2) */ - case 2: /* Replicate(Zeros(8):imm8:Zeros(16), 2) */ - case 3: /* Replicate(imm8:Zeros(24), 2) */ - { - int shift = cmode_3_1 * 8; - imm = bitfield_replicate(abcdefgh << shift, 32); - break; - } - case 4: /* Replicate(Zeros(8):imm8, 4) */ - case 5: /* Replicate(imm8:Zeros(8), 4) */ - { - int shift = (cmode_3_1 & 0x1) * 8; - imm = bitfield_replicate(abcdefgh << shift, 16); - break; - } - case 6: - if (cmode_0) { - /* Replicate(Zeros(8):imm8:Ones(16), 2) */ - imm = (abcdefgh << 16) | 0xffff; - } else { - /* Replicate(Zeros(16):imm8:Ones(8), 2) */ - imm = (abcdefgh << 8) | 0xff; - } - imm = bitfield_replicate(imm, 32); - break; - case 7: - if (!cmode_0 && !is_neg) { - imm = bitfield_replicate(abcdefgh, 8); - } else if (!cmode_0 && is_neg) { - int i; - imm = 0; - for (i = 0; i < 8; i++) { - if ((abcdefgh) & (1 << i)) { - imm |= 0xffULL << (i * 8); - } - } - } else if (cmode_0) { - if (is_neg) { - imm = (abcdefgh & 0x3f) << 48; - if (abcdefgh & 0x80) { - imm |= 0x8000000000000000ULL; - } - if (abcdefgh & 0x40) { - imm |= 0x3fc0000000000000ULL; - } else { - imm |= 0x4000000000000000ULL; - } - } else { - if (o2) { - /* FMOV (vector, immediate) - half-precision */ - imm = vfp_expand_imm(MO_16, abcdefgh); - /* now duplicate across the lanes */ - imm = bitfield_replicate(imm, 16); - } else { - imm = (abcdefgh & 0x3f) << 19; - if (abcdefgh & 0x80) { - imm |= 0x80000000; - } - if (abcdefgh & 0x40) { - imm |= 0x3e000000; - } else { - imm |= 0x40000000; - } - imm |= (imm << 32); - } - } - } - break; - default: - g_assert_not_reached(); - } - - if (cmode_3_1 != 7 && is_neg) { - imm = ~imm; + if (cmode == 15 && o2 && !is_neg) { + /* FMOV (vector, immediate) - half-precision */ + imm = vfp_expand_imm(MO_16, abcdefgh); + /* now duplicate across the lanes */ + imm = bitfield_replicate(imm, 16); + } else { + imm = asimd_imm_const(abcdefgh, cmode, is_neg); } if (!((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9)) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) case 14: if (op) { /* - * This is the only case where the top and bottom 32 bits - * of the encoded constant differ. + * This and cmode == 15 op == 1 are the only cases where + * the top and bottom 32 bits of the encoded constant differ. */ uint64_t imm64 = 0; int n; @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) imm |= (imm << 8) | (imm << 16) | (imm << 24); break; case 15: + if (op) { + /* Reserved encoding for AArch32; valid for AArch64 */ + uint64_t imm64 = (uint64_t)(imm & 0x3f) << 48; + if (imm & 0x80) { + imm64 |= 0x8000000000000000ULL; + } + if (imm & 0x40) { + imm64 |= 0x3fc0000000000000ULL; + } else { + imm64 |= 0x4000000000000000ULL; + } + return imm64; + } imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); break; -- 2.20.1 Use dup_const() instead of bitfield_replicate() in disas_simd_mod_imm(). (We can't replace the other use of bitfield_replicate() in this file, in logic_imm_decode_wmask(), because that location needs to handle 2 and 4 bit elements, which dup_const() cannot.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-6-peter.maydell@linaro.org --- target/arm/translate-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) /* FMOV (vector, immediate) - half-precision */ imm = vfp_expand_imm(MO_16, abcdefgh); /* now duplicate across the lanes */ - imm = bitfield_replicate(imm, 16); + imm = dup_const(MO_16, imm); } else { imm = asimd_imm_const(abcdefgh, cmode, is_neg); } -- 2.20.1 Implement the MVE logical-immediate insns (VMOV, VMVN, VORR and VBIC). These have essentially the same encoding as their Neon equivalents, and we implement the decode in the same way. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-7-peter.maydell@linaro.org --- target/arm/helper-mve.h | 4 +++ target/arm/mve.decode | 17 +++++++++++++ target/arm/mve_helper.c | 24 ++++++++++++++++++ target/arm/translate-mve.c | 50 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 95 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) +DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) +DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ # VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit %size_28 28:1 !function=plus_1 +# 1imm format immediate +%imm_28_16_0 28:1 16:3 0:4 + &vldr_vstr rn qd imm p a w size l u &1op qd qm size &2op qd qm qn size &2scalar qd qn rm size +&1imm qd imm cmode op @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2op_nosz .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn size=0 @2op_sz28 .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn \ size=%size_28 +@1imm .... .... .... .... .... cmode:4 .. op:1 . .... &1imm qd=%qd imm=%imm_28_16_0 # The _rev suffix indicates that Vn and Vm are reversed. This is # the case for shifts. In the Arm ARM these insns are documented @@ -XXX,XX +XXX,XX @@ VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rd # Predicate operations %mask_22_13 22:1 13:3 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 + +# Logical immediate operations (1 reg and modified-immediate) + +# The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but +# not in a way we can conveniently represent in decodetree without +# a lot of repetition: +# VORR: op=0, (cmode & 1) && cmode < 12 +# VBIC: op=1, (cmode & 1) && cmode < 12 +# VMOV: everything else +# So we have a single decode line and check the cmode/op in the +# trans function. +Vimm_1r 111 . 1111 1 . 00 0 ... ... 0 .... 0 1 . 1 .... @1imm diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_1OP(vnegw, 4, int32_t, DO_NEG) DO_1OP(vfnegh, 8, uint64_t, DO_FNEGH) DO_1OP(vfnegs, 8, uint64_t, DO_FNEGS) +/* + * 1 operand immediates: Vda is destination and possibly also one source. + * All these insns work at 64-bit widths. + */ +#define DO_1OP_IMM(OP, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vda, uint64_t imm) \ + { \ + uint64_t *da = vda; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / 8; e++, mask >>= 8) { \ + mergemask(&da[H8(e)], FN(da[H8(e)], imm), mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_MOVI(N, I) (I) +#define DO_ANDI(N, I) ((N) & (I)) +#define DO_ORRI(N, I) ((N) | (I)) + +DO_1OP_IMM(vmovi, DO_MOVI) +DO_1OP_IMM(vandi, DO_ANDI) +DO_1OP_IMM(vorri, DO_ORRI) + #define DO_2OP(OP, ESIZE, TYPE, FN) \ void HELPER(glue(mve_, OP))(CPUARMState *env, \ void *vd, void *vn, void *vm) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VADDV(DisasContext *s, arg_VADDV *a) mve_update_eci(s); return true; } + +static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn) +{ + TCGv_ptr qd; + uint64_t imm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + imm = asimd_imm_const(a->imm, a->cmode, a->op); + + qd = mve_qreg_ptr(a->qd); + fn(cpu_env, qd, tcg_constant_i64(imm)); + tcg_temp_free_ptr(qd); + mve_update_eci(s); + return true; +} + +static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a) +{ + /* Handle decode of cmode/op here between VORR/VBIC/VMOV */ + MVEGenOneOpImmFn *fn; + + if ((a->cmode & 1) && a->cmode < 12) { + if (a->op) { + /* + * For op=1, the immediate will be inverted by asimd_imm_const(), + * so the VBIC becomes a logical AND operation. + */ + fn = gen_helper_mve_vandi; + } else { + fn = gen_helper_mve_vorri; + } + } else { + /* There is one unallocated cmode/op combination in this space */ + if (a->cmode == 15 && a->op == 1) { + return false; + } + /* asimd_imm_const() sorts out VMVNI vs VMOVI for us */ + fn = gen_helper_mve_vmovi; + } + return do_1imm(s, a, fn); +} -- 2.20.1 Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL and VQSHLU. The size-and-immediate encoding here is the same as Neon, and we handle it the same way neon-dp.decode does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-8-peter.maydell@linaro.org --- target/arm/helper-mve.h | 16 +++++++++++ target/arm/mve.decode | 23 +++++++++++++++ target/arm/mve_helper.c | 57 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 51 ++++++++++++++++++++++++++++++++++ 4 files changed, 147 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) + +DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshlui_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshlui_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshlui_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2op qd qm qn size &2scalar qd qn rm size &1imm qd imm cmode op +&2shift qd qm shift size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2scalar .... .... .. size:2 .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn @2scalar_nosz .... .... .... .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn +@2_shl_b .... .... .. 001 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0 +@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 +@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2 + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 # So we have a single decode line and check the cmode/op in the # trans function. Vimm_1r 111 . 1111 1 . 00 0 ... ... 0 .... 0 1 . 1 .... @1imm + +# Shifts by immediate + +VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b +VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h +VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w + +VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b +VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h +VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w + +VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b +VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h +VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w + +VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_b +VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_h +VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_w diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT(vqsubsw, 4, int32_t, DO_SQSUB_W) WRAP_QRSHL_HELPER(do_sqrshl_bhs, N, M, true, satp) #define DO_UQRSHL_OP(N, M, satp) \ WRAP_QRSHL_HELPER(do_uqrshl_bhs, N, M, true, satp) +#define DO_SUQSHL_OP(N, M, satp) \ + WRAP_QRSHL_HELPER(do_suqrshl_bhs, N, M, false, satp) DO_2OP_SAT_S(vqshls, DO_SQSHL_OP) DO_2OP_SAT_U(vqshlu, DO_UQSHL_OP) @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvsw, 4, uint32_t) DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) + +/* Shifts by immediate */ +#define DO_2SHIFT(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + TYPE *d = vd, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], \ + FN(m[H##ESIZE(e)], shift), mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2SHIFT_SAT(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + TYPE *d = vd, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], \ + FN(m[H##ESIZE(e)], shift, &sat), mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +/* provide unsigned 2-op shift helpers for all sizes */ +#define DO_2SHIFT_U(OP, FN) \ + DO_2SHIFT(OP##b, 1, uint8_t, FN) \ + DO_2SHIFT(OP##h, 2, uint16_t, FN) \ + DO_2SHIFT(OP##w, 4, uint32_t, FN) + +#define DO_2SHIFT_SAT_U(OP, FN) \ + DO_2SHIFT_SAT(OP##b, 1, uint8_t, FN) \ + DO_2SHIFT_SAT(OP##h, 2, uint16_t, FN) \ + DO_2SHIFT_SAT(OP##w, 4, uint32_t, FN) +#define DO_2SHIFT_SAT_S(OP, FN) \ + DO_2SHIFT_SAT(OP##b, 1, int8_t, FN) \ + DO_2SHIFT_SAT(OP##h, 2, int16_t, FN) \ + DO_2SHIFT_SAT(OP##w, 4, int32_t, FN) + +DO_2SHIFT_U(vshli_u, DO_VSHLU) +DO_2SHIFT_SAT_U(vqshli_u, DO_UQSHL_OP) +DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) +DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); @@ -XXX,XX +XXX,XX @@ static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a) } return do_1imm(s, a, fn); } + +static bool do_2shift(DisasContext *s, arg_2shift *a, MVEGenTwoOpShiftFn fn, + bool negateshift) +{ + TCGv_ptr qd, qm; + int shift = a->shift; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* + * When we handle a right shift insn using a left-shift helper + * which permits a negative shift count to indicate a right-shift, + * we must negate the shift count. + */ + if (negateshift) { + shift = -shift; + } + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, tcg_constant_i32(shift)); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +#define DO_2SHIFT(INSN, FN, NEGATESHIFT) \ + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_2shift(s, a, fns[a->size], NEGATESHIFT); \ + } + +DO_2SHIFT(VSHLI, vshli_u, false) +DO_2SHIFT(VQSHLI_S, vqshli_s, false) +DO_2SHIFT(VQSHLI_U, vqshli_u, false) +DO_2SHIFT(VQSHLUI, vqshlui_s, false) -- 2.20.1 Implement the MVE vector shift right by immediate insns VSHRI and VRSHRI. As with Neon, we implement these by using helper functions which perform left shifts but allow negative shift counts to indicate right shifts. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-9-peter.maydell@linaro.org --- target/arm/helper-mve.h | 12 ++++++++++++ target/arm/translate.h | 20 ++++++++++++++++++++ target/arm/mve.decode | 28 ++++++++++++++++++++++++++++ target/arm/mve_helper.c | 7 +++++++ target/arm/translate-mve.c | 5 +++++ target/arm/translate-neon.c | 18 ------------------ 6 files changed, 72 insertions(+), 18 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqshlui_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqshlui_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqshlui_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vrshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline int times_2_plus_1(DisasContext *s, int x) return x * 2 + 1; } +static inline int rsub_64(DisasContext *s, int x) +{ + return 64 - x; +} + +static inline int rsub_32(DisasContext *s, int x) +{ + return 32 - x; +} + +static inline int rsub_16(DisasContext *s, int x) +{ + return 16 - x; +} + +static inline int rsub_8(DisasContext *s, int x) +{ + return 8 - x; +} + static inline int arm_dc_feature(DisasContext *dc, int feature) { return (dc->features & (1ULL << feature)) != 0; diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ @2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 @2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2 +# Right shifts are encoded as N - shift, where N is the element size in bits. +%rshift_i5 16:5 !function=rsub_32 +%rshift_i4 16:4 !function=rsub_16 +%rshift_i3 16:3 !function=rsub_8 + +@2_shr_b .... .... .. 001 ... .... .... .... .... &2shift qd=%qd qm=%qm \ + size=0 shift=%rshift_i3 +@2_shr_h .... .... .. 01 .... .... .... .... .... &2shift qd=%qd qm=%qm \ + size=1 shift=%rshift_i4 +@2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ + size=2 shift=%rshift_i5 + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_b VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_h VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_w + +VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b +VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h +VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w + +VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b +VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h +VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w + +VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b +VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h +VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w + +VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b +VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h +VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvuw, 4, uint32_t) DO_2SHIFT(OP##b, 1, uint8_t, FN) \ DO_2SHIFT(OP##h, 2, uint16_t, FN) \ DO_2SHIFT(OP##w, 4, uint32_t, FN) +#define DO_2SHIFT_S(OP, FN) \ + DO_2SHIFT(OP##b, 1, int8_t, FN) \ + DO_2SHIFT(OP##h, 2, int16_t, FN) \ + DO_2SHIFT(OP##w, 4, int32_t, FN) #define DO_2SHIFT_SAT_U(OP, FN) \ DO_2SHIFT_SAT(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvuw, 4, uint32_t) DO_2SHIFT_SAT(OP##w, 4, int32_t, FN) DO_2SHIFT_U(vshli_u, DO_VSHLU) +DO_2SHIFT_S(vshli_s, DO_VSHLS) DO_2SHIFT_SAT_U(vqshli_u, DO_UQSHL_OP) DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) +DO_2SHIFT_U(vrshli_u, DO_VRSHLU) +DO_2SHIFT_S(vrshli_s, DO_VRSHLS) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHLI, vshli_u, false) DO_2SHIFT(VQSHLI_S, vqshli_s, false) DO_2SHIFT(VQSHLI_U, vqshli_u, false) DO_2SHIFT(VQSHLUI, vqshlui_s, false) +/* These right shifts use a left-shift helper with negated shift count */ +DO_2SHIFT(VSHRI_S, vshli_s, true) +DO_2SHIFT(VSHRI_U, vshli_u, true) +DO_2SHIFT(VRSHRI_S, vrshli_s, true) +DO_2SHIFT(VRSHRI_U, vrshli_u, true) diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ static inline int plus1(DisasContext *s, int x) return x + 1; } -static inline int rsub_64(DisasContext *s, int x) -{ - return 64 - x; -} - -static inline int rsub_32(DisasContext *s, int x) -{ - return 32 - x; -} -static inline int rsub_16(DisasContext *s, int x) -{ - return 16 - x; -} -static inline int rsub_8(DisasContext *s, int x) -{ - return 8 - x; -} - static inline int neon_3same_fp_size(DisasContext *s, int x) { /* Convert 0==fp32, 1==fp16 into a MO_* value */ -- 2.20.1 Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org --- target/arm/helper-mve.h | 9 +++++++ target/arm/mve.decode | 53 +++++++++++++++++++++++++++++++++++--- target/arm/mve_helper.c | 32 +++++++++++++++++++++++ target/arm/translate-mve.c | 15 +++++++++++ 4 files changed, 105 insertions(+), 4 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshllbuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ @2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 @2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2 +@2_shll_b .... .... ... 01 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0 +@2_shll_h .... .... ... 1 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 +# VSHLL encoding T2 where shift == esize +@2_shll_esize_b .... .... .... 00 .. .... .... .... .... &2shift \ + qd=%qd qm=%qm size=0 shift=8 +@2_shll_esize_h .... .... .... 01 .. .... .... .... .... &2shift \ + qd=%qd qm=%qm size=1 shift=16 + # Right shifts are encoded as N - shift, where N is the element size in bits. %rshift_i5 16:5 !function=rsub_32 %rshift_i4 16:4 !function=rsub_16 @@ -XXX,XX +XXX,XX @@ VADD 1110 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op VSUB 1111 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op -VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op -VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op +# The VSHLL T2 encoding is not a @2op pattern, but is here because it +# overlaps what would be size=0b11 VMULH/VRMULH +{ + VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b + VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h -VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op -VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op +} + +{ + VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b + VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + + VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op +} + +{ + VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b + VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op +} + +{ + VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b + VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + + VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op +} VMAX_S 111 0 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op VMAX_U 111 1 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op @@ -XXX,XX +XXX,XX @@ VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w + +# VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file +VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b +VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h + +VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b +VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h + +VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b +VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h + +VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b +VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) DO_2SHIFT_U(vrshli_u, DO_VRSHLU) DO_2SHIFT_S(vrshli_s, DO_VRSHLS) + +/* + * Long shifts taking half-sized inputs from top or bottom of the input + * vector and producing a double-width result. ESIZE, TYPE are for + * the input, and LESIZE, LTYPE for the output. + * Unlike the normal shift helpers, we do not handle negative shift counts, + * because the long shift is strictly left-only. + */ +#define DO_VSHLL(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + LTYPE *d = vd; \ + TYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned le; \ + assert(shift <= 16); \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + LTYPE r = (LTYPE)m[H##ESIZE(le * 2 + TOP)] << shift; \ + mergemask(&d[H##LESIZE(le)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSHLL_ALL(OP, TOP) \ + DO_VSHLL(OP##sb, TOP, 1, int8_t, 2, int16_t) \ + DO_VSHLL(OP##ub, TOP, 1, uint8_t, 2, uint16_t) \ + DO_VSHLL(OP##sh, TOP, 2, int16_t, 4, int32_t) \ + DO_VSHLL(OP##uh, TOP, 2, uint16_t, 4, uint32_t) \ + +DO_VSHLL_ALL(vshllb, false) +DO_VSHLL_ALL(vshllt, true) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHRI_S, vshli_s, true) DO_2SHIFT(VSHRI_U, vshli_u, true) DO_2SHIFT(VRSHRI_S, vrshli_s, true) DO_2SHIFT(VRSHRI_U, vrshli_u, true) + +#define DO_VSHLL(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + }; \ + return do_2shift(s, a, fns[a->size], false); \ + } + +DO_VSHLL(VSHLL_BS, vshllbs) +DO_VSHLL(VSHLL_BU, vshllbu) +DO_VSHLL(VSHLL_TS, vshllts) +DO_VSHLL(VSHLL_TU, vshlltu) -- 2.20.1 Implement the MVE VSRI and VSLI insns, which perform a shift-and-insert operation. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-11-peter.maydell@linaro.org --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 9 ++++++++ target/arm/mve_helper.c | 42 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 3 +++ 4 files changed, 62 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vsrib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vsrih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h + +# Shift-and-insert +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_b +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_h +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w + +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) DO_2SHIFT_U(vrshli_u, DO_VRSHLU) DO_2SHIFT_S(vrshli_s, DO_VRSHLS) +/* Shift-and-insert; we always work with 64 bits at a time */ +#define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + uint64_t *d = vd, *m = vm; \ + uint16_t mask; \ + uint64_t shiftmask; \ + unsigned e; \ + if (shift == 0 || shift == ESIZE * 8) { \ + /* \ + * Only VSLI can shift by 0; only VSRI can shift by <dt>. \ + * The generic logic would give the right answer for 0 but \ + * fails for <dt>. \ + */ \ + goto done; \ + } \ + assert(shift < ESIZE * 8); \ + mask = mve_element_mask(env); \ + /* ESIZE / 2 gives the MO_* value if ESIZE is in [1,2,4] */ \ + shiftmask = dup_const(ESIZE / 2, MASKFN(ESIZE * 8, shift)); \ + for (e = 0; e < 16 / 8; e++, mask >>= 8) { \ + uint64_t r = (SHIFTFN(m[H8(e)], shift) & shiftmask) | \ + (d[H8(e)] & ~shiftmask); \ + mergemask(&d[H8(e)], r, mask); \ + } \ +done: \ + mve_advance_vpt(env); \ + } + +#define DO_SHL(N, SHIFT) ((N) << (SHIFT)) +#define DO_SHR(N, SHIFT) ((N) >> (SHIFT)) +#define SHL_MASK(EBITS, SHIFT) MAKE_64BIT_MASK((SHIFT), (EBITS) - (SHIFT)) +#define SHR_MASK(EBITS, SHIFT) MAKE_64BIT_MASK(0, (EBITS) - (SHIFT)) + +DO_2SHIFT_INSERT(vsrib, 1, DO_SHR, SHR_MASK) +DO_2SHIFT_INSERT(vsrih, 2, DO_SHR, SHR_MASK) +DO_2SHIFT_INSERT(vsriw, 4, DO_SHR, SHR_MASK) +DO_2SHIFT_INSERT(vslib, 1, DO_SHL, SHL_MASK) +DO_2SHIFT_INSERT(vslih, 2, DO_SHL, SHL_MASK) +DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK) + /* * Long shifts taking half-sized inputs from top or bottom of the input * vector and producing a double-width result. ESIZE, TYPE are for diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHRI_U, vshli_u, true) DO_2SHIFT(VRSHRI_S, vrshli_s, true) DO_2SHIFT(VRSHRI_U, vrshli_u, true) +DO_2SHIFT(VSRI, vsri, false) +DO_2SHIFT(VSLI, vsli, false) + #define DO_VSHLL(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ { \ -- 2.20.1 Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN. do_urshr() is borrowed from sve_helper.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-12-peter.maydell@linaro.org --- target/arm/helper-mve.h | 10 ++++++++++ target/arm/mve.decode | 11 +++++++++++ target/arm/mve_helper.c | 40 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 15 ++++++++++++++ 4 files changed, 76 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w + +# Narrowing shifts (which only support b and h sizes) +VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b +VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h +VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b +VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h + +VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b +VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h +VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b +VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK) DO_VSHLL_ALL(vshllb, false) DO_VSHLL_ALL(vshllt, true) + +/* + * Narrowing right shifts, taking a double sized input, shifting it + * and putting the result in either the top or bottom half of the output. + * ESIZE, TYPE are the output, and LESIZE, LTYPE the input. + */ +#define DO_VSHRN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned le; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + TYPE r = FN(m[H##LESIZE(le)], shift); \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSHRN_ALL(OP, FN) \ + DO_VSHRN(OP##bb, false, 1, uint8_t, 2, uint16_t, FN) \ + DO_VSHRN(OP##bh, false, 2, uint16_t, 4, uint32_t, FN) \ + DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN) \ + DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN) + +static inline uint64_t do_urshr(uint64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else if (sh == 64) { + return x >> 63; + } else { + return 0; + } +} + +DO_VSHRN_ALL(vshrn, DO_SHR) +DO_VSHRN_ALL(vrshrn, do_urshr) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VSHLL(VSHLL_BS, vshllbs) DO_VSHLL(VSHLL_BU, vshllbu) DO_VSHLL(VSHLL_TS, vshllts) DO_VSHLL(VSHLL_TU, vshlltu) + +#define DO_2SHIFT_N(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + }; \ + return do_2shift(s, a, fns[a->size], false); \ + } + +DO_2SHIFT_N(VSHRNB, vshrnb) +DO_2SHIFT_N(VSHRNT, vshrnt) +DO_2SHIFT_N(VRSHRNB, vrshrnb) +DO_2SHIFT_N(VRSHRNT, vrshrnt) -- 2.20.1 Implement the MVE saturating shift-right-and-narrow insns VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN. do_srshr() is borrowed from sve_helper.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-13-peter.maydell@linaro.org --- target/arm/helper-mve.h | 30 +++++++++++ target/arm/mve.decode | 28 ++++++++++ target/arm/mve_helper.c | 104 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 12 +++++ 4 files changed, 174 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h + +VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b +VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h +VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b +VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h +VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b +VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h +VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b +VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h + +VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b +VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h +VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b +VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h + +VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b +VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h +VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b +VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h +VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b +VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h +VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b +VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h + +VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b +VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h +VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b +VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t do_urshr(uint64_t x, unsigned sh) } } +static inline int64_t do_srshr(int64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else { + /* Rounding the sign bit always produces 0. */ + return 0; + } +} + DO_VSHRN_ALL(vshrn, DO_SHR) DO_VSHRN_ALL(vrshrn, do_urshr) + +static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max, + bool *satp) +{ + if (val > max) { + *satp = true; + return max; + } else if (val < min) { + *satp = true; + return min; + } else { + return val; + } +} + +/* Saturating narrowing right shifts */ +#define DO_VSHRN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ + void *vm, uint32_t shift) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + bool qc = false; \ + unsigned le; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + bool sat = false; \ + TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ + qc |= sat && (mask & 1 << (TOP * ESIZE)); \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSHRN_SAT_UB(BOP, TOP, FN) \ + DO_VSHRN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \ + DO_VSHRN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN) + +#define DO_VSHRN_SAT_UH(BOP, TOP, FN) \ + DO_VSHRN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \ + DO_VSHRN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN) + +#define DO_VSHRN_SAT_SB(BOP, TOP, FN) \ + DO_VSHRN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \ + DO_VSHRN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN) + +#define DO_VSHRN_SAT_SH(BOP, TOP, FN) \ + DO_VSHRN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \ + DO_VSHRN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN) + +#define DO_SHRN_SB(N, M, SATP) \ + do_sat_bhs((int64_t)(N) >> (M), INT8_MIN, INT8_MAX, SATP) +#define DO_SHRN_UB(N, M, SATP) \ + do_sat_bhs((uint64_t)(N) >> (M), 0, UINT8_MAX, SATP) +#define DO_SHRUN_B(N, M, SATP) \ + do_sat_bhs((int64_t)(N) >> (M), 0, UINT8_MAX, SATP) + +#define DO_SHRN_SH(N, M, SATP) \ + do_sat_bhs((int64_t)(N) >> (M), INT16_MIN, INT16_MAX, SATP) +#define DO_SHRN_UH(N, M, SATP) \ + do_sat_bhs((uint64_t)(N) >> (M), 0, UINT16_MAX, SATP) +#define DO_SHRUN_H(N, M, SATP) \ + do_sat_bhs((int64_t)(N) >> (M), 0, UINT16_MAX, SATP) + +#define DO_RSHRN_SB(N, M, SATP) \ + do_sat_bhs(do_srshr(N, M), INT8_MIN, INT8_MAX, SATP) +#define DO_RSHRN_UB(N, M, SATP) \ + do_sat_bhs(do_urshr(N, M), 0, UINT8_MAX, SATP) +#define DO_RSHRUN_B(N, M, SATP) \ + do_sat_bhs(do_srshr(N, M), 0, UINT8_MAX, SATP) + +#define DO_RSHRN_SH(N, M, SATP) \ + do_sat_bhs(do_srshr(N, M), INT16_MIN, INT16_MAX, SATP) +#define DO_RSHRN_UH(N, M, SATP) \ + do_sat_bhs(do_urshr(N, M), 0, UINT16_MAX, SATP) +#define DO_RSHRUN_H(N, M, SATP) \ + do_sat_bhs(do_srshr(N, M), 0, UINT16_MAX, SATP) + +DO_VSHRN_SAT_SB(vqshrnb_sb, vqshrnt_sb, DO_SHRN_SB) +DO_VSHRN_SAT_SH(vqshrnb_sh, vqshrnt_sh, DO_SHRN_SH) +DO_VSHRN_SAT_UB(vqshrnb_ub, vqshrnt_ub, DO_SHRN_UB) +DO_VSHRN_SAT_UH(vqshrnb_uh, vqshrnt_uh, DO_SHRN_UH) +DO_VSHRN_SAT_SB(vqshrunbb, vqshruntb, DO_SHRUN_B) +DO_VSHRN_SAT_SH(vqshrunbh, vqshrunth, DO_SHRUN_H) + +DO_VSHRN_SAT_SB(vqrshrnb_sb, vqrshrnt_sb, DO_RSHRN_SB) +DO_VSHRN_SAT_SH(vqrshrnb_sh, vqrshrnt_sh, DO_RSHRN_SH) +DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB) +DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) +DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) +DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_N(VSHRNB, vshrnb) DO_2SHIFT_N(VSHRNT, vshrnt) DO_2SHIFT_N(VRSHRNB, vrshrnb) DO_2SHIFT_N(VRSHRNT, vrshrnt) +DO_2SHIFT_N(VQSHRNB_S, vqshrnb_s) +DO_2SHIFT_N(VQSHRNT_S, vqshrnt_s) +DO_2SHIFT_N(VQSHRNB_U, vqshrnb_u) +DO_2SHIFT_N(VQSHRNT_U, vqshrnt_u) +DO_2SHIFT_N(VQSHRUNB, vqshrunb) +DO_2SHIFT_N(VQSHRUNT, vqshrunt) +DO_2SHIFT_N(VQRSHRNB_S, vqrshrnb_s) +DO_2SHIFT_N(VQRSHRNT_S, vqrshrnt_s) +DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u) +DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u) +DO_2SHIFT_N(VQRSHRUNB, vqrshrunb) +DO_2SHIFT_N(VQRSHRUNT, vqrshrunt) -- 2.20.1 Implement the MVE VSHLC insn, which performs a shift left of the entire vector with carry in bits provided from a general purpose register and carry out bits written back to that register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-14-peter.maydell@linaro.org --- target/arm/helper-mve.h | 2 ++ target/arm/mve.decode | 2 ++ target/arm/mve_helper.c | 38 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 30 ++++++++++++++++++++++++++++++ 4 files changed, 72 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h + +VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB) DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) + +uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, + uint32_t shift) +{ + uint32_t *d = vd; + uint16_t mask = mve_element_mask(env); + unsigned e; + uint32_t r; + + /* + * For each 32-bit element, we shift it left, bringing in the + * low 'shift' bits of rdm at the bottom. Bits shifted out at + * the top become the new rdm, if the predicate mask permits. + * The final rdm value is returned to update the register. + * shift == 0 here means "shift by 32 bits". + */ + if (shift == 0) { + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + r = rdm; + if (mask & 1) { + rdm = d[H4(e)]; + } + mergemask(&d[H4(e)], r, mask); + } + } else { + uint32_t shiftmask = MAKE_64BIT_MASK(0, shift); + + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + r = (d[H4(e)] << shift) | (rdm & shiftmask); + if (mask & 1) { + rdm = d[H4(e)] >> (32 - shift); + } + mergemask(&d[H4(e)], r, mask); + } + } + mve_advance_vpt(env); + return rdm; +} diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u) DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u) DO_2SHIFT_N(VQRSHRUNB, vqrshrunb) DO_2SHIFT_N(VQRSHRUNT, vqrshrunt) + +static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a) +{ + /* + * Whole Vector Left Shift with Carry. The carry is taken + * from a general purpose register and written back there. + * An imm of 0 means "shift by 32". + */ + TCGv_ptr qd; + TCGv_i32 rdm; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (a->rdm == 13 || a->rdm == 15) { + /* CONSTRAINED UNPREDICTABLE: we UNDEF */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rdm = load_reg(s, a->rdm); + gen_helper_mve_vshlc(rdm, cpu_env, qd, rdm, tcg_constant_i32(a->imm)); + store_reg(s, a->rdm, rdm); + tcg_temp_free_ptr(qd); + mve_update_eci(s); + return true; +} -- 2.20.1 Implement the MVE VADDLV insn; this is similar to VADDV, except that it accumulates 32-bit elements into a 64-bit accumulator stored in a pair of general-purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-15-peter.maydell@linaro.org --- target/arm/helper-mve.h | 3 ++ target/arm/mve.decode | 6 +++- target/arm/mve_helper.c | 19 ++++++++++++ target/arm/translate-mve.c | 63 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 90 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) +DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) + DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar # Vector add across vector -VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo +{ + VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo + VADDLV 111 u:1 1110 1 ... 1001 ... 0 1111 00 a:1 0 qm:3 0 \ + rdahi=%rdahi rdalo=%rdalo +} # Predicate operations %mask_22_13 22:1 13:3 diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) +#define DO_VADDLV(OP, TYPE, LTYPE) \ + uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ + uint64_t ra) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + if (mask & 1) { \ + ra += (LTYPE)m[H4(e)]; \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } \ + +DO_VADDLV(vaddlv_s, int32_t, int64_t) +DO_VADDLV(vaddlv_u, uint32_t, uint64_t) + /* Shifts by immediate */ #define DO_2SHIFT(OP, ESIZE, TYPE, FN) \ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VADDV(DisasContext *s, arg_VADDV *a) return true; } +static bool trans_VADDLV(DisasContext *s, arg_VADDLV *a) +{ + /* + * Vector Add Long Across Vector: accumulate the 32-bit + * elements of the vector into a 64-bit result stored in + * a pair of general-purpose registers. + * No need to check Qm's bank: it is only 3 bits in decode. + */ + TCGv_ptr qm; + TCGv_i64 rda; + TCGv_i32 rdalo, rdahi; + + if (!dc_isar_feature(aa32_mve, s)) { + return false; + } + /* + * rdahi == 13 is UNPREDICTABLE; rdahi == 15 is a related + * encoding; rdalo always has bit 0 clear so cannot be 13 or 15. + */ + if (a->rdahi == 13 || a->rdahi == 15) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* + * This insn is subject to beat-wise execution. Partial execution + * of an A=0 (no-accumulate) insn which does not execute the first + * beat must start with the current value of RdaHi:RdaLo, not zero. + */ + if (a->a || mve_skip_first_beat(s)) { + /* Accumulate input from RdaHi:RdaLo */ + rda = tcg_temp_new_i64(); + rdalo = load_reg(s, a->rdalo); + rdahi = load_reg(s, a->rdahi); + tcg_gen_concat_i32_i64(rda, rdalo, rdahi); + tcg_temp_free_i32(rdalo); + tcg_temp_free_i32(rdahi); + } else { + /* Accumulate starting at zero */ + rda = tcg_const_i64(0); + } + + qm = mve_qreg_ptr(a->qm); + if (a->u) { + gen_helper_mve_vaddlv_u(rda, cpu_env, qm, rda); + } else { + gen_helper_mve_vaddlv_s(rda, cpu_env, qm, rda); + } + tcg_temp_free_ptr(qm); + + rdalo = tcg_temp_new_i32(); + rdahi = tcg_temp_new_i32(); + tcg_gen_extrl_i64_i32(rdalo, rda); + tcg_gen_extrh_i64_i32(rdahi, rda); + store_reg(s, a->rdalo, rdalo); + store_reg(s, a->rdahi, rdahi); + tcg_temp_free_i64(rda); + mve_update_eci(s); + return true; +} + static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn) { TCGv_ptr qd; -- 2.20.1 The MVE extension to v8.1M includes some new shift instructions which sit entirely within the non-coprocessor part of the encoding space and which operate only on general-purpose registers. They take up the space which was previously UNPREDICTABLE MOVS and ORRS encodings with Rm == 13 or 15. Implement the long shifts by immediate, which perform shifts on a pair of general-purpose registers treated as a 64-bit quantity, with an immediate shift count between 1 and 32. Awkwardly, because the MOVS and ORRS trans functions do not UNDEF for the Rm==13,15 case, we need to explicitly emit code to UNDEF for the cases where v8.1M now requires that. (Trying to change MOVS and ORRS is too difficult, because the functions that generate the code are shared between a dozen different kinds of arithmetic or logical instruction for all A32, T16 and T32 encodings, and for some insns and some encodings Rm==13,15 are valid.) We make the helper functions we need for UQSHLL and SQSHLL take a 32-bit value which the helper casts to int8_t because we'll need these helpers also for the shift-by-register insns, where the shift count might be < 0 or > 32. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-16-peter.maydell@linaro.org --- target/arm/helper-mve.h | 3 ++ target/arm/translate.h | 1 + target/arm/t32.decode | 28 +++++++++++++ target/arm/mve_helper.c | 10 +++++ target/arm/translate.c | 90 +++++++++++++++++++++++++++++++++++++++++ 5 files changed, 132 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) + +DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr); typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); +typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); /** * arm_tbflags_from_tb: diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ &mcr !extern cp opc1 crn crm opc2 rt &mcrr !extern cp opc1 crm rt rt2 +&mve_shl_ri rdalo rdahi shim + +# rdahi: bits [3:1] from insn, bit 0 is 1 +# rdalo: bits [3:1] from insn, bit 0 is 0 +%rdahi_9 9:3 !function=times_2_plus_1 +%rdalo_17 17:3 !function=times_2 + # Data-processing (register) %imm5_12_6 12:3 6:2 @@ -XXX,XX +XXX,XX @@ @S_xrr_shi ....... .... . rn:4 .... .... .. shty:2 rm:4 \ &s_rrr_shi shim=%imm5_12_6 s=1 rd=0 +@mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \ + &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 + { TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi AND_rrri 1110101 0000 . .... 0 ... .... .... .... @s_rrr_shi } BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi { + # The v8.1M MVE shift insns overlap in encoding with MOVS/ORRS + # and are distinguished by having Rm==13 or 15. Those are UNPREDICTABLE + # cases for MOVS/ORRS. We decode the MVE cases first, ensuring that + # they explicitly call unallocated_encoding() for cases that must UNDEF + # (eg "using a new shift insn on a v8.1M CPU without MVE"), and letting + # the rest fall through (where ORR_rrri and MOV_rxri will end up + # handling them as r13 and r15 accesses with the same semantics as A32). + [ + LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri + LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri + ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri + + UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri + URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri + SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri + SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri + ] + MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, mve_advance_vpt(env); return rdm; } + +uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_sqrshl_d(n, (int8_t)shift, false, &env->QF); +} + +uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_uqrshl_d(n, (int8_t)shift, false, &env->QF); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_MOVT(DisasContext *s, arg_MOVW *a) return true; } +/* + * v8.1M MVE wide-shifts + */ +static bool do_mve_shl_ri(DisasContext *s, arg_mve_shl_ri *a, + WideShiftImmFn *fn) +{ + TCGv_i64 rda; + TCGv_i32 rdalo, rdahi; + + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ + return false; + } + if (a->rdahi == 15) { + /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */ + return false; + } + if (!dc_isar_feature(aa32_mve, s) || + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || + a->rdahi == 13) { + /* RdaHi == 13 is UNPREDICTABLE; we choose to UNDEF */ + unallocated_encoding(s); + return true; + } + + if (a->shim == 0) { + a->shim = 32; + } + + rda = tcg_temp_new_i64(); + rdalo = load_reg(s, a->rdalo); + rdahi = load_reg(s, a->rdahi); + tcg_gen_concat_i32_i64(rda, rdalo, rdahi); + + fn(rda, rda, a->shim); + + tcg_gen_extrl_i64_i32(rdalo, rda); + tcg_gen_extrh_i64_i32(rdahi, rda); + store_reg(s, a->rdalo, rdalo); + store_reg(s, a->rdahi, rdahi); + tcg_temp_free_i64(rda); + + return true; +} + +static bool trans_ASRL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, tcg_gen_sari_i64); +} + +static bool trans_LSLL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, tcg_gen_shli_i64); +} + +static bool trans_LSRL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, tcg_gen_shri_i64); +} + +static void gen_mve_sqshll(TCGv_i64 r, TCGv_i64 n, int64_t shift) +{ + gen_helper_mve_sqshll(r, cpu_env, n, tcg_constant_i32(shift)); +} + +static bool trans_SQSHLL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, gen_mve_sqshll); +} + +static void gen_mve_uqshll(TCGv_i64 r, TCGv_i64 n, int64_t shift) +{ + gen_helper_mve_uqshll(r, cpu_env, n, tcg_constant_i32(shift)); +} + +static bool trans_UQSHLL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, gen_mve_uqshll); +} + +static bool trans_SRSHRL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, gen_srshr64_i64); +} + +static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a) +{ + return do_mve_shl_ri(s, a, gen_urshr64_i64); +} + /* * Multiply and multiply accumulate */ -- 2.20.1 Implement the MVE long shifts by register, which perform shifts on a pair of general-purpose registers treated as a 64-bit quantity, with the shift count in another general-purpose register, which might be either positive or negative. Like the long-shifts-by-immediate, these encodings sit in the space that was previously the UNPREDICTABLE MOVS/ORRS with Rm==13,15. Because LSLL_rr and ASRL_rr overlap with both MOV_rxri/ORR_rrri and also with CSEL (as one of the previously-UNPREDICTABLE Rm==13 cases), we have to move the CSEL pattern into the same decodetree group. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-17-peter.maydell@linaro.org --- target/arm/helper-mve.h | 6 +++ target/arm/translate.h | 1 + target/arm/t32.decode | 16 +++++-- target/arm/mve_helper.c | 93 +++++++++++++++++++++++++++++++++++++++++ target/arm/translate.c | 69 ++++++++++++++++++++++++++++++ 5 files changed, 182 insertions(+), 3 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_3(mve_sshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_ushll, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32) +DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); +typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); /** * arm_tbflags_from_tb: diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ &mcrr !extern cp opc1 crm rt rt2 &mve_shl_ri rdalo rdahi shim +&mve_shl_rr rdalo rdahi rm # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 @@ -XXX,XX +XXX,XX @@ @mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \ &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 +@mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ + &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 { TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri + + LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr + ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr + UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr + SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr + UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr + SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr ] MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi + + # v8.1M CSEL and friends + CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4 } { MVN_rxri 1110101 0011 . 1111 0 ... .... .... .... @s_rxr_shi @@ -XXX,XX +XXX,XX @@ SBC_rrri 1110101 1011 . .... 0 ... .... .... .... @s_rrr_shi } RSB_rrri 1110101 1110 . .... 0 ... .... .... .... @s_rrr_shi -# v8.1M CSEL and friends -CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4 - # Data-processing (register-shifted register) MOV_rxrr 1111 1010 0 shty:2 s:1 rm:4 1111 rd:4 0000 rs:4 \ diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, return rdm; } +uint64_t HELPER(mve_sshrl)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_sqrshl_d(n, -(int8_t)shift, false, NULL); +} + +uint64_t HELPER(mve_ushll)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_uqrshl_d(n, (int8_t)shift, false, NULL); +} + uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift) { return do_sqrshl_d(n, (int8_t)shift, false, &env->QF); @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift) { return do_uqrshl_d(n, (int8_t)shift, false, &env->QF); } + +uint64_t HELPER(mve_sqrshrl)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_sqrshl_d(n, -(int8_t)shift, true, &env->QF); +} + +uint64_t HELPER(mve_uqrshll)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_uqrshl_d(n, (int8_t)shift, true, &env->QF); +} + +/* Operate on 64-bit values, but saturate at 48 bits */ +static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + if (shift <= -48) { + /* Rounding the sign bit always produces 0. */ + if (round) { + return 0; + } + return src >> 63; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < 48) { + int64_t val = src << shift; + int64_t extval = sextract64(val, 0, 48); + if (!sat || val == extval) { + return extval; + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return (1ULL << 47) - (src >= 0); +} + +/* Operate on 64-bit values, but saturate at 48 bits */ +static inline uint64_t do_uqrshl48_d(uint64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + uint64_t val, extval; + + if (shift <= -(48 + round)) { + return 0; + } else if (shift < 0) { + if (round) { + val = src >> (-shift - 1); + val = (val >> 1) + (val & 1); + } else { + val = src >> -shift; + } + extval = extract64(val, 0, 48); + if (!sat || val == extval) { + return extval; + } + } else if (shift < 48) { + uint64_t val = src << shift; + uint64_t extval = extract64(val, 0, 48); + if (!sat || val == extval) { + return extval; + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return MAKE_64BIT_MASK(0, 48); +} + +uint64_t HELPER(mve_sqrshrl48)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_sqrshl48_d(n, -(int8_t)shift, true, &env->QF); +} + +uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift) +{ + return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a) return do_mve_shl_ri(s, a, gen_urshr64_i64); } +static bool do_mve_shl_rr(DisasContext *s, arg_mve_shl_rr *a, WideShiftFn *fn) +{ + TCGv_i64 rda; + TCGv_i32 rdalo, rdahi; + + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ + return false; + } + if (a->rdahi == 15) { + /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */ + return false; + } + if (!dc_isar_feature(aa32_mve, s) || + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || + a->rdahi == 13 || a->rm == 13 || a->rm == 15 || + a->rm == a->rdahi || a->rm == a->rdalo) { + /* These rdahi/rdalo/rm cases are UNPREDICTABLE; we choose to UNDEF */ + unallocated_encoding(s); + return true; + } + + rda = tcg_temp_new_i64(); + rdalo = load_reg(s, a->rdalo); + rdahi = load_reg(s, a->rdahi); + tcg_gen_concat_i32_i64(rda, rdalo, rdahi); + + /* The helper takes care of the sign-extension of the low 8 bits of Rm */ + fn(rda, cpu_env, rda, cpu_R[a->rm]); + + tcg_gen_extrl_i64_i32(rdalo, rda); + tcg_gen_extrh_i64_i32(rdahi, rda); + store_reg(s, a->rdalo, rdalo); + store_reg(s, a->rdahi, rdahi); + tcg_temp_free_i64(rda); + + return true; +} + +static bool trans_LSLL_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_ushll); +} + +static bool trans_ASRL_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_sshrl); +} + +static bool trans_UQRSHLL64_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_uqrshll); +} + +static bool trans_SQRSHRL64_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl); +} + +static bool trans_UQRSHLL48_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_uqrshll48); +} + +static bool trans_SQRSHRL48_rr(DisasContext *s, arg_mve_shl_rr *a) +{ + return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl48); +} + /* * Multiply and multiply accumulate */ -- 2.20.1 Implement the MVE shifts by immediate, which perform shifts on a single general-purpose register. These patterns overlap with the long-shift-by-immediates, so we have to rearrange the grouping a little here. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-18-peter.maydell@linaro.org --- target/arm/helper-mve.h | 3 ++ target/arm/translate.h | 1 + target/arm/t32.decode | 31 ++++++++++++++----- target/arm/mve_helper.c | 10 ++++++ target/arm/translate.c | 68 +++++++++++++++++++++++++++++++++++++++-- 5 files changed, 104 insertions(+), 9 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) + +DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); +typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift); /** * arm_tbflags_from_tb: diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ &mve_shl_ri rdalo rdahi shim &mve_shl_rr rdalo rdahi rm +&mve_sh_ri rda shim # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 @@ -XXX,XX +XXX,XX @@ &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 @mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 +@mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \ + &mve_sh_ri shim=%imm5_12_6 { TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi # the rest fall through (where ORR_rrri and MOV_rxri will end up # handling them as r13 and r15 accesses with the same semantics as A32). [ - LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri - LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri - ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri + { + UQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 00 1111 @mve_sh_ri + LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri + UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri + } - UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri - URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri - SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri - SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri + { + URSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 01 1111 @mve_sh_ri + LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri + URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri + } + + { + SRSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 10 1111 @mve_sh_ri + ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri + SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri + } + + { + SQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 11 1111 @mve_sh_ri + SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri + } LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift) { return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF); } + +uint32_t HELPER(mve_uqshl)(CPUARMState *env, uint32_t n, uint32_t shift) +{ + return do_uqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); +} + +uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift) +{ + return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) { - TCGv_i32 t = tcg_temp_new_i32(); + TCGv_i32 t; + /* Handle shift by the input size for the benefit of trans_SRSHR_ri */ + if (sh == 32) { + tcg_gen_movi_i32(d, 0); + return; + } + t = tcg_temp_new_i32(); tcg_gen_extract_i32(t, a, sh - 1, 1); tcg_gen_sari_i32(d, a, sh); tcg_gen_add_i32(d, d, t); @@ -XXX,XX +XXX,XX @@ static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) { - TCGv_i32 t = tcg_temp_new_i32(); + TCGv_i32 t; + /* Handle shift by the input size for the benefit of trans_URSHR_ri */ + if (sh == 32) { + tcg_gen_extract_i32(d, a, sh - 1, 1); + return; + } + t = tcg_temp_new_i32(); tcg_gen_extract_i32(t, a, sh - 1, 1); tcg_gen_shri_i32(d, a, sh); tcg_gen_add_i32(d, d, t); @@ -XXX,XX +XXX,XX @@ static bool trans_SQRSHRL48_rr(DisasContext *s, arg_mve_shl_rr *a) return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl48); } +static bool do_mve_sh_ri(DisasContext *s, arg_mve_sh_ri *a, ShiftImmFn *fn) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ + return false; + } + if (!dc_isar_feature(aa32_mve, s) || + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || + a->rda == 13 || a->rda == 15) { + /* These rda cases are UNPREDICTABLE; we choose to UNDEF */ + unallocated_encoding(s); + return true; + } + + if (a->shim == 0) { + a->shim = 32; + } + fn(cpu_R[a->rda], cpu_R[a->rda], a->shim); + + return true; +} + +static bool trans_URSHR_ri(DisasContext *s, arg_mve_sh_ri *a) +{ + return do_mve_sh_ri(s, a, gen_urshr32_i32); +} + +static bool trans_SRSHR_ri(DisasContext *s, arg_mve_sh_ri *a) +{ + return do_mve_sh_ri(s, a, gen_srshr32_i32); +} + +static void gen_mve_sqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift) +{ + gen_helper_mve_sqshl(r, cpu_env, n, tcg_constant_i32(shift)); +} + +static bool trans_SQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) +{ + return do_mve_sh_ri(s, a, gen_mve_sqshl); +} + +static void gen_mve_uqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift) +{ + gen_helper_mve_uqshl(r, cpu_env, n, tcg_constant_i32(shift)); +} + +static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) +{ + return do_mve_sh_ri(s, a, gen_mve_uqshl); +} + /* * Multiply and multiply accumulate */ -- 2.20.1 Implement the MVE shifts by register, which perform shifts on a single general-purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-19-peter.maydell@linaro.org --- target/arm/helper-mve.h | 2 ++ target/arm/translate.h | 1 + target/arm/t32.decode | 18 ++++++++++++++---- target/arm/mve_helper.c | 10 ++++++++++ target/arm/translate.c | 30 ++++++++++++++++++++++++++++++ 5 files changed, 57 insertions(+), 4 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift); +typedef void ShiftFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); /** * arm_tbflags_from_tb: diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ &mve_shl_ri rdalo rdahi shim &mve_shl_rr rdalo rdahi rm &mve_sh_ri rda shim +&mve_sh_rr rda rm # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 @@ -XXX,XX +XXX,XX @@ &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 @mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \ &mve_sh_ri shim=%imm5_12_6 +@mve_sh_rr ....... .... . rda:4 rm:4 .... .... .... &mve_sh_rr { TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri } - LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr - ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr - UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr - SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr + { + UQRSHL_rr 1110101 0010 1 .... .... 1111 0000 1101 @mve_sh_rr + LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr + UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr + } + + { + SQRSHR_rr 1110101 0010 1 .... .... 1111 0010 1101 @mve_sh_rr + ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr + SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr + } + UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr ] diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift) { return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); } + +uint32_t HELPER(mve_uqrshl)(CPUARMState *env, uint32_t n, uint32_t shift) +{ + return do_uqrshl_bhs(n, (int8_t)shift, 32, true, &env->QF); +} + +uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift) +{ + return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) return do_mve_sh_ri(s, a, gen_mve_uqshl); } +static bool do_mve_sh_rr(DisasContext *s, arg_mve_sh_rr *a, ShiftFn *fn) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ + return false; + } + if (!dc_isar_feature(aa32_mve, s) || + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || + a->rda == 13 || a->rda == 15 || a->rm == 13 || a->rm == 15 || + a->rm == a->rda) { + /* These rda/rm cases are UNPREDICTABLE; we choose to UNDEF */ + unallocated_encoding(s); + return true; + } + + /* The helper takes care of the sign-extension of the low 8 bits of Rm */ + fn(cpu_R[a->rda], cpu_env, cpu_R[a->rda], cpu_R[a->rm]); + return true; +} + +static bool trans_SQRSHR_rr(DisasContext *s, arg_mve_sh_rr *a) +{ + return do_mve_sh_rr(s, a, gen_helper_mve_sqrshr); +} + +static bool trans_UQRSHL_rr(DisasContext *s, arg_mve_sh_rr *a) +{ + return do_mve_sh_rr(s, a, gen_helper_mve_uqrshl); +} + /* * Multiply and multiply accumulate */ -- 2.20.1 Hi; this pullreq includes FEAT_LSE2 support, the new bpim2u board, and some other smaller patchsets. thanks -- PMM The following changes since commit 369081c4558e7e940fa36ce59bf17b2e390f55d3: Merge tag 'pull-tcg-20230605' of https://gitlab.com/rth7680/qemu into staging (2023-06-05 13:16:56 -0700) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230606 for you to fetch changes up to f9ac778898cb28307e0f91421aba34d43c34b679: target/arm: trap DCC access in user mode emulation (2023-06-06 10:19:40 +0100) ---------------------------------------------------------------- target-arm queue: * Support gdbstub (guest debug) in HVF * xnlx-versal: Support CANFD controller * bpim2u: New board model: Banana Pi BPI-M2 Ultra * Emulate FEAT_LSE2 * allow DC CVA[D]P in user mode emulation * trap DCC access in user mode emulation ---------------------------------------------------------------- Francesco Cagnin (4): arm: move KVM breakpoints helpers hvf: handle access for more registers hvf: add breakpoint handlers hvf: add guest debugging handlers for Apple Silicon hosts Richard Henderson (20): target/arm: Add commentary for CPUARMState.exclusive_high target/arm: Add feature test for FEAT_LSE2 target/arm: Introduce finalize_memop_{atom,pair} target/arm: Use tcg_gen_qemu_ld_i128 for LDXP target/arm: Use tcg_gen_qemu_{st, ld}_i128 for do_fp_{st, ld} target/arm: Use tcg_gen_qemu_st_i128 for STZG, STZ2G target/arm: Use tcg_gen_qemu_{ld, st}_i128 in gen_sve_{ld, st}r target/arm: Sink gen_mte_check1 into load/store_exclusive target/arm: Load/store integer pair with one tcg operation target/arm: Hoist finalize_memop out of do_gpr_{ld, st} target/arm: Hoist finalize_memop out of do_fp_{ld, st} target/arm: Pass memop to gen_mte_check1* target/arm: Pass single_memop to gen_mte_checkN target/arm: Check alignment in helper_mte_check target/arm: Add SCTLR.nAA to TBFLAG_A64 target/arm: Relax ordered/atomic alignment checks for LSE2 target/arm: Move mte check for store-exclusive tests/tcg/aarch64: Use stz2g in mte-7.c tests/tcg/multiarch: Adjust sigbus.c target/arm: Enable FEAT_LSE2 for -cpu max Vikram Garhwal (4): hw/net/can: Introduce Xilinx Versal CANFD controller xlnx-versal: Connect Xilinx VERSAL CANFD controllers MAINTAINERS: Include canfd tests under Xilinx CAN tests/qtest: Introduce tests for Xilinx VERSAL CANFD controller Zhuojia Shen (3): target/arm: allow DC CVA[D]P in user mode emulation tests/tcg/aarch64: add DC CVA[D]P tests target/arm: trap DCC access in user mode emulation qianfan Zhao (11): hw: arm: Add bananapi M2-Ultra and allwinner-r40 support hw/arm/allwinner-r40: add Clock Control Unit hw: allwinner-r40: Complete uart devices hw: arm: allwinner-r40: Add i2c0 device hw/misc: Rename axp209 to axp22x and add support AXP221 PMU hw/arm/allwinner-r40: add SDRAM controller device hw: sd: allwinner-sdhost: Add sun50i-a64 SoC support hw: arm: allwinner-r40: Add emac and gmac support hw: arm: allwinner-sramc: Add SRAM Controller support for R40 tests: avocado: boot_linux_console: Add test case for bpim2u docs: system: arm: Introduce bananapi_m2u MAINTAINERS | 2 +- docs/system/arm/bananapi_m2u.rst | 139 +++ docs/system/arm/emulation.rst | 1 + docs/system/arm/xlnx-versal-virt.rst | 31 + docs/system/target-arm.rst | 1 + include/hw/arm/allwinner-r40.h | 143 +++ include/hw/arm/xlnx-versal.h | 12 + include/hw/misc/allwinner-r40-ccu.h | 65 + include/hw/misc/allwinner-r40-dramc.h | 108 ++ include/hw/misc/allwinner-sramc.h | 69 ++ include/hw/net/xlnx-versal-canfd.h | 87 ++ include/hw/sd/allwinner-sdhost.h | 9 + include/sysemu/hvf.h | 37 + include/sysemu/hvf_int.h | 2 + target/arm/cpu.h | 16 +- target/arm/hvf_arm.h | 7 + target/arm/internals.h | 53 +- target/arm/tcg/helper-a64.h | 3 + target/arm/tcg/translate-a64.h | 4 +- target/arm/tcg/translate.h | 65 +- accel/hvf/hvf-accel-ops.c | 119 ++ accel/hvf/hvf-all.c | 23 + hw/arm/allwinner-r40.c | 526 ++++++++ hw/arm/bananapi_m2u.c | 145 +++ hw/arm/xlnx-versal-virt.c | 53 + hw/arm/xlnx-versal.c | 37 + hw/misc/allwinner-r40-ccu.c | 209 ++++ hw/misc/allwinner-r40-dramc.c | 513 ++++++++ hw/misc/allwinner-sramc.c | 184 +++ hw/misc/axp209.c | 238 ---- hw/misc/axp2xx.c | 283 +++++ hw/net/can/xlnx-versal-canfd.c | 2107 +++++++++++++++++++++++++++++++++ hw/sd/allwinner-sdhost.c | 72 +- target/arm/cpu.c | 2 + target/arm/debug_helper.c | 5 + target/arm/helper.c | 6 +- target/arm/hvf/hvf.c | 750 +++++++++++- target/arm/hyp_gdbstub.c | 253 ++++ target/arm/kvm64.c | 276 ----- target/arm/tcg/cpu64.c | 1 + target/arm/tcg/helper-a64.c | 7 + target/arm/tcg/hflags.c | 6 + target/arm/tcg/mte_helper.c | 18 + target/arm/tcg/translate-a64.c | 477 +++++--- target/arm/tcg/translate-sve.c | 106 +- target/arm/tcg/translate.c | 1 + target/i386/hvf/hvf.c | 33 + tests/qtest/xlnx-canfd-test.c | 423 +++++++ tests/tcg/aarch64/dcpodp.c | 63 + tests/tcg/aarch64/dcpop.c | 63 + tests/tcg/aarch64/mte-7.c | 3 +- tests/tcg/multiarch/sigbus.c | 13 +- hw/arm/Kconfig | 14 +- hw/arm/meson.build | 1 + hw/misc/Kconfig | 5 +- hw/misc/meson.build | 5 +- hw/misc/trace-events | 26 +- hw/net/can/meson.build | 1 + hw/net/can/trace-events | 7 + target/arm/meson.build | 3 +- tests/avocado/boot_linux_console.py | 176 +++ tests/qtest/meson.build | 1 + tests/tcg/aarch64/Makefile.target | 11 + 63 files changed, 7386 insertions(+), 733 deletions(-) create mode 100644 docs/system/arm/bananapi_m2u.rst create mode 100644 include/hw/arm/allwinner-r40.h create mode 100644 include/hw/misc/allwinner-r40-ccu.h create mode 100644 include/hw/misc/allwinner-r40-dramc.h create mode 100644 include/hw/misc/allwinner-sramc.h create mode 100644 include/hw/net/xlnx-versal-canfd.h create mode 100644 hw/arm/allwinner-r40.c create mode 100644 hw/arm/bananapi_m2u.c create mode 100644 hw/misc/allwinner-r40-ccu.c create mode 100644 hw/misc/allwinner-r40-dramc.c create mode 100644 hw/misc/allwinner-sramc.c delete mode 100644 hw/misc/axp209.c create mode 100644 hw/misc/axp2xx.c create mode 100644 hw/net/can/xlnx-versal-canfd.c create mode 100644 target/arm/hyp_gdbstub.c create mode 100644 tests/qtest/xlnx-canfd-test.c create mode 100644 tests/tcg/aarch64/dcpodp.c create mode 100644 tests/tcg/aarch64/dcpop.c From: Francesco Cagnin <fcagnin@quarkslab.com> These helpers will be also used for HVF. Aside from reformatting a couple of comments for 'checkpatch.pl' and updating meson to compile 'hyp_gdbstub.c', this is just code motion. Signed-off-by: Francesco Cagnin <fcagnin@quarkslab.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230601153107.81955-2-fcagnin@quarkslab.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 50 +++++++ target/arm/hyp_gdbstub.c | 253 +++++++++++++++++++++++++++++++++++ target/arm/kvm64.c | 276 --------------------------------------- target/arm/meson.build | 3 +- 4 files changed, 305 insertions(+), 277 deletions(-) create mode 100644 target/arm/hyp_gdbstub.c diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline bool arm_fgt_active(CPUARMState *env, int el) } void assert_hflags_rebuild_correctly(CPUARMState *env); + +/* + * Although the ARM implementation of hardware assisted debugging + * allows for different breakpoints per-core, the current GDB + * interface treats them as a global pool of registers (which seems to + * be the case for x86, ppc and s390). As a result we store one copy + * of registers which is used for all active cores. + * + * Write access is serialised by virtue of the GDB protocol which + * updates things. Read access (i.e. when the values are copied to the + * vCPU) is also gated by GDB's run control. + * + * This is not unreasonable as most of the time debugging kernels you + * never know which core will eventually execute your function. + */ + +typedef struct { + uint64_t bcr; + uint64_t bvr; +} HWBreakpoint; + +/* + * The watchpoint registers can cover more area than the requested + * watchpoint so we need to store the additional information + * somewhere. We also need to supply a CPUWatchpoint to the GDB stub + * when the watchpoint is hit. + */ +typedef struct { + uint64_t wcr; + uint64_t wvr; + CPUWatchpoint details; +} HWWatchpoint; + +/* Maximum and current break/watch point counts */ +extern int max_hw_bps, max_hw_wps; +extern GArray *hw_breakpoints, *hw_watchpoints; + +#define cur_hw_wps (hw_watchpoints->len) +#define cur_hw_bps (hw_breakpoints->len) +#define get_hw_bp(i) (&g_array_index(hw_breakpoints, HWBreakpoint, i)) +#define get_hw_wp(i) (&g_array_index(hw_watchpoints, HWWatchpoint, i)) + +bool find_hw_breakpoint(CPUState *cpu, target_ulong pc); +int insert_hw_breakpoint(target_ulong pc); +int delete_hw_breakpoint(target_ulong pc); + +bool check_watchpoint_in_range(int i, target_ulong addr); +CPUWatchpoint *find_hw_watchpoint(CPUState *cpu, target_ulong addr); +int insert_hw_watchpoint(target_ulong addr, target_ulong len, int type); +int delete_hw_watchpoint(target_ulong addr, target_ulong len, int type); #endif diff --git a/target/arm/hyp_gdbstub.c b/target/arm/hyp_gdbstub.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/hyp_gdbstub.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM implementation of KVM and HVF hooks, 64 bit specific code + * + * Copyright Mian-M. Hamayun 2013, Virtual Open Systems + * Copyright Alex Bennée 2014, Linaro + * + * 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 "cpu.h" +#include "internals.h" +#include "exec/gdbstub.h" + +/* Maximum and current break/watch point counts */ +int max_hw_bps, max_hw_wps; +GArray *hw_breakpoints, *hw_watchpoints; + +/** + * insert_hw_breakpoint() + * @addr: address of breakpoint + * + * See ARM ARM D2.9.1 for details but here we are only going to create + * simple un-linked breakpoints (i.e. we don't chain breakpoints + * together to match address and context or vmid). The hardware is + * capable of fancier matching but that will require exposing that + * fanciness to GDB's interface + * + * DBGBCR<n>_EL1, Debug Breakpoint Control Registers + * + * 31 24 23 20 19 16 15 14 13 12 9 8 5 4 3 2 1 0 + * +------+------+-------+-----+----+------+-----+------+-----+---+ + * | RES0 | BT | LBN | SSC | HMC| RES0 | BAS | RES0 | PMC | E | + * +------+------+-------+-----+----+------+-----+------+-----+---+ + * + * BT: Breakpoint type (0 = unlinked address match) + * LBN: Linked BP number (0 = unused) + * SSC/HMC/PMC: Security, Higher and Priv access control (Table D-12) + * BAS: Byte Address Select (RES1 for AArch64) + * E: Enable bit + * + * DBGBVR<n>_EL1, Debug Breakpoint Value Registers + * + * 63 53 52 49 48 2 1 0 + * +------+-----------+----------+-----+ + * | RESS | VA[52:49] | VA[48:2] | 0 0 | + * +------+-----------+----------+-----+ + * + * Depending on the addressing mode bits the top bits of the register + * are a sign extension of the highest applicable VA bit. Some + * versions of GDB don't do it correctly so we ensure they are correct + * here so future PC comparisons will work properly. + */ + +int insert_hw_breakpoint(target_ulong addr) +{ + HWBreakpoint brk = { + .bcr = 0x1, /* BCR E=1, enable */ + .bvr = sextract64(addr, 0, 53) + }; + + if (cur_hw_bps >= max_hw_bps) { + return -ENOBUFS; + } + + brk.bcr = deposit32(brk.bcr, 1, 2, 0x3); /* PMC = 11 */ + brk.bcr = deposit32(brk.bcr, 5, 4, 0xf); /* BAS = RES1 */ + + g_array_append_val(hw_breakpoints, brk); + + return 0; +} + +/** + * delete_hw_breakpoint() + * @pc: address of breakpoint + * + * Delete a breakpoint and shuffle any above down + */ + +int delete_hw_breakpoint(target_ulong pc) +{ + int i; + for (i = 0; i < hw_breakpoints->len; i++) { + HWBreakpoint *brk = get_hw_bp(i); + if (brk->bvr == pc) { + g_array_remove_index(hw_breakpoints, i); + return 0; + } + } + return -ENOENT; +} + +/** + * insert_hw_watchpoint() + * @addr: address of watch point + * @len: size of area + * @type: type of watch point + * + * See ARM ARM D2.10. As with the breakpoints we can do some advanced + * stuff if we want to. The watch points can be linked with the break + * points above to make them context aware. However for simplicity + * currently we only deal with simple read/write watch points. + * + * D7.3.11 DBGWCR<n>_EL1, Debug Watchpoint Control Registers + * + * 31 29 28 24 23 21 20 19 16 15 14 13 12 5 4 3 2 1 0 + * +------+-------+------+----+-----+-----+-----+-----+-----+-----+---+ + * | RES0 | MASK | RES0 | WT | LBN | SSC | HMC | BAS | LSC | PAC | E | + * +------+-------+------+----+-----+-----+-----+-----+-----+-----+---+ + * + * MASK: num bits addr mask (0=none,01/10=res,11=3 bits (8 bytes)) + * WT: 0 - unlinked, 1 - linked (not currently used) + * LBN: Linked BP number (not currently used) + * SSC/HMC/PAC: Security, Higher and Priv access control (Table D2-11) + * BAS: Byte Address Select + * LSC: Load/Store control (01: load, 10: store, 11: both) + * E: Enable + * + * The bottom 2 bits of the value register are masked. Therefore to + * break on any sizes smaller than an unaligned word you need to set + * MASK=0, BAS=bit per byte in question. For larger regions (^2) you + * need to ensure you mask the address as required and set BAS=0xff + */ + +int insert_hw_watchpoint(target_ulong addr, target_ulong len, int type) +{ + HWWatchpoint wp = { + .wcr = R_DBGWCR_E_MASK, /* E=1, enable */ + .wvr = addr & (~0x7ULL), + .details = { .vaddr = addr, .len = len } + }; + + if (cur_hw_wps >= max_hw_wps) { + return -ENOBUFS; + } + + /* + * HMC=0 SSC=0 PAC=3 will hit EL0 or EL1, any security state, + * valid whether EL3 is implemented or not + */ + wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, PAC, 3); + + switch (type) { + case GDB_WATCHPOINT_READ: + wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, LSC, 1); + wp.details.flags = BP_MEM_READ; + break; + case GDB_WATCHPOINT_WRITE: + wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, LSC, 2); + wp.details.flags = BP_MEM_WRITE; + break; + case GDB_WATCHPOINT_ACCESS: + wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, LSC, 3); + wp.details.flags = BP_MEM_ACCESS; + break; + default: + g_assert_not_reached(); + break; + } + if (len <= 8) { + /* we align the address and set the bits in BAS */ + int off = addr & 0x7; + int bas = (1 << len) - 1; + + wp.wcr = deposit32(wp.wcr, 5 + off, 8 - off, bas); + } else { + /* For ranges above 8 bytes we need to be a power of 2 */ + if (is_power_of_2(len)) { + int bits = ctz64(len); + + wp.wvr &= ~((1 << bits) - 1); + wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, MASK, bits); + wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, BAS, 0xff); + } else { + return -ENOBUFS; + } + } + + g_array_append_val(hw_watchpoints, wp); + return 0; +} + +bool check_watchpoint_in_range(int i, target_ulong addr) +{ + HWWatchpoint *wp = get_hw_wp(i); + uint64_t addr_top, addr_bottom = wp->wvr; + int bas = extract32(wp->wcr, 5, 8); + int mask = extract32(wp->wcr, 24, 4); + + if (mask) { + addr_top = addr_bottom + (1 << mask); + } else { + /* + * BAS must be contiguous but can offset against the base + * address in DBGWVR + */ + addr_bottom = addr_bottom + ctz32(bas); + addr_top = addr_bottom + clo32(bas); + } + + if (addr >= addr_bottom && addr <= addr_top) { + return true; + } + + return false; +} + +/** + * delete_hw_watchpoint() + * @addr: address of breakpoint + * + * Delete a breakpoint and shuffle any above down + */ + +int delete_hw_watchpoint(target_ulong addr, target_ulong len, int type) +{ + int i; + for (i = 0; i < cur_hw_wps; i++) { + if (check_watchpoint_in_range(i, addr)) { + g_array_remove_index(hw_watchpoints, i); + return 0; + } + } + return -ENOENT; +} + +bool find_hw_breakpoint(CPUState *cpu, target_ulong pc) +{ + int i; + + for (i = 0; i < cur_hw_bps; i++) { + HWBreakpoint *bp = get_hw_bp(i); + if (bp->bvr == pc) { + return true; + } + } + return false; +} + +CPUWatchpoint *find_hw_watchpoint(CPUState *cpu, target_ulong addr) +{ + int i; + + for (i = 0; i < cur_hw_wps; i++) { + if (check_watchpoint_in_range(i, addr)) { + return &get_hw_wp(i)->details; + } + } + return NULL; +} diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ static bool have_guest_debug; -/* - * Although the ARM implementation of hardware assisted debugging - * allows for different breakpoints per-core, the current GDB - * interface treats them as a global pool of registers (which seems to - * be the case for x86, ppc and s390). As a result we store one copy - * of registers which is used for all active cores. - * - * Write access is serialised by virtue of the GDB protocol which - * updates things. Read access (i.e. when the values are copied to the - * vCPU) is also gated by GDB's run control. - * - * This is not unreasonable as most of the time debugging kernels you - * never know which core will eventually execute your function. - */ - -typedef struct { - uint64_t bcr; - uint64_t bvr; -} HWBreakpoint; - -/* The watchpoint registers can cover more area than the requested - * watchpoint so we need to store the additional information - * somewhere. We also need to supply a CPUWatchpoint to the GDB stub - * when the watchpoint is hit. - */ -typedef struct { - uint64_t wcr; - uint64_t wvr; - CPUWatchpoint details; -} HWWatchpoint; - -/* Maximum and current break/watch point counts */ -int max_hw_bps, max_hw_wps; -GArray *hw_breakpoints, *hw_watchpoints; - -#define cur_hw_wps (hw_watchpoints->len) -#define cur_hw_bps (hw_breakpoints->len) -#define get_hw_bp(i) (&g_array_index(hw_breakpoints, HWBreakpoint, i)) -#define get_hw_wp(i) (&g_array_index(hw_watchpoints, HWWatchpoint, i)) - void kvm_arm_init_debug(KVMState *s) { have_guest_debug = kvm_check_extension(s, @@ -XXX,XX +XXX,XX @@ void kvm_arm_init_debug(KVMState *s) return; } -/** - * insert_hw_breakpoint() - * @addr: address of breakpoint - * - * See ARM ARM D2.9.1 for details but here we are only going to create - * simple un-linked breakpoints (i.e. we don't chain breakpoints - * together to match address and context or vmid). The hardware is - * capable of fancier matching but that will require exposing that - * fanciness to GDB's interface - * - * DBGBCR<n>_EL1, Debug Breakpoint Control Registers - * - * 31 24 23 20 19 16 15 14 13 12 9 8 5 4 3 2 1 0 - * +------+------+-------+-----+----+------+-----+------+-----+---+ - * | RES0 | BT | LBN | SSC | HMC| RES0 | BAS | RES0 | PMC | E | - * +------+------+-------+-----+----+------+-----+------+-----+---+ - * - * BT: Breakpoint type (0 = unlinked address match) - * LBN: Linked BP number (0 = unused) - * SSC/HMC/PMC: Security, Higher and Priv access control (Table D-12) - * BAS: Byte Address Select (RES1 for AArch64) - * E: Enable bit - * - * DBGBVR<n>_EL1, Debug Breakpoint Value Registers - * - * 63 53 52 49 48 2 1 0 - * +------+-----------+----------+-----+ - * | RESS | VA[52:49] | VA[48:2] | 0 0 | - * +------+-----------+----------+-----+ - * - * Depending on the addressing mode bits the top bits of the register - * are a sign extension of the highest applicable VA bit. Some - * versions of GDB don't do it correctly so we ensure they are correct - * here so future PC comparisons will work properly. - */ - -static int insert_hw_breakpoint(target_ulong addr) -{ - HWBreakpoint brk = { - .bcr = 0x1, /* BCR E=1, enable */ - .bvr = sextract64(addr, 0, 53) - }; - - if (cur_hw_bps >= max_hw_bps) { - return -ENOBUFS; - } - - brk.bcr = deposit32(brk.bcr, 1, 2, 0x3); /* PMC = 11 */ - brk.bcr = deposit32(brk.bcr, 5, 4, 0xf); /* BAS = RES1 */ - - g_array_append_val(hw_breakpoints, brk); - - return 0; -} - -/** - * delete_hw_breakpoint() - * @pc: address of breakpoint - * - * Delete a breakpoint and shuffle any above down - */ - -static int delete_hw_breakpoint(target_ulong pc) -{ - int i; - for (i = 0; i < hw_breakpoints->len; i++) { - HWBreakpoint *brk = get_hw_bp(i); - if (brk->bvr == pc) { - g_array_remove_index(hw_breakpoints, i); - return 0; - } - } - return -ENOENT; -} - -/** - * insert_hw_watchpoint() - * @addr: address of watch point - * @len: size of area - * @type: type of watch point - * - * See ARM ARM D2.10. As with the breakpoints we can do some advanced - * stuff if we want to. The watch points can be linked with the break - * points above to make them context aware. However for simplicity - * currently we only deal with simple read/write watch points. - * - * D7.3.11 DBGWCR<n>_EL1, Debug Watchpoint Control Registers - * - * 31 29 28 24 23 21 20 19 16 15 14 13 12 5 4 3 2 1 0 - * +------+-------+------+----+-----+-----+-----+-----+-----+-----+---+ - * | RES0 | MASK | RES0 | WT | LBN | SSC | HMC | BAS | LSC | PAC | E | - * +------+-------+------+----+-----+-----+-----+-----+-----+-----+---+ - * - * MASK: num bits addr mask (0=none,01/10=res,11=3 bits (8 bytes)) - * WT: 0 - unlinked, 1 - linked (not currently used) - * LBN: Linked BP number (not currently used) - * SSC/HMC/PAC: Security, Higher and Priv access control (Table D2-11) - * BAS: Byte Address Select - * LSC: Load/Store control (01: load, 10: store, 11: both) - * E: Enable - * - * The bottom 2 bits of the value register are masked. Therefore to - * break on any sizes smaller than an unaligned word you need to set - * MASK=0, BAS=bit per byte in question. For larger regions (^2) you - * need to ensure you mask the address as required and set BAS=0xff - */ - -static int insert_hw_watchpoint(target_ulong addr, - target_ulong len, int type) -{ - HWWatchpoint wp = { - .wcr = R_DBGWCR_E_MASK, /* E=1, enable */ - .wvr = addr & (~0x7ULL), - .details = { .vaddr = addr, .len = len } - }; - - if (cur_hw_wps >= max_hw_wps) { - return -ENOBUFS; - } - - /* - * HMC=0 SSC=0 PAC=3 will hit EL0 or EL1, any security state, - * valid whether EL3 is implemented or not - */ - wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, PAC, 3); - - switch (type) { - case GDB_WATCHPOINT_READ: - wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, LSC, 1); - wp.details.flags = BP_MEM_READ; - break; - case GDB_WATCHPOINT_WRITE: - wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, LSC, 2); - wp.details.flags = BP_MEM_WRITE; - break; - case GDB_WATCHPOINT_ACCESS: - wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, LSC, 3); - wp.details.flags = BP_MEM_ACCESS; - break; - default: - g_assert_not_reached(); - break; - } - if (len <= 8) { - /* we align the address and set the bits in BAS */ - int off = addr & 0x7; - int bas = (1 << len) - 1; - - wp.wcr = deposit32(wp.wcr, 5 + off, 8 - off, bas); - } else { - /* For ranges above 8 bytes we need to be a power of 2 */ - if (is_power_of_2(len)) { - int bits = ctz64(len); - - wp.wvr &= ~((1 << bits) - 1); - wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, MASK, bits); - wp.wcr = FIELD_DP64(wp.wcr, DBGWCR, BAS, 0xff); - } else { - return -ENOBUFS; - } - } - - g_array_append_val(hw_watchpoints, wp); - return 0; -} - - -static bool check_watchpoint_in_range(int i, target_ulong addr) -{ - HWWatchpoint *wp = get_hw_wp(i); - uint64_t addr_top, addr_bottom = wp->wvr; - int bas = extract32(wp->wcr, 5, 8); - int mask = extract32(wp->wcr, 24, 4); - - if (mask) { - addr_top = addr_bottom + (1 << mask); - } else { - /* BAS must be contiguous but can offset against the base - * address in DBGWVR */ - addr_bottom = addr_bottom + ctz32(bas); - addr_top = addr_bottom + clo32(bas); - } - - if (addr >= addr_bottom && addr <= addr_top) { - return true; - } - - return false; -} - -/** - * delete_hw_watchpoint() - * @addr: address of breakpoint - * - * Delete a breakpoint and shuffle any above down - */ - -static int delete_hw_watchpoint(target_ulong addr, - target_ulong len, int type) -{ - int i; - for (i = 0; i < cur_hw_wps; i++) { - if (check_watchpoint_in_range(i, addr)) { - g_array_remove_index(hw_watchpoints, i); - return 0; - } - } - return -ENOENT; -} - - int kvm_arch_insert_hw_breakpoint(target_ulong addr, target_ulong len, int type) { @@ -XXX,XX +XXX,XX @@ bool kvm_arm_hw_debug_active(CPUState *cs) return ((cur_hw_wps > 0) || (cur_hw_bps > 0)); } -static bool find_hw_breakpoint(CPUState *cpu, target_ulong pc) -{ - int i; - - for (i = 0; i < cur_hw_bps; i++) { - HWBreakpoint *bp = get_hw_bp(i); - if (bp->bvr == pc) { - return true; - } - } - return false; -} - -static CPUWatchpoint *find_hw_watchpoint(CPUState *cpu, target_ulong addr) -{ - int i; - - for (i = 0; i < cur_hw_wps; i++) { - if (check_watchpoint_in_range(i, addr)) { - return &get_hw_wp(i)->details; - } - } - return NULL; -} - static bool kvm_arm_set_device_attr(CPUState *cs, struct kvm_device_attr *attr, const char *name) { diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( )) arm_ss.add(zlib) -arm_ss.add(when: 'CONFIG_KVM', if_true: files('kvm.c', 'kvm64.c'), if_false: files('kvm-stub.c')) +arm_ss.add(when: 'CONFIG_KVM', if_true: files('hyp_gdbstub.c', 'kvm.c', 'kvm64.c'), if_false: files('kvm-stub.c')) +arm_ss.add(when: 'CONFIG_HVF', if_true: files('hyp_gdbstub.c')) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( 'cpu64.c', -- 2.34.1 From: Francesco Cagnin <fcagnin@quarkslab.com> Required for guest debugging. Signed-off-by: Francesco Cagnin <fcagnin@quarkslab.com> Message-id: 20230601153107.81955-3-fcagnin@quarkslab.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/hvf/hvf.c | 213 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 213 insertions(+) diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ #define SYSREG_ICC_SGI1R_EL1 SYSREG(3, 0, 12, 11, 5) #define SYSREG_ICC_SRE_EL1 SYSREG(3, 0, 12, 12, 5) +#define SYSREG_MDSCR_EL1 SYSREG(2, 0, 0, 2, 2) +#define SYSREG_DBGBVR0_EL1 SYSREG(2, 0, 0, 0, 4) +#define SYSREG_DBGBCR0_EL1 SYSREG(2, 0, 0, 0, 5) +#define SYSREG_DBGWVR0_EL1 SYSREG(2, 0, 0, 0, 6) +#define SYSREG_DBGWCR0_EL1 SYSREG(2, 0, 0, 0, 7) +#define SYSREG_DBGBVR1_EL1 SYSREG(2, 0, 0, 1, 4) +#define SYSREG_DBGBCR1_EL1 SYSREG(2, 0, 0, 1, 5) +#define SYSREG_DBGWVR1_EL1 SYSREG(2, 0, 0, 1, 6) +#define SYSREG_DBGWCR1_EL1 SYSREG(2, 0, 0, 1, 7) +#define SYSREG_DBGBVR2_EL1 SYSREG(2, 0, 0, 2, 4) +#define SYSREG_DBGBCR2_EL1 SYSREG(2, 0, 0, 2, 5) +#define SYSREG_DBGWVR2_EL1 SYSREG(2, 0, 0, 2, 6) +#define SYSREG_DBGWCR2_EL1 SYSREG(2, 0, 0, 2, 7) +#define SYSREG_DBGBVR3_EL1 SYSREG(2, 0, 0, 3, 4) +#define SYSREG_DBGBCR3_EL1 SYSREG(2, 0, 0, 3, 5) +#define SYSREG_DBGWVR3_EL1 SYSREG(2, 0, 0, 3, 6) +#define SYSREG_DBGWCR3_EL1 SYSREG(2, 0, 0, 3, 7) +#define SYSREG_DBGBVR4_EL1 SYSREG(2, 0, 0, 4, 4) +#define SYSREG_DBGBCR4_EL1 SYSREG(2, 0, 0, 4, 5) +#define SYSREG_DBGWVR4_EL1 SYSREG(2, 0, 0, 4, 6) +#define SYSREG_DBGWCR4_EL1 SYSREG(2, 0, 0, 4, 7) +#define SYSREG_DBGBVR5_EL1 SYSREG(2, 0, 0, 5, 4) +#define SYSREG_DBGBCR5_EL1 SYSREG(2, 0, 0, 5, 5) +#define SYSREG_DBGWVR5_EL1 SYSREG(2, 0, 0, 5, 6) +#define SYSREG_DBGWCR5_EL1 SYSREG(2, 0, 0, 5, 7) +#define SYSREG_DBGBVR6_EL1 SYSREG(2, 0, 0, 6, 4) +#define SYSREG_DBGBCR6_EL1 SYSREG(2, 0, 0, 6, 5) +#define SYSREG_DBGWVR6_EL1 SYSREG(2, 0, 0, 6, 6) +#define SYSREG_DBGWCR6_EL1 SYSREG(2, 0, 0, 6, 7) +#define SYSREG_DBGBVR7_EL1 SYSREG(2, 0, 0, 7, 4) +#define SYSREG_DBGBCR7_EL1 SYSREG(2, 0, 0, 7, 5) +#define SYSREG_DBGWVR7_EL1 SYSREG(2, 0, 0, 7, 6) +#define SYSREG_DBGWCR7_EL1 SYSREG(2, 0, 0, 7, 7) +#define SYSREG_DBGBVR8_EL1 SYSREG(2, 0, 0, 8, 4) +#define SYSREG_DBGBCR8_EL1 SYSREG(2, 0, 0, 8, 5) +#define SYSREG_DBGWVR8_EL1 SYSREG(2, 0, 0, 8, 6) +#define SYSREG_DBGWCR8_EL1 SYSREG(2, 0, 0, 8, 7) +#define SYSREG_DBGBVR9_EL1 SYSREG(2, 0, 0, 9, 4) +#define SYSREG_DBGBCR9_EL1 SYSREG(2, 0, 0, 9, 5) +#define SYSREG_DBGWVR9_EL1 SYSREG(2, 0, 0, 9, 6) +#define SYSREG_DBGWCR9_EL1 SYSREG(2, 0, 0, 9, 7) +#define SYSREG_DBGBVR10_EL1 SYSREG(2, 0, 0, 10, 4) +#define SYSREG_DBGBCR10_EL1 SYSREG(2, 0, 0, 10, 5) +#define SYSREG_DBGWVR10_EL1 SYSREG(2, 0, 0, 10, 6) +#define SYSREG_DBGWCR10_EL1 SYSREG(2, 0, 0, 10, 7) +#define SYSREG_DBGBVR11_EL1 SYSREG(2, 0, 0, 11, 4) +#define SYSREG_DBGBCR11_EL1 SYSREG(2, 0, 0, 11, 5) +#define SYSREG_DBGWVR11_EL1 SYSREG(2, 0, 0, 11, 6) +#define SYSREG_DBGWCR11_EL1 SYSREG(2, 0, 0, 11, 7) +#define SYSREG_DBGBVR12_EL1 SYSREG(2, 0, 0, 12, 4) +#define SYSREG_DBGBCR12_EL1 SYSREG(2, 0, 0, 12, 5) +#define SYSREG_DBGWVR12_EL1 SYSREG(2, 0, 0, 12, 6) +#define SYSREG_DBGWCR12_EL1 SYSREG(2, 0, 0, 12, 7) +#define SYSREG_DBGBVR13_EL1 SYSREG(2, 0, 0, 13, 4) +#define SYSREG_DBGBCR13_EL1 SYSREG(2, 0, 0, 13, 5) +#define SYSREG_DBGWVR13_EL1 SYSREG(2, 0, 0, 13, 6) +#define SYSREG_DBGWCR13_EL1 SYSREG(2, 0, 0, 13, 7) +#define SYSREG_DBGBVR14_EL1 SYSREG(2, 0, 0, 14, 4) +#define SYSREG_DBGBCR14_EL1 SYSREG(2, 0, 0, 14, 5) +#define SYSREG_DBGWVR14_EL1 SYSREG(2, 0, 0, 14, 6) +#define SYSREG_DBGWCR14_EL1 SYSREG(2, 0, 0, 14, 7) +#define SYSREG_DBGBVR15_EL1 SYSREG(2, 0, 0, 15, 4) +#define SYSREG_DBGBCR15_EL1 SYSREG(2, 0, 0, 15, 5) +#define SYSREG_DBGWVR15_EL1 SYSREG(2, 0, 0, 15, 6) +#define SYSREG_DBGWCR15_EL1 SYSREG(2, 0, 0, 15, 7) + #define WFX_IS_WFE (1 << 0) #define TMR_CTL_ENABLE (1 << 0) @@ -XXX,XX +XXX,XX @@ static int hvf_sysreg_read(CPUState *cpu, uint32_t reg, uint32_t rt) hvf_raise_exception(cpu, EXCP_UDEF, syn_uncategorized()); } break; + case SYSREG_DBGBVR0_EL1: + case SYSREG_DBGBVR1_EL1: + case SYSREG_DBGBVR2_EL1: + case SYSREG_DBGBVR3_EL1: + case SYSREG_DBGBVR4_EL1: + case SYSREG_DBGBVR5_EL1: + case SYSREG_DBGBVR6_EL1: + case SYSREG_DBGBVR7_EL1: + case SYSREG_DBGBVR8_EL1: + case SYSREG_DBGBVR9_EL1: + case SYSREG_DBGBVR10_EL1: + case SYSREG_DBGBVR11_EL1: + case SYSREG_DBGBVR12_EL1: + case SYSREG_DBGBVR13_EL1: + case SYSREG_DBGBVR14_EL1: + case SYSREG_DBGBVR15_EL1: + val = env->cp15.dbgbvr[SYSREG_CRM(reg)]; + break; + case SYSREG_DBGBCR0_EL1: + case SYSREG_DBGBCR1_EL1: + case SYSREG_DBGBCR2_EL1: + case SYSREG_DBGBCR3_EL1: + case SYSREG_DBGBCR4_EL1: + case SYSREG_DBGBCR5_EL1: + case SYSREG_DBGBCR6_EL1: + case SYSREG_DBGBCR7_EL1: + case SYSREG_DBGBCR8_EL1: + case SYSREG_DBGBCR9_EL1: + case SYSREG_DBGBCR10_EL1: + case SYSREG_DBGBCR11_EL1: + case SYSREG_DBGBCR12_EL1: + case SYSREG_DBGBCR13_EL1: + case SYSREG_DBGBCR14_EL1: + case SYSREG_DBGBCR15_EL1: + val = env->cp15.dbgbcr[SYSREG_CRM(reg)]; + break; + case SYSREG_DBGWVR0_EL1: + case SYSREG_DBGWVR1_EL1: + case SYSREG_DBGWVR2_EL1: + case SYSREG_DBGWVR3_EL1: + case SYSREG_DBGWVR4_EL1: + case SYSREG_DBGWVR5_EL1: + case SYSREG_DBGWVR6_EL1: + case SYSREG_DBGWVR7_EL1: + case SYSREG_DBGWVR8_EL1: + case SYSREG_DBGWVR9_EL1: + case SYSREG_DBGWVR10_EL1: + case SYSREG_DBGWVR11_EL1: + case SYSREG_DBGWVR12_EL1: + case SYSREG_DBGWVR13_EL1: + case SYSREG_DBGWVR14_EL1: + case SYSREG_DBGWVR15_EL1: + val = env->cp15.dbgwvr[SYSREG_CRM(reg)]; + break; + case SYSREG_DBGWCR0_EL1: + case SYSREG_DBGWCR1_EL1: + case SYSREG_DBGWCR2_EL1: + case SYSREG_DBGWCR3_EL1: + case SYSREG_DBGWCR4_EL1: + case SYSREG_DBGWCR5_EL1: + case SYSREG_DBGWCR6_EL1: + case SYSREG_DBGWCR7_EL1: + case SYSREG_DBGWCR8_EL1: + case SYSREG_DBGWCR9_EL1: + case SYSREG_DBGWCR10_EL1: + case SYSREG_DBGWCR11_EL1: + case SYSREG_DBGWCR12_EL1: + case SYSREG_DBGWCR13_EL1: + case SYSREG_DBGWCR14_EL1: + case SYSREG_DBGWCR15_EL1: + val = env->cp15.dbgwcr[SYSREG_CRM(reg)]; + break; default: if (is_id_sysreg(reg)) { /* ID system registers read as RES0 */ @@ -XXX,XX +XXX,XX @@ static int hvf_sysreg_write(CPUState *cpu, uint32_t reg, uint64_t val) hvf_raise_exception(cpu, EXCP_UDEF, syn_uncategorized()); } break; + case SYSREG_MDSCR_EL1: + env->cp15.mdscr_el1 = val; + break; + case SYSREG_DBGBVR0_EL1: + case SYSREG_DBGBVR1_EL1: + case SYSREG_DBGBVR2_EL1: + case SYSREG_DBGBVR3_EL1: + case SYSREG_DBGBVR4_EL1: + case SYSREG_DBGBVR5_EL1: + case SYSREG_DBGBVR6_EL1: + case SYSREG_DBGBVR7_EL1: + case SYSREG_DBGBVR8_EL1: + case SYSREG_DBGBVR9_EL1: + case SYSREG_DBGBVR10_EL1: + case SYSREG_DBGBVR11_EL1: + case SYSREG_DBGBVR12_EL1: + case SYSREG_DBGBVR13_EL1: + case SYSREG_DBGBVR14_EL1: + case SYSREG_DBGBVR15_EL1: + env->cp15.dbgbvr[SYSREG_CRM(reg)] = val; + break; + case SYSREG_DBGBCR0_EL1: + case SYSREG_DBGBCR1_EL1: + case SYSREG_DBGBCR2_EL1: + case SYSREG_DBGBCR3_EL1: + case SYSREG_DBGBCR4_EL1: + case SYSREG_DBGBCR5_EL1: + case SYSREG_DBGBCR6_EL1: + case SYSREG_DBGBCR7_EL1: + case SYSREG_DBGBCR8_EL1: + case SYSREG_DBGBCR9_EL1: + case SYSREG_DBGBCR10_EL1: + case SYSREG_DBGBCR11_EL1: + case SYSREG_DBGBCR12_EL1: + case SYSREG_DBGBCR13_EL1: + case SYSREG_DBGBCR14_EL1: + case SYSREG_DBGBCR15_EL1: + env->cp15.dbgbcr[SYSREG_CRM(reg)] = val; + break; + case SYSREG_DBGWVR0_EL1: + case SYSREG_DBGWVR1_EL1: + case SYSREG_DBGWVR2_EL1: + case SYSREG_DBGWVR3_EL1: + case SYSREG_DBGWVR4_EL1: + case SYSREG_DBGWVR5_EL1: + case SYSREG_DBGWVR6_EL1: + case SYSREG_DBGWVR7_EL1: + case SYSREG_DBGWVR8_EL1: + case SYSREG_DBGWVR9_EL1: + case SYSREG_DBGWVR10_EL1: + case SYSREG_DBGWVR11_EL1: + case SYSREG_DBGWVR12_EL1: + case SYSREG_DBGWVR13_EL1: + case SYSREG_DBGWVR14_EL1: + case SYSREG_DBGWVR15_EL1: + env->cp15.dbgwvr[SYSREG_CRM(reg)] = val; + break; + case SYSREG_DBGWCR0_EL1: + case SYSREG_DBGWCR1_EL1: + case SYSREG_DBGWCR2_EL1: + case SYSREG_DBGWCR3_EL1: + case SYSREG_DBGWCR4_EL1: + case SYSREG_DBGWCR5_EL1: + case SYSREG_DBGWCR6_EL1: + case SYSREG_DBGWCR7_EL1: + case SYSREG_DBGWCR8_EL1: + case SYSREG_DBGWCR9_EL1: + case SYSREG_DBGWCR10_EL1: + case SYSREG_DBGWCR11_EL1: + case SYSREG_DBGWCR12_EL1: + case SYSREG_DBGWCR13_EL1: + case SYSREG_DBGWCR14_EL1: + case SYSREG_DBGWCR15_EL1: + env->cp15.dbgwcr[SYSREG_CRM(reg)] = val; + break; default: cpu_synchronize_state(cpu); trace_hvf_unhandled_sysreg_write(env->pc, reg, -- 2.34.1 From: Francesco Cagnin <fcagnin@quarkslab.com> Required for guest debugging. The code has been structured like the KVM counterpart. Signed-off-by: Francesco Cagnin <fcagnin@quarkslab.com> Message-id: 20230601153107.81955-4-fcagnin@quarkslab.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/hvf.h | 22 ++++++++ include/sysemu/hvf_int.h | 1 + accel/hvf/hvf-accel-ops.c | 109 ++++++++++++++++++++++++++++++++++++++ accel/hvf/hvf-all.c | 17 ++++++ target/arm/hvf/hvf.c | 63 ++++++++++++++++++++++ target/i386/hvf/hvf.c | 24 +++++++++ 6 files changed, 236 insertions(+) diff --git a/include/sysemu/hvf.h b/include/sysemu/hvf.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/hvf.h +++ b/include/sysemu/hvf.h @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #ifdef NEED_CPU_H +#include "cpu.h" #ifdef CONFIG_HVF uint32_t hvf_get_supported_cpuid(uint32_t func, uint32_t idx, @@ -XXX,XX +XXX,XX @@ typedef struct HVFState HVFState; DECLARE_INSTANCE_CHECKER(HVFState, HVF_STATE, TYPE_HVF_ACCEL) +#ifdef NEED_CPU_H +struct hvf_sw_breakpoint { + target_ulong pc; + target_ulong saved_insn; + int use_count; + QTAILQ_ENTRY(hvf_sw_breakpoint) entry; +}; + +struct hvf_sw_breakpoint *hvf_find_sw_breakpoint(CPUState *cpu, + target_ulong pc); +int hvf_sw_breakpoints_active(CPUState *cpu); + +int hvf_arch_insert_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp); +int hvf_arch_remove_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp); +int hvf_arch_insert_hw_breakpoint(target_ulong addr, target_ulong len, + int type); +int hvf_arch_remove_hw_breakpoint(target_ulong addr, target_ulong len, + int type); +void hvf_arch_remove_all_hw_breakpoints(void); +#endif /* NEED_CPU_H */ + #endif diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/hvf_int.h +++ b/include/sysemu/hvf_int.h @@ -XXX,XX +XXX,XX @@ struct HVFState { hvf_vcpu_caps *hvf_caps; uint64_t vtimer_offset; + QTAILQ_HEAD(, hvf_sw_breakpoint) hvf_sw_breakpoints; }; extern HVFState *hvf_state; diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c index XXXXXXX..XXXXXXX 100644 --- a/accel/hvf/hvf-accel-ops.c +++ b/accel/hvf/hvf-accel-ops.c @@ -XXX,XX +XXX,XX @@ #include "qemu/main-loop.h" #include "exec/address-spaces.h" #include "exec/exec-all.h" +#include "exec/gdbstub.h" #include "sysemu/cpus.h" #include "sysemu/hvf.h" #include "sysemu/hvf_int.h" @@ -XXX,XX +XXX,XX @@ static int hvf_accel_init(MachineState *ms) s->slots[x].slot_id = x; } + QTAILQ_INIT(&s->hvf_sw_breakpoints); + hvf_state = s; memory_listener_register(&hvf_memory_listener, &address_space_memory); @@ -XXX,XX +XXX,XX @@ static void hvf_start_vcpu_thread(CPUState *cpu) cpu, QEMU_THREAD_JOINABLE); } +static int hvf_insert_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len) +{ + struct hvf_sw_breakpoint *bp; + int err; + + if (type == GDB_BREAKPOINT_SW) { + bp = hvf_find_sw_breakpoint(cpu, addr); + if (bp) { + bp->use_count++; + return 0; + } + + bp = g_new(struct hvf_sw_breakpoint, 1); + bp->pc = addr; + bp->use_count = 1; + err = hvf_arch_insert_sw_breakpoint(cpu, bp); + if (err) { + g_free(bp); + return err; + } + + QTAILQ_INSERT_HEAD(&hvf_state->hvf_sw_breakpoints, bp, entry); + } else { + err = hvf_arch_insert_hw_breakpoint(addr, len, type); + if (err) { + return err; + } + } + + CPU_FOREACH(cpu) { + err = hvf_update_guest_debug(cpu); + if (err) { + return err; + } + } + return 0; +} + +static int hvf_remove_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len) +{ + struct hvf_sw_breakpoint *bp; + int err; + + if (type == GDB_BREAKPOINT_SW) { + bp = hvf_find_sw_breakpoint(cpu, addr); + if (!bp) { + return -ENOENT; + } + + if (bp->use_count > 1) { + bp->use_count--; + return 0; + } + + err = hvf_arch_remove_sw_breakpoint(cpu, bp); + if (err) { + return err; + } + + QTAILQ_REMOVE(&hvf_state->hvf_sw_breakpoints, bp, entry); + g_free(bp); + } else { + err = hvf_arch_remove_hw_breakpoint(addr, len, type); + if (err) { + return err; + } + } + + CPU_FOREACH(cpu) { + err = hvf_update_guest_debug(cpu); + if (err) { + return err; + } + } + return 0; +} + +static void hvf_remove_all_breakpoints(CPUState *cpu) +{ + struct hvf_sw_breakpoint *bp, *next; + CPUState *tmpcpu; + + QTAILQ_FOREACH_SAFE(bp, &hvf_state->hvf_sw_breakpoints, entry, next) { + if (hvf_arch_remove_sw_breakpoint(cpu, bp) != 0) { + /* Try harder to find a CPU that currently sees the breakpoint. */ + CPU_FOREACH(tmpcpu) + { + if (hvf_arch_remove_sw_breakpoint(tmpcpu, bp) == 0) { + break; + } + } + } + QTAILQ_REMOVE(&hvf_state->hvf_sw_breakpoints, bp, entry); + g_free(bp); + } + hvf_arch_remove_all_hw_breakpoints(); + + CPU_FOREACH(cpu) { + hvf_update_guest_debug(cpu); + } +} + static void hvf_accel_ops_class_init(ObjectClass *oc, void *data) { AccelOpsClass *ops = ACCEL_OPS_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static void hvf_accel_ops_class_init(ObjectClass *oc, void *data) ops->synchronize_post_init = hvf_cpu_synchronize_post_init; ops->synchronize_state = hvf_cpu_synchronize_state; ops->synchronize_pre_loadvm = hvf_cpu_synchronize_pre_loadvm; + + ops->insert_breakpoint = hvf_insert_breakpoint; + ops->remove_breakpoint = hvf_remove_breakpoint; + ops->remove_all_breakpoints = hvf_remove_all_breakpoints; }; static const TypeInfo hvf_accel_ops_type = { .name = ACCEL_OPS_NAME("hvf"), diff --git a/accel/hvf/hvf-all.c b/accel/hvf/hvf-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/hvf/hvf-all.c +++ b/accel/hvf/hvf-all.c @@ -XXX,XX +XXX,XX @@ void assert_hvf_ok(hv_return_t ret) abort(); } + +struct hvf_sw_breakpoint *hvf_find_sw_breakpoint(CPUState *cpu, target_ulong pc) +{ + struct hvf_sw_breakpoint *bp; + + QTAILQ_FOREACH(bp, &hvf_state->hvf_sw_breakpoints, entry) { + if (bp->pc == pc) { + return bp; + } + } + return NULL; +} + +int hvf_sw_breakpoints_active(CPUState *cpu) +{ + return !QTAILQ_EMPTY(&hvf_state->hvf_sw_breakpoints); +} diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ #include "trace/trace-target_arm_hvf.h" #include "migration/vmstate.h" +#include "exec/gdbstub.h" + #define HVF_SYSREG(crn, crm, op0, op1, op2) \ ENCODE_AA64_CP_REG(CP_REG_ARM64_SYSREG_CP, crn, crm, op0, op1, op2) #define PL1_WRITE_MASK 0x4 @@ -XXX,XX +XXX,XX @@ int hvf_arch_init(void) qemu_add_vm_change_state_handler(hvf_vm_state_change, &vtimer); return 0; } + +static const uint32_t brk_insn = 0xd4200000; + +int hvf_arch_insert_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp) +{ + if (cpu_memory_rw_debug(cpu, bp->pc, (uint8_t *)&bp->saved_insn, 4, 0) || + cpu_memory_rw_debug(cpu, bp->pc, (uint8_t *)&brk_insn, 4, 1)) { + return -EINVAL; + } + return 0; +} + +int hvf_arch_remove_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp) +{ + static uint32_t brk; + + if (cpu_memory_rw_debug(cpu, bp->pc, (uint8_t *)&brk, 4, 0) || + brk != brk_insn || + cpu_memory_rw_debug(cpu, bp->pc, (uint8_t *)&bp->saved_insn, 4, 1)) { + return -EINVAL; + } + return 0; +} + +int hvf_arch_insert_hw_breakpoint(target_ulong addr, target_ulong len, int type) +{ + switch (type) { + case GDB_BREAKPOINT_HW: + return insert_hw_breakpoint(addr); + case GDB_WATCHPOINT_READ: + case GDB_WATCHPOINT_WRITE: + case GDB_WATCHPOINT_ACCESS: + return insert_hw_watchpoint(addr, len, type); + default: + return -ENOSYS; + } +} + +int hvf_arch_remove_hw_breakpoint(target_ulong addr, target_ulong len, int type) +{ + switch (type) { + case GDB_BREAKPOINT_HW: + return delete_hw_breakpoint(addr); + case GDB_WATCHPOINT_READ: + case GDB_WATCHPOINT_WRITE: + case GDB_WATCHPOINT_ACCESS: + return delete_hw_watchpoint(addr, len, type); + default: + return -ENOSYS; + } +} + +void hvf_arch_remove_all_hw_breakpoints(void) +{ + if (cur_hw_wps > 0) { + g_array_remove_range(hw_watchpoints, 0, cur_hw_wps); + } + if (cur_hw_bps > 0) { + g_array_remove_range(hw_breakpoints, 0, cur_hw_bps); + } +} diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/hvf.c +++ b/target/i386/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) return ret; } + +int hvf_arch_insert_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp) +{ + return -ENOSYS; +} + +int hvf_arch_remove_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp) +{ + return -ENOSYS; +} + +int hvf_arch_insert_hw_breakpoint(target_ulong addr, target_ulong len, int type) +{ + return -ENOSYS; +} + +int hvf_arch_remove_hw_breakpoint(target_ulong addr, target_ulong len, int type) +{ + return -ENOSYS; +} + +void hvf_arch_remove_all_hw_breakpoints(void) +{ +} -- 2.34.1 From: Francesco Cagnin <fcagnin@quarkslab.com> Guests can now be debugged through the gdbstub. Support is added for single-stepping, software breakpoints, hardware breakpoints and watchpoints. The code has been structured like the KVM counterpart. While guest debugging is enabled, the guest can still read and write the DBG*_EL1 registers but they don't have any effect. Signed-off-by: Francesco Cagnin <fcagnin@quarkslab.com> Message-id: 20230601153107.81955-5-fcagnin@quarkslab.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/hvf.h | 15 ++ include/sysemu/hvf_int.h | 1 + target/arm/hvf_arm.h | 7 + accel/hvf/hvf-accel-ops.c | 10 + accel/hvf/hvf-all.c | 6 + target/arm/hvf/hvf.c | 474 +++++++++++++++++++++++++++++++++++++- target/i386/hvf/hvf.c | 9 + 7 files changed, 520 insertions(+), 2 deletions(-) diff --git a/include/sysemu/hvf.h b/include/sysemu/hvf.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/hvf.h +++ b/include/sysemu/hvf.h @@ -XXX,XX +XXX,XX @@ int hvf_arch_insert_hw_breakpoint(target_ulong addr, target_ulong len, int hvf_arch_remove_hw_breakpoint(target_ulong addr, target_ulong len, int type); void hvf_arch_remove_all_hw_breakpoints(void); + +/* + * hvf_update_guest_debug: + * @cs: CPUState for the CPU to update + * + * Update guest to enable or disable debugging. Per-arch specifics will be + * handled by calling down to hvf_arch_update_guest_debug. + */ +int hvf_update_guest_debug(CPUState *cpu); +void hvf_arch_update_guest_debug(CPUState *cpu); + +/* + * Return whether the guest supports debugging. + */ +bool hvf_arch_supports_guest_debug(void); #endif /* NEED_CPU_H */ #endif diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/hvf_int.h +++ b/include/sysemu/hvf_int.h @@ -XXX,XX +XXX,XX @@ struct hvf_vcpu_state { void *exit; bool vtimer_masked; sigset_t unblock_ipi_mask; + bool guest_debug_enabled; }; void assert_hvf_ok(hv_return_t ret); diff --git a/target/arm/hvf_arm.h b/target/arm/hvf_arm.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf_arm.h +++ b/target/arm/hvf_arm.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" +/** + * hvf_arm_init_debug() - initialize guest debug capabilities + * + * Should be called only once before using guest debug capabilities. + */ +void hvf_arm_init_debug(void); + void hvf_arm_set_cpu_features_from_host(ARMCPU *cpu); #endif diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c index XXXXXXX..XXXXXXX 100644 --- a/accel/hvf/hvf-accel-ops.c +++ b/accel/hvf/hvf-accel-ops.c @@ -XXX,XX +XXX,XX @@ static int hvf_accel_init(MachineState *ms) return hvf_arch_init(); } +static inline int hvf_gdbstub_sstep_flags(void) +{ + return SSTEP_ENABLE | SSTEP_NOIRQ; +} + static void hvf_accel_class_init(ObjectClass *oc, void *data) { AccelClass *ac = ACCEL_CLASS(oc); ac->name = "HVF"; ac->init_machine = hvf_accel_init; ac->allowed = &hvf_allowed; + ac->gdbstub_supported_sstep_flags = hvf_gdbstub_sstep_flags; } static const TypeInfo hvf_accel_type = { @@ -XXX,XX +XXX,XX @@ static int hvf_init_vcpu(CPUState *cpu) cpu->vcpu_dirty = 1; assert_hvf_ok(r); + cpu->hvf->guest_debug_enabled = false; + return hvf_arch_init_vcpu(cpu); } @@ -XXX,XX +XXX,XX @@ static void hvf_accel_ops_class_init(ObjectClass *oc, void *data) ops->insert_breakpoint = hvf_insert_breakpoint; ops->remove_breakpoint = hvf_remove_breakpoint; ops->remove_all_breakpoints = hvf_remove_all_breakpoints; + ops->update_guest_debug = hvf_update_guest_debug; + ops->supports_guest_debug = hvf_arch_supports_guest_debug; }; static const TypeInfo hvf_accel_ops_type = { .name = ACCEL_OPS_NAME("hvf"), diff --git a/accel/hvf/hvf-all.c b/accel/hvf/hvf-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/hvf/hvf-all.c +++ b/accel/hvf/hvf-all.c @@ -XXX,XX +XXX,XX @@ int hvf_sw_breakpoints_active(CPUState *cpu) { return !QTAILQ_EMPTY(&hvf_state->hvf_sw_breakpoints); } + +int hvf_update_guest_debug(CPUState *cpu) +{ + hvf_arch_update_guest_debug(cpu); + return 0; +} diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ #include "exec/gdbstub.h" +#define MDSCR_EL1_SS_SHIFT 0 +#define MDSCR_EL1_MDE_SHIFT 15 + +static uint16_t dbgbcr_regs[] = { + HV_SYS_REG_DBGBCR0_EL1, + HV_SYS_REG_DBGBCR1_EL1, + HV_SYS_REG_DBGBCR2_EL1, + HV_SYS_REG_DBGBCR3_EL1, + HV_SYS_REG_DBGBCR4_EL1, + HV_SYS_REG_DBGBCR5_EL1, + HV_SYS_REG_DBGBCR6_EL1, + HV_SYS_REG_DBGBCR7_EL1, + HV_SYS_REG_DBGBCR8_EL1, + HV_SYS_REG_DBGBCR9_EL1, + HV_SYS_REG_DBGBCR10_EL1, + HV_SYS_REG_DBGBCR11_EL1, + HV_SYS_REG_DBGBCR12_EL1, + HV_SYS_REG_DBGBCR13_EL1, + HV_SYS_REG_DBGBCR14_EL1, + HV_SYS_REG_DBGBCR15_EL1, +}; +static uint16_t dbgbvr_regs[] = { + HV_SYS_REG_DBGBVR0_EL1, + HV_SYS_REG_DBGBVR1_EL1, + HV_SYS_REG_DBGBVR2_EL1, + HV_SYS_REG_DBGBVR3_EL1, + HV_SYS_REG_DBGBVR4_EL1, + HV_SYS_REG_DBGBVR5_EL1, + HV_SYS_REG_DBGBVR6_EL1, + HV_SYS_REG_DBGBVR7_EL1, + HV_SYS_REG_DBGBVR8_EL1, + HV_SYS_REG_DBGBVR9_EL1, + HV_SYS_REG_DBGBVR10_EL1, + HV_SYS_REG_DBGBVR11_EL1, + HV_SYS_REG_DBGBVR12_EL1, + HV_SYS_REG_DBGBVR13_EL1, + HV_SYS_REG_DBGBVR14_EL1, + HV_SYS_REG_DBGBVR15_EL1, +}; +static uint16_t dbgwcr_regs[] = { + HV_SYS_REG_DBGWCR0_EL1, + HV_SYS_REG_DBGWCR1_EL1, + HV_SYS_REG_DBGWCR2_EL1, + HV_SYS_REG_DBGWCR3_EL1, + HV_SYS_REG_DBGWCR4_EL1, + HV_SYS_REG_DBGWCR5_EL1, + HV_SYS_REG_DBGWCR6_EL1, + HV_SYS_REG_DBGWCR7_EL1, + HV_SYS_REG_DBGWCR8_EL1, + HV_SYS_REG_DBGWCR9_EL1, + HV_SYS_REG_DBGWCR10_EL1, + HV_SYS_REG_DBGWCR11_EL1, + HV_SYS_REG_DBGWCR12_EL1, + HV_SYS_REG_DBGWCR13_EL1, + HV_SYS_REG_DBGWCR14_EL1, + HV_SYS_REG_DBGWCR15_EL1, +}; +static uint16_t dbgwvr_regs[] = { + HV_SYS_REG_DBGWVR0_EL1, + HV_SYS_REG_DBGWVR1_EL1, + HV_SYS_REG_DBGWVR2_EL1, + HV_SYS_REG_DBGWVR3_EL1, + HV_SYS_REG_DBGWVR4_EL1, + HV_SYS_REG_DBGWVR5_EL1, + HV_SYS_REG_DBGWVR6_EL1, + HV_SYS_REG_DBGWVR7_EL1, + HV_SYS_REG_DBGWVR8_EL1, + HV_SYS_REG_DBGWVR9_EL1, + HV_SYS_REG_DBGWVR10_EL1, + HV_SYS_REG_DBGWVR11_EL1, + HV_SYS_REG_DBGWVR12_EL1, + HV_SYS_REG_DBGWVR13_EL1, + HV_SYS_REG_DBGWVR14_EL1, + HV_SYS_REG_DBGWVR15_EL1, +}; + +static inline int hvf_arm_num_brps(hv_vcpu_config_t config) +{ + uint64_t val; + hv_return_t ret; + ret = hv_vcpu_config_get_feature_reg(config, HV_FEATURE_REG_ID_AA64DFR0_EL1, + &val); + assert_hvf_ok(ret); + return FIELD_EX64(val, ID_AA64DFR0, BRPS) + 1; +} + +static inline int hvf_arm_num_wrps(hv_vcpu_config_t config) +{ + uint64_t val; + hv_return_t ret; + ret = hv_vcpu_config_get_feature_reg(config, HV_FEATURE_REG_ID_AA64DFR0_EL1, + &val); + assert_hvf_ok(ret); + return FIELD_EX64(val, ID_AA64DFR0, WRPS) + 1; +} + +void hvf_arm_init_debug(void) +{ + hv_vcpu_config_t config; + config = hv_vcpu_config_create(); + + max_hw_bps = hvf_arm_num_brps(config); + hw_breakpoints = + g_array_sized_new(true, true, sizeof(HWBreakpoint), max_hw_bps); + + max_hw_wps = hvf_arm_num_wrps(config); + hw_watchpoints = + g_array_sized_new(true, true, sizeof(HWWatchpoint), max_hw_wps); +} + #define HVF_SYSREG(crn, crm, op0, op1, op2) \ ENCODE_AA64_CP_REG(CP_REG_ARM64_SYSREG_CP, crn, crm, op0, op1, op2) #define PL1_WRITE_MASK 0x4 @@ -XXX,XX +XXX,XX @@ int hvf_get_registers(CPUState *cpu) continue; } + if (cpu->hvf->guest_debug_enabled) { + /* Handle debug registers */ + switch (hvf_sreg_match[i].reg) { + case HV_SYS_REG_DBGBVR0_EL1: + case HV_SYS_REG_DBGBCR0_EL1: + case HV_SYS_REG_DBGWVR0_EL1: + case HV_SYS_REG_DBGWCR0_EL1: + case HV_SYS_REG_DBGBVR1_EL1: + case HV_SYS_REG_DBGBCR1_EL1: + case HV_SYS_REG_DBGWVR1_EL1: + case HV_SYS_REG_DBGWCR1_EL1: + case HV_SYS_REG_DBGBVR2_EL1: + case HV_SYS_REG_DBGBCR2_EL1: + case HV_SYS_REG_DBGWVR2_EL1: + case HV_SYS_REG_DBGWCR2_EL1: + case HV_SYS_REG_DBGBVR3_EL1: + case HV_SYS_REG_DBGBCR3_EL1: + case HV_SYS_REG_DBGWVR3_EL1: + case HV_SYS_REG_DBGWCR3_EL1: + case HV_SYS_REG_DBGBVR4_EL1: + case HV_SYS_REG_DBGBCR4_EL1: + case HV_SYS_REG_DBGWVR4_EL1: + case HV_SYS_REG_DBGWCR4_EL1: + case HV_SYS_REG_DBGBVR5_EL1: + case HV_SYS_REG_DBGBCR5_EL1: + case HV_SYS_REG_DBGWVR5_EL1: + case HV_SYS_REG_DBGWCR5_EL1: + case HV_SYS_REG_DBGBVR6_EL1: + case HV_SYS_REG_DBGBCR6_EL1: + case HV_SYS_REG_DBGWVR6_EL1: + case HV_SYS_REG_DBGWCR6_EL1: + case HV_SYS_REG_DBGBVR7_EL1: + case HV_SYS_REG_DBGBCR7_EL1: + case HV_SYS_REG_DBGWVR7_EL1: + case HV_SYS_REG_DBGWCR7_EL1: + case HV_SYS_REG_DBGBVR8_EL1: + case HV_SYS_REG_DBGBCR8_EL1: + case HV_SYS_REG_DBGWVR8_EL1: + case HV_SYS_REG_DBGWCR8_EL1: + case HV_SYS_REG_DBGBVR9_EL1: + case HV_SYS_REG_DBGBCR9_EL1: + case HV_SYS_REG_DBGWVR9_EL1: + case HV_SYS_REG_DBGWCR9_EL1: + case HV_SYS_REG_DBGBVR10_EL1: + case HV_SYS_REG_DBGBCR10_EL1: + case HV_SYS_REG_DBGWVR10_EL1: + case HV_SYS_REG_DBGWCR10_EL1: + case HV_SYS_REG_DBGBVR11_EL1: + case HV_SYS_REG_DBGBCR11_EL1: + case HV_SYS_REG_DBGWVR11_EL1: + case HV_SYS_REG_DBGWCR11_EL1: + case HV_SYS_REG_DBGBVR12_EL1: + case HV_SYS_REG_DBGBCR12_EL1: + case HV_SYS_REG_DBGWVR12_EL1: + case HV_SYS_REG_DBGWCR12_EL1: + case HV_SYS_REG_DBGBVR13_EL1: + case HV_SYS_REG_DBGBCR13_EL1: + case HV_SYS_REG_DBGWVR13_EL1: + case HV_SYS_REG_DBGWCR13_EL1: + case HV_SYS_REG_DBGBVR14_EL1: + case HV_SYS_REG_DBGBCR14_EL1: + case HV_SYS_REG_DBGWVR14_EL1: + case HV_SYS_REG_DBGWCR14_EL1: + case HV_SYS_REG_DBGBVR15_EL1: + case HV_SYS_REG_DBGBCR15_EL1: + case HV_SYS_REG_DBGWVR15_EL1: + case HV_SYS_REG_DBGWCR15_EL1: { + /* + * If the guest is being debugged, the vCPU's debug registers + * are holding the gdbstub's view of the registers (set in + * hvf_arch_update_guest_debug()). + * Since the environment is used to store only the guest's view + * of the registers, don't update it with the values from the + * vCPU but simply keep the values from the previous + * environment. + */ + const ARMCPRegInfo *ri; + ri = get_arm_cp_reginfo(arm_cpu->cp_regs, hvf_sreg_match[i].key); + val = read_raw_cp_reg(env, ri); + + arm_cpu->cpreg_values[hvf_sreg_match[i].cp_idx] = val; + continue; + } + } + } + ret = hv_vcpu_get_sys_reg(cpu->hvf->fd, hvf_sreg_match[i].reg, &val); assert_hvf_ok(ret); @@ -XXX,XX +XXX,XX @@ int hvf_put_registers(CPUState *cpu) continue; } + if (cpu->hvf->guest_debug_enabled) { + /* Handle debug registers */ + switch (hvf_sreg_match[i].reg) { + case HV_SYS_REG_DBGBVR0_EL1: + case HV_SYS_REG_DBGBCR0_EL1: + case HV_SYS_REG_DBGWVR0_EL1: + case HV_SYS_REG_DBGWCR0_EL1: + case HV_SYS_REG_DBGBVR1_EL1: + case HV_SYS_REG_DBGBCR1_EL1: + case HV_SYS_REG_DBGWVR1_EL1: + case HV_SYS_REG_DBGWCR1_EL1: + case HV_SYS_REG_DBGBVR2_EL1: + case HV_SYS_REG_DBGBCR2_EL1: + case HV_SYS_REG_DBGWVR2_EL1: + case HV_SYS_REG_DBGWCR2_EL1: + case HV_SYS_REG_DBGBVR3_EL1: + case HV_SYS_REG_DBGBCR3_EL1: + case HV_SYS_REG_DBGWVR3_EL1: + case HV_SYS_REG_DBGWCR3_EL1: + case HV_SYS_REG_DBGBVR4_EL1: + case HV_SYS_REG_DBGBCR4_EL1: + case HV_SYS_REG_DBGWVR4_EL1: + case HV_SYS_REG_DBGWCR4_EL1: + case HV_SYS_REG_DBGBVR5_EL1: + case HV_SYS_REG_DBGBCR5_EL1: + case HV_SYS_REG_DBGWVR5_EL1: + case HV_SYS_REG_DBGWCR5_EL1: + case HV_SYS_REG_DBGBVR6_EL1: + case HV_SYS_REG_DBGBCR6_EL1: + case HV_SYS_REG_DBGWVR6_EL1: + case HV_SYS_REG_DBGWCR6_EL1: + case HV_SYS_REG_DBGBVR7_EL1: + case HV_SYS_REG_DBGBCR7_EL1: + case HV_SYS_REG_DBGWVR7_EL1: + case HV_SYS_REG_DBGWCR7_EL1: + case HV_SYS_REG_DBGBVR8_EL1: + case HV_SYS_REG_DBGBCR8_EL1: + case HV_SYS_REG_DBGWVR8_EL1: + case HV_SYS_REG_DBGWCR8_EL1: + case HV_SYS_REG_DBGBVR9_EL1: + case HV_SYS_REG_DBGBCR9_EL1: + case HV_SYS_REG_DBGWVR9_EL1: + case HV_SYS_REG_DBGWCR9_EL1: + case HV_SYS_REG_DBGBVR10_EL1: + case HV_SYS_REG_DBGBCR10_EL1: + case HV_SYS_REG_DBGWVR10_EL1: + case HV_SYS_REG_DBGWCR10_EL1: + case HV_SYS_REG_DBGBVR11_EL1: + case HV_SYS_REG_DBGBCR11_EL1: + case HV_SYS_REG_DBGWVR11_EL1: + case HV_SYS_REG_DBGWCR11_EL1: + case HV_SYS_REG_DBGBVR12_EL1: + case HV_SYS_REG_DBGBCR12_EL1: + case HV_SYS_REG_DBGWVR12_EL1: + case HV_SYS_REG_DBGWCR12_EL1: + case HV_SYS_REG_DBGBVR13_EL1: + case HV_SYS_REG_DBGBCR13_EL1: + case HV_SYS_REG_DBGWVR13_EL1: + case HV_SYS_REG_DBGWCR13_EL1: + case HV_SYS_REG_DBGBVR14_EL1: + case HV_SYS_REG_DBGBCR14_EL1: + case HV_SYS_REG_DBGWVR14_EL1: + case HV_SYS_REG_DBGWCR14_EL1: + case HV_SYS_REG_DBGBVR15_EL1: + case HV_SYS_REG_DBGBCR15_EL1: + case HV_SYS_REG_DBGWVR15_EL1: + case HV_SYS_REG_DBGWCR15_EL1: + /* + * If the guest is being debugged, the vCPU's debug registers + * are already holding the gdbstub's view of the registers (set + * in hvf_arch_update_guest_debug()). + */ + continue; + } + } + val = arm_cpu->cpreg_values[hvf_sreg_match[i].cp_idx]; ret = hv_vcpu_set_sys_reg(cpu->hvf->fd, hvf_sreg_match[i].reg, val); assert_hvf_ok(ret); @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) { ARMCPU *arm_cpu = ARM_CPU(cpu); CPUARMState *env = &arm_cpu->env; + int ret; hv_vcpu_exit_t *hvf_exit = cpu->hvf->exit; hv_return_t r; bool advance_pc = false; - if (hvf_inject_interrupts(cpu)) { + if (!(cpu->singlestep_enabled & SSTEP_NOIRQ) && + hvf_inject_interrupts(cpu)) { return EXCP_INTERRUPT; } @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) uint64_t syndrome = hvf_exit->exception.syndrome; uint32_t ec = syn_get_ec(syndrome); + ret = 0; qemu_mutex_lock_iothread(); switch (exit_reason) { case HV_EXIT_REASON_EXCEPTION: @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) hvf_sync_vtimer(cpu); switch (ec) { + case EC_SOFTWARESTEP: { + ret = EXCP_DEBUG; + + if (!cpu->singlestep_enabled) { + error_report("EC_SOFTWARESTEP but single-stepping not enabled"); + } + break; + } + case EC_AA64_BKPT: { + ret = EXCP_DEBUG; + + cpu_synchronize_state(cpu); + + if (!hvf_find_sw_breakpoint(cpu, env->pc)) { + /* Re-inject into the guest */ + ret = 0; + hvf_raise_exception(cpu, EXCP_BKPT, syn_aa64_bkpt(0)); + } + break; + } + case EC_BREAKPOINT: { + ret = EXCP_DEBUG; + + cpu_synchronize_state(cpu); + + if (!find_hw_breakpoint(cpu, env->pc)) { + error_report("EC_BREAKPOINT but unknown hw breakpoint"); + } + break; + } + case EC_WATCHPOINT: { + ret = EXCP_DEBUG; + + cpu_synchronize_state(cpu); + + CPUWatchpoint *wp = + find_hw_watchpoint(cpu, hvf_exit->exception.virtual_address); + if (!wp) { + error_report("EXCP_DEBUG but unknown hw watchpoint"); + } + cpu->watchpoint_hit = wp; + break; + } case EC_DATAABORT: { bool isv = syndrome & ARM_EL_ISV; bool iswrite = (syndrome >> 6) & 1; @@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu) pc += 4; r = hv_vcpu_set_reg(cpu->hvf->fd, HV_REG_PC, pc); assert_hvf_ok(r); + + /* Handle single-stepping over instructions which trigger a VM exit */ + if (cpu->singlestep_enabled) { + ret = EXCP_DEBUG; + } } - return 0; + return ret; } static const VMStateDescription vmstate_hvf_vtimer = { @@ -XXX,XX +XXX,XX @@ int hvf_arch_init(void) hvf_state->vtimer_offset = mach_absolute_time(); vmstate_register(NULL, 0, &vmstate_hvf_vtimer, &vtimer); qemu_add_vm_change_state_handler(hvf_vm_state_change, &vtimer); + + hvf_arm_init_debug(); + return 0; } @@ -XXX,XX +XXX,XX @@ void hvf_arch_remove_all_hw_breakpoints(void) g_array_remove_range(hw_breakpoints, 0, cur_hw_bps); } } + +/* + * Update the vCPU with the gdbstub's view of debug registers. This view + * consists of all hardware breakpoints and watchpoints inserted so far while + * debugging the guest. + */ +static void hvf_put_gdbstub_debug_registers(CPUState *cpu) +{ + hv_return_t r = HV_SUCCESS; + int i; + + for (i = 0; i < cur_hw_bps; i++) { + HWBreakpoint *bp = get_hw_bp(i); + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgbcr_regs[i], bp->bcr); + assert_hvf_ok(r); + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgbvr_regs[i], bp->bvr); + assert_hvf_ok(r); + } + for (i = cur_hw_bps; i < max_hw_bps; i++) { + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgbcr_regs[i], 0); + assert_hvf_ok(r); + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgbvr_regs[i], 0); + assert_hvf_ok(r); + } + + for (i = 0; i < cur_hw_wps; i++) { + HWWatchpoint *wp = get_hw_wp(i); + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgwcr_regs[i], wp->wcr); + assert_hvf_ok(r); + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgwvr_regs[i], wp->wvr); + assert_hvf_ok(r); + } + for (i = cur_hw_wps; i < max_hw_wps; i++) { + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgwcr_regs[i], 0); + assert_hvf_ok(r); + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgwvr_regs[i], 0); + assert_hvf_ok(r); + } +} + +/* + * Update the vCPU with the guest's view of debug registers. This view is kept + * in the environment at all times. + */ +static void hvf_put_guest_debug_registers(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + hv_return_t r = HV_SUCCESS; + int i; + + for (i = 0; i < max_hw_bps; i++) { + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgbcr_regs[i], + env->cp15.dbgbcr[i]); + assert_hvf_ok(r); + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgbvr_regs[i], + env->cp15.dbgbvr[i]); + assert_hvf_ok(r); + } + + for (i = 0; i < max_hw_wps; i++) { + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgwcr_regs[i], + env->cp15.dbgwcr[i]); + assert_hvf_ok(r); + r = hv_vcpu_set_sys_reg(cpu->hvf->fd, dbgwvr_regs[i], + env->cp15.dbgwvr[i]); + assert_hvf_ok(r); + } +} + +static inline bool hvf_arm_hw_debug_active(CPUState *cpu) +{ + return ((cur_hw_wps > 0) || (cur_hw_bps > 0)); +} + +static void hvf_arch_set_traps(void) +{ + CPUState *cpu; + bool should_enable_traps = false; + hv_return_t r = HV_SUCCESS; + + /* Check whether guest debugging is enabled for at least one vCPU; if it + * is, enable exiting the guest on all vCPUs */ + CPU_FOREACH(cpu) { + should_enable_traps |= cpu->hvf->guest_debug_enabled; + } + CPU_FOREACH(cpu) { + /* Set whether debug exceptions exit the guest */ + r = hv_vcpu_set_trap_debug_exceptions(cpu->hvf->fd, + should_enable_traps); + assert_hvf_ok(r); + + /* Set whether accesses to debug registers exit the guest */ + r = hv_vcpu_set_trap_debug_reg_accesses(cpu->hvf->fd, + should_enable_traps); + assert_hvf_ok(r); + } +} + +void hvf_arch_update_guest_debug(CPUState *cpu) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + + /* Check whether guest debugging is enabled */ + cpu->hvf->guest_debug_enabled = cpu->singlestep_enabled || + hvf_sw_breakpoints_active(cpu) || + hvf_arm_hw_debug_active(cpu); + + /* Update debug registers */ + if (cpu->hvf->guest_debug_enabled) { + hvf_put_gdbstub_debug_registers(cpu); + } else { + hvf_put_guest_debug_registers(cpu); + } + + cpu_synchronize_state(cpu); + + /* Enable/disable single-stepping */ + if (cpu->singlestep_enabled) { + env->cp15.mdscr_el1 = + deposit64(env->cp15.mdscr_el1, MDSCR_EL1_SS_SHIFT, 1, 1); + pstate_write(env, pstate_read(env) | PSTATE_SS); + } else { + env->cp15.mdscr_el1 = + deposit64(env->cp15.mdscr_el1, MDSCR_EL1_SS_SHIFT, 1, 0); + } + + /* Enable/disable Breakpoint exceptions */ + if (hvf_arm_hw_debug_active(cpu)) { + env->cp15.mdscr_el1 = + deposit64(env->cp15.mdscr_el1, MDSCR_EL1_MDE_SHIFT, 1, 1); + } else { + env->cp15.mdscr_el1 = + deposit64(env->cp15.mdscr_el1, MDSCR_EL1_MDE_SHIFT, 1, 0); + } + + hvf_arch_set_traps(); +} + +inline bool hvf_arch_supports_guest_debug(void) +{ + return true; +} diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/hvf/hvf.c +++ b/target/i386/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ int hvf_arch_remove_hw_breakpoint(target_ulong addr, target_ulong len, int type) void hvf_arch_remove_all_hw_breakpoints(void) { } + +void hvf_arch_update_guest_debug(CPUState *cpu) +{ +} + +inline bool hvf_arch_supports_guest_debug(void) +{ + return false; +} -- 2.34.1 From: Vikram Garhwal <vikram.garhwal@amd.com> The Xilinx Versal CANFD controller is developed based on SocketCAN, QEMU CAN bus implementation. Bus connection and socketCAN connection for each CAN module can be set through command lines. Signed-off-by: Vikram Garhwal <vikram.garhwal@amd.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/xlnx-versal-canfd.h | 87 ++ hw/net/can/xlnx-versal-canfd.c | 2107 ++++++++++++++++++++++++++++ hw/net/can/meson.build | 1 + hw/net/can/trace-events | 7 + 4 files changed, 2202 insertions(+) create mode 100644 include/hw/net/xlnx-versal-canfd.h create mode 100644 hw/net/can/xlnx-versal-canfd.c diff --git a/include/hw/net/xlnx-versal-canfd.h b/include/hw/net/xlnx-versal-canfd.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/xlnx-versal-canfd.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx Versal CANFD Controller. + * + * Copyright (c) 2023 Advanced Micro Devices, Inc. + * + * Written-by: Vikram Garhwal<vikram.garhwal@amd.com> + * Based on QEMU CANFD Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa. + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef HW_CANFD_XILINX_H +#define HW_CANFD_XILINX_H + +#include "hw/register.h" +#include "hw/ptimer.h" +#include "net/can_emu.h" +#include "hw/qdev-clock.h" + +#define TYPE_XILINX_CANFD "xlnx.versal-canfd" + +OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCANFDState, XILINX_CANFD) + +#define NUM_REGS_PER_MSG_SPACE 18 /* 1 ID + 1 DLC + 16 Data(DW0 - DW15) regs. */ +#define MAX_NUM_RX 64 +#define OFFSET_RX1_DW15 (0x4144 / 4) +#define CANFD_TIMER_MAX 0xFFFFUL +#define CANFD_DEFAULT_CLOCK (25 * 1000 * 1000) + +#define XLNX_VERSAL_CANFD_R_MAX (OFFSET_RX1_DW15 + \ + ((MAX_NUM_RX - 1) * NUM_REGS_PER_MSG_SPACE) + 1) + +typedef struct XlnxVersalCANFDState { + SysBusDevice parent_obj; + MemoryRegion iomem; + + qemu_irq irq_canfd_int; + qemu_irq irq_addr_err; + + RegisterInfo reg_info[XLNX_VERSAL_CANFD_R_MAX]; + RegisterAccessInfo *tx_regs; + RegisterAccessInfo *rx0_regs; + RegisterAccessInfo *rx1_regs; + RegisterAccessInfo *af_regs; + RegisterAccessInfo *txe_regs; + RegisterAccessInfo *rx_mailbox_regs; + RegisterAccessInfo *af_mask_regs_mailbox; + + uint32_t regs[XLNX_VERSAL_CANFD_R_MAX]; + + ptimer_state *canfd_timer; + + CanBusClientState bus_client; + CanBusState *canfdbus; + + struct { + uint8_t rx0_fifo; + uint8_t rx1_fifo; + uint8_t tx_fifo; + bool enable_rx_fifo1; + uint32_t ext_clk_freq; + } cfg; + +} XlnxVersalCANFDState; + +typedef struct tx_ready_reg_info { + uint32_t can_id; + uint32_t reg_num; +} tx_ready_reg_info; + +#endif diff --git a/hw/net/can/xlnx-versal-canfd.c b/hw/net/can/xlnx-versal-canfd.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/can/xlnx-versal-canfd.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx Versal CANFD device. + * + * This implementation is based on the following datasheet: + * https://docs.xilinx.com/v/u/2.0-English/pg223-canfd + * + * Copyright (c) 2023 Advanced Micro Devices, Inc. + * + * Written-by: Vikram Garhwal <vikram.garhwal@amd.com> + * + * Based on QEMU CANFD Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "hw/sysbus.h" +#include "hw/irq.h" +#include "hw/register.h" +#include "qapi/error.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/cutils.h" +#include "qemu/event_notifier.h" +#include "hw/qdev-properties.h" +#include "qom/object_interfaces.h" +#include "migration/vmstate.h" +#include "hw/net/xlnx-versal-canfd.h" +#include "trace.h" + +REG32(SOFTWARE_RESET_REGISTER, 0x0) + FIELD(SOFTWARE_RESET_REGISTER, CEN, 1, 1) + FIELD(SOFTWARE_RESET_REGISTER, SRST, 0, 1) +REG32(MODE_SELECT_REGISTER, 0x4) + FIELD(MODE_SELECT_REGISTER, ITO, 8, 8) + FIELD(MODE_SELECT_REGISTER, ABR, 7, 1) + FIELD(MODE_SELECT_REGISTER, SBR, 6, 1) + FIELD(MODE_SELECT_REGISTER, DPEE, 5, 1) + FIELD(MODE_SELECT_REGISTER, DAR, 4, 1) + FIELD(MODE_SELECT_REGISTER, BRSD, 3, 1) + FIELD(MODE_SELECT_REGISTER, SNOOP, 2, 1) + FIELD(MODE_SELECT_REGISTER, LBACK, 1, 1) + FIELD(MODE_SELECT_REGISTER, SLEEP, 0, 1) +REG32(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, 0x8) + FIELD(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, BRP, 0, 8) +REG32(ARBITRATION_PHASE_BIT_TIMING_REGISTER, 0xc) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, SJW, 16, 7) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS2, 8, 7) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS1, 0, 8) +REG32(ERROR_COUNTER_REGISTER, 0x10) + FIELD(ERROR_COUNTER_REGISTER, REC, 8, 8) + FIELD(ERROR_COUNTER_REGISTER, TEC, 0, 8) +REG32(ERROR_STATUS_REGISTER, 0x14) + FIELD(ERROR_STATUS_REGISTER, F_BERR, 11, 1) + FIELD(ERROR_STATUS_REGISTER, F_STER, 10, 1) + FIELD(ERROR_STATUS_REGISTER, F_FMER, 9, 1) + FIELD(ERROR_STATUS_REGISTER, F_CRCER, 8, 1) + FIELD(ERROR_STATUS_REGISTER, ACKER, 4, 1) + FIELD(ERROR_STATUS_REGISTER, BERR, 3, 1) + FIELD(ERROR_STATUS_REGISTER, STER, 2, 1) + FIELD(ERROR_STATUS_REGISTER, FMER, 1, 1) + FIELD(ERROR_STATUS_REGISTER, CRCER, 0, 1) +REG32(STATUS_REGISTER, 0x18) + FIELD(STATUS_REGISTER, TDCV, 16, 7) + FIELD(STATUS_REGISTER, SNOOP, 12, 1) + FIELD(STATUS_REGISTER, BSFR_CONFIG, 10, 1) + FIELD(STATUS_REGISTER, PEE_CONFIG, 9, 1) + FIELD(STATUS_REGISTER, ESTAT, 7, 2) + FIELD(STATUS_REGISTER, ERRWRN, 6, 1) + FIELD(STATUS_REGISTER, BBSY, 5, 1) + FIELD(STATUS_REGISTER, BIDLE, 4, 1) + FIELD(STATUS_REGISTER, NORMAL, 3, 1) + FIELD(STATUS_REGISTER, SLEEP, 2, 1) + FIELD(STATUS_REGISTER, LBACK, 1, 1) + FIELD(STATUS_REGISTER, CONFIG, 0, 1) +REG32(INTERRUPT_STATUS_REGISTER, 0x1c) + FIELD(INTERRUPT_STATUS_REGISTER, TXEWMFLL, 31, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXEOFLW, 30, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXBOFLW_BI, 24, 6) + FIELD(INTERRUPT_STATUS_REGISTER, RXLRM_BI, 18, 6) + FIELD(INTERRUPT_STATUS_REGISTER, RXMNF, 17, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXFWMFLL_1, 16, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXFOFLW_1, 15, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXCRS, 14, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXRRS, 13, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXFWMFLL, 12, 1) + FIELD(INTERRUPT_STATUS_REGISTER, WKUP, 11, 1) + FIELD(INTERRUPT_STATUS_REGISTER, SLP, 10, 1) + FIELD(INTERRUPT_STATUS_REGISTER, BSOFF, 9, 1) + /* + * In the original HW description below bit is named as ERROR but an ERROR + * field name collides with a macro in Windows build. To avoid Windows build + * failures, the bit is renamed to ERROR_BIT. + */ + FIELD(INTERRUPT_STATUS_REGISTER, ERROR_BIT, 8, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXFOFLW, 6, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TSCNT_OFLW, 5, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXOK, 4, 1) + FIELD(INTERRUPT_STATUS_REGISTER, BSFRD, 3, 1) + FIELD(INTERRUPT_STATUS_REGISTER, PEE, 2, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXOK, 1, 1) + FIELD(INTERRUPT_STATUS_REGISTER, ARBLST, 0, 1) +REG32(INTERRUPT_ENABLE_REGISTER, 0x20) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXEWMFLL, 31, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXEOFLW, 30, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXMNF, 17, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXFWMFLL_1, 16, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXFOFLW_1, 15, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXCRS, 14, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXRRS, 13, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXFWMFLL, 12, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EWKUP, 11, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ESLP, 10, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EBSOFF, 9, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EERROR, 8, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERFXOFLW, 6, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETSCNT_OFLW, 5, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXOK, 4, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EBSFRD, 3, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EPEE, 2, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXOK, 1, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EARBLOST, 0, 1) +REG32(INTERRUPT_CLEAR_REGISTER, 0x24) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXEWMFLL, 31, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXEOFLW, 30, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXMNF, 17, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXFWMFLL_1, 16, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXFOFLW_1, 15, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXCRS, 14, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXRRS, 13, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXFWMFLL, 12, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CWKUP, 11, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CSLP, 10, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CBSOFF, 9, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CERROR, 8, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRFXOFLW, 6, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTSCNT_OFLW, 5, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXOK, 4, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CBSFRD, 3, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CPEE, 2, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXOK, 1, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CARBLOST, 0, 1) +REG32(TIMESTAMP_REGISTER, 0x28) + FIELD(TIMESTAMP_REGISTER, TIMESTAMP_CNT, 16, 16) + FIELD(TIMESTAMP_REGISTER, CTS, 0, 1) +REG32(DATA_PHASE_BAUD_RATE_PRESCALER_REGISTER, 0x88) + FIELD(DATA_PHASE_BAUD_RATE_PRESCALER_REGISTER, TDC, 16, 1) + FIELD(DATA_PHASE_BAUD_RATE_PRESCALER_REGISTER, TDCOFF, 8, 6) + FIELD(DATA_PHASE_BAUD_RATE_PRESCALER_REGISTER, DP_BRP, 0, 8) +REG32(DATA_PHASE_BIT_TIMING_REGISTER, 0x8c) + FIELD(DATA_PHASE_BIT_TIMING_REGISTER, DP_SJW, 16, 4) + FIELD(DATA_PHASE_BIT_TIMING_REGISTER, DP_TS2, 8, 4) + FIELD(DATA_PHASE_BIT_TIMING_REGISTER, DP_TS1, 0, 5) +REG32(TX_BUFFER_READY_REQUEST_REGISTER, 0x90) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR31, 31, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR30, 30, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR29, 29, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR28, 28, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR27, 27, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR26, 26, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR25, 25, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR24, 24, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR23, 23, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR22, 22, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR21, 21, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR20, 20, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR19, 19, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR18, 18, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR17, 17, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR16, 16, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR15, 15, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR14, 14, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR13, 13, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR12, 12, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR11, 11, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR10, 10, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR9, 9, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR8, 8, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR7, 7, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR6, 6, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR5, 5, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR4, 4, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR3, 3, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR2, 2, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR1, 1, 1) + FIELD(TX_BUFFER_READY_REQUEST_REGISTER, RR0, 0, 1) +REG32(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, 0x94) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS31, 31, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS30, 30, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS29, 29, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS28, 28, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS27, 27, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS26, 26, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS25, 25, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS24, 24, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS23, 23, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS22, 22, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS21, 21, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS20, 20, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS19, 19, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS18, 18, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS17, 17, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS16, 16, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS15, 15, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS14, 14, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS13, 13, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS12, 12, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS11, 11, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS10, 10, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS9, 9, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS8, 8, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS7, 7, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS6, 6, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS5, 5, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS4, 4, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS3, 3, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS2, 2, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS1, 1, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, ERRS0, 0, 1) +REG32(TX_BUFFER_CANCEL_REQUEST_REGISTER, 0x98) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR31, 31, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR30, 30, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR29, 29, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR28, 28, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR27, 27, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR26, 26, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR25, 25, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR24, 24, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR23, 23, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR22, 22, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR21, 21, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR20, 20, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR19, 19, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR18, 18, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR17, 17, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR16, 16, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR15, 15, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR14, 14, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR13, 13, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR12, 12, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR11, 11, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR10, 10, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR9, 9, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR8, 8, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR7, 7, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR6, 6, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR5, 5, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR4, 4, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR3, 3, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR2, 2, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR1, 1, 1) + FIELD(TX_BUFFER_CANCEL_REQUEST_REGISTER, CR0, 0, 1) +REG32(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, 0x9c) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS31, 31, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS30, 30, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS29, 29, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS28, 28, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS27, 27, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS26, 26, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS25, 25, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS24, 24, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS23, 23, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS22, 22, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS21, 21, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS20, 20, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS19, 19, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS18, 18, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS17, 17, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS16, 16, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS15, 15, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS14, 14, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS13, 13, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS12, 12, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS11, 11, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS10, 10, + 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS9, 9, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS8, 8, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS7, 7, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS6, 6, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS5, 5, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS4, 4, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS3, 3, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS2, 2, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS1, 1, 1) + FIELD(INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, ECRS0, 0, 1) +REG32(TX_EVENT_FIFO_STATUS_REGISTER, 0xa0) + FIELD(TX_EVENT_FIFO_STATUS_REGISTER, TXE_FL, 8, 6) + FIELD(TX_EVENT_FIFO_STATUS_REGISTER, TXE_IRI, 7, 1) + FIELD(TX_EVENT_FIFO_STATUS_REGISTER, TXE_RI, 0, 5) +REG32(TX_EVENT_FIFO_WATERMARK_REGISTER, 0xa4) + FIELD(TX_EVENT_FIFO_WATERMARK_REGISTER, TXE_FWM, 0, 5) +REG32(ACCEPTANCE_FILTER_CONTROL_REGISTER, 0xe0) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF31, 31, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF30, 30, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF29, 29, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF28, 28, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF27, 27, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF26, 26, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF25, 25, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF24, 24, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF23, 23, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF22, 22, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF21, 21, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF20, 20, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF19, 19, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF18, 18, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF17, 17, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF16, 16, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF15, 15, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF14, 14, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF13, 13, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF12, 12, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF11, 11, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF10, 10, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF9, 9, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF8, 8, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF7, 7, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF6, 6, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF5, 5, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF4, 4, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF3, 3, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF2, 2, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF1, 1, 1) + FIELD(ACCEPTANCE_FILTER_CONTROL_REGISTER, UAF0, 0, 1) +REG32(RX_FIFO_STATUS_REGISTER, 0xe8) + FIELD(RX_FIFO_STATUS_REGISTER, FL_1, 24, 7) + FIELD(RX_FIFO_STATUS_REGISTER, IRI_1, 23, 1) + FIELD(RX_FIFO_STATUS_REGISTER, RI_1, 16, 6) + FIELD(RX_FIFO_STATUS_REGISTER, FL, 8, 7) + FIELD(RX_FIFO_STATUS_REGISTER, IRI, 7, 1) + FIELD(RX_FIFO_STATUS_REGISTER, RI, 0, 6) +REG32(RX_FIFO_WATERMARK_REGISTER, 0xec) + FIELD(RX_FIFO_WATERMARK_REGISTER, RXFP, 16, 5) + FIELD(RX_FIFO_WATERMARK_REGISTER, RXFWM_1, 8, 6) + FIELD(RX_FIFO_WATERMARK_REGISTER, RXFWM, 0, 6) +REG32(TB_ID_REGISTER, 0x100) + FIELD(TB_ID_REGISTER, ID, 21, 11) + FIELD(TB_ID_REGISTER, SRR_RTR_RRS, 20, 1) + FIELD(TB_ID_REGISTER, IDE, 19, 1) + FIELD(TB_ID_REGISTER, ID_EXT, 1, 18) + FIELD(TB_ID_REGISTER, RTR_RRS, 0, 1) +REG32(TB0_DLC_REGISTER, 0x104) + FIELD(TB0_DLC_REGISTER, DLC, 28, 4) + FIELD(TB0_DLC_REGISTER, FDF, 27, 1) + FIELD(TB0_DLC_REGISTER, BRS, 26, 1) + FIELD(TB0_DLC_REGISTER, RSVD2, 25, 1) + FIELD(TB0_DLC_REGISTER, EFC, 24, 1) + FIELD(TB0_DLC_REGISTER, MM, 16, 8) + FIELD(TB0_DLC_REGISTER, RSVD1, 0, 16) +REG32(TB_DW0_REGISTER, 0x108) + FIELD(TB_DW0_REGISTER, DATA_BYTES0, 24, 8) + FIELD(TB_DW0_REGISTER, DATA_BYTES1, 16, 8) + FIELD(TB_DW0_REGISTER, DATA_BYTES2, 8, 8) + FIELD(TB_DW0_REGISTER, DATA_BYTES3, 0, 8) +REG32(TB_DW1_REGISTER, 0x10c) + FIELD(TB_DW1_REGISTER, DATA_BYTES4, 24, 8) + FIELD(TB_DW1_REGISTER, DATA_BYTES5, 16, 8) + FIELD(TB_DW1_REGISTER, DATA_BYTES6, 8, 8) + FIELD(TB_DW1_REGISTER, DATA_BYTES7, 0, 8) +REG32(TB_DW2_REGISTER, 0x110) + FIELD(TB_DW2_REGISTER, DATA_BYTES8, 24, 8) + FIELD(TB_DW2_REGISTER, DATA_BYTES9, 16, 8) + FIELD(TB_DW2_REGISTER, DATA_BYTES10, 8, 8) + FIELD(TB_DW2_REGISTER, DATA_BYTES11, 0, 8) +REG32(TB_DW3_REGISTER, 0x114) + FIELD(TB_DW3_REGISTER, DATA_BYTES12, 24, 8) + FIELD(TB_DW3_REGISTER, DATA_BYTES13, 16, 8) + FIELD(TB_DW3_REGISTER, DATA_BYTES14, 8, 8) + FIELD(TB_DW3_REGISTER, DATA_BYTES15, 0, 8) +REG32(TB_DW4_REGISTER, 0x118) + FIELD(TB_DW4_REGISTER, DATA_BYTES16, 24, 8) + FIELD(TB_DW4_REGISTER, DATA_BYTES17, 16, 8) + FIELD(TB_DW4_REGISTER, DATA_BYTES18, 8, 8) + FIELD(TB_DW4_REGISTER, DATA_BYTES19, 0, 8) +REG32(TB_DW5_REGISTER, 0x11c) + FIELD(TB_DW5_REGISTER, DATA_BYTES20, 24, 8) + FIELD(TB_DW5_REGISTER, DATA_BYTES21, 16, 8) + FIELD(TB_DW5_REGISTER, DATA_BYTES22, 8, 8) + FIELD(TB_DW5_REGISTER, DATA_BYTES23, 0, 8) +REG32(TB_DW6_REGISTER, 0x120) + FIELD(TB_DW6_REGISTER, DATA_BYTES24, 24, 8) + FIELD(TB_DW6_REGISTER, DATA_BYTES25, 16, 8) + FIELD(TB_DW6_REGISTER, DATA_BYTES26, 8, 8) + FIELD(TB_DW6_REGISTER, DATA_BYTES27, 0, 8) +REG32(TB_DW7_REGISTER, 0x124) + FIELD(TB_DW7_REGISTER, DATA_BYTES28, 24, 8) + FIELD(TB_DW7_REGISTER, DATA_BYTES29, 16, 8) + FIELD(TB_DW7_REGISTER, DATA_BYTES30, 8, 8) + FIELD(TB_DW7_REGISTER, DATA_BYTES31, 0, 8) +REG32(TB_DW8_REGISTER, 0x128) + FIELD(TB_DW8_REGISTER, DATA_BYTES32, 24, 8) + FIELD(TB_DW8_REGISTER, DATA_BYTES33, 16, 8) + FIELD(TB_DW8_REGISTER, DATA_BYTES34, 8, 8) + FIELD(TB_DW8_REGISTER, DATA_BYTES35, 0, 8) +REG32(TB_DW9_REGISTER, 0x12c) + FIELD(TB_DW9_REGISTER, DATA_BYTES36, 24, 8) + FIELD(TB_DW9_REGISTER, DATA_BYTES37, 16, 8) + FIELD(TB_DW9_REGISTER, DATA_BYTES38, 8, 8) + FIELD(TB_DW9_REGISTER, DATA_BYTES39, 0, 8) +REG32(TB_DW10_REGISTER, 0x130) + FIELD(TB_DW10_REGISTER, DATA_BYTES40, 24, 8) + FIELD(TB_DW10_REGISTER, DATA_BYTES41, 16, 8) + FIELD(TB_DW10_REGISTER, DATA_BYTES42, 8, 8) + FIELD(TB_DW10_REGISTER, DATA_BYTES43, 0, 8) +REG32(TB_DW11_REGISTER, 0x134) + FIELD(TB_DW11_REGISTER, DATA_BYTES44, 24, 8) + FIELD(TB_DW11_REGISTER, DATA_BYTES45, 16, 8) + FIELD(TB_DW11_REGISTER, DATA_BYTES46, 8, 8) + FIELD(TB_DW11_REGISTER, DATA_BYTES47, 0, 8) +REG32(TB_DW12_REGISTER, 0x138) + FIELD(TB_DW12_REGISTER, DATA_BYTES48, 24, 8) + FIELD(TB_DW12_REGISTER, DATA_BYTES49, 16, 8) + FIELD(TB_DW12_REGISTER, DATA_BYTES50, 8, 8) + FIELD(TB_DW12_REGISTER, DATA_BYTES51, 0, 8) +REG32(TB_DW13_REGISTER, 0x13c) + FIELD(TB_DW13_REGISTER, DATA_BYTES52, 24, 8) + FIELD(TB_DW13_REGISTER, DATA_BYTES53, 16, 8) + FIELD(TB_DW13_REGISTER, DATA_BYTES54, 8, 8) + FIELD(TB_DW13_REGISTER, DATA_BYTES55, 0, 8) +REG32(TB_DW14_REGISTER, 0x140) + FIELD(TB_DW14_REGISTER, DATA_BYTES56, 24, 8) + FIELD(TB_DW14_REGISTER, DATA_BYTES57, 16, 8) + FIELD(TB_DW14_REGISTER, DATA_BYTES58, 8, 8) + FIELD(TB_DW14_REGISTER, DATA_BYTES59, 0, 8) +REG32(TB_DW15_REGISTER, 0x144) + FIELD(TB_DW15_REGISTER, DATA_BYTES60, 24, 8) + FIELD(TB_DW15_REGISTER, DATA_BYTES61, 16, 8) + FIELD(TB_DW15_REGISTER, DATA_BYTES62, 8, 8) + FIELD(TB_DW15_REGISTER, DATA_BYTES63, 0, 8) +REG32(AFMR_REGISTER, 0xa00) + FIELD(AFMR_REGISTER, AMID, 21, 11) + FIELD(AFMR_REGISTER, AMSRR, 20, 1) + FIELD(AFMR_REGISTER, AMIDE, 19, 1) + FIELD(AFMR_REGISTER, AMID_EXT, 1, 18) + FIELD(AFMR_REGISTER, AMRTR, 0, 1) +REG32(AFIR_REGISTER, 0xa04) + FIELD(AFIR_REGISTER, AIID, 21, 11) + FIELD(AFIR_REGISTER, AISRR, 20, 1) + FIELD(AFIR_REGISTER, AIIDE, 19, 1) + FIELD(AFIR_REGISTER, AIID_EXT, 1, 18) + FIELD(AFIR_REGISTER, AIRTR, 0, 1) +REG32(TXE_FIFO_TB_ID_REGISTER, 0x2000) + FIELD(TXE_FIFO_TB_ID_REGISTER, ID, 21, 11) + FIELD(TXE_FIFO_TB_ID_REGISTER, SRR_RTR_RRS, 20, 1) + FIELD(TXE_FIFO_TB_ID_REGISTER, IDE, 19, 1) + FIELD(TXE_FIFO_TB_ID_REGISTER, ID_EXT, 1, 18) + FIELD(TXE_FIFO_TB_ID_REGISTER, RTR_RRS, 0, 1) +REG32(TXE_FIFO_TB_DLC_REGISTER, 0x2004) + FIELD(TXE_FIFO_TB_DLC_REGISTER, DLC, 28, 4) + FIELD(TXE_FIFO_TB_DLC_REGISTER, FDF, 27, 1) + FIELD(TXE_FIFO_TB_DLC_REGISTER, BRS, 26, 1) + FIELD(TXE_FIFO_TB_DLC_REGISTER, ET, 24, 2) + FIELD(TXE_FIFO_TB_DLC_REGISTER, MM, 16, 8) + FIELD(TXE_FIFO_TB_DLC_REGISTER, TIMESTAMP, 0, 16) +REG32(RB_ID_REGISTER, 0x2100) + FIELD(RB_ID_REGISTER, ID, 21, 11) + FIELD(RB_ID_REGISTER, SRR_RTR_RRS, 20, 1) + FIELD(RB_ID_REGISTER, IDE, 19, 1) + FIELD(RB_ID_REGISTER, ID_EXT, 1, 18) + FIELD(RB_ID_REGISTER, RTR_RRS, 0, 1) +REG32(RB_DLC_REGISTER, 0x2104) + FIELD(RB_DLC_REGISTER, DLC, 28, 4) + FIELD(RB_DLC_REGISTER, FDF, 27, 1) + FIELD(RB_DLC_REGISTER, BRS, 26, 1) + FIELD(RB_DLC_REGISTER, ESI, 25, 1) + FIELD(RB_DLC_REGISTER, MATCHED_FILTER_INDEX, 16, 5) + FIELD(RB_DLC_REGISTER, TIMESTAMP, 0, 16) +REG32(RB_DW0_REGISTER, 0x2108) + FIELD(RB_DW0_REGISTER, DATA_BYTES0, 24, 8) + FIELD(RB_DW0_REGISTER, DATA_BYTES1, 16, 8) + FIELD(RB_DW0_REGISTER, DATA_BYTES2, 8, 8) + FIELD(RB_DW0_REGISTER, DATA_BYTES3, 0, 8) +REG32(RB_DW1_REGISTER, 0x210c) + FIELD(RB_DW1_REGISTER, DATA_BYTES4, 24, 8) + FIELD(RB_DW1_REGISTER, DATA_BYTES5, 16, 8) + FIELD(RB_DW1_REGISTER, DATA_BYTES6, 8, 8) + FIELD(RB_DW1_REGISTER, DATA_BYTES7, 0, 8) +REG32(RB_DW2_REGISTER, 0x2110) + FIELD(RB_DW2_REGISTER, DATA_BYTES8, 24, 8) + FIELD(RB_DW2_REGISTER, DATA_BYTES9, 16, 8) + FIELD(RB_DW2_REGISTER, DATA_BYTES10, 8, 8) + FIELD(RB_DW2_REGISTER, DATA_BYTES11, 0, 8) +REG32(RB_DW3_REGISTER, 0x2114) + FIELD(RB_DW3_REGISTER, DATA_BYTES12, 24, 8) + FIELD(RB_DW3_REGISTER, DATA_BYTES13, 16, 8) + FIELD(RB_DW3_REGISTER, DATA_BYTES14, 8, 8) + FIELD(RB_DW3_REGISTER, DATA_BYTES15, 0, 8) +REG32(RB_DW4_REGISTER, 0x2118) + FIELD(RB_DW4_REGISTER, DATA_BYTES16, 24, 8) + FIELD(RB_DW4_REGISTER, DATA_BYTES17, 16, 8) + FIELD(RB_DW4_REGISTER, DATA_BYTES18, 8, 8) + FIELD(RB_DW4_REGISTER, DATA_BYTES19, 0, 8) +REG32(RB_DW5_REGISTER, 0x211c) + FIELD(RB_DW5_REGISTER, DATA_BYTES20, 24, 8) + FIELD(RB_DW5_REGISTER, DATA_BYTES21, 16, 8) + FIELD(RB_DW5_REGISTER, DATA_BYTES22, 8, 8) + FIELD(RB_DW5_REGISTER, DATA_BYTES23, 0, 8) +REG32(RB_DW6_REGISTER, 0x2120) + FIELD(RB_DW6_REGISTER, DATA_BYTES24, 24, 8) + FIELD(RB_DW6_REGISTER, DATA_BYTES25, 16, 8) + FIELD(RB_DW6_REGISTER, DATA_BYTES26, 8, 8) + FIELD(RB_DW6_REGISTER, DATA_BYTES27, 0, 8) +REG32(RB_DW7_REGISTER, 0x2124) + FIELD(RB_DW7_REGISTER, DATA_BYTES28, 24, 8) + FIELD(RB_DW7_REGISTER, DATA_BYTES29, 16, 8) + FIELD(RB_DW7_REGISTER, DATA_BYTES30, 8, 8) + FIELD(RB_DW7_REGISTER, DATA_BYTES31, 0, 8) +REG32(RB_DW8_REGISTER, 0x2128) + FIELD(RB_DW8_REGISTER, DATA_BYTES32, 24, 8) + FIELD(RB_DW8_REGISTER, DATA_BYTES33, 16, 8) + FIELD(RB_DW8_REGISTER, DATA_BYTES34, 8, 8) + FIELD(RB_DW8_REGISTER, DATA_BYTES35, 0, 8) +REG32(RB_DW9_REGISTER, 0x212c) + FIELD(RB_DW9_REGISTER, DATA_BYTES36, 24, 8) + FIELD(RB_DW9_REGISTER, DATA_BYTES37, 16, 8) + FIELD(RB_DW9_REGISTER, DATA_BYTES38, 8, 8) + FIELD(RB_DW9_REGISTER, DATA_BYTES39, 0, 8) +REG32(RB_DW10_REGISTER, 0x2130) + FIELD(RB_DW10_REGISTER, DATA_BYTES40, 24, 8) + FIELD(RB_DW10_REGISTER, DATA_BYTES41, 16, 8) + FIELD(RB_DW10_REGISTER, DATA_BYTES42, 8, 8) + FIELD(RB_DW10_REGISTER, DATA_BYTES43, 0, 8) +REG32(RB_DW11_REGISTER, 0x2134) + FIELD(RB_DW11_REGISTER, DATA_BYTES44, 24, 8) + FIELD(RB_DW11_REGISTER, DATA_BYTES45, 16, 8) + FIELD(RB_DW11_REGISTER, DATA_BYTES46, 8, 8) + FIELD(RB_DW11_REGISTER, DATA_BYTES47, 0, 8) +REG32(RB_DW12_REGISTER, 0x2138) + FIELD(RB_DW12_REGISTER, DATA_BYTES48, 24, 8) + FIELD(RB_DW12_REGISTER, DATA_BYTES49, 16, 8) + FIELD(RB_DW12_REGISTER, DATA_BYTES50, 8, 8) + FIELD(RB_DW12_REGISTER, DATA_BYTES51, 0, 8) +REG32(RB_DW13_REGISTER, 0x213c) + FIELD(RB_DW13_REGISTER, DATA_BYTES52, 24, 8) + FIELD(RB_DW13_REGISTER, DATA_BYTES53, 16, 8) + FIELD(RB_DW13_REGISTER, DATA_BYTES54, 8, 8) + FIELD(RB_DW13_REGISTER, DATA_BYTES55, 0, 8) +REG32(RB_DW14_REGISTER, 0x2140) + FIELD(RB_DW14_REGISTER, DATA_BYTES56, 24, 8) + FIELD(RB_DW14_REGISTER, DATA_BYTES57, 16, 8) + FIELD(RB_DW14_REGISTER, DATA_BYTES58, 8, 8) + FIELD(RB_DW14_REGISTER, DATA_BYTES59, 0, 8) +REG32(RB_DW15_REGISTER, 0x2144) + FIELD(RB_DW15_REGISTER, DATA_BYTES60, 24, 8) + FIELD(RB_DW15_REGISTER, DATA_BYTES61, 16, 8) + FIELD(RB_DW15_REGISTER, DATA_BYTES62, 8, 8) + FIELD(RB_DW15_REGISTER, DATA_BYTES63, 0, 8) +REG32(RB_ID_REGISTER_1, 0x4100) + FIELD(RB_ID_REGISTER_1, ID, 21, 11) + FIELD(RB_ID_REGISTER_1, SRR_RTR_RRS, 20, 1) + FIELD(RB_ID_REGISTER_1, IDE, 19, 1) + FIELD(RB_ID_REGISTER_1, ID_EXT, 1, 18) + FIELD(RB_ID_REGISTER_1, RTR_RRS, 0, 1) +REG32(RB_DLC_REGISTER_1, 0x4104) + FIELD(RB_DLC_REGISTER_1, DLC, 28, 4) + FIELD(RB_DLC_REGISTER_1, FDF, 27, 1) + FIELD(RB_DLC_REGISTER_1, BRS, 26, 1) + FIELD(RB_DLC_REGISTER_1, ESI, 25, 1) + FIELD(RB_DLC_REGISTER_1, MATCHED_FILTER_INDEX, 16, 5) + FIELD(RB_DLC_REGISTER_1, TIMESTAMP, 0, 16) +REG32(RB0_DW0_REGISTER_1, 0x4108) + FIELD(RB0_DW0_REGISTER_1, DATA_BYTES0, 24, 8) + FIELD(RB0_DW0_REGISTER_1, DATA_BYTES1, 16, 8) + FIELD(RB0_DW0_REGISTER_1, DATA_BYTES2, 8, 8) + FIELD(RB0_DW0_REGISTER_1, DATA_BYTES3, 0, 8) +REG32(RB_DW1_REGISTER_1, 0x410c) + FIELD(RB_DW1_REGISTER_1, DATA_BYTES4, 24, 8) + FIELD(RB_DW1_REGISTER_1, DATA_BYTES5, 16, 8) + FIELD(RB_DW1_REGISTER_1, DATA_BYTES6, 8, 8) + FIELD(RB_DW1_REGISTER_1, DATA_BYTES7, 0, 8) +REG32(RB_DW2_REGISTER_1, 0x4110) + FIELD(RB_DW2_REGISTER_1, DATA_BYTES8, 24, 8) + FIELD(RB_DW2_REGISTER_1, DATA_BYTES9, 16, 8) + FIELD(RB_DW2_REGISTER_1, DATA_BYTES10, 8, 8) + FIELD(RB_DW2_REGISTER_1, DATA_BYTES11, 0, 8) +REG32(RB_DW3_REGISTER_1, 0x4114) + FIELD(RB_DW3_REGISTER_1, DATA_BYTES12, 24, 8) + FIELD(RB_DW3_REGISTER_1, DATA_BYTES13, 16, 8) + FIELD(RB_DW3_REGISTER_1, DATA_BYTES14, 8, 8) + FIELD(RB_DW3_REGISTER_1, DATA_BYTES15, 0, 8) +REG32(RB_DW4_REGISTER_1, 0x4118) + FIELD(RB_DW4_REGISTER_1, DATA_BYTES16, 24, 8) + FIELD(RB_DW4_REGISTER_1, DATA_BYTES17, 16, 8) + FIELD(RB_DW4_REGISTER_1, DATA_BYTES18, 8, 8) + FIELD(RB_DW4_REGISTER_1, DATA_BYTES19, 0, 8) +REG32(RB_DW5_REGISTER_1, 0x411c) + FIELD(RB_DW5_REGISTER_1, DATA_BYTES20, 24, 8) + FIELD(RB_DW5_REGISTER_1, DATA_BYTES21, 16, 8) + FIELD(RB_DW5_REGISTER_1, DATA_BYTES22, 8, 8) + FIELD(RB_DW5_REGISTER_1, DATA_BYTES23, 0, 8) +REG32(RB_DW6_REGISTER_1, 0x4120) + FIELD(RB_DW6_REGISTER_1, DATA_BYTES24, 24, 8) + FIELD(RB_DW6_REGISTER_1, DATA_BYTES25, 16, 8) + FIELD(RB_DW6_REGISTER_1, DATA_BYTES26, 8, 8) + FIELD(RB_DW6_REGISTER_1, DATA_BYTES27, 0, 8) +REG32(RB_DW7_REGISTER_1, 0x4124) + FIELD(RB_DW7_REGISTER_1, DATA_BYTES28, 24, 8) + FIELD(RB_DW7_REGISTER_1, DATA_BYTES29, 16, 8) + FIELD(RB_DW7_REGISTER_1, DATA_BYTES30, 8, 8) + FIELD(RB_DW7_REGISTER_1, DATA_BYTES31, 0, 8) +REG32(RB_DW8_REGISTER_1, 0x4128) + FIELD(RB_DW8_REGISTER_1, DATA_BYTES32, 24, 8) + FIELD(RB_DW8_REGISTER_1, DATA_BYTES33, 16, 8) + FIELD(RB_DW8_REGISTER_1, DATA_BYTES34, 8, 8) + FIELD(RB_DW8_REGISTER_1, DATA_BYTES35, 0, 8) +REG32(RB_DW9_REGISTER_1, 0x412c) + FIELD(RB_DW9_REGISTER_1, DATA_BYTES36, 24, 8) + FIELD(RB_DW9_REGISTER_1, DATA_BYTES37, 16, 8) + FIELD(RB_DW9_REGISTER_1, DATA_BYTES38, 8, 8) + FIELD(RB_DW9_REGISTER_1, DATA_BYTES39, 0, 8) +REG32(RB_DW10_REGISTER_1, 0x4130) + FIELD(RB_DW10_REGISTER_1, DATA_BYTES40, 24, 8) + FIELD(RB_DW10_REGISTER_1, DATA_BYTES41, 16, 8) + FIELD(RB_DW10_REGISTER_1, DATA_BYTES42, 8, 8) + FIELD(RB_DW10_REGISTER_1, DATA_BYTES43, 0, 8) +REG32(RB_DW11_REGISTER_1, 0x4134) + FIELD(RB_DW11_REGISTER_1, DATA_BYTES44, 24, 8) + FIELD(RB_DW11_REGISTER_1, DATA_BYTES45, 16, 8) + FIELD(RB_DW11_REGISTER_1, DATA_BYTES46, 8, 8) + FIELD(RB_DW11_REGISTER_1, DATA_BYTES47, 0, 8) +REG32(RB_DW12_REGISTER_1, 0x4138) + FIELD(RB_DW12_REGISTER_1, DATA_BYTES48, 24, 8) + FIELD(RB_DW12_REGISTER_1, DATA_BYTES49, 16, 8) + FIELD(RB_DW12_REGISTER_1, DATA_BYTES50, 8, 8) + FIELD(RB_DW12_REGISTER_1, DATA_BYTES51, 0, 8) +REG32(RB_DW13_REGISTER_1, 0x413c) + FIELD(RB_DW13_REGISTER_1, DATA_BYTES52, 24, 8) + FIELD(RB_DW13_REGISTER_1, DATA_BYTES53, 16, 8) + FIELD(RB_DW13_REGISTER_1, DATA_BYTES54, 8, 8) + FIELD(RB_DW13_REGISTER_1, DATA_BYTES55, 0, 8) +REG32(RB_DW14_REGISTER_1, 0x4140) + FIELD(RB_DW14_REGISTER_1, DATA_BYTES56, 24, 8) + FIELD(RB_DW14_REGISTER_1, DATA_BYTES57, 16, 8) + FIELD(RB_DW14_REGISTER_1, DATA_BYTES58, 8, 8) + FIELD(RB_DW14_REGISTER_1, DATA_BYTES59, 0, 8) +REG32(RB_DW15_REGISTER_1, 0x4144) + FIELD(RB_DW15_REGISTER_1, DATA_BYTES60, 24, 8) + FIELD(RB_DW15_REGISTER_1, DATA_BYTES61, 16, 8) + FIELD(RB_DW15_REGISTER_1, DATA_BYTES62, 8, 8) + FIELD(RB_DW15_REGISTER_1, DATA_BYTES63, 0, 8) + +static uint8_t canfd_dlc_array[8] = {8, 12, 16, 20, 24, 32, 48, 64}; + +static void canfd_update_irq(XlnxVersalCANFDState *s) +{ + unsigned int irq = s->regs[R_INTERRUPT_STATUS_REGISTER] & + s->regs[R_INTERRUPT_ENABLE_REGISTER]; + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + /* RX watermark interrupts. */ + if (ARRAY_FIELD_EX32(s->regs, RX_FIFO_STATUS_REGISTER, FL) > + ARRAY_FIELD_EX32(s->regs, RX_FIFO_WATERMARK_REGISTER, RXFWM)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFWMFLL, 1); + } + + if (ARRAY_FIELD_EX32(s->regs, RX_FIFO_STATUS_REGISTER, FL_1) > + ARRAY_FIELD_EX32(s->regs, RX_FIFO_WATERMARK_REGISTER, RXFWM_1)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFWMFLL_1, 1); + } + + /* TX watermark interrupt. */ + if (ARRAY_FIELD_EX32(s->regs, TX_EVENT_FIFO_STATUS_REGISTER, TXE_FL) > + ARRAY_FIELD_EX32(s->regs, TX_EVENT_FIFO_WATERMARK_REGISTER, TXE_FWM)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXEWMFLL, 1); + } + + trace_xlnx_canfd_update_irq(path, s->regs[R_INTERRUPT_STATUS_REGISTER], + s->regs[R_INTERRUPT_ENABLE_REGISTER], irq); + + qemu_set_irq(s->irq_canfd_int, irq); +} + +static void canfd_ier_post_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + + canfd_update_irq(s); +} + +static uint64_t canfd_icr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + uint32_t val = val64; + + s->regs[R_INTERRUPT_STATUS_REGISTER] &= ~val; + + /* + * RXBOFLW_BI field is automatically cleared to default if RXBOFLW bit is + * cleared in ISR. + */ + if (ARRAY_FIELD_EX32(s->regs, INTERRUPT_STATUS_REGISTER, RXFWMFLL_1)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXBOFLW_BI, 0); + } + + canfd_update_irq(s); + + return 0; +} + +static void canfd_config_reset(XlnxVersalCANFDState *s) +{ + + unsigned int i; + + /* Reset all the configuration registers. */ + for (i = 0; i < R_RX_FIFO_WATERMARK_REGISTER; ++i) { + register_reset(&s->reg_info[i]); + } + + canfd_update_irq(s); +} + +static void canfd_config_mode(XlnxVersalCANFDState *s) +{ + register_reset(&s->reg_info[R_ERROR_COUNTER_REGISTER]); + register_reset(&s->reg_info[R_ERROR_STATUS_REGISTER]); + register_reset(&s->reg_info[R_STATUS_REGISTER]); + + /* Put XlnxVersalCANFDState in configuration mode. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, BSOFF, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ERROR_BIT, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFOFLW, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFOFLW_1, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ARBLST, 0); + + /* Clear the time stamp. */ + ptimer_transaction_begin(s->canfd_timer); + ptimer_set_count(s->canfd_timer, 0); + ptimer_transaction_commit(s->canfd_timer); + + canfd_update_irq(s); +} + +static void update_status_register_mode_bits(XlnxVersalCANFDState *s) +{ + bool sleep_status = ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP); + bool sleep_mode = ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP); + /* Wake up interrupt bit. */ + bool wakeup_irq_val = !sleep_mode && sleep_status; + /* Sleep interrupt bit. */ + bool sleep_irq_val = sleep_mode && !sleep_status; + + /* Clear previous core mode status bits. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 0); + + /* set current mode bit and generate irqs accordingly. */ + if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, LBACK)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 1); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, + sleep_irq_val); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SNOOP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 1); + } else { + /* If all bits are zero, XlnxVersalCANFDState is set in normal mode. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 1); + /* Set wakeup interrupt bit. */ + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, + wakeup_irq_val); + } + + /* Put the CANFD in error active state. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, ESTAT, 1); + + canfd_update_irq(s); +} + +static uint64_t canfd_msr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + uint32_t val = val64; + uint8_t multi_mode = 0; + + /* + * Multiple mode set check. This is done to make sure user doesn't set + * multiple modes. + */ + multi_mode = FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP); + + if (multi_mode > 1) { + qemu_log_mask(LOG_GUEST_ERROR, "Attempting to configure several modes" + " simultaneously. One mode will be selected according to" + " their priority: LBACK > SLEEP > SNOOP.\n"); + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + /* In configuration mode, any mode can be selected. */ + s->regs[R_MODE_SELECT_REGISTER] = val; + } else { + bool sleep_mode_bit = FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP); + + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, sleep_mode_bit); + + if (FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK)) { + qemu_log_mask(LOG_GUEST_ERROR, "Attempting to set LBACK mode" + " without setting CEN bit as 0\n"); + } else if (FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP)) { + qemu_log_mask(LOG_GUEST_ERROR, "Attempting to set SNOOP mode" + " without setting CEN bit as 0\n"); + } + + update_status_register_mode_bits(s); + } + + return s->regs[R_MODE_SELECT_REGISTER]; +} + +static void canfd_exit_sleep_mode(XlnxVersalCANFDState *s) +{ + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, 0); + update_status_register_mode_bits(s); +} + +static void regs2frame(XlnxVersalCANFDState *s, qemu_can_frame *frame, + uint32_t reg_num) +{ + uint32_t i = 0; + uint32_t j = 0; + uint32_t val = 0; + uint32_t dlc_reg_val = 0; + uint32_t dlc_value = 0; + + /* Check that reg_num should be within TX register space. */ + assert(reg_num <= R_TB_ID_REGISTER + (NUM_REGS_PER_MSG_SPACE * + s->cfg.tx_fifo)); + + dlc_reg_val = s->regs[reg_num + 1]; + dlc_value = FIELD_EX32(dlc_reg_val, TB0_DLC_REGISTER, DLC); + + frame->can_id = s->regs[reg_num]; + + if (FIELD_EX32(dlc_reg_val, TB0_DLC_REGISTER, FDF)) { + /* + * CANFD frame. + * Converting dlc(0 to 15) 4 Byte data to plain length(i.e. 0 to 64) + * 1 Byte data. This is done to make it work with SocketCAN. + * On actual CANFD frame, this value can't be more than 0xF. + * Conversion table for DLC to plain length: + * + * DLC Plain Length + * 0 - 8 0 - 8 + * 9 9 - 12 + * 10 13 - 16 + * 11 17 - 20 + * 12 21 - 24 + * 13 25 - 32 + * 14 33 - 48 + * 15 49 - 64 + */ + + frame->flags = QEMU_CAN_FRMF_TYPE_FD; + + if (dlc_value < 8) { + frame->can_dlc = dlc_value; + } else { + assert((dlc_value - 8) < ARRAY_SIZE(canfd_dlc_array)); + frame->can_dlc = canfd_dlc_array[dlc_value - 8]; + } + } else { + /* + * FD Format bit not set that means it is a CAN Frame. + * Conversion table for classic CAN: + * + * DLC Plain Length + * 0 - 7 0 - 7 + * 8 - 15 8 + */ + + if (dlc_value > 8) { + frame->can_dlc = 8; + qemu_log_mask(LOG_GUEST_ERROR, "Maximum DLC value for Classic CAN" + " frame is 8. Only 8 byte data will be sent.\n"); + } else { + frame->can_dlc = dlc_value; + } + } + + for (j = 0; j < frame->can_dlc; j++) { + val = 8 * i; + + frame->data[j] = extract32(s->regs[reg_num + 2 + (j / 4)], val, 8); + i++; + + if (i % 4 == 0) { + i = 0; + } + } +} + +static void process_cancellation_requests(XlnxVersalCANFDState *s) +{ + uint32_t clear_mask = s->regs[R_TX_BUFFER_READY_REQUEST_REGISTER] & + s->regs[R_TX_BUFFER_CANCEL_REQUEST_REGISTER]; + + s->regs[R_TX_BUFFER_READY_REQUEST_REGISTER] &= ~clear_mask; + s->regs[R_TX_BUFFER_CANCEL_REQUEST_REGISTER] &= ~clear_mask; + + canfd_update_irq(s); +} + +static void store_rx_sequential(XlnxVersalCANFDState *s, + const qemu_can_frame *frame, + uint32_t fill_level, uint32_t read_index, + uint32_t store_location, uint8_t rx_fifo, + bool rx_fifo_id, uint8_t filter_index) +{ + int i; + bool is_canfd_frame; + uint8_t dlc = frame->can_dlc; + uint8_t rx_reg_num = 0; + uint32_t dlc_reg_val = 0; + uint32_t data_reg_val = 0; + + /* Getting RX0/1 fill level */ + if ((fill_level) > rx_fifo - 1) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: RX%d Buffer is full. Discarding the" + " message\n", path, rx_fifo_id); + + /* Set the corresponding RF buffer overflow interrupt. */ + if (rx_fifo_id == 0) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFOFLW, 1); + } else { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFOFLW_1, 1); + } + } else { + uint16_t rx_timestamp = CANFD_TIMER_MAX - + ptimer_get_count(s->canfd_timer); + + if (rx_timestamp == 0xFFFF) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TSCNT_OFLW, 1); + } else { + ARRAY_FIELD_DP32(s->regs, TIMESTAMP_REGISTER, TIMESTAMP_CNT, + rx_timestamp); + } + + if (rx_fifo_id == 0) { + ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, FL, + fill_level + 1); + assert(store_location <= + R_RB_ID_REGISTER + (s->cfg.rx0_fifo * + NUM_REGS_PER_MSG_SPACE)); + } else { + ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, FL_1, + fill_level + 1); + assert(store_location <= + R_RB_ID_REGISTER_1 + (s->cfg.rx1_fifo * + NUM_REGS_PER_MSG_SPACE)); + } + + s->regs[store_location] = frame->can_id; + + dlc = frame->can_dlc; + + if (frame->flags == QEMU_CAN_FRMF_TYPE_FD) { + is_canfd_frame = true; + + /* Store dlc value in Xilinx specific format. */ + for (i = 0; i < ARRAY_SIZE(canfd_dlc_array); i++) { + if (canfd_dlc_array[i] == frame->can_dlc) { + dlc_reg_val = FIELD_DP32(0, RB_DLC_REGISTER, DLC, 8 + i); + } + } + } else { + is_canfd_frame = false; + + if (frame->can_dlc > 8) { + dlc = 8; + } + + dlc_reg_val = FIELD_DP32(0, RB_DLC_REGISTER, DLC, dlc); + } + + dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, FDF, is_canfd_frame); + dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, TIMESTAMP, rx_timestamp); + dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, MATCHED_FILTER_INDEX, + filter_index); + s->regs[store_location + 1] = dlc_reg_val; + + for (i = 0; i < dlc; i++) { + /* Register size is 4 byte but frame->data each is 1 byte. */ + switch (i % 4) { + case 0: + rx_reg_num = i / 4; + + data_reg_val = FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES3, + frame->data[i]); + break; + case 1: + data_reg_val |= FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES2, + frame->data[i]); + break; + case 2: + data_reg_val |= FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES1, + frame->data[i]); + break; + case 3: + data_reg_val |= FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES0, + frame->data[i]); + /* + * Last Bytes data which means we have all 4 bytes ready to + * store in one rx regs. + */ + s->regs[store_location + rx_reg_num + 2] = data_reg_val; + break; + } + } + + if (i % 4) { + /* + * In case DLC is not multiplier of 4, data is not saved to RX FIFO + * in above switch case. Store the remaining bytes here. + */ + s->regs[store_location + rx_reg_num + 2] = data_reg_val; + } + + /* set the interrupt as RXOK. */ + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 1); + } +} + +static void update_rx_sequential(XlnxVersalCANFDState *s, + const qemu_can_frame *frame) +{ + bool filter_pass = false; + uint8_t filter_index = 0; + int i; + int filter_partition = ARRAY_FIELD_EX32(s->regs, + RX_FIFO_WATERMARK_REGISTER, RXFP); + uint32_t store_location; + uint32_t fill_level; + uint32_t read_index; + uint8_t store_index = 0; + g_autofree char *path = NULL; + /* + * If all UAF bits are set to 0, then received messages are not stored + * in the RX buffers. + */ + if (s->regs[R_ACCEPTANCE_FILTER_CONTROL_REGISTER]) { + uint32_t acceptance_filter_status = + s->regs[R_ACCEPTANCE_FILTER_CONTROL_REGISTER]; + + for (i = 0; i < 32; i++) { + if (acceptance_filter_status & 0x1) { + uint32_t msg_id_masked = s->regs[R_AFMR_REGISTER + 2 * i] & + frame->can_id; + uint32_t afir_id_masked = s->regs[R_AFIR_REGISTER + 2 * i] & + s->regs[R_AFMR_REGISTER + 2 * i]; + uint16_t std_msg_id_masked = FIELD_EX32(msg_id_masked, + AFIR_REGISTER, AIID); + uint16_t std_afir_id_masked = FIELD_EX32(afir_id_masked, + AFIR_REGISTER, AIID); + uint32_t ext_msg_id_masked = FIELD_EX32(msg_id_masked, + AFIR_REGISTER, + AIID_EXT); + uint32_t ext_afir_id_masked = FIELD_EX32(afir_id_masked, + AFIR_REGISTER, + AIID_EXT); + bool ext_ide = FIELD_EX32(s->regs[R_AFMR_REGISTER + 2 * i], + AFMR_REGISTER, AMIDE); + + if (std_msg_id_masked == std_afir_id_masked) { + if (ext_ide) { + /* Extended message ID message. */ + if (ext_msg_id_masked == ext_afir_id_masked) { + filter_pass = true; + filter_index = i; + + break; + } + } else { + /* Standard message ID. */ + filter_pass = true; + filter_index = i; + + break; + } + } + } + acceptance_filter_status >>= 1; + } + } + + if (!filter_pass) { + path = object_get_canonical_path(OBJECT(s)); + + trace_xlnx_canfd_rx_fifo_filter_reject(path, frame->can_id, + frame->can_dlc); + } else { + if (filter_index <= filter_partition) { + fill_level = ARRAY_FIELD_EX32(s->regs, RX_FIFO_STATUS_REGISTER, FL); + read_index = ARRAY_FIELD_EX32(s->regs, RX_FIFO_STATUS_REGISTER, RI); + store_index = read_index + fill_level; + + if (read_index == s->cfg.rx0_fifo - 1) { + /* + * When ri is s->cfg.rx0_fifo - 1 i.e. max, it goes cyclic that + * means we reset the ri to 0x0. + */ + read_index = 0; + ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, RI, + read_index); + } + + if (store_index > s->cfg.rx0_fifo - 1) { + store_index -= s->cfg.rx0_fifo - 1; + } + + store_location = R_RB_ID_REGISTER + + (store_index * NUM_REGS_PER_MSG_SPACE); + + store_rx_sequential(s, frame, fill_level, read_index, + store_location, s->cfg.rx0_fifo, 0, + filter_index); + } else { + /* RX 1 fill level message */ + fill_level = ARRAY_FIELD_EX32(s->regs, RX_FIFO_STATUS_REGISTER, + FL_1); + read_index = ARRAY_FIELD_EX32(s->regs, RX_FIFO_STATUS_REGISTER, + RI_1); + store_index = read_index + fill_level; + + if (read_index == s->cfg.rx1_fifo - 1) { + /* + * When ri is s->cfg.rx1_fifo - 1 i.e. max, it goes cyclic that + * means we reset the ri to 0x0. + */ + read_index = 0; + ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, RI_1, + read_index); + } + + if (store_index > s->cfg.rx1_fifo - 1) { + store_index -= s->cfg.rx1_fifo - 1; + } + + store_location = R_RB_ID_REGISTER_1 + + (store_index * NUM_REGS_PER_MSG_SPACE); + + store_rx_sequential(s, frame, fill_level, read_index, + store_location, s->cfg.rx1_fifo, 1, + filter_index); + } + + path = object_get_canonical_path(OBJECT(s)); + + trace_xlnx_canfd_rx_data(path, frame->can_id, frame->can_dlc, + frame->flags); + canfd_update_irq(s); + } +} + +static bool tx_ready_check(XlnxVersalCANFDState *s) +{ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer data while" + " XlnxVersalCANFDState is in reset mode\n", path); + + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer data while" + " XlnxVersalCANFDState is in configuration mode." + " Reset the core so operations can start fresh\n", + path); + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer data while" + " XlnxVersalCANFDState is in SNOOP MODE\n", + path); + return false; + } + + return true; +} + +static void tx_fifo_stamp(XlnxVersalCANFDState *s, uint32_t tb0_regid) +{ + /* + * If EFC bit in DLC message is set, this means we will store the + * event of this transmitted message with time stamp. + */ + uint32_t dlc_reg_val = 0; + + if (FIELD_EX32(s->regs[tb0_regid + 1], TB0_DLC_REGISTER, EFC)) { + uint8_t dlc_val = FIELD_EX32(s->regs[tb0_regid + 1], TB0_DLC_REGISTER, + DLC); + bool fdf_val = FIELD_EX32(s->regs[tb0_regid + 1], TB0_DLC_REGISTER, + FDF); + bool brs_val = FIELD_EX32(s->regs[tb0_regid + 1], TB0_DLC_REGISTER, + BRS); + uint8_t mm_val = FIELD_EX32(s->regs[tb0_regid + 1], TB0_DLC_REGISTER, + MM); + uint8_t fill_level = ARRAY_FIELD_EX32(s->regs, + TX_EVENT_FIFO_STATUS_REGISTER, + TXE_FL); + uint8_t read_index = ARRAY_FIELD_EX32(s->regs, + TX_EVENT_FIFO_STATUS_REGISTER, + TXE_RI); + uint8_t store_index = fill_level + read_index; + + if ((fill_level) > s->cfg.tx_fifo - 1) { + qemu_log_mask(LOG_GUEST_ERROR, "TX Event Buffer is full." + " Discarding the message\n"); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXEOFLW, 1); + } else { + if (read_index == s->cfg.tx_fifo - 1) { + /* + * When ri is s->cfg.tx_fifo - 1 i.e. max, it goes cyclic that + * means we reset the ri to 0x0. + */ + read_index = 0; + ARRAY_FIELD_DP32(s->regs, TX_EVENT_FIFO_STATUS_REGISTER, TXE_RI, + read_index); + } + + if (store_index > s->cfg.tx_fifo - 1) { + store_index -= s->cfg.tx_fifo - 1; + } + + assert(store_index < s->cfg.tx_fifo); + + uint32_t tx_event_reg0_id = R_TXE_FIFO_TB_ID_REGISTER + + (store_index * 2); + + /* Store message ID in TX event register. */ + s->regs[tx_event_reg0_id] = s->regs[tb0_regid]; + + uint16_t tx_timestamp = CANFD_TIMER_MAX - + ptimer_get_count(s->canfd_timer); + + /* Store DLC with time stamp in DLC regs. */ + dlc_reg_val = FIELD_DP32(0, TXE_FIFO_TB_DLC_REGISTER, DLC, dlc_val); + dlc_reg_val |= FIELD_DP32(0, TXE_FIFO_TB_DLC_REGISTER, FDF, + fdf_val); + dlc_reg_val |= FIELD_DP32(0, TXE_FIFO_TB_DLC_REGISTER, BRS, + brs_val); + dlc_reg_val |= FIELD_DP32(0, TXE_FIFO_TB_DLC_REGISTER, ET, 0x3); + dlc_reg_val |= FIELD_DP32(0, TXE_FIFO_TB_DLC_REGISTER, MM, mm_val); + dlc_reg_val |= FIELD_DP32(0, TXE_FIFO_TB_DLC_REGISTER, TIMESTAMP, + tx_timestamp); + s->regs[tx_event_reg0_id + 1] = dlc_reg_val; + + ARRAY_FIELD_DP32(s->regs, TX_EVENT_FIFO_STATUS_REGISTER, TXE_FL, + fill_level + 1); + } + } +} + +static gint g_cmp_ids(gconstpointer data1, gconstpointer data2) +{ + tx_ready_reg_info *tx_reg_1 = (tx_ready_reg_info *) data1; + tx_ready_reg_info *tx_reg_2 = (tx_ready_reg_info *) data2; + + return tx_reg_1->can_id - tx_reg_2->can_id; +} + +static void free_list(GSList *list) +{ + GSList *iterator = NULL; + + for (iterator = list; iterator != NULL; iterator = iterator->next) { + g_free((tx_ready_reg_info *)iterator->data); + } + + g_slist_free(list); + + return; +} + +static GSList *prepare_tx_data(XlnxVersalCANFDState *s) +{ + uint8_t i = 0; + GSList *list = NULL; + uint32_t reg_num = 0; + uint32_t reg_ready = s->regs[R_TX_BUFFER_READY_REQUEST_REGISTER]; + + /* First find the messages which are ready for transmission. */ + for (i = 0; i < s->cfg.tx_fifo; i++) { + if (reg_ready & 1) { + reg_num = R_TB_ID_REGISTER + (NUM_REGS_PER_MSG_SPACE * i); + tx_ready_reg_info *temp = g_new(tx_ready_reg_info, 1); + + temp->can_id = s->regs[reg_num]; + temp->reg_num = reg_num; + list = g_slist_prepend(list, temp); + list = g_slist_sort(list, g_cmp_ids); + } + + reg_ready >>= 1; + } + + s->regs[R_TX_BUFFER_READY_REQUEST_REGISTER] = 0; + s->regs[R_TX_BUFFER_CANCEL_REQUEST_REGISTER] = 0; + + return list; +} + +static void transfer_data(XlnxVersalCANFDState *s) +{ + bool canfd_tx = tx_ready_check(s); + GSList *list, *iterator = NULL; + qemu_can_frame frame; + + if (!canfd_tx) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Controller not enabled for data" + " transfer\n", path); + return; + } + + list = prepare_tx_data(s); + if (list == NULL) { + return; + } + + for (iterator = list; iterator != NULL; iterator = iterator->next) { + regs2frame(s, &frame, + ((tx_ready_reg_info *)iterator->data)->reg_num); + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, LBACK)) { + update_rx_sequential(s, &frame); + tx_fifo_stamp(s, ((tx_ready_reg_info *)iterator->data)->reg_num); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 1); + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + trace_xlnx_canfd_tx_data(path, frame.can_id, frame.can_dlc, + frame.flags); + can_bus_client_send(&s->bus_client, &frame, 1); + tx_fifo_stamp(s, + ((tx_ready_reg_info *)iterator->data)->reg_num); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXRRS, 1); + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP)) { + canfd_exit_sleep_mode(s); + } + } + } + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 1); + free_list(list); + + canfd_update_irq(s); +} + +static uint64_t canfd_srr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + uint32_t val = val64; + + ARRAY_FIELD_DP32(s->regs, SOFTWARE_RESET_REGISTER, CEN, + FIELD_EX32(val, SOFTWARE_RESET_REGISTER, CEN)); + + if (FIELD_EX32(val, SOFTWARE_RESET_REGISTER, SRST)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + trace_xlnx_canfd_reset(path, val64); + + /* First, core will do software reset then will enter in config mode. */ + canfd_config_reset(s); + } else if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + canfd_config_mode(s); + } else { + /* + * Leave config mode. Now XlnxVersalCANFD core will enter Normal, Sleep, + * snoop or Loopback mode depending upon LBACK, SLEEP, SNOOP register + * states. + */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 0); + + ptimer_transaction_begin(s->canfd_timer); + ptimer_set_count(s->canfd_timer, 0); + ptimer_transaction_commit(s->canfd_timer); + update_status_register_mode_bits(s); + transfer_data(s); + } + + return s->regs[R_SOFTWARE_RESET_REGISTER]; +} + +static uint64_t filter_mask(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + uint32_t reg_idx = (reg->access->addr) / 4; + uint32_t val = val64; + uint32_t filter_offset = (reg_idx - R_AFMR_REGISTER) / 2; + + if (!(s->regs[R_ACCEPTANCE_FILTER_CONTROL_REGISTER] & + (1 << filter_offset))) { + s->regs[reg_idx] = val; + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d not enabled\n", + path, filter_offset + 1); + } + + return s->regs[reg_idx]; +} + +static uint64_t filter_id(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + hwaddr reg_idx = (reg->access->addr) / 4; + uint32_t val = val64; + uint32_t filter_offset = (reg_idx - R_AFIR_REGISTER) / 2; + + if (!(s->regs[R_ACCEPTANCE_FILTER_CONTROL_REGISTER] & + (1 << filter_offset))) { + s->regs[reg_idx] = val; + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d not enabled\n", + path, filter_offset + 1); + } + + return s->regs[reg_idx]; +} + +static uint64_t canfd_tx_fifo_status_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + uint32_t val = val64; + uint8_t read_ind = 0; + uint8_t fill_ind = ARRAY_FIELD_EX32(s->regs, TX_EVENT_FIFO_STATUS_REGISTER, + TXE_FL); + + if (FIELD_EX32(val, TX_EVENT_FIFO_STATUS_REGISTER, TXE_IRI) && fill_ind) { + read_ind = ARRAY_FIELD_EX32(s->regs, TX_EVENT_FIFO_STATUS_REGISTER, + TXE_RI) + 1; + + if (read_ind > s->cfg.tx_fifo - 1) { + read_ind = 0; + } + + /* + * Increase the read index by 1 and decrease the fill level by 1. + */ + ARRAY_FIELD_DP32(s->regs, TX_EVENT_FIFO_STATUS_REGISTER, TXE_RI, + read_ind); + ARRAY_FIELD_DP32(s->regs, TX_EVENT_FIFO_STATUS_REGISTER, TXE_FL, + fill_ind - 1); + } + + return s->regs[R_TX_EVENT_FIFO_STATUS_REGISTER]; +} + +static uint64_t canfd_rx_fifo_status_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + uint32_t val = val64; + uint8_t read_ind = 0; + uint8_t fill_ind = 0; + + if (FIELD_EX32(val, RX_FIFO_STATUS_REGISTER, IRI)) { + /* FL index is zero, setting IRI bit has no effect. */ + if (FIELD_EX32(val, RX_FIFO_STATUS_REGISTER, FL) != 0) { + read_ind = FIELD_EX32(val, RX_FIFO_STATUS_REGISTER, RI) + 1; + + if (read_ind > s->cfg.rx0_fifo - 1) { + read_ind = 0; + } + + fill_ind = FIELD_EX32(val, RX_FIFO_STATUS_REGISTER, FL) - 1; + + ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, RI, read_ind); + ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, FL, fill_ind); + } + } + + if (FIELD_EX32(val, RX_FIFO_STATUS_REGISTER, IRI_1)) { + /* FL_1 index is zero, setting IRI_1 bit has no effect. */ + if (FIELD_EX32(val, RX_FIFO_STATUS_REGISTER, FL_1) != 0) { + read_ind = FIELD_EX32(val, RX_FIFO_STATUS_REGISTER, RI_1) + 1; + + if (read_ind > s->cfg.rx1_fifo - 1) { + read_ind = 0; + } + + fill_ind = FIELD_EX32(val, RX_FIFO_STATUS_REGISTER, FL_1) - 1; + + ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, RI_1, read_ind); + ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, FL_1, fill_ind); + } + } + + return s->regs[R_RX_FIFO_STATUS_REGISTER]; +} + +static uint64_t canfd_tsr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + uint32_t val = val64; + + if (FIELD_EX32(val, TIMESTAMP_REGISTER, CTS)) { + ARRAY_FIELD_DP32(s->regs, TIMESTAMP_REGISTER, TIMESTAMP_CNT, 0); + ptimer_transaction_begin(s->canfd_timer); + ptimer_set_count(s->canfd_timer, 0); + ptimer_transaction_commit(s->canfd_timer); + } + + return 0; +} + +static uint64_t canfd_trr_reg_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + + if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Controller is in SNOOP mode." + " tx_ready_register will stay in reset mode\n", path); + return 0; + } else { + return val64; + } +} + +static void canfd_trr_reg_postw(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + + transfer_data(s); +} + +static void canfd_cancel_reg_postw(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + + process_cancellation_requests(s); +} + +static uint64_t canfd_write_check_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(reg->opaque); + uint32_t val = val64; + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + return val; + } + return 0; +} + +static const RegisterAccessInfo canfd_tx_regs[] = { + { .name = "TB_ID_REGISTER", .addr = A_TB_ID_REGISTER, + },{ .name = "TB0_DLC_REGISTER", .addr = A_TB0_DLC_REGISTER, + },{ .name = "TB_DW0_REGISTER", .addr = A_TB_DW0_REGISTER, + },{ .name = "TB_DW1_REGISTER", .addr = A_TB_DW1_REGISTER, + },{ .name = "TB_DW2_REGISTER", .addr = A_TB_DW2_REGISTER, + },{ .name = "TB_DW3_REGISTER", .addr = A_TB_DW3_REGISTER, + },{ .name = "TB_DW4_REGISTER", .addr = A_TB_DW4_REGISTER, + },{ .name = "TB_DW5_REGISTER", .addr = A_TB_DW5_REGISTER, + },{ .name = "TB_DW6_REGISTER", .addr = A_TB_DW6_REGISTER, + },{ .name = "TB_DW7_REGISTER", .addr = A_TB_DW7_REGISTER, + },{ .name = "TB_DW8_REGISTER", .addr = A_TB_DW8_REGISTER, + },{ .name = "TB_DW9_REGISTER", .addr = A_TB_DW9_REGISTER, + },{ .name = "TB_DW10_REGISTER", .addr = A_TB_DW10_REGISTER, + },{ .name = "TB_DW11_REGISTER", .addr = A_TB_DW11_REGISTER, + },{ .name = "TB_DW12_REGISTER", .addr = A_TB_DW12_REGISTER, + },{ .name = "TB_DW13_REGISTER", .addr = A_TB_DW13_REGISTER, + },{ .name = "TB_DW14_REGISTER", .addr = A_TB_DW14_REGISTER, + },{ .name = "TB_DW15_REGISTER", .addr = A_TB_DW15_REGISTER, + } +}; + +static const RegisterAccessInfo canfd_rx0_regs[] = { + { .name = "RB_ID_REGISTER", .addr = A_RB_ID_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DLC_REGISTER", .addr = A_RB_DLC_REGISTER, + .ro = 0xfe1fffff, + },{ .name = "RB_DW0_REGISTER", .addr = A_RB_DW0_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW1_REGISTER", .addr = A_RB_DW1_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW2_REGISTER", .addr = A_RB_DW2_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW3_REGISTER", .addr = A_RB_DW3_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW4_REGISTER", .addr = A_RB_DW4_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW5_REGISTER", .addr = A_RB_DW5_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW6_REGISTER", .addr = A_RB_DW6_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW7_REGISTER", .addr = A_RB_DW7_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW8_REGISTER", .addr = A_RB_DW8_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW9_REGISTER", .addr = A_RB_DW9_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW10_REGISTER", .addr = A_RB_DW10_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW11_REGISTER", .addr = A_RB_DW11_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW12_REGISTER", .addr = A_RB_DW12_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW13_REGISTER", .addr = A_RB_DW13_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW14_REGISTER", .addr = A_RB_DW14_REGISTER, + .ro = 0xffffffff, + },{ .name = "RB_DW15_REGISTER", .addr = A_RB_DW15_REGISTER, + .ro = 0xffffffff, + } +}; + +static const RegisterAccessInfo canfd_rx1_regs[] = { + { .name = "RB_ID_REGISTER_1", .addr = A_RB_ID_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DLC_REGISTER_1", .addr = A_RB_DLC_REGISTER_1, + .ro = 0xfe1fffff, + },{ .name = "RB0_DW0_REGISTER_1", .addr = A_RB0_DW0_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW1_REGISTER_1", .addr = A_RB_DW1_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW2_REGISTER_1", .addr = A_RB_DW2_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW3_REGISTER_1", .addr = A_RB_DW3_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW4_REGISTER_1", .addr = A_RB_DW4_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW5_REGISTER_1", .addr = A_RB_DW5_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW6_REGISTER_1", .addr = A_RB_DW6_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW7_REGISTER_1", .addr = A_RB_DW7_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW8_REGISTER_1", .addr = A_RB_DW8_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW9_REGISTER_1", .addr = A_RB_DW9_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW10_REGISTER_1", .addr = A_RB_DW10_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW11_REGISTER_1", .addr = A_RB_DW11_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW12_REGISTER_1", .addr = A_RB_DW12_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW13_REGISTER_1", .addr = A_RB_DW13_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW14_REGISTER_1", .addr = A_RB_DW14_REGISTER_1, + .ro = 0xffffffff, + },{ .name = "RB_DW15_REGISTER_1", .addr = A_RB_DW15_REGISTER_1, + .ro = 0xffffffff, + } +}; + +/* Acceptance filter registers. */ +static const RegisterAccessInfo canfd_af_regs[] = { + { .name = "AFMR_REGISTER", .addr = A_AFMR_REGISTER, + .pre_write = filter_mask, + },{ .name = "AFIR_REGISTER", .addr = A_AFIR_REGISTER, + .pre_write = filter_id, + } +}; + +static const RegisterAccessInfo canfd_txe_regs[] = { + { .name = "TXE_FIFO_TB_ID_REGISTER", .addr = A_TXE_FIFO_TB_ID_REGISTER, + .ro = 0xffffffff, + },{ .name = "TXE_FIFO_TB_DLC_REGISTER", .addr = A_TXE_FIFO_TB_DLC_REGISTER, + .ro = 0xffffffff, + } +}; + +static const RegisterAccessInfo canfd_regs_info[] = { + { .name = "SOFTWARE_RESET_REGISTER", .addr = A_SOFTWARE_RESET_REGISTER, + .pre_write = canfd_srr_pre_write, + },{ .name = "MODE_SELECT_REGISTER", .addr = A_MODE_SELECT_REGISTER, + .pre_write = canfd_msr_pre_write, + },{ .name = "ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER", + .addr = A_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, + .pre_write = canfd_write_check_prew, + },{ .name = "ARBITRATION_PHASE_BIT_TIMING_REGISTER", + .addr = A_ARBITRATION_PHASE_BIT_TIMING_REGISTER, + .pre_write = canfd_write_check_prew, + },{ .name = "ERROR_COUNTER_REGISTER", .addr = A_ERROR_COUNTER_REGISTER, + .ro = 0xffff, + },{ .name = "ERROR_STATUS_REGISTER", .addr = A_ERROR_STATUS_REGISTER, + .w1c = 0xf1f, + },{ .name = "STATUS_REGISTER", .addr = A_STATUS_REGISTER, + .reset = 0x1, + .ro = 0x7f17ff, + },{ .name = "INTERRUPT_STATUS_REGISTER", + .addr = A_INTERRUPT_STATUS_REGISTER, + .ro = 0xffffff7f, + },{ .name = "INTERRUPT_ENABLE_REGISTER", + .addr = A_INTERRUPT_ENABLE_REGISTER, + .post_write = canfd_ier_post_write, + },{ .name = "INTERRUPT_CLEAR_REGISTER", + .addr = A_INTERRUPT_CLEAR_REGISTER, .pre_write = canfd_icr_pre_write, + },{ .name = "TIMESTAMP_REGISTER", .addr = A_TIMESTAMP_REGISTER, + .ro = 0xffff0000, + .pre_write = canfd_tsr_pre_write, + },{ .name = "DATA_PHASE_BAUD_RATE_PRESCALER_REGISTER", + .addr = A_DATA_PHASE_BAUD_RATE_PRESCALER_REGISTER, + .pre_write = canfd_write_check_prew, + },{ .name = "DATA_PHASE_BIT_TIMING_REGISTER", + .addr = A_DATA_PHASE_BIT_TIMING_REGISTER, + .pre_write = canfd_write_check_prew, + },{ .name = "TX_BUFFER_READY_REQUEST_REGISTER", + .addr = A_TX_BUFFER_READY_REQUEST_REGISTER, + .pre_write = canfd_trr_reg_prew, + .post_write = canfd_trr_reg_postw, + },{ .name = "INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER", + .addr = A_INTERRUPT_ENABLE_TX_BUFFER_READY_REQUEST_REGISTER, + },{ .name = "TX_BUFFER_CANCEL_REQUEST_REGISTER", + .addr = A_TX_BUFFER_CANCEL_REQUEST_REGISTER, + .post_write = canfd_cancel_reg_postw, + },{ .name = "INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER", + .addr = A_INTERRUPT_ENABLE_TX_BUFFER_CANCELLATION_REQUEST_REGISTER, + },{ .name = "TX_EVENT_FIFO_STATUS_REGISTER", + .addr = A_TX_EVENT_FIFO_STATUS_REGISTER, + .ro = 0x3f1f, .pre_write = canfd_tx_fifo_status_prew, + },{ .name = "TX_EVENT_FIFO_WATERMARK_REGISTER", + .addr = A_TX_EVENT_FIFO_WATERMARK_REGISTER, + .reset = 0xf, + .pre_write = canfd_write_check_prew, + },{ .name = "ACCEPTANCE_FILTER_CONTROL_REGISTER", + .addr = A_ACCEPTANCE_FILTER_CONTROL_REGISTER, + },{ .name = "RX_FIFO_STATUS_REGISTER", .addr = A_RX_FIFO_STATUS_REGISTER, + .ro = 0x7f3f7f3f, .pre_write = canfd_rx_fifo_status_prew, + },{ .name = "RX_FIFO_WATERMARK_REGISTER", + .addr = A_RX_FIFO_WATERMARK_REGISTER, + .reset = 0x1f0f0f, + .pre_write = canfd_write_check_prew, + } +}; + +static void xlnx_versal_canfd_ptimer_cb(void *opaque) +{ + /* No action required on the timer rollover. */ +} + +static const MemoryRegionOps canfd_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void canfd_reset(DeviceState *dev) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(dev); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(s->reg_info); ++i) { + register_reset(&s->reg_info[i]); + } + + ptimer_transaction_begin(s->canfd_timer); + ptimer_set_count(s->canfd_timer, 0); + ptimer_transaction_commit(s->canfd_timer); +} + +static bool can_xilinx_canfd_receive(CanBusClientState *client) +{ + XlnxVersalCANFDState *s = container_of(client, XlnxVersalCANFDState, + bus_client); + + bool reset_state = ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST); + bool can_enabled = ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN); + + return !reset_state && can_enabled; +} + +static ssize_t canfd_xilinx_receive(CanBusClientState *client, + const qemu_can_frame *buf, + size_t buf_size) +{ + XlnxVersalCANFDState *s = container_of(client, XlnxVersalCANFDState, + bus_client); + const qemu_can_frame *frame = buf; + + assert(buf_size > 0); + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, LBACK)) { + /* + * XlnxVersalCANFDState will not participate in normal bus communication + * and does not receive any messages transmitted by other CAN nodes. + */ + return 1; + } + + /* Update the status register that we are receiving message. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, BBSY, 1); + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SNOOP)) { + /* Snoop Mode: Just keep the data. no response back. */ + update_rx_sequential(s, frame); + } else { + if ((ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP))) { + /* + * XlnxVersalCANFDState is in sleep mode. Any data on bus will bring + * it to the wake up state. + */ + canfd_exit_sleep_mode(s); + } + + update_rx_sequential(s, frame); + } + + /* Message processing done. Update the status back to !busy */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, BBSY, 0); + return 1; +} + +static CanBusClientInfo canfd_xilinx_bus_client_info = { + .can_receive = can_xilinx_canfd_receive, + .receive = canfd_xilinx_receive, +}; + +static int xlnx_canfd_connect_to_bus(XlnxVersalCANFDState *s, + CanBusState *bus) +{ + s->bus_client.info = &canfd_xilinx_bus_client_info; + + return can_bus_insert_client(bus, &s->bus_client); +} + +#define NUM_REG_PER_AF ARRAY_SIZE(canfd_af_regs) +#define NUM_AF 32 +#define NUM_REG_PER_TXE ARRAY_SIZE(canfd_txe_regs) +#define NUM_TXE 32 + +static int canfd_populate_regarray(XlnxVersalCANFDState *s, + RegisterInfoArray *r_array, int pos, + const RegisterAccessInfo *rae, + int num_rae) +{ + int i; + + for (i = 0; i < num_rae; i++) { + int index = rae[i].addr / 4; + RegisterInfo *r = &s->reg_info[index]; + + object_initialize(r, sizeof(*r), TYPE_REGISTER); + + *r = (RegisterInfo) { + .data = &s->regs[index], + .data_size = sizeof(uint32_t), + .access = &rae[i], + .opaque = OBJECT(s), + }; + + r_array->r[i + pos] = r; + } + return i + pos; +} + +static void canfd_create_rai(RegisterAccessInfo *rai_array, + const RegisterAccessInfo *canfd_regs, + int template_rai_array_sz, + int num_template_to_copy) +{ + int i; + int reg_num; + + for (reg_num = 0; reg_num < num_template_to_copy; reg_num++) { + int pos = reg_num * template_rai_array_sz; + + memcpy(rai_array + pos, canfd_regs, + template_rai_array_sz * sizeof(RegisterAccessInfo)); + + for (i = 0; i < template_rai_array_sz; i++) { + const char *name = canfd_regs[i].name; + uint64_t addr = canfd_regs[i].addr; + rai_array[i + pos].name = g_strdup_printf("%s%d", name, reg_num); + rai_array[i + pos].addr = addr + pos * 4; + } + } +} + +static RegisterInfoArray *canfd_create_regarray(XlnxVersalCANFDState *s) +{ + const char *device_prefix = object_get_typename(OBJECT(s)); + uint64_t memory_size = XLNX_VERSAL_CANFD_R_MAX * 4; + int num_regs; + int pos = 0; + RegisterInfoArray *r_array; + + num_regs = ARRAY_SIZE(canfd_regs_info) + + s->cfg.tx_fifo * NUM_REGS_PER_MSG_SPACE + + s->cfg.rx0_fifo * NUM_REGS_PER_MSG_SPACE + + NUM_AF * NUM_REG_PER_AF + + NUM_TXE * NUM_REG_PER_TXE; + + s->tx_regs = g_new0(RegisterAccessInfo, + s->cfg.tx_fifo * ARRAY_SIZE(canfd_tx_regs)); + + canfd_create_rai(s->tx_regs, canfd_tx_regs, + ARRAY_SIZE(canfd_tx_regs), s->cfg.tx_fifo); + + s->rx0_regs = g_new0(RegisterAccessInfo, + s->cfg.rx0_fifo * ARRAY_SIZE(canfd_rx0_regs)); + + canfd_create_rai(s->rx0_regs, canfd_rx0_regs, + ARRAY_SIZE(canfd_rx0_regs), s->cfg.rx0_fifo); + + s->af_regs = g_new0(RegisterAccessInfo, + NUM_AF * ARRAY_SIZE(canfd_af_regs)); + + canfd_create_rai(s->af_regs, canfd_af_regs, + ARRAY_SIZE(canfd_af_regs), NUM_AF); + + s->txe_regs = g_new0(RegisterAccessInfo, + NUM_TXE * ARRAY_SIZE(canfd_txe_regs)); + + canfd_create_rai(s->txe_regs, canfd_txe_regs, + ARRAY_SIZE(canfd_txe_regs), NUM_TXE); + + if (s->cfg.enable_rx_fifo1) { + num_regs += s->cfg.rx1_fifo * NUM_REGS_PER_MSG_SPACE; + + s->rx1_regs = g_new0(RegisterAccessInfo, + s->cfg.rx1_fifo * ARRAY_SIZE(canfd_rx1_regs)); + + canfd_create_rai(s->rx1_regs, canfd_rx1_regs, + ARRAY_SIZE(canfd_rx1_regs), s->cfg.rx1_fifo); + } + + r_array = g_new0(RegisterInfoArray, 1); + r_array->r = g_new0(RegisterInfo * , num_regs); + r_array->num_elements = num_regs; + r_array->prefix = device_prefix; + + pos = canfd_populate_regarray(s, r_array, pos, + canfd_regs_info, + ARRAY_SIZE(canfd_regs_info)); + pos = canfd_populate_regarray(s, r_array, pos, + s->tx_regs, s->cfg.tx_fifo * + NUM_REGS_PER_MSG_SPACE); + pos = canfd_populate_regarray(s, r_array, pos, + s->rx0_regs, s->cfg.rx0_fifo * + NUM_REGS_PER_MSG_SPACE); + if (s->cfg.enable_rx_fifo1) { + pos = canfd_populate_regarray(s, r_array, pos, + s->rx1_regs, s->cfg.rx1_fifo * + NUM_REGS_PER_MSG_SPACE); + } + pos = canfd_populate_regarray(s, r_array, pos, + s->af_regs, NUM_AF * NUM_REG_PER_AF); + pos = canfd_populate_regarray(s, r_array, pos, + s->txe_regs, NUM_TXE * NUM_REG_PER_TXE); + + memory_region_init_io(&r_array->mem, OBJECT(s), &canfd_ops, r_array, + device_prefix, memory_size); + return r_array; +} + +static void canfd_realize(DeviceState *dev, Error **errp) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(dev); + RegisterInfoArray *reg_array; + + reg_array = canfd_create_regarray(s); + memory_region_add_subregion(&s->iomem, 0x00, &reg_array->mem); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq_canfd_int); + + if (s->canfdbus) { + if (xlnx_canfd_connect_to_bus(s, s->canfdbus) < 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + error_setg(errp, "%s: xlnx_canfd_connect_to_bus failed", path); + return; + } + + } + + /* Allocate a new timer. */ + s->canfd_timer = ptimer_init(xlnx_versal_canfd_ptimer_cb, s, + PTIMER_POLICY_WRAP_AFTER_ONE_PERIOD | + PTIMER_POLICY_TRIGGER_ONLY_ON_DECREMENT | + PTIMER_POLICY_NO_IMMEDIATE_RELOAD); + + ptimer_transaction_begin(s->canfd_timer); + + ptimer_set_freq(s->canfd_timer, s->cfg.ext_clk_freq); + ptimer_set_limit(s->canfd_timer, CANFD_TIMER_MAX, 1); + ptimer_run(s->canfd_timer, 0); + ptimer_transaction_commit(s->canfd_timer); +} + +static void canfd_init(Object *obj) +{ + XlnxVersalCANFDState *s = XILINX_CANFD(obj); + + memory_region_init(&s->iomem, obj, TYPE_XILINX_CANFD, + XLNX_VERSAL_CANFD_R_MAX * 4); +} + +static const VMStateDescription vmstate_canfd = { + .name = TYPE_XILINX_CANFD, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, XlnxVersalCANFDState, + XLNX_VERSAL_CANFD_R_MAX), + VMSTATE_PTIMER(canfd_timer, XlnxVersalCANFDState), + VMSTATE_END_OF_LIST(), + } +}; + +static Property canfd_core_properties[] = { + DEFINE_PROP_UINT8("rx-fifo0", XlnxVersalCANFDState, cfg.rx0_fifo, 0x40), + DEFINE_PROP_UINT8("rx-fifo1", XlnxVersalCANFDState, cfg.rx1_fifo, 0x40), + DEFINE_PROP_UINT8("tx-fifo", XlnxVersalCANFDState, cfg.tx_fifo, 0x20), + DEFINE_PROP_BOOL("enable-rx-fifo1", XlnxVersalCANFDState, + cfg.enable_rx_fifo1, true), + DEFINE_PROP_UINT32("ext_clk_freq", XlnxVersalCANFDState, cfg.ext_clk_freq, + CANFD_DEFAULT_CLOCK), + DEFINE_PROP_LINK("canfdbus", XlnxVersalCANFDState, canfdbus, TYPE_CAN_BUS, + CanBusState *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void canfd_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = canfd_reset; + dc->realize = canfd_realize; + device_class_set_props(dc, canfd_core_properties); + dc->vmsd = &vmstate_canfd; +} + +static const TypeInfo canfd_info = { + .name = TYPE_XILINX_CANFD, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxVersalCANFDState), + .class_init = canfd_class_init, + .instance_init = canfd_init, +}; + +static void canfd_register_types(void) +{ + type_register_static(&canfd_info); +} + +type_init(canfd_register_types) diff --git a/hw/net/can/meson.build b/hw/net/can/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/net/can/meson.build +++ b/hw/net/can/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_mioe3680_pci.c')) softmmu_ss.add(when: 'CONFIG_CAN_CTUCANFD', if_true: files('ctucan_core.c')) softmmu_ss.add(when: 'CONFIG_CAN_CTUCANFD_PCI', if_true: files('ctucan_pci.c')) softmmu_ss.add(when: 'CONFIG_XLNX_ZYNQMP', if_true: files('xlnx-zynqmp-can.c')) +softmmu_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-canfd.c')) diff --git a/hw/net/can/trace-events b/hw/net/can/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/net/can/trace-events +++ b/hw/net/can/trace-events @@ -XXX,XX +XXX,XX @@ xlnx_can_filter_mask_pre_write(uint8_t filter_num, uint32_t value) "Filter%d MAS xlnx_can_tx_data(uint32_t id, uint8_t dlc, uint8_t db0, uint8_t db1, uint8_t db2, uint8_t db3, uint8_t db4, uint8_t db5, uint8_t db6, uint8_t db7) "Frame: ID: 0x%08x DLC: 0x%02x DATA: 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x" xlnx_can_rx_data(uint32_t id, uint32_t dlc, uint8_t db0, uint8_t db1, uint8_t db2, uint8_t db3, uint8_t db4, uint8_t db5, uint8_t db6, uint8_t db7) "Frame: ID: 0x%08x DLC: 0x%02x DATA: 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x" xlnx_can_rx_discard(uint32_t status) "Controller is not enabled for bus communication. Status Register: 0x%08x" + +# xlnx-versal-canfd.c +xlnx_canfd_update_irq(char *path, uint32_t isr, uint32_t ier, uint32_t irq) "%s: ISR: 0x%08x IER: 0x%08x IRQ: 0x%08x" +xlnx_canfd_rx_fifo_filter_reject(char *path, uint32_t id, uint8_t dlc) "%s: Frame: ID: 0x%08x DLC: 0x%02x" +xlnx_canfd_rx_data(char *path, uint32_t id, uint8_t dlc, uint8_t flags) "%s: Frame: ID: 0x%08x DLC: 0x%02x CANFD Flag: 0x%02x" +xlnx_canfd_tx_data(char *path, uint32_t id, uint8_t dlc, uint8_t flgas) "%s: Frame: ID: 0x%08x DLC: 0x%02x CANFD Flag: 0x%02x" +xlnx_canfd_reset(char *path, uint32_t val) "%s: Resetting controller with value = 0x%08x" -- 2.34.1 From: Vikram Garhwal <vikram.garhwal@amd.com> Connect CANFD0 and CANFD1 on the Versal-virt machine and update xlnx-versal-virt document with CANFD command line examples. Signed-off-by: Vikram Garhwal <vikram.garhwal@amd.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/xlnx-versal-virt.rst | 31 ++++++++++++++++ include/hw/arm/xlnx-versal.h | 12 +++++++ hw/arm/xlnx-versal-virt.c | 53 ++++++++++++++++++++++++++++ hw/arm/xlnx-versal.c | 37 +++++++++++++++++++ 4 files changed, 133 insertions(+) diff --git a/docs/system/arm/xlnx-versal-virt.rst b/docs/system/arm/xlnx-versal-virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/xlnx-versal-virt.rst +++ b/docs/system/arm/xlnx-versal-virt.rst @@ -XXX,XX +XXX,XX @@ Implemented devices: - DDR memory - BBRAM (36 bytes of Battery-backed RAM) - eFUSE (3072 bytes of one-time field-programmable bit array) +- 2 CANFDs QEMU does not yet model any other devices, including the PL and the AI Engine. @@ -XXX,XX +XXX,XX @@ To use a different index value, N, from default of 1, add: Better yet, do not use actual product data when running guest image on this Xilinx Versal Virt board. + +Using CANFDs for Versal Virt +"""""""""""""""""""""""""""" +Versal CANFD controller is developed based on SocketCAN and QEMU CAN bus +implementation. Bus connection and socketCAN connection for each CAN module +can be set through command lines. + +To connect both CANFD0 and CANFD1 on the same bus: + +.. code-block:: bash + + -object can-bus,id=canbus -machine canbus0=canbus -machine canbus1=canbus + +To connect CANFD0 and CANFD1 to separate buses: + +.. code-block:: bash + + -object can-bus,id=canbus0 -object can-bus,id=canbus1 \ + -machine canbus0=canbus0 -machine canbus1=canbus1 + +The SocketCAN interface can connect to a Physical or a Virtual CAN interfaces on +the host machine. Please check this document to learn about CAN interface on +Linux: docs/system/devices/can.rst + +To connect CANFD0 and CANFD1 to host machine's CAN interface can0: + +.. code-block:: bash + + -object can-bus,id=canbus -machine canbus0=canbus -machine canbus1=canbus + -object can-host-socketcan,id=canhost0,if=can0,canbus=canbus 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/dma/xlnx_csu_dma.h" #include "hw/misc/xlnx-versal-crl.h" #include "hw/misc/xlnx-versal-pmc-iou-slcr.h" +#include "hw/net/xlnx-versal-canfd.h" #define TYPE_XLNX_VERSAL "xlnx-versal" OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) #define XLNX_VERSAL_NR_SDS 2 #define XLNX_VERSAL_NR_XRAM 4 #define XLNX_VERSAL_NR_IRQS 192 +#define XLNX_VERSAL_NR_CANFD 2 +#define XLNX_VERSAL_CANFD_REF_CLK (24 * 1000 * 1000) struct Versal { /*< private >*/ @@ -XXX,XX +XXX,XX @@ struct Versal { CadenceGEMState gem[XLNX_VERSAL_NR_GEMS]; XlnxZDMA adma[XLNX_VERSAL_NR_ADMAS]; VersalUsb2 usb; + CanBusState *canbus[XLNX_VERSAL_NR_CANFD]; + XlnxVersalCANFDState canfd[XLNX_VERSAL_NR_CANFD]; } iou; /* Real-time Processing Unit. */ @@ -XXX,XX +XXX,XX @@ struct Versal { #define VERSAL_CRL_IRQ 10 #define VERSAL_UART0_IRQ_0 18 #define VERSAL_UART1_IRQ_0 19 +#define VERSAL_CANFD0_IRQ_0 20 +#define VERSAL_CANFD1_IRQ_0 21 #define VERSAL_USB0_IRQ_0 22 #define VERSAL_GEM0_IRQ_0 56 #define VERSAL_GEM0_WAKE_IRQ_0 57 @@ -XXX,XX +XXX,XX @@ struct Versal { #define MM_UART1 0xff010000U #define MM_UART1_SIZE 0x10000 +#define MM_CANFD0 0xff060000U +#define MM_CANFD0_SIZE 0x10000 +#define MM_CANFD1 0xff070000U +#define MM_CANFD1_SIZE 0x10000 + #define MM_GEM0 0xff0c0000U #define MM_GEM0_SIZE 0x10000 #define MM_GEM1 0xff0d0000U 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 @@ struct VersalVirt { uint32_t clk_25Mhz; uint32_t usb; uint32_t dwc; + uint32_t canfd[2]; } phandle; struct arm_boot_info binfo; + CanBusState *canbus[XLNX_VERSAL_NR_CANFD]; struct { bool secure; } cfg; @@ -XXX,XX +XXX,XX @@ static void fdt_add_uart_nodes(VersalVirt *s) } } +static void fdt_add_canfd_nodes(VersalVirt *s) +{ + uint64_t addrs[] = { MM_CANFD1, MM_CANFD0 }; + uint32_t size[] = { MM_CANFD1_SIZE, MM_CANFD0_SIZE }; + unsigned int irqs[] = { VERSAL_CANFD1_IRQ_0, VERSAL_CANFD0_IRQ_0 }; + const char clocknames[] = "can_clk\0s_axi_aclk"; + int i; + + /* Create and connect CANFD0 and CANFD1 nodes to canbus0. */ + for (i = 0; i < ARRAY_SIZE(addrs); i++) { + char *name = g_strdup_printf("/canfd@%" PRIx64, addrs[i]); + qemu_fdt_add_subnode(s->fdt, name); + + qemu_fdt_setprop_cell(s->fdt, name, "rx-fifo-depth", 0x40); + qemu_fdt_setprop_cell(s->fdt, name, "tx-mailbox-count", 0x20); + + qemu_fdt_setprop_cells(s->fdt, name, "clocks", + s->phandle.clk_25Mhz, s->phandle.clk_25Mhz); + qemu_fdt_setprop(s->fdt, name, "clock-names", + clocknames, sizeof(clocknames)); + qemu_fdt_setprop_cells(s->fdt, name, "interrupts", + GIC_FDT_IRQ_TYPE_SPI, irqs[i], + GIC_FDT_IRQ_FLAGS_LEVEL_HI); + qemu_fdt_setprop_sized_cells(s->fdt, name, "reg", + 2, addrs[i], 2, size[i]); + qemu_fdt_setprop_string(s->fdt, name, "compatible", + "xlnx,canfd-2.0"); + + g_free(name); + } +} + static void fdt_add_fixed_link_nodes(VersalVirt *s, char *gemname, uint32_t phandle) { @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) TYPE_XLNX_VERSAL); object_property_set_link(OBJECT(&s->soc), "ddr", OBJECT(machine->ram), &error_abort); + object_property_set_link(OBJECT(&s->soc), "canbus0", OBJECT(s->canbus[0]), + &error_abort); + object_property_set_link(OBJECT(&s->soc), "canbus1", OBJECT(s->canbus[1]), + &error_abort); sysbus_realize(SYS_BUS_DEVICE(&s->soc), &error_fatal); fdt_create(s); create_virtio_regions(s); fdt_add_gem_nodes(s); fdt_add_uart_nodes(s); + fdt_add_canfd_nodes(s); fdt_add_gic_nodes(s); fdt_add_timer_nodes(s); fdt_add_zdma_nodes(s); @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) static void versal_virt_machine_instance_init(Object *obj) { + VersalVirt *s = XLNX_VERSAL_VIRT_MACHINE(obj); + + /* + * User can set canbus0 and canbus1 properties to can-bus object and connect + * to socketcan(optional) interface via command line. + */ + object_property_add_link(obj, "canbus0", TYPE_CAN_BUS, + (Object **)&s->canbus[0], + object_property_allow_set_link, + 0); + object_property_add_link(obj, "canbus1", TYPE_CAN_BUS, + (Object **)&s->canbus[1], + object_property_allow_set_link, + 0); } static void versal_virt_machine_class_init(ObjectClass *oc, void *data) 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_uarts(Versal *s, qemu_irq *pic) } } +static void versal_create_canfds(Versal *s, qemu_irq *pic) +{ + int i; + uint32_t irqs[] = { VERSAL_CANFD0_IRQ_0, VERSAL_CANFD1_IRQ_0}; + uint64_t addrs[] = { MM_CANFD0, MM_CANFD1 }; + + for (i = 0; i < ARRAY_SIZE(s->lpd.iou.canfd); i++) { + char *name = g_strdup_printf("canfd%d", i); + SysBusDevice *sbd; + MemoryRegion *mr; + + object_initialize_child(OBJECT(s), name, &s->lpd.iou.canfd[i], + TYPE_XILINX_CANFD); + sbd = SYS_BUS_DEVICE(&s->lpd.iou.canfd[i]); + + object_property_set_int(OBJECT(&s->lpd.iou.canfd[i]), "ext_clk_freq", + XLNX_VERSAL_CANFD_REF_CLK , &error_abort); + + object_property_set_link(OBJECT(&s->lpd.iou.canfd[i]), "canfdbus", + OBJECT(s->lpd.iou.canbus[i]), + &error_abort); + + sysbus_realize(sbd, &error_fatal); + + mr = sysbus_mmio_get_region(sbd, 0); + memory_region_add_subregion(&s->mr_ps, addrs[i], mr); + + sysbus_connect_irq(sbd, 0, pic[irqs[i]]); + g_free(name); + } +} + static void versal_create_usbs(Versal *s, qemu_irq *pic) { DeviceState *dev; @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_apu_gic(s, pic); versal_create_rpu_cpus(s); versal_create_uarts(s, pic); + versal_create_canfds(s, pic); versal_create_usbs(s, pic); versal_create_gems(s, pic); versal_create_admas(s, pic); @@ -XXX,XX +XXX,XX @@ static void versal_init(Object *obj) static Property versal_properties[] = { DEFINE_PROP_LINK("ddr", Versal, cfg.mr_ddr, TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_LINK("canbus0", Versal, lpd.iou.canbus[0], + TYPE_CAN_BUS, CanBusState *), + DEFINE_PROP_LINK("canbus1", Versal, lpd.iou.canbus[1], + TYPE_CAN_BUS, CanBusState *), DEFINE_PROP_END_OF_LIST() }; -- 2.34.1 From: Vikram Garhwal <vikram.garhwal@amd.com> Signed-off-by: Vikram Garhwal <vikram.garhwal@amd.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Francisco Iglesias <francisco.iglesias@amd.com> S: Maintained F: hw/net/can/xlnx-* F: include/hw/net/xlnx-* -F: tests/qtest/xlnx-can-test* +F: tests/qtest/xlnx-can*-test* EDU M: Jiri Slaby <jslaby@suse.cz> -- 2.34.1 From: Vikram Garhwal <vikram.garhwal@amd.com> The QTests perform three tests on the Xilinx VERSAL CANFD controller: Tests the CANFD controllers in loopback. Tests the CANFD controllers in normal mode with CAN frame. Tests the CANFD controllers in normal mode with CANFD frame. Signed-off-by: Vikram Garhwal <vikram.garhwal@amd.com> Acked-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/xlnx-canfd-test.c | 423 ++++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 1 + 2 files changed, 424 insertions(+) create mode 100644 tests/qtest/xlnx-canfd-test.c diff --git a/tests/qtest/xlnx-canfd-test.c b/tests/qtest/xlnx-canfd-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/xlnx-canfd-test.c @@ -XXX,XX +XXX,XX @@ +/* + * SPDX-License-Identifier: MIT + * + * QTests for the Xilinx Versal CANFD controller. + * + * Copyright (c) 2022 AMD Inc. + * + * Written-by: Vikram Garhwal<vikram.garhwal@amd.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "libqtest.h" + +/* Base address. */ +#define CANFD0_BASE_ADDR 0xff060000 +#define CANFD1_BASE_ADDR 0xff070000 + +/* Register addresses. */ +#define R_SRR_OFFSET 0x00 +#define R_MSR_OFFSET 0x04 +#define R_FILTER_CONTROL_REGISTER 0xe0 +#define R_SR_OFFSET 0x18 +#define R_ISR_OFFSET 0x1c +#define R_IER_OFFSET 0x20 +#define R_ICR_OFFSET 0x24 +#define R_TX_READY_REQ_REGISTER 0x90 +#define RX_FIFO_STATUS_REGISTER 0xe8 +#define R_TXID_OFFSET 0x100 +#define R_TXDLC_OFFSET 0x104 +#define R_TXDATA1_OFFSET 0x108 +#define R_TXDATA2_OFFSET 0x10c +#define R_AFMR_REGISTER0 0xa00 +#define R_AFIR_REGISTER0 0xa04 +#define R_RX0_ID_OFFSET 0x2100 +#define R_RX0_DLC_OFFSET 0x2104 +#define R_RX0_DATA1_OFFSET 0x2108 +#define R_RX0_DATA2_OFFSET 0x210c + +/* CANFD modes. */ +#define SRR_CONFIG_MODE 0x00 +#define MSR_NORMAL_MODE 0x00 +#define MSR_LOOPBACK_MODE (1 << 1) +#define ENABLE_CANFD (1 << 1) + +/* CANFD status. */ +#define STATUS_CONFIG_MODE (1 << 0) +#define STATUS_NORMAL_MODE (1 << 3) +#define STATUS_LOOPBACK_MODE (1 << 1) +#define ISR_TXOK (1 << 1) +#define ISR_RXOK (1 << 4) + +#define ENABLE_ALL_FILTERS 0xffffffff +#define ENABLE_ALL_INTERRUPTS 0xffffffff + +/* We are sending one canfd message. */ +#define TX_READY_REG_VAL 0x1 + +#define FIRST_RX_STORE_INDEX 0x1 +#define STATUS_REG_MASK 0xf +#define DLC_FD_BIT_SHIFT 0x1b +#define DLC_FD_BIT_MASK 0xf8000000 +#define FIFO_STATUS_READ_INDEX_MASK 0x3f +#define FIFO_STATUS_FILL_LEVEL_MASK 0x7f00 +#define FILL_LEVEL_SHIFT 0x8 + +/* CANFD frame size ID, DLC and 16 DATA word. */ +#define CANFD_FRAME_SIZE 18 +/* CAN frame size ID, DLC and 2 DATA word. */ +#define CAN_FRAME_SIZE 4 + +/* Set the filters for CANFD controller. */ +static void enable_filters(QTestState *qts) +{ + const uint32_t arr_afmr[32] = { 0xb423deaa, 0xa2a40bdc, 0x1b64f486, + 0x95c0d4ee, 0xe0c44528, 0x4b407904, + 0xd2673f46, 0x9fc638d6, 0x8844f3d8, + 0xa607d1e8, 0x67871bf4, 0xc2557dc, + 0x9ea5b53e, 0x3643c0cc, 0x5a05ea8e, + 0x83a46d84, 0x4a25c2b8, 0x93a66008, + 0x2e467470, 0xedc66118, 0x9086f9f2, + 0xfa23dd36, 0xb6654b90, 0xb221b8ca, + 0x3467d1e2, 0xa3a55542, 0x5b26a012, + 0x2281ea7e, 0xcea0ece8, 0xdc61e588, + 0x2e5676a, 0x16821320 }; + + const uint32_t arr_afir[32] = { 0xa833dfa1, 0x255a477e, 0x3a4bb1c5, + 0x8f560a6c, 0x27f38903, 0x2fecec4d, + 0xa014c66d, 0xec289b8, 0x7e52dead, + 0x82e94f3c, 0xcf3e3c5c, 0x66059871, + 0x3f213df4, 0x25ac3959, 0xa12e9bef, + 0xa3ad3af, 0xbafd7fe, 0xb3cb40fd, + 0x5d9caa81, 0x2ed61902, 0x7cd64a0, + 0x4b1fa538, 0x9b5ced8c, 0x150de059, + 0xd2794227, 0x635e820a, 0xbb6b02cf, + 0xbb58176, 0x570025bb, 0xa78d9658, + 0x49d735df, 0xe5399d2f }; + + /* Passing the respective array values to all the AFMR and AFIR pairs. */ + for (int i = 0; i < 32; i++) { + /* For CANFD0. */ + qtest_writel(qts, CANFD0_BASE_ADDR + R_AFMR_REGISTER0 + 8 * i, + arr_afmr[i]); + qtest_writel(qts, CANFD0_BASE_ADDR + R_AFIR_REGISTER0 + 8 * i, + arr_afir[i]); + + /* For CANFD1. */ + qtest_writel(qts, CANFD1_BASE_ADDR + R_AFMR_REGISTER0 + 8 * i, + arr_afmr[i]); + qtest_writel(qts, CANFD1_BASE_ADDR + R_AFIR_REGISTER0 + 8 * i, + arr_afir[i]); + } + + /* Enable all the pairs from AFR register. */ + qtest_writel(qts, CANFD0_BASE_ADDR + R_FILTER_CONTROL_REGISTER, + ENABLE_ALL_FILTERS); + qtest_writel(qts, CANFD1_BASE_ADDR + R_FILTER_CONTROL_REGISTER, + ENABLE_ALL_FILTERS); +} + +static void configure_canfd(QTestState *qts, uint8_t mode) +{ + uint32_t status = 0; + + /* Put CANFD0 and CANFD1 in config mode. */ + qtest_writel(qts, CANFD0_BASE_ADDR + R_SRR_OFFSET, SRR_CONFIG_MODE); + qtest_writel(qts, CANFD1_BASE_ADDR + R_SRR_OFFSET, SRR_CONFIG_MODE); + + /* Write mode of operation in Mode select register. */ + qtest_writel(qts, CANFD0_BASE_ADDR + R_MSR_OFFSET, mode); + qtest_writel(qts, CANFD1_BASE_ADDR + R_MSR_OFFSET, mode); + + enable_filters(qts); + + /* Check here if CANFD0 and CANFD1 are in config mode. */ + status = qtest_readl(qts, CANFD0_BASE_ADDR + R_SR_OFFSET); + status = status & STATUS_REG_MASK; + g_assert_cmpint(status, ==, STATUS_CONFIG_MODE); + + status = qtest_readl(qts, CANFD1_BASE_ADDR + R_SR_OFFSET); + status = status & STATUS_REG_MASK; + g_assert_cmpint(status, ==, STATUS_CONFIG_MODE); + + qtest_writel(qts, CANFD1_BASE_ADDR + R_IER_OFFSET, ENABLE_ALL_INTERRUPTS); + qtest_writel(qts, CANFD1_BASE_ADDR + R_IER_OFFSET, ENABLE_ALL_INTERRUPTS); + + qtest_writel(qts, CANFD0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CANFD); + qtest_writel(qts, CANFD1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CANFD); +} + +static void generate_random_data(uint32_t *buf_tx, bool is_canfd_frame) +{ + /* Generate random TX data for CANFD frame. */ + if (is_canfd_frame) { + for (int i = 0; i < CANFD_FRAME_SIZE - 2; i++) { + buf_tx[2 + i] = rand(); + } + } else { + /* Generate random TX data for CAN frame. */ + for (int i = 0; i < CAN_FRAME_SIZE - 2; i++) { + buf_tx[2 + i] = rand(); + } + } +} + +static void read_data(QTestState *qts, uint64_t can_base_addr, uint32_t *buf_rx) +{ + uint32_t int_status; + uint32_t fifo_status_reg_value; + /* At which RX FIFO the received data is stored. */ + uint8_t store_ind = 0; + bool is_canfd_frame = false; + + /* Read the interrupt on CANFD rx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_RXOK; + + g_assert_cmpint(int_status, ==, ISR_RXOK); + + /* Find the fill level and read index. */ + fifo_status_reg_value = qtest_readl(qts, can_base_addr + + RX_FIFO_STATUS_REGISTER); + + store_ind = (fifo_status_reg_value & FIFO_STATUS_READ_INDEX_MASK) + + ((fifo_status_reg_value & FIFO_STATUS_FILL_LEVEL_MASK) >> + FILL_LEVEL_SHIFT); + + g_assert_cmpint(store_ind, ==, FIRST_RX_STORE_INDEX); + + /* Read the RX register data for CANFD. */ + buf_rx[0] = qtest_readl(qts, can_base_addr + R_RX0_ID_OFFSET); + buf_rx[1] = qtest_readl(qts, can_base_addr + R_RX0_DLC_OFFSET); + + is_canfd_frame = (buf_rx[1] >> DLC_FD_BIT_SHIFT) & 1; + + if (is_canfd_frame) { + for (int i = 0; i < CANFD_FRAME_SIZE - 2; i++) { + buf_rx[i + 2] = qtest_readl(qts, + can_base_addr + R_RX0_DATA1_OFFSET + 4 * i); + } + } else { + buf_rx[2] = qtest_readl(qts, can_base_addr + R_RX0_DATA1_OFFSET); + buf_rx[3] = qtest_readl(qts, can_base_addr + R_RX0_DATA2_OFFSET); + } + + /* Clear the RX interrupt. */ + qtest_writel(qts, CANFD1_BASE_ADDR + R_ICR_OFFSET, ISR_RXOK); +} + +static void write_data(QTestState *qts, uint64_t can_base_addr, + const uint32_t *buf_tx, bool is_canfd_frame) +{ + /* Write the TX register data for CANFD. */ + qtest_writel(qts, can_base_addr + R_TXID_OFFSET, buf_tx[0]); + qtest_writel(qts, can_base_addr + R_TXDLC_OFFSET, buf_tx[1]); + + if (is_canfd_frame) { + for (int i = 0; i < CANFD_FRAME_SIZE - 2; i++) { + qtest_writel(qts, can_base_addr + R_TXDATA1_OFFSET + 4 * i, + buf_tx[2 + i]); + } + } else { + qtest_writel(qts, can_base_addr + R_TXDATA1_OFFSET, buf_tx[2]); + qtest_writel(qts, can_base_addr + R_TXDATA2_OFFSET, buf_tx[3]); + } +} + +static void send_data(QTestState *qts, uint64_t can_base_addr) +{ + uint32_t int_status; + + qtest_writel(qts, can_base_addr + R_TX_READY_REQ_REGISTER, + TX_READY_REG_VAL); + + /* Read the interrupt on CANFD for tx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_TXOK; + + g_assert_cmpint(int_status, ==, ISR_TXOK); + + /* Clear the interrupt for tx. */ + qtest_writel(qts, CANFD0_BASE_ADDR + R_ICR_OFFSET, ISR_TXOK); +} + +static void match_rx_tx_data(const uint32_t *buf_tx, const uint32_t *buf_rx, + bool is_canfd_frame) +{ + uint16_t size = 0; + uint8_t len = CAN_FRAME_SIZE; + + if (is_canfd_frame) { + len = CANFD_FRAME_SIZE; + } + + while (size < len) { + if (R_RX0_ID_OFFSET + 4 * size == R_RX0_DLC_OFFSET) { + g_assert_cmpint((buf_rx[size] & DLC_FD_BIT_MASK), ==, + (buf_tx[size] & DLC_FD_BIT_MASK)); + } else { + if (!is_canfd_frame && size == 4) { + break; + } + + g_assert_cmpint(buf_rx[size], ==, buf_tx[size]); + } + + size++; + } +} +/* + * Xilinx CANFD supports both CAN and CANFD frames. This test will be + * transferring CAN frame i.e. 8 bytes of data from CANFD0 and CANFD1 through + * canbus. CANFD0 initiate the data transfer to can-bus, CANFD1 receives the + * data. Test compares the can frame data sent from CANFD0 and received on + * CANFD1. + */ +static void test_can_data_transfer(void) +{ + uint32_t buf_tx[CAN_FRAME_SIZE] = { 0x5a5bb9a4, 0x80000000, + 0x12345678, 0x87654321 }; + uint32_t buf_rx[CAN_FRAME_SIZE] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + + generate_random_data(buf_tx, false); + + QTestState *qts = qtest_init("-machine xlnx-versal-virt" + " -object can-bus,id=canbus" + " -machine canbus0=canbus" + " -machine canbus1=canbus" + ); + + configure_canfd(qts, MSR_NORMAL_MODE); + + /* Check if CANFD0 and CANFD1 are in Normal mode. */ + status = qtest_readl(qts, CANFD0_BASE_ADDR + R_SR_OFFSET); + status = status & STATUS_REG_MASK; + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CANFD1_BASE_ADDR + R_SR_OFFSET); + status = status & STATUS_REG_MASK; + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + write_data(qts, CANFD0_BASE_ADDR, buf_tx, false); + + send_data(qts, CANFD0_BASE_ADDR); + read_data(qts, CANFD1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, false); + + qtest_quit(qts); +} + +/* + * This test will be transferring CANFD frame i.e. 64 bytes of data from CANFD0 + * and CANFD1 through canbus. CANFD0 initiate the data transfer to can-bus, + * CANFD1 receives the data. Test compares the CANFD frame data sent from CANFD0 + * with received on CANFD1. + */ +static void test_canfd_data_transfer(void) +{ + uint32_t buf_tx[CANFD_FRAME_SIZE] = { 0x5a5bb9a4, 0xf8000000 }; + uint32_t buf_rx[CANFD_FRAME_SIZE] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + + generate_random_data(buf_tx, true); + + QTestState *qts = qtest_init("-machine xlnx-versal-virt" + " -object can-bus,id=canbus" + " -machine canbus0=canbus" + " -machine canbus1=canbus" + ); + + configure_canfd(qts, MSR_NORMAL_MODE); + + /* Check if CANFD0 and CANFD1 are in Normal mode. */ + status = qtest_readl(qts, CANFD0_BASE_ADDR + R_SR_OFFSET); + status = status & STATUS_REG_MASK; + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CANFD1_BASE_ADDR + R_SR_OFFSET); + status = status & STATUS_REG_MASK; + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + write_data(qts, CANFD0_BASE_ADDR, buf_tx, true); + + send_data(qts, CANFD0_BASE_ADDR); + read_data(qts, CANFD1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, true); + + qtest_quit(qts); +} + +/* + * This test is performing loopback mode on CANFD0 and CANFD1. Data sent from + * TX of each CANFD0 and CANFD1 are compared with RX register data for + * respective CANFD Controller. + */ +static void test_can_loopback(void) +{ + uint32_t buf_tx[CANFD_FRAME_SIZE] = { 0x5a5bb9a4, 0xf8000000 }; + uint32_t buf_rx[CANFD_FRAME_SIZE] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + + generate_random_data(buf_tx, true); + + QTestState *qts = qtest_init("-machine xlnx-versal-virt" + " -object can-bus,id=canbus" + " -machine canbus0=canbus" + " -machine canbus1=canbus" + ); + + configure_canfd(qts, MSR_LOOPBACK_MODE); + + /* Check if CANFD0 and CANFD1 are set in correct loopback mode. */ + status = qtest_readl(qts, CANFD0_BASE_ADDR + R_SR_OFFSET); + status = status & STATUS_REG_MASK; + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + status = qtest_readl(qts, CANFD1_BASE_ADDR + R_SR_OFFSET); + status = status & STATUS_REG_MASK; + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + write_data(qts, CANFD0_BASE_ADDR, buf_tx, true); + + send_data(qts, CANFD0_BASE_ADDR); + read_data(qts, CANFD0_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, true); + + generate_random_data(buf_tx, true); + + write_data(qts, CANFD1_BASE_ADDR, buf_tx, true); + + send_data(qts, CANFD1_BASE_ADDR); + read_data(qts, CANFD1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, true); + + qtest_quit(qts); +} + +int main(int argc, char **argv) +{ + g_test_init(&argc, &argv, NULL); + + qtest_add_func("/net/canfd/can_data_transfer", test_can_data_transfer); + qtest_add_func("/net/canfd/canfd_data_transfer", test_canfd_data_transfer); + qtest_add_func("/net/canfd/can_loopback", test_can_loopback); + + return g_test_run(); +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_aarch64 = \ (config_all.has_key('CONFIG_TCG') and config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? \ ['tpm-tis-device-test', 'tpm-tis-device-swtpm-test'] : []) + \ (config_all_devices.has_key('CONFIG_XLNX_ZYNQMP_ARM') ? ['xlnx-can-test', 'fuzz-xlnx-dp-test'] : []) + \ + (config_all_devices.has_key('CONFIG_XLNX_VERSAL') ? ['xlnx-canfd-test'] : []) + \ (config_all_devices.has_key('CONFIG_RASPI') ? ['bcm2835-dma-test'] : []) + \ (config_all.has_key('CONFIG_TCG') and \ config_all_devices.has_key('CONFIG_TPM_TIS_I2C') ? ['tpm-tis-i2c-test'] : []) + \ -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> Allwinner R40 (sun8i) SoC features a Quad-Core Cortex-A7 ARM CPU, and a Mali400 MP2 GPU from ARM. It's also known as the Allwinner T3 for In-Car Entertainment usage, A40i and A40pro are variants that differ in applicable temperatures range (industrial and military). Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-r40.h | 110 +++++++++ hw/arm/allwinner-r40.c | 415 +++++++++++++++++++++++++++++++++ hw/arm/bananapi_m2u.c | 129 ++++++++++ hw/arm/Kconfig | 10 + hw/arm/meson.build | 1 + 5 files changed, 665 insertions(+) create mode 100644 include/hw/arm/allwinner-r40.h create mode 100644 hw/arm/allwinner-r40.c create mode 100644 hw/arm/bananapi_m2u.c diff --git a/include/hw/arm/allwinner-r40.h b/include/hw/arm/allwinner-r40.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/allwinner-r40.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner R40/A40i/T3 System on Chip emulation + * + * Copyright (C) 2023 qianfan Zhao <qianfanguijin@163.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_ARM_ALLWINNER_R40_H +#define HW_ARM_ALLWINNER_R40_H + +#include "qom/object.h" +#include "hw/arm/boot.h" +#include "hw/timer/allwinner-a10-pit.h" +#include "hw/intc/arm_gic.h" +#include "hw/sd/allwinner-sdhost.h" +#include "target/arm/cpu.h" +#include "sysemu/block-backend.h" + +enum { + AW_R40_DEV_SRAM_A1, + AW_R40_DEV_SRAM_A2, + AW_R40_DEV_SRAM_A3, + AW_R40_DEV_SRAM_A4, + AW_R40_DEV_MMC0, + AW_R40_DEV_MMC1, + AW_R40_DEV_MMC2, + AW_R40_DEV_MMC3, + AW_R40_DEV_CCU, + AW_R40_DEV_PIT, + AW_R40_DEV_UART0, + AW_R40_DEV_GIC_DIST, + AW_R40_DEV_GIC_CPU, + AW_R40_DEV_GIC_HYP, + AW_R40_DEV_GIC_VCPU, + AW_R40_DEV_SDRAM +}; + +#define AW_R40_NUM_CPUS (4) + +/** + * Allwinner R40 object model + * @{ + */ + +/** Object type for the Allwinner R40 SoC */ +#define TYPE_AW_R40 "allwinner-r40" + +/** Convert input object to Allwinner R40 state object */ +OBJECT_DECLARE_SIMPLE_TYPE(AwR40State, AW_R40) + +/** @} */ + +/** + * Allwinner R40 object + * + * This struct contains the state of all the devices + * which are currently emulated by the R40 SoC code. + */ +#define AW_R40_NUM_MMCS 4 + +struct AwR40State { + /*< private >*/ + DeviceState parent_obj; + /*< public >*/ + + ARMCPU cpus[AW_R40_NUM_CPUS]; + const hwaddr *memmap; + AwA10PITState timer; + AwSdHostState mmc[AW_R40_NUM_MMCS]; + GICState gic; + MemoryRegion sram_a1; + MemoryRegion sram_a2; + MemoryRegion sram_a3; + MemoryRegion sram_a4; +}; + +/** + * Emulate Boot ROM firmware setup functionality. + * + * A real Allwinner R40 SoC contains a Boot ROM + * which is the first code that runs right after + * the SoC is powered on. The Boot ROM is responsible + * for loading user code (e.g. a bootloader) from any + * of the supported external devices and writing the + * downloaded code to internal SRAM. After loading the SoC + * begins executing the code written to SRAM. + * + * This function emulates the Boot ROM by copying 32 KiB + * of data from the given block device and writes it to + * the start of the first internal SRAM memory. + * + * @s: Allwinner R40 state object pointer + * @blk: Block backend device object pointer + * @unit: the mmc control's unit + */ +bool allwinner_r40_bootrom_setup(AwR40State *s, BlockBackend *blk, int unit); + +#endif /* HW_ARM_ALLWINNER_R40_H */ diff --git a/hw/arm/allwinner-r40.c b/hw/arm/allwinner-r40.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/allwinner-r40.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner R40/A40i/T3 System on Chip emulation + * + * Copyright (C) 2023 qianfan Zhao <qianfanguijin@163.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/>. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/bswap.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "hw/qdev-core.h" +#include "hw/sysbus.h" +#include "hw/char/serial.h" +#include "hw/misc/unimp.h" +#include "hw/usb/hcd-ehci.h" +#include "hw/loader.h" +#include "sysemu/sysemu.h" +#include "hw/arm/allwinner-r40.h" + +/* Memory map */ +const hwaddr allwinner_r40_memmap[] = { + [AW_R40_DEV_SRAM_A1] = 0x00000000, + [AW_R40_DEV_SRAM_A2] = 0x00004000, + [AW_R40_DEV_SRAM_A3] = 0x00008000, + [AW_R40_DEV_SRAM_A4] = 0x0000b400, + [AW_R40_DEV_MMC0] = 0x01c0f000, + [AW_R40_DEV_MMC1] = 0x01c10000, + [AW_R40_DEV_MMC2] = 0x01c11000, + [AW_R40_DEV_MMC3] = 0x01c12000, + [AW_R40_DEV_PIT] = 0x01c20c00, + [AW_R40_DEV_UART0] = 0x01c28000, + [AW_R40_DEV_GIC_DIST] = 0x01c81000, + [AW_R40_DEV_GIC_CPU] = 0x01c82000, + [AW_R40_DEV_GIC_HYP] = 0x01c84000, + [AW_R40_DEV_GIC_VCPU] = 0x01c86000, + [AW_R40_DEV_SDRAM] = 0x40000000 +}; + +/* List of unimplemented devices */ +struct AwR40Unimplemented { + const char *device_name; + hwaddr base; + hwaddr size; +}; + +static struct AwR40Unimplemented r40_unimplemented[] = { + { "d-engine", 0x01000000, 4 * MiB }, + { "d-inter", 0x01400000, 128 * KiB }, + { "sram-c", 0x01c00000, 4 * KiB }, + { "dma", 0x01c02000, 4 * KiB }, + { "nfdc", 0x01c03000, 4 * KiB }, + { "ts", 0x01c04000, 4 * KiB }, + { "spi0", 0x01c05000, 4 * KiB }, + { "spi1", 0x01c06000, 4 * KiB }, + { "cs0", 0x01c09000, 4 * KiB }, + { "keymem", 0x01c0a000, 4 * KiB }, + { "emac", 0x01c0b000, 4 * KiB }, + { "usb0-otg", 0x01c13000, 4 * KiB }, + { "usb0-host", 0x01c14000, 4 * KiB }, + { "crypto", 0x01c15000, 4 * KiB }, + { "spi2", 0x01c17000, 4 * KiB }, + { "sata", 0x01c18000, 4 * KiB }, + { "usb1-host", 0x01c19000, 4 * KiB }, + { "sid", 0x01c1b000, 4 * KiB }, + { "usb2-host", 0x01c1c000, 4 * KiB }, + { "cs1", 0x01c1d000, 4 * KiB }, + { "spi3", 0x01c1f000, 4 * KiB }, + { "ccu", 0x01c20000, 1 * KiB }, + { "rtc", 0x01c20400, 1 * KiB }, + { "pio", 0x01c20800, 1 * KiB }, + { "owa", 0x01c21000, 1 * KiB }, + { "ac97", 0x01c21400, 1 * KiB }, + { "cir0", 0x01c21800, 1 * KiB }, + { "cir1", 0x01c21c00, 1 * KiB }, + { "pcm0", 0x01c22000, 1 * KiB }, + { "pcm1", 0x01c22400, 1 * KiB }, + { "pcm2", 0x01c22800, 1 * KiB }, + { "audio", 0x01c22c00, 1 * KiB }, + { "keypad", 0x01c23000, 1 * KiB }, + { "pwm", 0x01c23400, 1 * KiB }, + { "keyadc", 0x01c24400, 1 * KiB }, + { "ths", 0x01c24c00, 1 * KiB }, + { "rtp", 0x01c25000, 1 * KiB }, + { "pmu", 0x01c25400, 1 * KiB }, + { "cpu-cfg", 0x01c25c00, 1 * KiB }, + { "uart0", 0x01c28000, 1 * KiB }, + { "uart1", 0x01c28400, 1 * KiB }, + { "uart2", 0x01c28800, 1 * KiB }, + { "uart3", 0x01c28c00, 1 * KiB }, + { "uart4", 0x01c29000, 1 * KiB }, + { "uart5", 0x01c29400, 1 * KiB }, + { "uart6", 0x01c29800, 1 * KiB }, + { "uart7", 0x01c29c00, 1 * KiB }, + { "ps20", 0x01c2a000, 1 * KiB }, + { "ps21", 0x01c2a400, 1 * KiB }, + { "twi0", 0x01c2ac00, 1 * KiB }, + { "twi1", 0x01c2b000, 1 * KiB }, + { "twi2", 0x01c2b400, 1 * KiB }, + { "twi3", 0x01c2b800, 1 * KiB }, + { "twi4", 0x01c2c000, 1 * KiB }, + { "scr", 0x01c2c400, 1 * KiB }, + { "tvd-top", 0x01c30000, 4 * KiB }, + { "tvd0", 0x01c31000, 4 * KiB }, + { "tvd1", 0x01c32000, 4 * KiB }, + { "tvd2", 0x01c33000, 4 * KiB }, + { "tvd3", 0x01c34000, 4 * KiB }, + { "gpu", 0x01c40000, 64 * KiB }, + { "gmac", 0x01c50000, 64 * KiB }, + { "hstmr", 0x01c60000, 4 * KiB }, + { "dram-com", 0x01c62000, 4 * KiB }, + { "dram-ctl", 0x01c63000, 4 * KiB }, + { "tcon-top", 0x01c70000, 4 * KiB }, + { "lcd0", 0x01c71000, 4 * KiB }, + { "lcd1", 0x01c72000, 4 * KiB }, + { "tv0", 0x01c73000, 4 * KiB }, + { "tv1", 0x01c74000, 4 * KiB }, + { "tve-top", 0x01c90000, 16 * KiB }, + { "tve0", 0x01c94000, 16 * KiB }, + { "tve1", 0x01c98000, 16 * KiB }, + { "mipi_dsi", 0x01ca0000, 4 * KiB }, + { "mipi_dphy", 0x01ca1000, 4 * KiB }, + { "ve", 0x01d00000, 1024 * KiB }, + { "mp", 0x01e80000, 128 * KiB }, + { "hdmi", 0x01ee0000, 128 * KiB }, + { "prcm", 0x01f01400, 1 * KiB }, + { "debug", 0x3f500000, 64 * KiB }, + { "cpubist", 0x3f501000, 4 * KiB }, + { "dcu", 0x3fff0000, 64 * KiB }, + { "hstmr", 0x01c60000, 4 * KiB }, + { "brom", 0xffff0000, 36 * KiB } +}; + +/* Per Processor Interrupts */ +enum { + AW_R40_GIC_PPI_MAINT = 9, + AW_R40_GIC_PPI_HYPTIMER = 10, + AW_R40_GIC_PPI_VIRTTIMER = 11, + AW_R40_GIC_PPI_SECTIMER = 13, + AW_R40_GIC_PPI_PHYSTIMER = 14 +}; + +/* Shared Processor Interrupts */ +enum { + AW_R40_GIC_SPI_UART0 = 1, + AW_R40_GIC_SPI_TIMER0 = 22, + AW_R40_GIC_SPI_TIMER1 = 23, + AW_R40_GIC_SPI_MMC0 = 32, + AW_R40_GIC_SPI_MMC1 = 33, + AW_R40_GIC_SPI_MMC2 = 34, + AW_R40_GIC_SPI_MMC3 = 35, +}; + +/* Allwinner R40 general constants */ +enum { + AW_R40_GIC_NUM_SPI = 128 +}; + +#define BOOT0_MAGIC "eGON.BT0" + +/* The low 8-bits of the 'boot_media' field in the SPL header */ +#define SUNXI_BOOTED_FROM_MMC0 0 +#define SUNXI_BOOTED_FROM_NAND 1 +#define SUNXI_BOOTED_FROM_MMC2 2 +#define SUNXI_BOOTED_FROM_SPI 3 + +struct boot_file_head { + uint32_t b_instruction; + uint8_t magic[8]; + uint32_t check_sum; + uint32_t length; + uint32_t pub_head_size; + uint32_t fel_script_address; + uint32_t fel_uEnv_length; + uint32_t dt_name_offset; + uint32_t dram_size; + uint32_t boot_media; + uint32_t string_pool[13]; +}; + +bool allwinner_r40_bootrom_setup(AwR40State *s, BlockBackend *blk, int unit) +{ + const int64_t rom_size = 32 * KiB; + g_autofree uint8_t *buffer = g_new0(uint8_t, rom_size); + struct boot_file_head *head = (struct boot_file_head *)buffer; + + if (blk_pread(blk, 8 * KiB, rom_size, buffer, 0) < 0) { + error_setg(&error_fatal, "%s: failed to read BlockBackend data", + __func__); + return false; + } + + /* we only check the magic string here. */ + if (memcmp(head->magic, BOOT0_MAGIC, sizeof(head->magic))) { + return false; + } + + /* + * Simulate the behavior of the bootROM, it will change the boot_media + * flag to indicate where the chip is booting from. R40 can boot from + * mmc0 or mmc2, the default value of boot_media is zero + * (SUNXI_BOOTED_FROM_MMC0), let's fix this flag when it is booting from + * the others. + */ + if (unit == 2) { + head->boot_media = cpu_to_le32(SUNXI_BOOTED_FROM_MMC2); + } else { + head->boot_media = cpu_to_le32(SUNXI_BOOTED_FROM_MMC0); + } + + rom_add_blob("allwinner-r40.bootrom", buffer, rom_size, + rom_size, s->memmap[AW_R40_DEV_SRAM_A1], + NULL, NULL, NULL, NULL, false); + return true; +} + +static void allwinner_r40_init(Object *obj) +{ + static const char *mmc_names[AW_R40_NUM_MMCS] = { + "mmc0", "mmc1", "mmc2", "mmc3" + }; + AwR40State *s = AW_R40(obj); + + s->memmap = allwinner_r40_memmap; + + for (int i = 0; i < AW_R40_NUM_CPUS; i++) { + object_initialize_child(obj, "cpu[*]", &s->cpus[i], + ARM_CPU_TYPE_NAME("cortex-a7")); + } + + object_initialize_child(obj, "gic", &s->gic, TYPE_ARM_GIC); + + object_initialize_child(obj, "timer", &s->timer, TYPE_AW_A10_PIT); + object_property_add_alias(obj, "clk0-freq", OBJECT(&s->timer), + "clk0-freq"); + object_property_add_alias(obj, "clk1-freq", OBJECT(&s->timer), + "clk1-freq"); + + for (int i = 0; i < AW_R40_NUM_MMCS; i++) { + object_initialize_child(obj, mmc_names[i], &s->mmc[i], + TYPE_AW_SDHOST_SUN5I); + } +} + +static void allwinner_r40_realize(DeviceState *dev, Error **errp) +{ + AwR40State *s = AW_R40(dev); + unsigned i; + + /* CPUs */ + for (i = 0; i < AW_R40_NUM_CPUS; i++) { + + /* + * Disable secondary CPUs. Guest EL3 firmware will start + * them via CPU reset control registers. + */ + qdev_prop_set_bit(DEVICE(&s->cpus[i]), "start-powered-off", + i > 0); + + /* All exception levels required */ + qdev_prop_set_bit(DEVICE(&s->cpus[i]), "has_el3", true); + qdev_prop_set_bit(DEVICE(&s->cpus[i]), "has_el2", true); + + /* Mark realized */ + qdev_realize(DEVICE(&s->cpus[i]), NULL, &error_fatal); + } + + /* Generic Interrupt Controller */ + qdev_prop_set_uint32(DEVICE(&s->gic), "num-irq", AW_R40_GIC_NUM_SPI + + GIC_INTERNAL); + qdev_prop_set_uint32(DEVICE(&s->gic), "revision", 2); + qdev_prop_set_uint32(DEVICE(&s->gic), "num-cpu", AW_R40_NUM_CPUS); + qdev_prop_set_bit(DEVICE(&s->gic), "has-security-extensions", false); + qdev_prop_set_bit(DEVICE(&s->gic), "has-virtualization-extensions", true); + sysbus_realize(SYS_BUS_DEVICE(&s->gic), &error_fatal); + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 0, s->memmap[AW_R40_DEV_GIC_DIST]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 1, s->memmap[AW_R40_DEV_GIC_CPU]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 2, s->memmap[AW_R40_DEV_GIC_HYP]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 3, s->memmap[AW_R40_DEV_GIC_VCPU]); + + /* + * Wire the outputs from each CPU's generic timer and the GICv2 + * maintenance interrupt signal to the appropriate GIC PPI inputs, + * and the GIC's IRQ/FIQ/VIRQ/VFIQ interrupt outputs to the CPU's inputs. + */ + for (i = 0; i < AW_R40_NUM_CPUS; i++) { + DeviceState *cpudev = DEVICE(&s->cpus[i]); + int ppibase = AW_R40_GIC_NUM_SPI + i * GIC_INTERNAL + GIC_NR_SGIS; + int irq; + /* + * Mapping from the output timer irq lines from the CPU to the + * GIC PPI inputs used for this board. + */ + const int timer_irq[] = { + [GTIMER_PHYS] = AW_R40_GIC_PPI_PHYSTIMER, + [GTIMER_VIRT] = AW_R40_GIC_PPI_VIRTTIMER, + [GTIMER_HYP] = AW_R40_GIC_PPI_HYPTIMER, + [GTIMER_SEC] = AW_R40_GIC_PPI_SECTIMER, + }; + + /* Connect CPU timer outputs to GIC PPI inputs */ + for (irq = 0; irq < ARRAY_SIZE(timer_irq); irq++) { + qdev_connect_gpio_out(cpudev, irq, + qdev_get_gpio_in(DEVICE(&s->gic), + ppibase + timer_irq[irq])); + } + + /* Connect GIC outputs to CPU interrupt inputs */ + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i, + qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + AW_R40_NUM_CPUS, + qdev_get_gpio_in(cpudev, ARM_CPU_FIQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + (2 * AW_R40_NUM_CPUS), + qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + (3 * AW_R40_NUM_CPUS), + qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ)); + + /* GIC maintenance signal */ + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + (4 * AW_R40_NUM_CPUS), + qdev_get_gpio_in(DEVICE(&s->gic), + ppibase + AW_R40_GIC_PPI_MAINT)); + } + + /* Timer */ + sysbus_realize(SYS_BUS_DEVICE(&s->timer), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->timer), 0, s->memmap[AW_R40_DEV_PIT]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer), 0, + qdev_get_gpio_in(DEVICE(&s->gic), + AW_R40_GIC_SPI_TIMER0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer), 1, + qdev_get_gpio_in(DEVICE(&s->gic), + AW_R40_GIC_SPI_TIMER1)); + + /* SRAM */ + memory_region_init_ram(&s->sram_a1, OBJECT(dev), "sram A1", + 16 * KiB, &error_abort); + memory_region_init_ram(&s->sram_a2, OBJECT(dev), "sram A2", + 16 * KiB, &error_abort); + memory_region_init_ram(&s->sram_a3, OBJECT(dev), "sram A3", + 13 * KiB, &error_abort); + memory_region_init_ram(&s->sram_a4, OBJECT(dev), "sram A4", + 3 * KiB, &error_abort); + memory_region_add_subregion(get_system_memory(), + s->memmap[AW_R40_DEV_SRAM_A1], &s->sram_a1); + memory_region_add_subregion(get_system_memory(), + s->memmap[AW_R40_DEV_SRAM_A2], &s->sram_a2); + memory_region_add_subregion(get_system_memory(), + s->memmap[AW_R40_DEV_SRAM_A3], &s->sram_a3); + memory_region_add_subregion(get_system_memory(), + s->memmap[AW_R40_DEV_SRAM_A4], &s->sram_a4); + + /* SD/MMC */ + for (int i = 0; i < AW_R40_NUM_MMCS; i++) { + qemu_irq irq = qdev_get_gpio_in(DEVICE(&s->gic), + AW_R40_GIC_SPI_MMC0 + i); + const hwaddr addr = s->memmap[AW_R40_DEV_MMC0 + i]; + + object_property_set_link(OBJECT(&s->mmc[i]), "dma-memory", + OBJECT(get_system_memory()), &error_fatal); + sysbus_realize(SYS_BUS_DEVICE(&s->mmc[i]), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->mmc[i]), 0, addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->mmc[i]), 0, irq); + } + + /* UART0. For future clocktree API: All UARTS are connected to APB2_CLK. */ + serial_mm_init(get_system_memory(), s->memmap[AW_R40_DEV_UART0], 2, + qdev_get_gpio_in(DEVICE(&s->gic), AW_R40_GIC_SPI_UART0), + 115200, serial_hd(0), DEVICE_NATIVE_ENDIAN); + + /* Unimplemented devices */ + for (i = 0; i < ARRAY_SIZE(r40_unimplemented); i++) { + create_unimplemented_device(r40_unimplemented[i].device_name, + r40_unimplemented[i].base, + r40_unimplemented[i].size); + } +} + +static void allwinner_r40_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + + dc->realize = allwinner_r40_realize; + /* Reason: uses serial_hd() in realize function */ + dc->user_creatable = false; +} + +static const TypeInfo allwinner_r40_type_info = { + .name = TYPE_AW_R40, + .parent = TYPE_DEVICE, + .instance_size = sizeof(AwR40State), + .instance_init = allwinner_r40_init, + .class_init = allwinner_r40_class_init, +}; + +static void allwinner_r40_register_types(void) +{ + type_register_static(&allwinner_r40_type_info); +} + +type_init(allwinner_r40_register_types) diff --git a/hw/arm/bananapi_m2u.c b/hw/arm/bananapi_m2u.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/bananapi_m2u.c @@ -XXX,XX +XXX,XX @@ +/* + * Bananapi M2U emulation + * + * Copyright (C) 2023 qianfan Zhao <qianfanguijin@163.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/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "exec/address-spaces.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "hw/arm/allwinner-r40.h" + +static struct arm_boot_info bpim2u_binfo; + +/* + * R40 can boot from mmc0 and mmc2, and bpim2u has two mmc interface, one is + * connected to sdcard and another mount an emmc media. + * Attach the mmc driver and try loading bootloader. + */ +static void mmc_attach_drive(AwR40State *s, AwSdHostState *mmc, int unit, + bool load_bootroom, bool *bootroom_loaded) +{ + DriveInfo *di = drive_get(IF_SD, 0, unit); + BlockBackend *blk = di ? blk_by_legacy_dinfo(di) : NULL; + BusState *bus; + DeviceState *carddev; + + bus = qdev_get_child_bus(DEVICE(mmc), "sd-bus"); + if (bus == NULL) { + error_report("No SD bus found in SOC object"); + exit(1); + } + + carddev = qdev_new(TYPE_SD_CARD); + qdev_prop_set_drive_err(carddev, "drive", blk, &error_fatal); + qdev_realize_and_unref(carddev, bus, &error_fatal); + + if (load_bootroom && blk && blk_is_available(blk)) { + /* Use Boot ROM to copy data from SD card to SRAM */ + *bootroom_loaded = allwinner_r40_bootrom_setup(s, blk, unit); + } +} + +static void bpim2u_init(MachineState *machine) +{ + bool bootroom_loaded = false; + AwR40State *r40; + + /* BIOS is not supported by this board */ + if (machine->firmware) { + error_report("BIOS not supported for this machine"); + exit(1); + } + + /* Only allow Cortex-A7 for this board */ + if (strcmp(machine->cpu_type, ARM_CPU_TYPE_NAME("cortex-a7")) != 0) { + error_report("This board can only be used with cortex-a7 CPU"); + exit(1); + } + + r40 = AW_R40(object_new(TYPE_AW_R40)); + object_property_add_child(OBJECT(machine), "soc", OBJECT(r40)); + object_unref(OBJECT(r40)); + + /* Setup timer properties */ + object_property_set_int(OBJECT(r40), "clk0-freq", 32768, &error_abort); + object_property_set_int(OBJECT(r40), "clk1-freq", 24 * 1000 * 1000, + &error_abort); + + /* Mark R40 object realized */ + qdev_realize(DEVICE(r40), NULL, &error_abort); + + /* + * Plug in SD card and try load bootrom, R40 has 4 mmc controllers but can + * only booting from mmc0 and mmc2. + */ + for (int i = 0; i < AW_R40_NUM_MMCS; i++) { + switch (i) { + case 0: + case 2: + mmc_attach_drive(r40, &r40->mmc[i], i, + !machine->kernel_filename && !bootroom_loaded, + &bootroom_loaded); + break; + default: + mmc_attach_drive(r40, &r40->mmc[i], i, false, NULL); + break; + } + } + + /* SDRAM */ + memory_region_add_subregion(get_system_memory(), + r40->memmap[AW_R40_DEV_SDRAM], machine->ram); + + bpim2u_binfo.loader_start = r40->memmap[AW_R40_DEV_SDRAM]; + bpim2u_binfo.ram_size = machine->ram_size; + bpim2u_binfo.psci_conduit = QEMU_PSCI_CONDUIT_SMC; + arm_load_kernel(ARM_CPU(first_cpu), machine, &bpim2u_binfo); +} + +static void bpim2u_machine_init(MachineClass *mc) +{ + mc->desc = "Bananapi M2U (Cortex-A7)"; + mc->init = bpim2u_init; + mc->min_cpus = AW_R40_NUM_CPUS; + mc->max_cpus = AW_R40_NUM_CPUS; + mc->default_cpus = AW_R40_NUM_CPUS; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a7"); + mc->default_ram_size = 1 * GiB; + mc->default_ram_id = "bpim2u.ram"; +} + +DEFINE_MACHINE("bpim2u", bpim2u_machine_init) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_H3 select USB_EHCI_SYSBUS select SD +config ALLWINNER_R40 + bool + default y if TCG && ARM + select ALLWINNER_A10_PIT + select SERIAL + select ARM_TIMER + select ARM_GIC + select UNIMP + select SD + config RASPI bool default y diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_OMAP', if_true: files('omap1.c', 'omap2.c')) arm_ss.add(when: 'CONFIG_STRONGARM', if_true: files('strongarm.c')) arm_ss.add(when: 'CONFIG_ALLWINNER_A10', if_true: files('allwinner-a10.c', 'cubieboard.c')) arm_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3.c', 'orangepi.c')) +arm_ss.add(when: 'CONFIG_ALLWINNER_R40', if_true: files('allwinner-r40.c', 'bananapi_m2u.c')) arm_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2836.c', 'raspi.c')) arm_ss.add(when: 'CONFIG_STM32F100_SOC', if_true: files('stm32f100_soc.c')) arm_ss.add(when: 'CONFIG_STM32F205_SOC', if_true: files('stm32f205_soc.c')) -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> The CCU provides the registers to program the PLLs and the controls most of the clock generation, division, distribution, synchronization and gating. This commit adds support for the Clock Control Unit which emulates a simple read/write register interface. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-r40.h | 2 + include/hw/misc/allwinner-r40-ccu.h | 65 +++++++++ hw/arm/allwinner-r40.c | 8 +- hw/misc/allwinner-r40-ccu.c | 209 ++++++++++++++++++++++++++++ hw/misc/meson.build | 1 + 5 files changed, 284 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-r40-ccu.h create mode 100644 hw/misc/allwinner-r40-ccu.c diff --git a/include/hw/arm/allwinner-r40.h b/include/hw/arm/allwinner-r40.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-r40.h +++ b/include/hw/arm/allwinner-r40.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" #include "hw/sd/allwinner-sdhost.h" +#include "hw/misc/allwinner-r40-ccu.h" #include "target/arm/cpu.h" #include "sysemu/block-backend.h" @@ -XXX,XX +XXX,XX @@ struct AwR40State { const hwaddr *memmap; AwA10PITState timer; AwSdHostState mmc[AW_R40_NUM_MMCS]; + AwR40ClockCtlState ccu; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/misc/allwinner-r40-ccu.h b/include/hw/misc/allwinner-r40-ccu.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-r40-ccu.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner R40 Clock Control Unit emulation + * + * Copyright (C) 2023 qianfan Zhao <qianfanguijin@163.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_MISC_ALLWINNER_R40_CCU_H +#define HW_MISC_ALLWINNER_R40_CCU_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * @name Constants + * @{ + */ + +/** Size of register I/O address space used by CCU device */ +#define AW_R40_CCU_IOSIZE (0x400) + +/** Total number of known registers */ +#define AW_R40_CCU_REGS_NUM (AW_R40_CCU_IOSIZE / sizeof(uint32_t)) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_R40_CCU "allwinner-r40-ccu" +OBJECT_DECLARE_SIMPLE_TYPE(AwR40ClockCtlState, AW_R40_CCU) + +/** @} */ + +/** + * Allwinner R40 CCU object instance state. + */ +struct AwR40ClockCtlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_R40_CCU_REGS_NUM]; + +}; + +#endif /* HW_MISC_ALLWINNER_R40_CCU_H */ diff --git a/hw/arm/allwinner-r40.c b/hw/arm/allwinner-r40.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-r40.c +++ b/hw/arm/allwinner-r40.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_r40_memmap[] = { [AW_R40_DEV_MMC1] = 0x01c10000, [AW_R40_DEV_MMC2] = 0x01c11000, [AW_R40_DEV_MMC3] = 0x01c12000, + [AW_R40_DEV_CCU] = 0x01c20000, [AW_R40_DEV_PIT] = 0x01c20c00, [AW_R40_DEV_UART0] = 0x01c28000, [AW_R40_DEV_GIC_DIST] = 0x01c81000, @@ -XXX,XX +XXX,XX @@ static struct AwR40Unimplemented r40_unimplemented[] = { { "usb2-host", 0x01c1c000, 4 * KiB }, { "cs1", 0x01c1d000, 4 * KiB }, { "spi3", 0x01c1f000, 4 * KiB }, - { "ccu", 0x01c20000, 1 * KiB }, { "rtc", 0x01c20400, 1 * KiB }, { "pio", 0x01c20800, 1 * KiB }, { "owa", 0x01c21000, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_init(Object *obj) object_property_add_alias(obj, "clk1-freq", OBJECT(&s->timer), "clk1-freq"); + object_initialize_child(obj, "ccu", &s->ccu, TYPE_AW_R40_CCU); + for (int i = 0; i < AW_R40_NUM_MMCS; i++) { object_initialize_child(obj, mmc_names[i], &s->mmc[i], TYPE_AW_SDHOST_SUN5I); @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(get_system_memory(), s->memmap[AW_R40_DEV_SRAM_A4], &s->sram_a4); + /* Clock Control Unit */ + sysbus_realize(SYS_BUS_DEVICE(&s->ccu), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccu), 0, s->memmap[AW_R40_DEV_CCU]); + /* SD/MMC */ for (int i = 0; i < AW_R40_NUM_MMCS; i++) { qemu_irq irq = qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/misc/allwinner-r40-ccu.c b/hw/misc/allwinner-r40-ccu.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-r40-ccu.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner R40 Clock Control Unit emulation + * + * Copyright (C) 2023 qianfan Zhao <qianfanguijin@163.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/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/allwinner-r40-ccu.h" + +/* CCU register offsets */ +enum { + REG_PLL_CPUX_CTRL = 0x0000, + REG_PLL_AUDIO_CTRL = 0x0008, + REG_PLL_VIDEO0_CTRL = 0x0010, + REG_PLL_VE_CTRL = 0x0018, + REG_PLL_DDR0_CTRL = 0x0020, + REG_PLL_PERIPH0_CTRL = 0x0028, + REG_PLL_PERIPH1_CTRL = 0x002c, + REG_PLL_VIDEO1_CTRL = 0x0030, + REG_PLL_SATA_CTRL = 0x0034, + REG_PLL_GPU_CTRL = 0x0038, + REG_PLL_MIPI_CTRL = 0x0040, + REG_PLL_DE_CTRL = 0x0048, + REG_PLL_DDR1_CTRL = 0x004c, + REG_AHB1_APB1_CFG = 0x0054, + REG_APB2_CFG = 0x0058, + REG_MMC0_CLK = 0x0088, + REG_MMC1_CLK = 0x008c, + REG_MMC2_CLK = 0x0090, + REG_MMC3_CLK = 0x0094, + REG_USBPHY_CFG = 0x00cc, + REG_PLL_DDR_AUX = 0x00f0, + REG_DRAM_CFG = 0x00f4, + REG_PLL_DDR1_CFG = 0x00f8, + REG_DRAM_CLK_GATING = 0x0100, + REG_GMAC_CLK = 0x0164, + REG_SYS_32K_CLK = 0x0310, + REG_PLL_LOCK_CTRL = 0x0320, +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* CCU register flags */ +enum { + REG_PLL_ENABLE = (1 << 31), + REG_PLL_LOCK = (1 << 28), +}; + +static uint64_t allwinner_r40_ccu_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwR40ClockCtlState *s = AW_R40_CCU(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case 0x324 ... AW_R40_CCU_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_r40_ccu_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwR40ClockCtlState *s = AW_R40_CCU(opaque); + + switch (offset) { + case REG_DRAM_CFG: /* DRAM Configuration(for DDR0) */ + /* bit16: SDRCLK_UPD (SDRCLK configuration 0 update) */ + val &= ~(1 << 16); + break; + case REG_PLL_DDR1_CTRL: /* DDR1 Control register */ + /* bit30: SDRPLL_UPD */ + val &= ~(1 << 30); + if (val & REG_PLL_ENABLE) { + val |= REG_PLL_LOCK; + } + break; + case REG_PLL_CPUX_CTRL: + case REG_PLL_AUDIO_CTRL: + case REG_PLL_VE_CTRL: + case REG_PLL_VIDEO0_CTRL: + case REG_PLL_DDR0_CTRL: + case REG_PLL_PERIPH0_CTRL: + case REG_PLL_PERIPH1_CTRL: + case REG_PLL_VIDEO1_CTRL: + case REG_PLL_SATA_CTRL: + case REG_PLL_GPU_CTRL: + case REG_PLL_MIPI_CTRL: + case REG_PLL_DE_CTRL: + if (val & REG_PLL_ENABLE) { + val |= REG_PLL_LOCK; + } + break; + case 0x324 ... AW_R40_CCU_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented write offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } + + s->regs[REG_INDEX(offset)] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_r40_ccu_ops = { + .read = allwinner_r40_ccu_read, + .write = allwinner_r40_ccu_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_r40_ccu_reset(DeviceState *dev) +{ + AwR40ClockCtlState *s = AW_R40_CCU(dev); + + memset(s->regs, 0, sizeof(s->regs)); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_PLL_CPUX_CTRL)] = 0x00001000; + s->regs[REG_INDEX(REG_PLL_AUDIO_CTRL)] = 0x00035514; + s->regs[REG_INDEX(REG_PLL_VIDEO0_CTRL)] = 0x03006207; + s->regs[REG_INDEX(REG_PLL_VE_CTRL)] = 0x03006207; + s->regs[REG_INDEX(REG_PLL_DDR0_CTRL)] = 0x00001000, + s->regs[REG_INDEX(REG_PLL_PERIPH0_CTRL)] = 0x00041811; + s->regs[REG_INDEX(REG_PLL_PERIPH1_CTRL)] = 0x00041811; + s->regs[REG_INDEX(REG_PLL_VIDEO1_CTRL)] = 0x03006207; + s->regs[REG_INDEX(REG_PLL_SATA_CTRL)] = 0x00001811; + s->regs[REG_INDEX(REG_PLL_GPU_CTRL)] = 0x03006207; + s->regs[REG_INDEX(REG_PLL_MIPI_CTRL)] = 0x00000515; + s->regs[REG_INDEX(REG_PLL_DE_CTRL)] = 0x03006207; + s->regs[REG_INDEX(REG_PLL_DDR1_CTRL)] = 0x00001800; + s->regs[REG_INDEX(REG_AHB1_APB1_CFG)] = 0x00001010; + s->regs[REG_INDEX(REG_APB2_CFG)] = 0x01000000; + s->regs[REG_INDEX(REG_PLL_DDR_AUX)] = 0x00000001; + s->regs[REG_INDEX(REG_PLL_DDR1_CFG)] = 0x0ccca000; + s->regs[REG_INDEX(REG_SYS_32K_CLK)] = 0x0000000f; +} + +static void allwinner_r40_ccu_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwR40ClockCtlState *s = AW_R40_CCU(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_r40_ccu_ops, s, + TYPE_AW_R40_CCU, AW_R40_CCU_IOSIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_r40_ccu_vmstate = { + .name = "allwinner-r40-ccu", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwR40ClockCtlState, AW_R40_CCU_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_r40_ccu_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_r40_ccu_reset; + dc->vmsd = &allwinner_r40_ccu_vmstate; +} + +static const TypeInfo allwinner_r40_ccu_info = { + .name = TYPE_AW_R40_CCU, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_r40_ccu_init, + .instance_size = sizeof(AwR40ClockCtlState), + .class_init = allwinner_r40_ccu_class_init, +}; + +static void allwinner_r40_ccu_register(void) +{ + type_register_static(&allwinner_r40_ccu_info); +} + +type_init(allwinner_r40_ccu_register) 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 @@ specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c' softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-sysctrl.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-sid.c')) +softmmu_ss.add(when: 'CONFIG_ALLWINNER_R40', if_true: files('allwinner-r40-ccu.c')) softmmu_ss.add(when: 'CONFIG_AXP209_PMU', if_true: files('axp209.c')) softmmu_ss.add(when: 'CONFIG_REALVIEW', if_true: files('arm_sysctl.c')) softmmu_ss.add(when: 'CONFIG_NSERIES', if_true: files('cbus.c')) -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> R40 has eight UARTs, support both 16450 and 16550 compatible modes. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-r40.h | 8 ++++++++ hw/arm/allwinner-r40.c | 34 +++++++++++++++++++++++++++++++--- 2 files changed, 39 insertions(+), 3 deletions(-) diff --git a/include/hw/arm/allwinner-r40.h b/include/hw/arm/allwinner-r40.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-r40.h +++ b/include/hw/arm/allwinner-r40.h @@ -XXX,XX +XXX,XX @@ enum { AW_R40_DEV_CCU, AW_R40_DEV_PIT, AW_R40_DEV_UART0, + AW_R40_DEV_UART1, + AW_R40_DEV_UART2, + AW_R40_DEV_UART3, + AW_R40_DEV_UART4, + AW_R40_DEV_UART5, + AW_R40_DEV_UART6, + AW_R40_DEV_UART7, AW_R40_DEV_GIC_DIST, AW_R40_DEV_GIC_CPU, AW_R40_DEV_GIC_HYP, @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(AwR40State, AW_R40) * which are currently emulated by the R40 SoC code. */ #define AW_R40_NUM_MMCS 4 +#define AW_R40_NUM_UARTS 8 struct AwR40State { /*< private >*/ diff --git a/hw/arm/allwinner-r40.c b/hw/arm/allwinner-r40.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-r40.c +++ b/hw/arm/allwinner-r40.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_r40_memmap[] = { [AW_R40_DEV_CCU] = 0x01c20000, [AW_R40_DEV_PIT] = 0x01c20c00, [AW_R40_DEV_UART0] = 0x01c28000, + [AW_R40_DEV_UART1] = 0x01c28400, + [AW_R40_DEV_UART2] = 0x01c28800, + [AW_R40_DEV_UART3] = 0x01c28c00, + [AW_R40_DEV_UART4] = 0x01c29000, + [AW_R40_DEV_UART5] = 0x01c29400, + [AW_R40_DEV_UART6] = 0x01c29800, + [AW_R40_DEV_UART7] = 0x01c29c00, [AW_R40_DEV_GIC_DIST] = 0x01c81000, [AW_R40_DEV_GIC_CPU] = 0x01c82000, [AW_R40_DEV_GIC_HYP] = 0x01c84000, @@ -XXX,XX +XXX,XX @@ enum { /* Shared Processor Interrupts */ enum { AW_R40_GIC_SPI_UART0 = 1, + AW_R40_GIC_SPI_UART1 = 2, + AW_R40_GIC_SPI_UART2 = 3, + AW_R40_GIC_SPI_UART3 = 4, + AW_R40_GIC_SPI_UART4 = 17, + AW_R40_GIC_SPI_UART5 = 18, + AW_R40_GIC_SPI_UART6 = 19, + AW_R40_GIC_SPI_UART7 = 20, AW_R40_GIC_SPI_TIMER0 = 22, AW_R40_GIC_SPI_TIMER1 = 23, AW_R40_GIC_SPI_MMC0 = 32, @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_realize(DeviceState *dev, Error **errp) } /* UART0. For future clocktree API: All UARTS are connected to APB2_CLK. */ - serial_mm_init(get_system_memory(), s->memmap[AW_R40_DEV_UART0], 2, - qdev_get_gpio_in(DEVICE(&s->gic), AW_R40_GIC_SPI_UART0), - 115200, serial_hd(0), DEVICE_NATIVE_ENDIAN); + for (int i = 0; i < AW_R40_NUM_UARTS; i++) { + static const int uart_irqs[AW_R40_NUM_UARTS] = { + AW_R40_GIC_SPI_UART0, + AW_R40_GIC_SPI_UART1, + AW_R40_GIC_SPI_UART2, + AW_R40_GIC_SPI_UART3, + AW_R40_GIC_SPI_UART4, + AW_R40_GIC_SPI_UART5, + AW_R40_GIC_SPI_UART6, + AW_R40_GIC_SPI_UART7, + }; + const hwaddr addr = s->memmap[AW_R40_DEV_UART0 + i]; + + serial_mm_init(get_system_memory(), addr, 2, + qdev_get_gpio_in(DEVICE(&s->gic), uart_irqs[i]), + 115200, serial_hd(i), DEVICE_NATIVE_ENDIAN); + } /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(r40_unimplemented); i++) { -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> TWI(i2c) is designed to be used as an interface between CPU host and the serial 2-Wire bus. It can support all standard 2-Wire transfer, can be operated in standard mode(100kbit/s) or fast-mode, supporting data rate up to 400kbit/s. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-r40.h | 3 +++ hw/arm/allwinner-r40.c | 11 ++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/include/hw/arm/allwinner-r40.h b/include/hw/arm/allwinner-r40.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-r40.h +++ b/include/hw/arm/allwinner-r40.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gic.h" #include "hw/sd/allwinner-sdhost.h" #include "hw/misc/allwinner-r40-ccu.h" +#include "hw/i2c/allwinner-i2c.h" #include "target/arm/cpu.h" #include "sysemu/block-backend.h" @@ -XXX,XX +XXX,XX @@ enum { AW_R40_DEV_UART5, AW_R40_DEV_UART6, AW_R40_DEV_UART7, + AW_R40_DEV_TWI0, AW_R40_DEV_GIC_DIST, AW_R40_DEV_GIC_CPU, AW_R40_DEV_GIC_HYP, @@ -XXX,XX +XXX,XX @@ struct AwR40State { AwA10PITState timer; AwSdHostState mmc[AW_R40_NUM_MMCS]; AwR40ClockCtlState ccu; + AWI2CState i2c0; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/hw/arm/allwinner-r40.c b/hw/arm/allwinner-r40.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-r40.c +++ b/hw/arm/allwinner-r40.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_r40_memmap[] = { [AW_R40_DEV_UART5] = 0x01c29400, [AW_R40_DEV_UART6] = 0x01c29800, [AW_R40_DEV_UART7] = 0x01c29c00, + [AW_R40_DEV_TWI0] = 0x01c2ac00, [AW_R40_DEV_GIC_DIST] = 0x01c81000, [AW_R40_DEV_GIC_CPU] = 0x01c82000, [AW_R40_DEV_GIC_HYP] = 0x01c84000, @@ -XXX,XX +XXX,XX @@ static struct AwR40Unimplemented r40_unimplemented[] = { { "uart7", 0x01c29c00, 1 * KiB }, { "ps20", 0x01c2a000, 1 * KiB }, { "ps21", 0x01c2a400, 1 * KiB }, - { "twi0", 0x01c2ac00, 1 * KiB }, { "twi1", 0x01c2b000, 1 * KiB }, { "twi2", 0x01c2b400, 1 * KiB }, { "twi3", 0x01c2b800, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ enum { AW_R40_GIC_SPI_UART1 = 2, AW_R40_GIC_SPI_UART2 = 3, AW_R40_GIC_SPI_UART3 = 4, + AW_R40_GIC_SPI_TWI0 = 7, AW_R40_GIC_SPI_UART4 = 17, AW_R40_GIC_SPI_UART5 = 18, AW_R40_GIC_SPI_UART6 = 19, @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_init(Object *obj) object_initialize_child(obj, mmc_names[i], &s->mmc[i], TYPE_AW_SDHOST_SUN5I); } + + object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C_SUN6I); } static void allwinner_r40_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_realize(DeviceState *dev, Error **errp) 115200, serial_hd(i), DEVICE_NATIVE_ENDIAN); } + /* I2C */ + sysbus_realize(SYS_BUS_DEVICE(&s->i2c0), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c0), 0, s->memmap[AW_R40_DEV_TWI0]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_R40_GIC_SPI_TWI0)); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(r40_unimplemented); i++) { create_unimplemented_device(r40_unimplemented[i].device_name, -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> This patch adds minimal support for AXP-221 PMU and connect it to bananapi M2U board. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/bananapi_m2u.c | 6 + hw/misc/axp209.c | 238 ----------------------------------- hw/misc/axp2xx.c | 283 ++++++++++++++++++++++++++++++++++++++++++ hw/arm/Kconfig | 3 +- hw/misc/Kconfig | 2 +- hw/misc/meson.build | 2 +- hw/misc/trace-events | 8 +- 7 files changed, 297 insertions(+), 245 deletions(-) delete mode 100644 hw/misc/axp209.c create mode 100644 hw/misc/axp2xx.c diff --git a/hw/arm/bananapi_m2u.c b/hw/arm/bananapi_m2u.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bananapi_m2u.c +++ b/hw/arm/bananapi_m2u.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "qemu/error-report.h" #include "hw/boards.h" +#include "hw/i2c/i2c.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-r40.h" @@ -XXX,XX +XXX,XX @@ static void bpim2u_init(MachineState *machine) { bool bootroom_loaded = false; AwR40State *r40; + I2CBus *i2c; /* BIOS is not supported by this board */ if (machine->firmware) { @@ -XXX,XX +XXX,XX @@ static void bpim2u_init(MachineState *machine) } } + /* Connect AXP221 */ + i2c = I2C_BUS(qdev_get_child_bus(DEVICE(&r40->i2c0), "i2c")); + i2c_slave_create_simple(i2c, "axp221_pmu", 0x34); + /* SDRAM */ memory_region_add_subregion(get_system_memory(), r40->memmap[AW_R40_DEV_SDRAM], machine->ram); diff --git a/hw/misc/axp209.c b/hw/misc/axp209.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/misc/axp209.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * AXP-209 PMU Emulation - * - * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * - * SPDX-License-Identifier: MIT - */ - -#include "qemu/osdep.h" -#include "qemu/log.h" -#include "trace.h" -#include "hw/i2c/i2c.h" -#include "migration/vmstate.h" - -#define TYPE_AXP209_PMU "axp209_pmu" - -#define AXP209(obj) \ - OBJECT_CHECK(AXP209I2CState, (obj), TYPE_AXP209_PMU) - -/* registers */ -enum { - REG_POWER_STATUS = 0x0u, - REG_OPERATING_MODE, - REG_OTG_VBUS_STATUS, - REG_CHIP_VERSION, - REG_DATA_CACHE_0, - REG_DATA_CACHE_1, - REG_DATA_CACHE_2, - REG_DATA_CACHE_3, - REG_DATA_CACHE_4, - REG_DATA_CACHE_5, - REG_DATA_CACHE_6, - REG_DATA_CACHE_7, - REG_DATA_CACHE_8, - REG_DATA_CACHE_9, - REG_DATA_CACHE_A, - REG_DATA_CACHE_B, - REG_POWER_OUTPUT_CTRL = 0x12u, - REG_DC_DC2_OUT_V_CTRL = 0x23u, - REG_DC_DC2_DVS_CTRL = 0x25u, - REG_DC_DC3_OUT_V_CTRL = 0x27u, - REG_LDO2_4_OUT_V_CTRL, - REG_LDO3_OUT_V_CTRL, - REG_VBUS_CH_MGMT = 0x30u, - REG_SHUTDOWN_V_CTRL, - REG_SHUTDOWN_CTRL, - REG_CHARGE_CTRL_1, - REG_CHARGE_CTRL_2, - REG_SPARE_CHARGE_CTRL, - REG_PEK_KEY_CTRL, - REG_DC_DC_FREQ_SET, - REG_CHR_TEMP_TH_SET, - REG_CHR_HIGH_TEMP_TH_CTRL, - REG_IPSOUT_WARN_L1, - REG_IPSOUT_WARN_L2, - REG_DISCHR_TEMP_TH_SET, - REG_DISCHR_HIGH_TEMP_TH_CTRL, - REG_IRQ_BANK_1_CTRL = 0x40u, - REG_IRQ_BANK_2_CTRL, - REG_IRQ_BANK_3_CTRL, - REG_IRQ_BANK_4_CTRL, - REG_IRQ_BANK_5_CTRL, - REG_IRQ_BANK_1_STAT = 0x48u, - REG_IRQ_BANK_2_STAT, - REG_IRQ_BANK_3_STAT, - REG_IRQ_BANK_4_STAT, - REG_IRQ_BANK_5_STAT, - REG_ADC_ACIN_V_H = 0x56u, - REG_ADC_ACIN_V_L, - REG_ADC_ACIN_CURR_H, - REG_ADC_ACIN_CURR_L, - REG_ADC_VBUS_V_H, - REG_ADC_VBUS_V_L, - REG_ADC_VBUS_CURR_H, - REG_ADC_VBUS_CURR_L, - REG_ADC_INT_TEMP_H, - REG_ADC_INT_TEMP_L, - REG_ADC_TEMP_SENS_V_H = 0x62u, - REG_ADC_TEMP_SENS_V_L, - REG_ADC_BAT_V_H = 0x78u, - REG_ADC_BAT_V_L, - REG_ADC_BAT_DISCHR_CURR_H, - REG_ADC_BAT_DISCHR_CURR_L, - REG_ADC_BAT_CHR_CURR_H, - REG_ADC_BAT_CHR_CURR_L, - REG_ADC_IPSOUT_V_H, - REG_ADC_IPSOUT_V_L, - REG_DC_DC_MOD_SEL = 0x80u, - REG_ADC_EN_1, - REG_ADC_EN_2, - REG_ADC_SR_CTRL, - REG_ADC_IN_RANGE, - REG_GPIO1_ADC_IRQ_RISING_TH, - REG_GPIO1_ADC_IRQ_FALLING_TH, - REG_TIMER_CTRL = 0x8au, - REG_VBUS_CTRL_MON_SRP, - REG_OVER_TEMP_SHUTDOWN = 0x8fu, - REG_GPIO0_FEAT_SET, - REG_GPIO_OUT_HIGH_SET, - REG_GPIO1_FEAT_SET, - REG_GPIO2_FEAT_SET, - REG_GPIO_SIG_STATE_SET_MON, - REG_GPIO3_SET, - REG_COULOMB_CNTR_CTRL = 0xb8u, - REG_POWER_MEAS_RES, - NR_REGS -}; - -#define AXP209_CHIP_VERSION_ID (0x01) -#define AXP209_DC_DC2_OUT_V_CTRL_RESET (0x16) -#define AXP209_IRQ_BANK_1_CTRL_RESET (0xd8) - -/* A simple I2C slave which returns values of ID or CNT register. */ -typedef struct AXP209I2CState { - /*< private >*/ - I2CSlave i2c; - /*< public >*/ - uint8_t regs[NR_REGS]; /* peripheral registers */ - uint8_t ptr; /* current register index */ - uint8_t count; /* counter used for tx/rx */ -} AXP209I2CState; - -/* Reset all counters and load ID register */ -static void axp209_reset_enter(Object *obj, ResetType type) -{ - AXP209I2CState *s = AXP209(obj); - - memset(s->regs, 0, NR_REGS); - s->ptr = 0; - s->count = 0; - s->regs[REG_CHIP_VERSION] = AXP209_CHIP_VERSION_ID; - s->regs[REG_DC_DC2_OUT_V_CTRL] = AXP209_DC_DC2_OUT_V_CTRL_RESET; - s->regs[REG_IRQ_BANK_1_CTRL] = AXP209_IRQ_BANK_1_CTRL_RESET; -} - -/* Handle events from master. */ -static int axp209_event(I2CSlave *i2c, enum i2c_event event) -{ - AXP209I2CState *s = AXP209(i2c); - - s->count = 0; - - return 0; -} - -/* Called when master requests read */ -static uint8_t axp209_rx(I2CSlave *i2c) -{ - AXP209I2CState *s = AXP209(i2c); - uint8_t ret = 0xff; - - if (s->ptr < NR_REGS) { - ret = s->regs[s->ptr++]; - } - - trace_axp209_rx(s->ptr - 1, ret); - - return ret; -} - -/* - * Called when master sends write. - * Update ptr with byte 0, then perform write with second byte. - */ -static int axp209_tx(I2CSlave *i2c, uint8_t data) -{ - AXP209I2CState *s = AXP209(i2c); - - if (s->count == 0) { - /* Store register address */ - s->ptr = data; - s->count++; - trace_axp209_select(data); - } else { - trace_axp209_tx(s->ptr, data); - if (s->ptr == REG_DC_DC2_OUT_V_CTRL) { - s->regs[s->ptr++] = data; - } - } - - return 0; -} - -static const VMStateDescription vmstate_axp209 = { - .name = TYPE_AXP209_PMU, - .version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT8_ARRAY(regs, AXP209I2CState, NR_REGS), - VMSTATE_UINT8(count, AXP209I2CState), - VMSTATE_UINT8(ptr, AXP209I2CState), - VMSTATE_END_OF_LIST() - } -}; - -static void axp209_class_init(ObjectClass *oc, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(oc); - I2CSlaveClass *isc = I2C_SLAVE_CLASS(oc); - ResettableClass *rc = RESETTABLE_CLASS(oc); - - rc->phases.enter = axp209_reset_enter; - dc->vmsd = &vmstate_axp209; - isc->event = axp209_event; - isc->recv = axp209_rx; - isc->send = axp209_tx; -} - -static const TypeInfo axp209_info = { - .name = TYPE_AXP209_PMU, - .parent = TYPE_I2C_SLAVE, - .instance_size = sizeof(AXP209I2CState), - .class_init = axp209_class_init -}; - -static void axp209_register_devices(void) -{ - type_register_static(&axp209_info); -} - -type_init(axp209_register_devices); diff --git a/hw/misc/axp2xx.c b/hw/misc/axp2xx.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/axp2xx.c @@ -XXX,XX +XXX,XX @@ +/* + * AXP-2XX PMU Emulation, supported lists: + * AXP209 + * AXP221 + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * Copyright (C) 2023 qianfan Zhao <qianfanguijin@163.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * SPDX-License-Identifier: MIT + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qom/object.h" +#include "trace.h" +#include "hw/i2c/i2c.h" +#include "migration/vmstate.h" + +#define TYPE_AXP2XX "axp2xx_pmu" +#define TYPE_AXP209_PMU "axp209_pmu" +#define TYPE_AXP221_PMU "axp221_pmu" + +OBJECT_DECLARE_TYPE(AXP2xxI2CState, AXP2xxClass, AXP2XX) + +#define NR_REGS (0xff) + +/* A simple I2C slave which returns values of ID or CNT register. */ +typedef struct AXP2xxI2CState { + /*< private >*/ + I2CSlave i2c; + /*< public >*/ + uint8_t regs[NR_REGS]; /* peripheral registers */ + uint8_t ptr; /* current register index */ + uint8_t count; /* counter used for tx/rx */ +} AXP2xxI2CState; + +typedef struct AXP2xxClass { + /*< private >*/ + I2CSlaveClass parent_class; + /*< public >*/ + void (*reset_enter)(AXP2xxI2CState *s, ResetType type); +} AXP2xxClass; + +#define AXP209_CHIP_VERSION_ID (0x01) +#define AXP209_DC_DC2_OUT_V_CTRL_RESET (0x16) + +/* Reset all counters and load ID register */ +static void axp209_reset_enter(AXP2xxI2CState *s, ResetType type) +{ + memset(s->regs, 0, NR_REGS); + s->ptr = 0; + s->count = 0; + + s->regs[0x03] = AXP209_CHIP_VERSION_ID; + s->regs[0x23] = AXP209_DC_DC2_OUT_V_CTRL_RESET; + + s->regs[0x30] = 0x60; + s->regs[0x32] = 0x46; + s->regs[0x34] = 0x41; + s->regs[0x35] = 0x22; + s->regs[0x36] = 0x5d; + s->regs[0x37] = 0x08; + s->regs[0x38] = 0xa5; + s->regs[0x39] = 0x1f; + s->regs[0x3a] = 0x68; + s->regs[0x3b] = 0x5f; + s->regs[0x3c] = 0xfc; + s->regs[0x3d] = 0x16; + s->regs[0x40] = 0xd8; + s->regs[0x42] = 0xff; + s->regs[0x43] = 0x3b; + s->regs[0x80] = 0xe0; + s->regs[0x82] = 0x83; + s->regs[0x83] = 0x80; + s->regs[0x84] = 0x32; + s->regs[0x86] = 0xff; + s->regs[0x90] = 0x07; + s->regs[0x91] = 0xa0; + s->regs[0x92] = 0x07; + s->regs[0x93] = 0x07; +} + +#define AXP221_PWR_STATUS_ACIN_PRESENT BIT(7) +#define AXP221_PWR_STATUS_ACIN_AVAIL BIT(6) +#define AXP221_PWR_STATUS_VBUS_PRESENT BIT(5) +#define AXP221_PWR_STATUS_VBUS_USED BIT(4) +#define AXP221_PWR_STATUS_BAT_CHARGING BIT(2) +#define AXP221_PWR_STATUS_ACIN_VBUS_POWERED BIT(1) + +/* Reset all counters and load ID register */ +static void axp221_reset_enter(AXP2xxI2CState *s, ResetType type) +{ + memset(s->regs, 0, NR_REGS); + s->ptr = 0; + s->count = 0; + + /* input power status register */ + s->regs[0x00] = AXP221_PWR_STATUS_ACIN_PRESENT + | AXP221_PWR_STATUS_ACIN_AVAIL + | AXP221_PWR_STATUS_ACIN_VBUS_POWERED; + + s->regs[0x01] = 0x00; /* no battery is connected */ + + /* + * CHIPID register, no documented on datasheet, but it is checked in + * u-boot spl. I had read it from AXP221s and got 0x06 value. + * So leave 06h here. + */ + s->regs[0x03] = 0x06; + + s->regs[0x10] = 0xbf; + s->regs[0x13] = 0x01; + s->regs[0x30] = 0x60; + s->regs[0x31] = 0x03; + s->regs[0x32] = 0x43; + s->regs[0x33] = 0xc6; + s->regs[0x34] = 0x45; + s->regs[0x35] = 0x0e; + s->regs[0x36] = 0x5d; + s->regs[0x37] = 0x08; + s->regs[0x38] = 0xa5; + s->regs[0x39] = 0x1f; + s->regs[0x3c] = 0xfc; + s->regs[0x3d] = 0x16; + s->regs[0x80] = 0x80; + s->regs[0x82] = 0xe0; + s->regs[0x84] = 0x32; + s->regs[0x8f] = 0x01; + + s->regs[0x90] = 0x07; + s->regs[0x91] = 0x1f; + s->regs[0x92] = 0x07; + s->regs[0x93] = 0x1f; + + s->regs[0x40] = 0xd8; + s->regs[0x41] = 0xff; + s->regs[0x42] = 0x03; + s->regs[0x43] = 0x03; + + s->regs[0xb8] = 0xc0; + s->regs[0xb9] = 0x64; + s->regs[0xe6] = 0xa0; +} + +static void axp2xx_reset_enter(Object *obj, ResetType type) +{ + AXP2xxI2CState *s = AXP2XX(obj); + AXP2xxClass *sc = AXP2XX_GET_CLASS(s); + + sc->reset_enter(s, type); +} + +/* Handle events from master. */ +static int axp2xx_event(I2CSlave *i2c, enum i2c_event event) +{ + AXP2xxI2CState *s = AXP2XX(i2c); + + s->count = 0; + + return 0; +} + +/* Called when master requests read */ +static uint8_t axp2xx_rx(I2CSlave *i2c) +{ + AXP2xxI2CState *s = AXP2XX(i2c); + uint8_t ret = 0xff; + + if (s->ptr < NR_REGS) { + ret = s->regs[s->ptr++]; + } + + trace_axp2xx_rx(s->ptr - 1, ret); + + return ret; +} + +/* + * Called when master sends write. + * Update ptr with byte 0, then perform write with second byte. + */ +static int axp2xx_tx(I2CSlave *i2c, uint8_t data) +{ + AXP2xxI2CState *s = AXP2XX(i2c); + + if (s->count == 0) { + /* Store register address */ + s->ptr = data; + s->count++; + trace_axp2xx_select(data); + } else { + trace_axp2xx_tx(s->ptr, data); + s->regs[s->ptr++] = data; + } + + return 0; +} + +static const VMStateDescription vmstate_axp2xx = { + .name = TYPE_AXP2XX, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8_ARRAY(regs, AXP2xxI2CState, NR_REGS), + VMSTATE_UINT8(ptr, AXP2xxI2CState), + VMSTATE_UINT8(count, AXP2xxI2CState), + VMSTATE_END_OF_LIST() + } +}; + +static void axp2xx_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + I2CSlaveClass *isc = I2C_SLAVE_CLASS(oc); + ResettableClass *rc = RESETTABLE_CLASS(oc); + + rc->phases.enter = axp2xx_reset_enter; + dc->vmsd = &vmstate_axp2xx; + isc->event = axp2xx_event; + isc->recv = axp2xx_rx; + isc->send = axp2xx_tx; +} + +static const TypeInfo axp2xx_info = { + .name = TYPE_AXP2XX, + .parent = TYPE_I2C_SLAVE, + .instance_size = sizeof(AXP2xxI2CState), + .class_size = sizeof(AXP2xxClass), + .class_init = axp2xx_class_init, + .abstract = true, +}; + +static void axp209_class_init(ObjectClass *oc, void *data) +{ + AXP2xxClass *sc = AXP2XX_CLASS(oc); + + sc->reset_enter = axp209_reset_enter; +} + +static const TypeInfo axp209_info = { + .name = TYPE_AXP209_PMU, + .parent = TYPE_AXP2XX, + .class_init = axp209_class_init +}; + +static void axp221_class_init(ObjectClass *oc, void *data) +{ + AXP2xxClass *sc = AXP2XX_CLASS(oc); + + sc->reset_enter = axp221_reset_enter; +} + +static const TypeInfo axp221_info = { + .name = TYPE_AXP221_PMU, + .parent = TYPE_AXP2XX, + .class_init = axp221_class_init, +}; + +static void axp2xx_register_devices(void) +{ + type_register_static(&axp2xx_info); + type_register_static(&axp209_info); + type_register_static(&axp221_info); +} + +type_init(axp2xx_register_devices); diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select ALLWINNER_WDT select ALLWINNER_EMAC select ALLWINNER_I2C - select AXP209_PMU + select AXP2XX_PMU select SERIAL select UNIMP @@ -XXX,XX +XXX,XX @@ config ALLWINNER_R40 bool default y if TCG && ARM select ALLWINNER_A10_PIT + select AXP2XX_PMU select SERIAL select ARM_TIMER select ARM_GIC diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10_CCM config ALLWINNER_A10_DRAMC bool -config AXP209_PMU +config AXP2XX_PMU bool depends on I2C 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_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-sysctrl.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-sid.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_R40', if_true: files('allwinner-r40-ccu.c')) -softmmu_ss.add(when: 'CONFIG_AXP209_PMU', if_true: files('axp209.c')) +softmmu_ss.add(when: 'CONFIG_AXP2XX_PMU', if_true: files('axp2xx.c')) softmmu_ss.add(when: 'CONFIG_REALVIEW', if_true: files('arm_sysctl.c')) softmmu_ss.add(when: 'CONFIG_NSERIES', if_true: files('cbus.c')) softmmu_ss.add(when: 'CONFIG_ECCMEMCTL', if_true: files('eccmemctl.c')) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ allwinner_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" avr_power_read(uint8_t value) "power_reduc read value:%u" avr_power_write(uint8_t value) "power_reduc write value:%u" -# axp209.c -axp209_rx(uint8_t reg, uint8_t data) "Read reg 0x%" PRIx8 " : 0x%" PRIx8 -axp209_select(uint8_t reg) "Accessing reg 0x%" PRIx8 -axp209_tx(uint8_t reg, uint8_t data) "Write reg 0x%" PRIx8 " : 0x%" PRIx8 +# axp2xx +axp2xx_rx(uint8_t reg, uint8_t data) "Read reg 0x%" PRIx8 " : 0x%" PRIx8 +axp2xx_select(uint8_t reg) "Accessing reg 0x%" PRIx8 +axp2xx_tx(uint8_t reg, uint8_t data) "Write reg 0x%" PRIx8 " : 0x%" PRIx8 # eccmemctl.c ecc_mem_writel_mer(uint32_t val) "Write memory enable 0x%08x" -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> Types of memory that the SDRAM controller supports are DDR2/DDR3 and capacities of up to 2GiB. This commit adds emulation support of the Allwinner R40 SDRAM controller. This driver only support 256M, 512M and 1024M memory now. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-r40.h | 13 +- include/hw/misc/allwinner-r40-dramc.h | 108 ++++++ hw/arm/allwinner-r40.c | 21 +- hw/arm/bananapi_m2u.c | 7 + hw/misc/allwinner-r40-dramc.c | 513 ++++++++++++++++++++++++++ hw/misc/meson.build | 1 + hw/misc/trace-events | 14 + 7 files changed, 674 insertions(+), 3 deletions(-) create mode 100644 include/hw/misc/allwinner-r40-dramc.h create mode 100644 hw/misc/allwinner-r40-dramc.c diff --git a/include/hw/arm/allwinner-r40.h b/include/hw/arm/allwinner-r40.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-r40.h +++ b/include/hw/arm/allwinner-r40.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gic.h" #include "hw/sd/allwinner-sdhost.h" #include "hw/misc/allwinner-r40-ccu.h" +#include "hw/misc/allwinner-r40-dramc.h" #include "hw/i2c/allwinner-i2c.h" #include "target/arm/cpu.h" #include "sysemu/block-backend.h" @@ -XXX,XX +XXX,XX @@ enum { AW_R40_DEV_GIC_CPU, AW_R40_DEV_GIC_HYP, AW_R40_DEV_GIC_VCPU, - AW_R40_DEV_SDRAM + AW_R40_DEV_SDRAM, + AW_R40_DEV_DRAMCOM, + AW_R40_DEV_DRAMCTL, + AW_R40_DEV_DRAMPHY, }; #define AW_R40_NUM_CPUS (4) @@ -XXX,XX +XXX,XX @@ struct AwR40State { DeviceState parent_obj; /*< public >*/ + /** Physical base address for start of RAM */ + hwaddr ram_addr; + + /** Total RAM size in megabytes */ + uint32_t ram_size; + ARMCPU cpus[AW_R40_NUM_CPUS]; const hwaddr *memmap; AwA10PITState timer; AwSdHostState mmc[AW_R40_NUM_MMCS]; AwR40ClockCtlState ccu; + AwR40DramCtlState dramc; AWI2CState i2c0; GICState gic; MemoryRegion sram_a1; diff --git a/include/hw/misc/allwinner-r40-dramc.h b/include/hw/misc/allwinner-r40-dramc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-r40-dramc.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner R40 SDRAM Controller emulation + * + * Copyright (C) 2023 qianfan Zhao <qianfanguijin@163.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_MISC_ALLWINNER_R40_DRAMC_H +#define HW_MISC_ALLWINNER_R40_DRAMC_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "exec/hwaddr.h" + +/** + * Constants + * @{ + */ + +/** Highest register address used by DRAMCOM module */ +#define AW_R40_DRAMCOM_REGS_MAXADDR (0x804) + +/** Total number of known DRAMCOM registers */ +#define AW_R40_DRAMCOM_REGS_NUM (AW_R40_DRAMCOM_REGS_MAXADDR / \ + sizeof(uint32_t)) + +/** Highest register address used by DRAMCTL module */ +#define AW_R40_DRAMCTL_REGS_MAXADDR (0x88c) + +/** Total number of known DRAMCTL registers */ +#define AW_R40_DRAMCTL_REGS_NUM (AW_R40_DRAMCTL_REGS_MAXADDR / \ + sizeof(uint32_t)) + +/** Highest register address used by DRAMPHY module */ +#define AW_R40_DRAMPHY_REGS_MAXADDR (0x4) + +/** Total number of known DRAMPHY registers */ +#define AW_R40_DRAMPHY_REGS_NUM (AW_R40_DRAMPHY_REGS_MAXADDR / \ + sizeof(uint32_t)) + +/** @} */ + +/** + * Object model + * @{ + */ + +#define TYPE_AW_R40_DRAMC "allwinner-r40-dramc" +OBJECT_DECLARE_SIMPLE_TYPE(AwR40DramCtlState, AW_R40_DRAMC) + +/** @} */ + +/** + * Allwinner R40 SDRAM Controller object instance state. + */ +struct AwR40DramCtlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Physical base address for start of RAM */ + hwaddr ram_addr; + + /** Total RAM size in megabytes */ + uint32_t ram_size; + + uint8_t set_row_bits; + uint8_t set_bank_bits; + uint8_t set_col_bits; + + /** + * @name Memory Regions + * @{ + */ + MemoryRegion dramcom_iomem; /**< DRAMCOM module I/O registers */ + MemoryRegion dramctl_iomem; /**< DRAMCTL module I/O registers */ + MemoryRegion dramphy_iomem; /**< DRAMPHY module I/O registers */ + MemoryRegion dram_high; /**< The high 1G dram for dualrank detect */ + MemoryRegion detect_cells; /**< DRAM memory cells for auto detect */ + + /** @} */ + + /** + * @name Hardware Registers + * @{ + */ + + uint32_t dramcom[AW_R40_DRAMCOM_REGS_NUM]; /**< DRAMCOM registers */ + uint32_t dramctl[AW_R40_DRAMCTL_REGS_NUM]; /**< DRAMCTL registers */ + uint32_t dramphy[AW_R40_DRAMPHY_REGS_NUM] ;/**< DRAMPHY registers */ + + /** @} */ + +}; + +#endif /* HW_MISC_ALLWINNER_R40_DRAMC_H */ diff --git a/hw/arm/allwinner-r40.c b/hw/arm/allwinner-r40.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-r40.c +++ b/hw/arm/allwinner-r40.c @@ -XXX,XX +XXX,XX @@ #include "hw/loader.h" #include "sysemu/sysemu.h" #include "hw/arm/allwinner-r40.h" +#include "hw/misc/allwinner-r40-dramc.h" /* Memory map */ const hwaddr allwinner_r40_memmap[] = { @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_r40_memmap[] = { [AW_R40_DEV_UART6] = 0x01c29800, [AW_R40_DEV_UART7] = 0x01c29c00, [AW_R40_DEV_TWI0] = 0x01c2ac00, + [AW_R40_DEV_DRAMCOM] = 0x01c62000, + [AW_R40_DEV_DRAMCTL] = 0x01c63000, + [AW_R40_DEV_DRAMPHY] = 0x01c65000, [AW_R40_DEV_GIC_DIST] = 0x01c81000, [AW_R40_DEV_GIC_CPU] = 0x01c82000, [AW_R40_DEV_GIC_HYP] = 0x01c84000, @@ -XXX,XX +XXX,XX @@ static struct AwR40Unimplemented r40_unimplemented[] = { { "gpu", 0x01c40000, 64 * KiB }, { "gmac", 0x01c50000, 64 * KiB }, { "hstmr", 0x01c60000, 4 * KiB }, - { "dram-com", 0x01c62000, 4 * KiB }, - { "dram-ctl", 0x01c63000, 4 * KiB }, { "tcon-top", 0x01c70000, 4 * KiB }, { "lcd0", 0x01c71000, 4 * KiB }, { "lcd1", 0x01c72000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_init(Object *obj) } object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C_SUN6I); + + object_initialize_child(obj, "dramc", &s->dramc, TYPE_AW_R40_DRAMC); + object_property_add_alias(obj, "ram-addr", OBJECT(&s->dramc), + "ram-addr"); + object_property_add_alias(obj, "ram-size", OBJECT(&s->dramc), + "ram-size"); } static void allwinner_r40_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0, qdev_get_gpio_in(DEVICE(&s->gic), AW_R40_GIC_SPI_TWI0)); + /* DRAMC */ + sysbus_realize(SYS_BUS_DEVICE(&s->dramc), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 0, + s->memmap[AW_R40_DEV_DRAMCOM]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 1, + s->memmap[AW_R40_DEV_DRAMCTL]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 2, + s->memmap[AW_R40_DEV_DRAMPHY]); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(r40_unimplemented); i++) { create_unimplemented_device(r40_unimplemented[i].device_name, diff --git a/hw/arm/bananapi_m2u.c b/hw/arm/bananapi_m2u.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bananapi_m2u.c +++ b/hw/arm/bananapi_m2u.c @@ -XXX,XX +XXX,XX @@ static void bpim2u_init(MachineState *machine) object_property_set_int(OBJECT(r40), "clk1-freq", 24 * 1000 * 1000, &error_abort); + /* DRAMC */ + r40->ram_size = machine->ram_size / MiB; + object_property_set_uint(OBJECT(r40), "ram-addr", + r40->memmap[AW_R40_DEV_SDRAM], &error_abort); + object_property_set_int(OBJECT(r40), "ram-size", + r40->ram_size, &error_abort); + /* Mark R40 object realized */ qdev_realize(DEVICE(r40), NULL, &error_abort); diff --git a/hw/misc/allwinner-r40-dramc.c b/hw/misc/allwinner-r40-dramc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-r40-dramc.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner R40 SDRAM Controller emulation + * + * CCopyright (C) 2023 qianfan Zhao <qianfanguijin@163.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/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qemu/error-report.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "exec/address-spaces.h" +#include "hw/qdev-properties.h" +#include "qapi/error.h" +#include "qemu/bitops.h" +#include "hw/misc/allwinner-r40-dramc.h" +#include "trace.h" + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* DRAMCOM register offsets */ +enum { + REG_DRAMCOM_CR = 0x0000, /* Control Register */ +}; + +/* DRAMCOMM register flags */ +enum { + REG_DRAMCOM_CR_DUAL_RANK = (1 << 0), +}; + +/* DRAMCTL register offsets */ +enum { + REG_DRAMCTL_PIR = 0x0000, /* PHY Initialization Register */ + REG_DRAMCTL_PGSR = 0x0010, /* PHY General Status Register */ + REG_DRAMCTL_STATR = 0x0018, /* Status Register */ + REG_DRAMCTL_PGCR = 0x0100, /* PHY general configuration registers */ +}; + +/* DRAMCTL register flags */ +enum { + REG_DRAMCTL_PGSR_INITDONE = (1 << 0), + REG_DRAMCTL_PGSR_READ_TIMEOUT = (1 << 13), + REG_DRAMCTL_PGCR_ENABLE_READ_TIMEOUT = (1 << 25), +}; + +enum { + REG_DRAMCTL_STATR_ACTIVE = (1 << 0), +}; + +#define DRAM_MAX_ROW_BITS 16 +#define DRAM_MAX_COL_BITS 13 /* 8192 */ +#define DRAM_MAX_BANK 3 + +static uint64_t dram_autodetect_cells[DRAM_MAX_ROW_BITS] + [DRAM_MAX_BANK] + [DRAM_MAX_COL_BITS]; +struct VirtualDDRChip { + uint32_t ram_size; + uint8_t bank_bits; + uint8_t row_bits; + uint8_t col_bits; +}; + +/* + * Only power of 2 RAM sizes from 256MiB up to 2048MiB are supported, + * 2GiB memory is not supported due to dual rank feature. + */ +static const struct VirtualDDRChip dummy_ddr_chips[] = { + { + .ram_size = 256, + .bank_bits = 3, + .row_bits = 12, + .col_bits = 13, + }, { + .ram_size = 512, + .bank_bits = 3, + .row_bits = 13, + .col_bits = 13, + }, { + .ram_size = 1024, + .bank_bits = 3, + .row_bits = 14, + .col_bits = 13, + }, { + 0 + } +}; + +static const struct VirtualDDRChip *get_match_ddr(uint32_t ram_size) +{ + const struct VirtualDDRChip *ddr; + + for (ddr = &dummy_ddr_chips[0]; ddr->ram_size; ddr++) { + if (ddr->ram_size == ram_size) { + return ddr; + } + } + + return NULL; +} + +static uint64_t *address_to_autodetect_cells(AwR40DramCtlState *s, + const struct VirtualDDRChip *ddr, + uint32_t offset) +{ + int row_index = 0, bank_index = 0, col_index = 0; + uint32_t row_addr, bank_addr, col_addr; + + row_addr = extract32(offset, s->set_col_bits + s->set_bank_bits, + s->set_row_bits); + bank_addr = extract32(offset, s->set_col_bits, s->set_bank_bits); + col_addr = extract32(offset, 0, s->set_col_bits); + + for (int i = 0; i < ddr->row_bits; i++) { + if (row_addr & BIT(i)) { + row_index = i; + } + } + + for (int i = 0; i < ddr->bank_bits; i++) { + if (bank_addr & BIT(i)) { + bank_index = i; + } + } + + for (int i = 0; i < ddr->col_bits; i++) { + if (col_addr & BIT(i)) { + col_index = i; + } + } + + trace_allwinner_r40_dramc_offset_to_cell(offset, row_index, bank_index, + col_index); + return &dram_autodetect_cells[row_index][bank_index][col_index]; +} + +static void allwinner_r40_dramc_map_rows(AwR40DramCtlState *s, uint8_t row_bits, + uint8_t bank_bits, uint8_t col_bits) +{ + const struct VirtualDDRChip *ddr = get_match_ddr(s->ram_size); + bool enable_detect_cells; + + trace_allwinner_r40_dramc_map_rows(row_bits, bank_bits, col_bits); + + if (!ddr) { + return; + } + + s->set_row_bits = row_bits; + s->set_bank_bits = bank_bits; + s->set_col_bits = col_bits; + + enable_detect_cells = ddr->bank_bits != bank_bits + || ddr->row_bits != row_bits + || ddr->col_bits != col_bits; + + if (enable_detect_cells) { + trace_allwinner_r40_dramc_detect_cells_enable(); + } else { + trace_allwinner_r40_dramc_detect_cells_disable(); + } + + memory_region_set_enabled(&s->detect_cells, enable_detect_cells); +} + +static uint64_t allwinner_r40_dramcom_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwR40DramCtlState *s = AW_R40_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_R40_DRAMCOM_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_r40_dramcom_read(offset, s->dramcom[idx], size); + return s->dramcom[idx]; +} + +static void allwinner_r40_dramcom_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwR40DramCtlState *s = AW_R40_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + trace_allwinner_r40_dramcom_write(offset, val, size); + + if (idx >= AW_R40_DRAMCOM_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + switch (offset) { + case REG_DRAMCOM_CR: /* Control Register */ + if (!(val & REG_DRAMCOM_CR_DUAL_RANK)) { + allwinner_r40_dramc_map_rows(s, ((val >> 4) & 0xf) + 1, + ((val >> 2) & 0x1) + 2, + (((val >> 8) & 0xf) + 3)); + } + break; + }; + + s->dramcom[idx] = (uint32_t) val; +} + +static uint64_t allwinner_r40_dramctl_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwR40DramCtlState *s = AW_R40_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_R40_DRAMCTL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_r40_dramctl_read(offset, s->dramctl[idx], size); + return s->dramctl[idx]; +} + +static void allwinner_r40_dramctl_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwR40DramCtlState *s = AW_R40_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + trace_allwinner_r40_dramctl_write(offset, val, size); + + if (idx >= AW_R40_DRAMCTL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + switch (offset) { + case REG_DRAMCTL_PIR: /* PHY Initialization Register */ + s->dramctl[REG_INDEX(REG_DRAMCTL_PGSR)] |= REG_DRAMCTL_PGSR_INITDONE; + s->dramctl[REG_INDEX(REG_DRAMCTL_STATR)] |= REG_DRAMCTL_STATR_ACTIVE; + break; + } + + s->dramctl[idx] = (uint32_t) val; +} + +static uint64_t allwinner_r40_dramphy_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwR40DramCtlState *s = AW_R40_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_R40_DRAMPHY_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_r40_dramphy_read(offset, s->dramphy[idx], size); + return s->dramphy[idx]; +} + +static void allwinner_r40_dramphy_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwR40DramCtlState *s = AW_R40_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + trace_allwinner_r40_dramphy_write(offset, val, size); + + if (idx >= AW_R40_DRAMPHY_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + s->dramphy[idx] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_r40_dramcom_ops = { + .read = allwinner_r40_dramcom_read, + .write = allwinner_r40_dramcom_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static const MemoryRegionOps allwinner_r40_dramctl_ops = { + .read = allwinner_r40_dramctl_read, + .write = allwinner_r40_dramctl_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static const MemoryRegionOps allwinner_r40_dramphy_ops = { + .read = allwinner_r40_dramphy_read, + .write = allwinner_r40_dramphy_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static uint64_t allwinner_r40_detect_read(void *opaque, hwaddr offset, + unsigned size) +{ + AwR40DramCtlState *s = AW_R40_DRAMC(opaque); + const struct VirtualDDRChip *ddr = get_match_ddr(s->ram_size); + uint64_t data = 0; + + if (ddr) { + data = *address_to_autodetect_cells(s, ddr, (uint32_t)offset); + } + + trace_allwinner_r40_dramc_detect_cell_read(offset, data); + return data; +} + +static void allwinner_r40_detect_write(void *opaque, hwaddr offset, + uint64_t data, unsigned size) +{ + AwR40DramCtlState *s = AW_R40_DRAMC(opaque); + const struct VirtualDDRChip *ddr = get_match_ddr(s->ram_size); + + if (ddr) { + uint64_t *cell = address_to_autodetect_cells(s, ddr, (uint32_t)offset); + trace_allwinner_r40_dramc_detect_cell_write(offset, data); + *cell = data; + } +} + +static const MemoryRegionOps allwinner_r40_detect_ops = { + .read = allwinner_r40_detect_read, + .write = allwinner_r40_detect_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +/* + * mctl_r40_detect_rank_count in u-boot will write the high 1G of DDR + * to detect wether the board support dual_rank or not. Create a virtual memory + * if the board's ram_size less or equal than 1G, and set read time out flag of + * REG_DRAMCTL_PGSR when the user touch this high dram. + */ +static uint64_t allwinner_r40_dualrank_detect_read(void *opaque, hwaddr offset, + unsigned size) +{ + AwR40DramCtlState *s = AW_R40_DRAMC(opaque); + uint32_t reg; + + reg = s->dramctl[REG_INDEX(REG_DRAMCTL_PGCR)]; + if (reg & REG_DRAMCTL_PGCR_ENABLE_READ_TIMEOUT) { /* Enable read time out */ + /* + * this driver only support one rank, mark READ_TIMEOUT when try + * read the second rank. + */ + s->dramctl[REG_INDEX(REG_DRAMCTL_PGSR)] + |= REG_DRAMCTL_PGSR_READ_TIMEOUT; + } + + return 0; +} + +static const MemoryRegionOps allwinner_r40_dualrank_detect_ops = { + .read = allwinner_r40_dualrank_detect_read, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_r40_dramc_reset(DeviceState *dev) +{ + AwR40DramCtlState *s = AW_R40_DRAMC(dev); + + /* Set default values for registers */ + memset(&s->dramcom, 0, sizeof(s->dramcom)); + memset(&s->dramctl, 0, sizeof(s->dramctl)); + memset(&s->dramphy, 0, sizeof(s->dramphy)); +} + +static void allwinner_r40_dramc_realize(DeviceState *dev, Error **errp) +{ + AwR40DramCtlState *s = AW_R40_DRAMC(dev); + + if (!get_match_ddr(s->ram_size)) { + error_report("%s: ram-size %u MiB is not supported", + __func__, s->ram_size); + exit(1); + } + + /* detect_cells */ + sysbus_mmio_map_overlap(SYS_BUS_DEVICE(s), 3, s->ram_addr, 10); + memory_region_set_enabled(&s->detect_cells, false); + + /* + * We only support DRAM size up to 1G now, so prepare a high memory page + * after 1G for dualrank detect. index = 4 + */ + memory_region_init_io(&s->dram_high, OBJECT(s), + &allwinner_r40_dualrank_detect_ops, s, + "DRAMHIGH", KiB); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->dram_high); + sysbus_mmio_map(SYS_BUS_DEVICE(s), 4, s->ram_addr + GiB); +} + +static void allwinner_r40_dramc_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwR40DramCtlState *s = AW_R40_DRAMC(obj); + + /* DRAMCOM registers, index 0 */ + memory_region_init_io(&s->dramcom_iomem, OBJECT(s), + &allwinner_r40_dramcom_ops, s, + "DRAMCOM", 4 * KiB); + sysbus_init_mmio(sbd, &s->dramcom_iomem); + + /* DRAMCTL registers, index 1 */ + memory_region_init_io(&s->dramctl_iomem, OBJECT(s), + &allwinner_r40_dramctl_ops, s, + "DRAMCTL", 4 * KiB); + sysbus_init_mmio(sbd, &s->dramctl_iomem); + + /* DRAMPHY registers. index 2 */ + memory_region_init_io(&s->dramphy_iomem, OBJECT(s), + &allwinner_r40_dramphy_ops, s, + "DRAMPHY", 4 * KiB); + sysbus_init_mmio(sbd, &s->dramphy_iomem); + + /* R40 support max 2G memory but we only support up to 1G now. index 3 */ + memory_region_init_io(&s->detect_cells, OBJECT(s), + &allwinner_r40_detect_ops, s, + "DRAMCELLS", 1 * GiB); + sysbus_init_mmio(sbd, &s->detect_cells); +} + +static Property allwinner_r40_dramc_properties[] = { + DEFINE_PROP_UINT64("ram-addr", AwR40DramCtlState, ram_addr, 0x0), + DEFINE_PROP_UINT32("ram-size", AwR40DramCtlState, ram_size, 256), /* MiB */ + DEFINE_PROP_END_OF_LIST() +}; + +static const VMStateDescription allwinner_r40_dramc_vmstate = { + .name = "allwinner-r40-dramc", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(dramcom, AwR40DramCtlState, + AW_R40_DRAMCOM_REGS_NUM), + VMSTATE_UINT32_ARRAY(dramctl, AwR40DramCtlState, + AW_R40_DRAMCTL_REGS_NUM), + VMSTATE_UINT32_ARRAY(dramphy, AwR40DramCtlState, + AW_R40_DRAMPHY_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_r40_dramc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_r40_dramc_reset; + dc->vmsd = &allwinner_r40_dramc_vmstate; + dc->realize = allwinner_r40_dramc_realize; + device_class_set_props(dc, allwinner_r40_dramc_properties); +} + +static const TypeInfo allwinner_r40_dramc_info = { + .name = TYPE_AW_R40_DRAMC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_r40_dramc_init, + .instance_size = sizeof(AwR40DramCtlState), + .class_init = allwinner_r40_dramc_class_init, +}; + +static void allwinner_r40_dramc_register(void) +{ + type_register_static(&allwinner_r40_dramc_info); +} + +type_init(allwinner_r40_dramc_register) 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_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-sysctrl.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-sid.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_R40', if_true: files('allwinner-r40-ccu.c')) +softmmu_ss.add(when: 'CONFIG_ALLWINNER_R40', if_true: files('allwinner-r40-dramc.c')) softmmu_ss.add(when: 'CONFIG_AXP2XX_PMU', if_true: files('axp2xx.c')) softmmu_ss.add(when: 'CONFIG_REALVIEW', if_true: files('arm_sysctl.c')) softmmu_ss.add(when: 'CONFIG_NSERIES', if_true: files('cbus.c')) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ allwinner_h3_dramctl_write(uint64_t offset, uint64_t data, unsigned size) "Write allwinner_h3_dramphy_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 allwinner_h3_dramphy_write(uint64_t offset, uint64_t data, unsigned size) "write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +# allwinner-r40-dramc.c +allwinner_r40_dramc_detect_cells_disable(void) "Disable detect cells" +allwinner_r40_dramc_detect_cells_enable(void) "Enable detect cells" +allwinner_r40_dramc_map_rows(uint8_t row_bits, uint8_t bank_bits, uint8_t col_bits) "DRAM layout: row_bits %d, bank_bits %d, col_bits %d" +allwinner_r40_dramc_offset_to_cell(uint64_t offset, int row, int bank, int col) "offset 0x%" PRIx64 " row %d bank %d col %d" +allwinner_r40_dramc_detect_cell_write(uint64_t offset, uint64_t data) "offset 0x%" PRIx64 " data 0x%" PRIx64 "" +allwinner_r40_dramc_detect_cell_read(uint64_t offset, uint64_t data) "offset 0x%" PRIx64 " data 0x%" PRIx64 "" +allwinner_r40_dramcom_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_r40_dramcom_write(uint64_t offset, uint64_t data, unsigned size) "Write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_r40_dramctl_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_r40_dramctl_write(uint64_t offset, uint64_t data, unsigned size) "Write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_r40_dramphy_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_r40_dramphy_write(uint64_t offset, uint64_t data, unsigned size) "write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 + # allwinner-sid.c allwinner_sid_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 allwinner_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> A64's sd register was similar to H3, and it introduced a new register named SAMP_DL_REG location at 0x144. The dma descriptor buffer size of mmc2 is only 8K and the other mmc controllers has 64K. Also fix allwinner-r40's mmc controller type. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/sd/allwinner-sdhost.h | 9 ++++ hw/arm/allwinner-r40.c | 2 +- hw/sd/allwinner-sdhost.c | 72 ++++++++++++++++++++++++++++++-- 3 files changed, 79 insertions(+), 4 deletions(-) diff --git a/include/hw/sd/allwinner-sdhost.h b/include/hw/sd/allwinner-sdhost.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/sd/allwinner-sdhost.h +++ b/include/hw/sd/allwinner-sdhost.h @@ -XXX,XX +XXX,XX @@ /** Allwinner sun5i family and newer (A13, H2+, H3, etc) */ #define TYPE_AW_SDHOST_SUN5I TYPE_AW_SDHOST "-sun5i" +/** Allwinner sun50i-a64 */ +#define TYPE_AW_SDHOST_SUN50I_A64 TYPE_AW_SDHOST "-sun50i-a64" + +/** Allwinner sun50i-a64 emmc */ +#define TYPE_AW_SDHOST_SUN50I_A64_EMMC TYPE_AW_SDHOST "-sun50i-a64-emmc" + /** @} */ /** @@ -XXX,XX +XXX,XX @@ struct AwSdHostState { uint32_t startbit_detect; /**< eMMC DDR Start Bit Detection Control */ uint32_t response_crc; /**< Response CRC */ uint32_t data_crc[8]; /**< Data CRC */ + uint32_t sample_delay; /**< Sample delay control */ uint32_t status_crc; /**< Status CRC */ /** @} */ @@ -XXX,XX +XXX,XX @@ struct AwSdHostClass { size_t max_desc_size; bool is_sun4i; + /** does the IP block support autocalibration? */ + bool can_calibrate; }; #endif /* HW_SD_ALLWINNER_SDHOST_H */ diff --git a/hw/arm/allwinner-r40.c b/hw/arm/allwinner-r40.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-r40.c +++ b/hw/arm/allwinner-r40.c @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_init(Object *obj) for (int i = 0; i < AW_R40_NUM_MMCS; i++) { object_initialize_child(obj, mmc_names[i], &s->mmc[i], - TYPE_AW_SDHOST_SUN5I); + TYPE_AW_SDHOST_SUN50I_A64); } object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C_SUN6I); diff --git a/hw/sd/allwinner-sdhost.c b/hw/sd/allwinner-sdhost.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/allwinner-sdhost.c +++ b/hw/sd/allwinner-sdhost.c @@ -XXX,XX +XXX,XX @@ enum { REG_SD_DATA1_CRC = 0x12C, /* CRC Data 1 from card/eMMC */ REG_SD_DATA0_CRC = 0x130, /* CRC Data 0 from card/eMMC */ REG_SD_CRC_STA = 0x134, /* CRC status from card/eMMC during write */ + REG_SD_SAMP_DL = 0x144, /* Sample Delay Control (sun50i-a64) */ REG_SD_FIFO = 0x200, /* Read/Write FIFO */ }; @@ -XXX,XX +XXX,XX @@ enum { REG_SD_RES_CRC_RST = 0x0, REG_SD_DATA_CRC_RST = 0x0, REG_SD_CRC_STA_RST = 0x0, + REG_SD_SAMPLE_DL_RST = 0x00002000, REG_SD_FIFO_RST = 0x0, }; @@ -XXX,XX +XXX,XX @@ static uint64_t allwinner_sdhost_read(void *opaque, hwaddr offset, { AwSdHostState *s = AW_SDHOST(opaque); AwSdHostClass *sc = AW_SDHOST_GET_CLASS(s); + bool out_of_bounds = false; uint32_t res = 0; switch (offset) { @@ -XXX,XX +XXX,XX @@ static uint64_t allwinner_sdhost_read(void *opaque, hwaddr offset, case REG_SD_FIFO: /* Read/Write FIFO */ res = allwinner_sdhost_fifo_read(s); break; + case REG_SD_SAMP_DL: /* Sample Delay */ + if (sc->can_calibrate) { + res = s->sample_delay; + } else { + out_of_bounds = true; + } + break; default: - qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset %" - HWADDR_PRIx"\n", __func__, offset); + out_of_bounds = true; res = 0; break; } + if (out_of_bounds) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset %" + HWADDR_PRIx"\n", __func__, offset); + } + trace_allwinner_sdhost_read(offset, res, size); return res; } @@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_write(void *opaque, hwaddr offset, { AwSdHostState *s = AW_SDHOST(opaque); AwSdHostClass *sc = AW_SDHOST_GET_CLASS(s); + bool out_of_bounds = false; trace_allwinner_sdhost_write(offset, value, size); @@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_write(void *opaque, hwaddr offset, case REG_SD_DATA0_CRC: /* CRC Data 0 from card/eMMC */ case REG_SD_CRC_STA: /* CRC status from card/eMMC in write operation */ break; + case REG_SD_SAMP_DL: /* Sample delay control */ + if (sc->can_calibrate) { + s->sample_delay = value; + } else { + out_of_bounds = true; + } + break; default: + out_of_bounds = true; + break; + } + + if (out_of_bounds) { qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset %" HWADDR_PRIx"\n", __func__, offset); - break; } } @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_allwinner_sdhost = { VMSTATE_UINT32(response_crc, AwSdHostState), VMSTATE_UINT32_ARRAY(data_crc, AwSdHostState, 8), VMSTATE_UINT32(status_crc, AwSdHostState), + VMSTATE_UINT32(sample_delay, AwSdHostState), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_realize(DeviceState *dev, Error **errp) static void allwinner_sdhost_reset(DeviceState *dev) { AwSdHostState *s = AW_SDHOST(dev); + AwSdHostClass *sc = AW_SDHOST_GET_CLASS(s); s->global_ctl = REG_SD_GCTL_RST; s->clock_ctl = REG_SD_CKCR_RST; @@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_reset(DeviceState *dev) } s->status_crc = REG_SD_CRC_STA_RST; + + if (sc->can_calibrate) { + s->sample_delay = REG_SD_SAMPLE_DL_RST; + } } static void allwinner_sdhost_bus_class_init(ObjectClass *klass, void *data) @@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_sun4i_class_init(ObjectClass *klass, void *data) AwSdHostClass *sc = AW_SDHOST_CLASS(klass); sc->max_desc_size = 8 * KiB; sc->is_sun4i = true; + sc->can_calibrate = false; } static void allwinner_sdhost_sun5i_class_init(ObjectClass *klass, void *data) @@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_sun5i_class_init(ObjectClass *klass, void *data) AwSdHostClass *sc = AW_SDHOST_CLASS(klass); sc->max_desc_size = 64 * KiB; sc->is_sun4i = false; + sc->can_calibrate = false; +} + +static void allwinner_sdhost_sun50i_a64_class_init(ObjectClass *klass, + void *data) +{ + AwSdHostClass *sc = AW_SDHOST_CLASS(klass); + sc->max_desc_size = 64 * KiB; + sc->is_sun4i = false; + sc->can_calibrate = true; +} + +static void allwinner_sdhost_sun50i_a64_emmc_class_init(ObjectClass *klass, + void *data) +{ + AwSdHostClass *sc = AW_SDHOST_CLASS(klass); + sc->max_desc_size = 8 * KiB; + sc->is_sun4i = false; + sc->can_calibrate = true; } static const TypeInfo allwinner_sdhost_info = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo allwinner_sdhost_sun5i_info = { .class_init = allwinner_sdhost_sun5i_class_init, }; +static const TypeInfo allwinner_sdhost_sun50i_a64_info = { + .name = TYPE_AW_SDHOST_SUN50I_A64, + .parent = TYPE_AW_SDHOST, + .class_init = allwinner_sdhost_sun50i_a64_class_init, +}; + +static const TypeInfo allwinner_sdhost_sun50i_a64_emmc_info = { + .name = TYPE_AW_SDHOST_SUN50I_A64_EMMC, + .parent = TYPE_AW_SDHOST, + .class_init = allwinner_sdhost_sun50i_a64_emmc_class_init, +}; + static const TypeInfo allwinner_sdhost_bus_info = { .name = TYPE_AW_SDHOST_BUS, .parent = TYPE_SD_BUS, @@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_register_types(void) type_register_static(&allwinner_sdhost_info); type_register_static(&allwinner_sdhost_sun4i_info); type_register_static(&allwinner_sdhost_sun5i_info); + type_register_static(&allwinner_sdhost_sun50i_a64_info); + type_register_static(&allwinner_sdhost_sun50i_a64_emmc_info); type_register_static(&allwinner_sdhost_bus_info); } -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> R40 has two ethernet controllers named as emac and gmac. The emac is compatibled with A10, and the GMAC is compatibled with H3. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-r40.h | 6 ++++ hw/arm/allwinner-r40.c | 50 ++++++++++++++++++++++++++++++++-- hw/arm/bananapi_m2u.c | 3 ++ 3 files changed, 57 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/allwinner-r40.h b/include/hw/arm/allwinner-r40.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-r40.h +++ b/include/hw/arm/allwinner-r40.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-r40-ccu.h" #include "hw/misc/allwinner-r40-dramc.h" #include "hw/i2c/allwinner-i2c.h" +#include "hw/net/allwinner_emac.h" +#include "hw/net/allwinner-sun8i-emac.h" #include "target/arm/cpu.h" #include "sysemu/block-backend.h" @@ -XXX,XX +XXX,XX @@ enum { AW_R40_DEV_SRAM_A2, AW_R40_DEV_SRAM_A3, AW_R40_DEV_SRAM_A4, + AW_R40_DEV_EMAC, AW_R40_DEV_MMC0, AW_R40_DEV_MMC1, AW_R40_DEV_MMC2, @@ -XXX,XX +XXX,XX @@ enum { AW_R40_DEV_UART6, AW_R40_DEV_UART7, AW_R40_DEV_TWI0, + AW_R40_DEV_GMAC, AW_R40_DEV_GIC_DIST, AW_R40_DEV_GIC_CPU, AW_R40_DEV_GIC_HYP, @@ -XXX,XX +XXX,XX @@ struct AwR40State { AwR40ClockCtlState ccu; AwR40DramCtlState dramc; AWI2CState i2c0; + AwEmacState emac; + AwSun8iEmacState gmac; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/hw/arm/allwinner-r40.c b/hw/arm/allwinner-r40.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-r40.c +++ b/hw/arm/allwinner-r40.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_r40_memmap[] = { [AW_R40_DEV_SRAM_A2] = 0x00004000, [AW_R40_DEV_SRAM_A3] = 0x00008000, [AW_R40_DEV_SRAM_A4] = 0x0000b400, + [AW_R40_DEV_EMAC] = 0x01c0b000, [AW_R40_DEV_MMC0] = 0x01c0f000, [AW_R40_DEV_MMC1] = 0x01c10000, [AW_R40_DEV_MMC2] = 0x01c11000, @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_r40_memmap[] = { [AW_R40_DEV_UART6] = 0x01c29800, [AW_R40_DEV_UART7] = 0x01c29c00, [AW_R40_DEV_TWI0] = 0x01c2ac00, + [AW_R40_DEV_GMAC] = 0x01c50000, [AW_R40_DEV_DRAMCOM] = 0x01c62000, [AW_R40_DEV_DRAMCTL] = 0x01c63000, [AW_R40_DEV_DRAMPHY] = 0x01c65000, @@ -XXX,XX +XXX,XX @@ static struct AwR40Unimplemented r40_unimplemented[] = { { "spi1", 0x01c06000, 4 * KiB }, { "cs0", 0x01c09000, 4 * KiB }, { "keymem", 0x01c0a000, 4 * KiB }, - { "emac", 0x01c0b000, 4 * KiB }, { "usb0-otg", 0x01c13000, 4 * KiB }, { "usb0-host", 0x01c14000, 4 * KiB }, { "crypto", 0x01c15000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ static struct AwR40Unimplemented r40_unimplemented[] = { { "tvd2", 0x01c33000, 4 * KiB }, { "tvd3", 0x01c34000, 4 * KiB }, { "gpu", 0x01c40000, 64 * KiB }, - { "gmac", 0x01c50000, 64 * KiB }, { "hstmr", 0x01c60000, 4 * KiB }, { "tcon-top", 0x01c70000, 4 * KiB }, { "lcd0", 0x01c71000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ enum { AW_R40_GIC_SPI_MMC1 = 33, AW_R40_GIC_SPI_MMC2 = 34, AW_R40_GIC_SPI_MMC3 = 35, + AW_R40_GIC_SPI_EMAC = 55, + AW_R40_GIC_SPI_GMAC = 85, }; /* Allwinner R40 general constants */ @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_init(Object *obj) object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C_SUN6I); + object_initialize_child(obj, "emac", &s->emac, TYPE_AW_EMAC); + object_initialize_child(obj, "gmac", &s->gmac, TYPE_AW_SUN8I_EMAC); + object_property_add_alias(obj, "gmac-phy-addr", + OBJECT(&s->gmac), "phy-addr"); + object_initialize_child(obj, "dramc", &s->dramc, TYPE_AW_R40_DRAMC); object_property_add_alias(obj, "ram-addr", OBJECT(&s->dramc), "ram-addr"); @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_init(Object *obj) static void allwinner_r40_realize(DeviceState *dev, Error **errp) { + const char *r40_nic_models[] = { "gmac", "emac", NULL }; AwR40State *s = AW_R40(dev); unsigned i; @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 2, s->memmap[AW_R40_DEV_DRAMPHY]); + /* nic support gmac and emac */ + for (int i = 0; i < ARRAY_SIZE(r40_nic_models) - 1; i++) { + NICInfo *nic = &nd_table[i]; + + if (!nic->used) { + continue; + } + if (qemu_show_nic_models(nic->model, r40_nic_models)) { + exit(0); + } + + switch (qemu_find_nic_model(nic, r40_nic_models, r40_nic_models[0])) { + case 0: /* gmac */ + qdev_set_nic_properties(DEVICE(&s->gmac), nic); + break; + case 1: /* emac */ + qdev_set_nic_properties(DEVICE(&s->emac), nic); + break; + default: + exit(1); + break; + } + } + + /* GMAC */ + object_property_set_link(OBJECT(&s->gmac), "dma-memory", + OBJECT(get_system_memory()), &error_fatal); + sysbus_realize(SYS_BUS_DEVICE(&s->gmac), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gmac), 0, s->memmap[AW_R40_DEV_GMAC]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gmac), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_R40_GIC_SPI_GMAC)); + + /* EMAC */ + sysbus_realize(SYS_BUS_DEVICE(&s->emac), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->emac), 0, s->memmap[AW_R40_DEV_EMAC]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->emac), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_R40_GIC_SPI_EMAC)); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(r40_unimplemented); i++) { create_unimplemented_device(r40_unimplemented[i].device_name, diff --git a/hw/arm/bananapi_m2u.c b/hw/arm/bananapi_m2u.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bananapi_m2u.c +++ b/hw/arm/bananapi_m2u.c @@ -XXX,XX +XXX,XX @@ static void bpim2u_init(MachineState *machine) object_property_set_int(OBJECT(r40), "ram-size", r40->ram_size, &error_abort); + /* GMAC PHY */ + object_property_set_uint(OBJECT(r40), "gmac-phy-addr", 1, &error_abort); + /* Mark R40 object realized */ qdev_realize(DEVICE(r40), NULL, &error_abort); -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> Only a few important registers are added, especially the SRAM_VER register. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-r40.h | 3 + include/hw/misc/allwinner-sramc.h | 69 +++++++++++ hw/arm/allwinner-r40.c | 7 +- hw/misc/allwinner-sramc.c | 184 ++++++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/misc/Kconfig | 3 + hw/misc/meson.build | 1 + hw/misc/trace-events | 4 + 8 files changed, 271 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-sramc.h create mode 100644 hw/misc/allwinner-sramc.c diff --git a/include/hw/arm/allwinner-r40.h b/include/hw/arm/allwinner-r40.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-r40.h +++ b/include/hw/arm/allwinner-r40.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/allwinner-sdhost.h" #include "hw/misc/allwinner-r40-ccu.h" #include "hw/misc/allwinner-r40-dramc.h" +#include "hw/misc/allwinner-sramc.h" #include "hw/i2c/allwinner-i2c.h" #include "hw/net/allwinner_emac.h" #include "hw/net/allwinner-sun8i-emac.h" @@ -XXX,XX +XXX,XX @@ enum { AW_R40_DEV_SRAM_A2, AW_R40_DEV_SRAM_A3, AW_R40_DEV_SRAM_A4, + AW_R40_DEV_SRAMC, AW_R40_DEV_EMAC, AW_R40_DEV_MMC0, AW_R40_DEV_MMC1, @@ -XXX,XX +XXX,XX @@ struct AwR40State { ARMCPU cpus[AW_R40_NUM_CPUS]; const hwaddr *memmap; + AwSRAMCState sramc; AwA10PITState timer; AwSdHostState mmc[AW_R40_NUM_MMCS]; AwR40ClockCtlState ccu; diff --git a/include/hw/misc/allwinner-sramc.h b/include/hw/misc/allwinner-sramc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-sramc.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner SRAM controller emulation + * + * Copyright (C) 2023 qianfan Zhao <qianfanguijin@163.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_MISC_ALLWINNER_SRAMC_H +#define HW_MISC_ALLWINNER_SRAMC_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "qemu/uuid.h" + +/** + * Object model + * @{ + */ +#define TYPE_AW_SRAMC "allwinner-sramc" +#define TYPE_AW_SRAMC_SUN8I_R40 TYPE_AW_SRAMC "-sun8i-r40" +OBJECT_DECLARE_TYPE(AwSRAMCState, AwSRAMCClass, AW_SRAMC) + +/** @} */ + +/** + * Allwinner SRAMC object instance state + */ +struct AwSRAMCState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /* registers */ + uint32_t sram_ctl1; + uint32_t sram_ver; + uint32_t sram_soft_entry_reg0; +}; + +/** + * Allwinner SRAM Controller class-level struct. + * + * This struct is filled by each sunxi device specific code + * such that the generic code can use this struct to support + * all devices. + */ +struct AwSRAMCClass { + /*< private >*/ + SysBusDeviceClass parent_class; + /*< public >*/ + + uint32_t sram_version_code; +}; + +#endif /* HW_MISC_ALLWINNER_SRAMC_H */ diff --git a/hw/arm/allwinner-r40.c b/hw/arm/allwinner-r40.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-r40.c +++ b/hw/arm/allwinner-r40.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_r40_memmap[] = { [AW_R40_DEV_SRAM_A2] = 0x00004000, [AW_R40_DEV_SRAM_A3] = 0x00008000, [AW_R40_DEV_SRAM_A4] = 0x0000b400, + [AW_R40_DEV_SRAMC] = 0x01c00000, [AW_R40_DEV_EMAC] = 0x01c0b000, [AW_R40_DEV_MMC0] = 0x01c0f000, [AW_R40_DEV_MMC1] = 0x01c10000, @@ -XXX,XX +XXX,XX @@ struct AwR40Unimplemented { static struct AwR40Unimplemented r40_unimplemented[] = { { "d-engine", 0x01000000, 4 * MiB }, { "d-inter", 0x01400000, 128 * KiB }, - { "sram-c", 0x01c00000, 4 * KiB }, { "dma", 0x01c02000, 4 * KiB }, { "nfdc", 0x01c03000, 4 * KiB }, { "ts", 0x01c04000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_init(Object *obj) "ram-addr"); object_property_add_alias(obj, "ram-size", OBJECT(&s->dramc), "ram-size"); + + object_initialize_child(obj, "sramc", &s->sramc, TYPE_AW_SRAMC_SUN8I_R40); } static void allwinner_r40_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_r40_realize(DeviceState *dev, Error **errp) AW_R40_GIC_SPI_TIMER1)); /* SRAM */ + sysbus_realize(SYS_BUS_DEVICE(&s->sramc), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->sramc), 0, s->memmap[AW_R40_DEV_SRAMC]); + memory_region_init_ram(&s->sram_a1, OBJECT(dev), "sram A1", 16 * KiB, &error_abort); memory_region_init_ram(&s->sram_a2, OBJECT(dev), "sram A2", diff --git a/hw/misc/allwinner-sramc.c b/hw/misc/allwinner-sramc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-sramc.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner R40 SRAM controller emulation + * + * Copyright (C) 2023 qianfan Zhao <qianfanguijin@163.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/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qapi/error.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" +#include "hw/misc/allwinner-sramc.h" +#include "trace.h" + +/* + * register offsets + * https://linux-sunxi.org/SRAM_Controller_Register_Guide + */ +enum { + REG_SRAM_CTL1_CFG = 0x04, /* SRAM Control register 1 */ + REG_SRAM_VER = 0x24, /* SRAM Version register */ + REG_SRAM_R40_SOFT_ENTRY_REG0 = 0xbc, +}; + +/* REG_SRAMC_VERSION bit defines */ +#define SRAM_VER_READ_ENABLE (1 << 15) +#define SRAM_VER_VERSION_SHIFT 16 +#define SRAM_VERSION_SUN8I_R40 0x1701 + +static uint64_t allwinner_sramc_read(void *opaque, hwaddr offset, + unsigned size) +{ + AwSRAMCState *s = AW_SRAMC(opaque); + AwSRAMCClass *sc = AW_SRAMC_GET_CLASS(s); + uint64_t val = 0; + + switch (offset) { + case REG_SRAM_CTL1_CFG: + val = s->sram_ctl1; + break; + case REG_SRAM_VER: + /* bit15: lock bit, set this bit before reading this register */ + if (s->sram_ver & SRAM_VER_READ_ENABLE) { + val = SRAM_VER_READ_ENABLE | + (sc->sram_version_code << SRAM_VER_VERSION_SHIFT); + } + break; + case REG_SRAM_R40_SOFT_ENTRY_REG0: + val = s->sram_soft_entry_reg0; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_sramc_read(offset, val); + + return val; +} + +static void allwinner_sramc_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwSRAMCState *s = AW_SRAMC(opaque); + + trace_allwinner_sramc_write(offset, val); + + switch (offset) { + case REG_SRAM_CTL1_CFG: + s->sram_ctl1 = val; + break; + case REG_SRAM_VER: + /* Only the READ_ENABLE bit is writeable */ + s->sram_ver = val & SRAM_VER_READ_ENABLE; + break; + case REG_SRAM_R40_SOFT_ENTRY_REG0: + s->sram_soft_entry_reg0 = val; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } +} + +static const MemoryRegionOps allwinner_sramc_ops = { + .read = allwinner_sramc_read, + .write = allwinner_sramc_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static const VMStateDescription allwinner_sramc_vmstate = { + .name = "allwinner-sramc", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(sram_ver, AwSRAMCState), + VMSTATE_UINT32(sram_soft_entry_reg0, AwSRAMCState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_sramc_reset(DeviceState *dev) +{ + AwSRAMCState *s = AW_SRAMC(dev); + AwSRAMCClass *sc = AW_SRAMC_GET_CLASS(s); + + switch (sc->sram_version_code) { + case SRAM_VERSION_SUN8I_R40: + s->sram_ctl1 = 0x1300; + break; + } +} + +static void allwinner_sramc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_sramc_reset; + dc->vmsd = &allwinner_sramc_vmstate; +} + +static void allwinner_sramc_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwSRAMCState *s = AW_SRAMC(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_sramc_ops, s, + TYPE_AW_SRAMC, 1 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const TypeInfo allwinner_sramc_info = { + .name = TYPE_AW_SRAMC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_sramc_init, + .instance_size = sizeof(AwSRAMCState), + .class_init = allwinner_sramc_class_init, +}; + +static void allwinner_r40_sramc_class_init(ObjectClass *klass, void *data) +{ + AwSRAMCClass *sc = AW_SRAMC_CLASS(klass); + + sc->sram_version_code = SRAM_VERSION_SUN8I_R40; +} + +static const TypeInfo allwinner_r40_sramc_info = { + .name = TYPE_AW_SRAMC_SUN8I_R40, + .parent = TYPE_AW_SRAMC, + .class_init = allwinner_r40_sramc_class_init, +}; + +static void allwinner_sramc_register(void) +{ + type_register_static(&allwinner_sramc_info); + type_register_static(&allwinner_r40_sramc_info); +} + +type_init(allwinner_sramc_register) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_H3 config ALLWINNER_R40 bool default y if TCG && ARM + select ALLWINNER_SRAMC select ALLWINNER_A10_PIT select AXP2XX_PMU select SERIAL diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config VIRT_CTRL config LASI bool +config ALLWINNER_SRAMC + bool + config ALLWINNER_A10_CCM bool 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 @@ subdir('macio') softmmu_ss.add(when: 'CONFIG_IVSHMEM_DEVICE', if_true: files('ivshmem.c')) +softmmu_ss.add(when: 'CONFIG_ALLWINNER_SRAMC', if_true: files('allwinner-sramc.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_CCM', if_true: files('allwinner-a10-ccm.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_DRAMC', if_true: files('allwinner-a10-dramc.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-ccu.c')) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ allwinner_r40_dramphy_write(uint64_t offset, uint64_t data, unsigned size) "writ allwinner_sid_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 allwinner_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +# allwinner-sramc.c +allwinner_sramc_read(uint64_t offset, uint64_t data) "offset 0x%" PRIx64 " data 0x%" PRIx64 +allwinner_sramc_write(uint64_t offset, uint64_t data) "offset 0x%" PRIx64 " data 0x%" PRIx64 + # avr_power.c avr_power_read(uint8_t value) "power_reduc read value:%u" avr_power_write(uint8_t value) "power_reduc write value:%u" -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> Add test case for booting from initrd and sd card. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Tested-by: Niek Linnenbank <nieklinnenbank@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/avocado/boot_linux_console.py | 176 ++++++++++++++++++++++++++++ 1 file changed, 176 insertions(+) diff --git a/tests/avocado/boot_linux_console.py b/tests/avocado/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/boot_linux_console.py +++ b/tests/avocado/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def test_arm_quanta_gsj_initrd(self): self.wait_for_console_pattern( 'Give root password for system maintenance') + def test_arm_bpim2u(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:bpim2u + :avocado: tags=accel:tcg + """ + deb_url = ('https://apt.armbian.com/pool/main/l/linux-5.10.16-sunxi/' + 'linux-image-current-sunxi_21.02.2_armhf.deb') + deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, + '/boot/vmlinuz-5.10.16-sunxi') + dtb_path = ('/usr/lib/linux-image-current-sunxi/' + 'sun8i-r40-bananapi-m2-ultra.dtb') + dtb_path = self.extract_from_deb(deb_path, dtb_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200n8 ' + 'earlycon=uart,mmio32,0x1c28000') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-append', kernel_command_line) + self.vm.launch() + console_pattern = 'Kernel command line: %s' % kernel_command_line + self.wait_for_console_pattern(console_pattern) + + def test_arm_bpim2u_initrd(self): + """ + :avocado: tags=arch:arm + :avocado: tags=accel:tcg + :avocado: tags=machine:bpim2u + """ + deb_url = ('https://apt.armbian.com/pool/main/l/linux-5.10.16-sunxi/' + 'linux-image-current-sunxi_21.02.2_armhf.deb') + deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, + '/boot/vmlinuz-5.10.16-sunxi') + dtb_path = ('/usr/lib/linux-image-current-sunxi/' + 'sun8i-r40-bananapi-m2-ultra.dtb') + dtb_path = self.extract_from_deb(deb_path, dtb_path) + 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 + + 'console=ttyS0,115200 ' + 'panic=-1 noreboot') + 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', + 'Allwinner sun8i Family') + exec_command_and_wait_for_pattern(self, 'cat /proc/iomem', + 'system-control@1c00000') + exec_command_and_wait_for_pattern(self, 'reboot', + 'reboot: Restarting system') + # Wait for VM to shut down gracefully + self.vm.wait() + + def test_arm_bpim2u_gmac(self): + """ + :avocado: tags=arch:arm + :avocado: tags=accel:tcg + :avocado: tags=machine:bpim2u + :avocado: tags=device:sd + """ + self.require_netdev('user') + + deb_url = ('https://apt.armbian.com/pool/main/l/linux-5.10.16-sunxi/' + 'linux-image-current-sunxi_21.02.2_armhf.deb') + deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, + '/boot/vmlinuz-5.10.16-sunxi') + dtb_path = ('/usr/lib/linux-image-current-sunxi/' + 'sun8i-r40-bananapi-m2-ultra.dtb') + dtb_path = self.extract_from_deb(deb_path, dtb_path) + rootfs_url = ('http://storage.kernelci.org/images/rootfs/buildroot/' + 'buildroot-baseline/20221116.0/armel/rootfs.ext2.xz') + rootfs_hash = 'fae32f337c7b87547b10f42599acf109da8b6d9a' + rootfs_path_xz = self.fetch_asset(rootfs_url, asset_hash=rootfs_hash) + rootfs_path = os.path.join(self.workdir, 'rootfs.cpio') + archive.lzma_uncompress(rootfs_path_xz, rootfs_path) + image_pow2ceil_expand(rootfs_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200 ' + 'root=/dev/mmcblk0 rootwait rw ' + 'panic=-1 noreboot') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-drive', 'file=' + rootfs_path + ',if=sd,format=raw', + '-net', 'nic,model=gmac,netdev=host_gmac', + '-netdev', 'user,id=host_gmac', + '-append', kernel_command_line, + '-no-reboot') + self.vm.launch() + shell_ready = "/bin/sh: can't access tty; job control turned off" + self.wait_for_console_pattern(shell_ready) + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'Allwinner sun8i Family') + exec_command_and_wait_for_pattern(self, 'cat /proc/partitions', + 'mmcblk0') + exec_command_and_wait_for_pattern(self, 'ifconfig eth0 up', + 'eth0: Link is Up') + exec_command_and_wait_for_pattern(self, 'udhcpc eth0', + 'udhcpc: lease of 10.0.2.15 obtained') + exec_command_and_wait_for_pattern(self, 'ping -c 3 10.0.2.2', + '3 packets transmitted, 3 packets received, 0% packet loss') + exec_command_and_wait_for_pattern(self, 'reboot', + 'reboot: Restarting system') + # Wait for VM to shut down gracefully + self.vm.wait() + + @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') + def test_arm_bpim2u_openwrt_22_03_3(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:bpim2u + :avocado: tags=device:sd + """ + + # This test download a 8.9 MiB compressed image and expand it + # to 127 MiB. + image_url = ('https://downloads.openwrt.org/releases/22.03.3/targets/' + 'sunxi/cortexa7/openwrt-22.03.3-sunxi-cortexa7-' + 'sinovoip_bananapi-m2-ultra-ext4-sdcard.img.gz') + image_hash = ('5b41b4e11423e562c6011640f9a7cd3b' + 'dd0a3d42b83430f7caa70a432e6cd82c') + image_path_gz = self.fetch_asset(image_url, asset_hash=image_hash, + algorithm='sha256') + image_path = archive.extract(image_path_gz, self.workdir) + image_pow2ceil_expand(image_path) + + self.vm.set_console() + self.vm.add_args('-drive', 'file=' + image_path + ',if=sd,format=raw', + '-nic', 'user', + '-no-reboot') + self.vm.launch() + + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'usbcore.nousb ' + 'noreboot') + + self.wait_for_console_pattern('U-Boot SPL') + + interrupt_interactive_console_until_pattern( + self, 'Hit any key to stop autoboot:', '=>') + exec_command_and_wait_for_pattern(self, "setenv extraargs '" + + kernel_command_line + "'", '=>') + exec_command_and_wait_for_pattern(self, 'boot', 'Starting kernel ...'); + + self.wait_for_console_pattern( + 'Please press Enter to activate this console.') + + exec_command_and_wait_for_pattern(self, ' ', 'root@') + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'Allwinner sun8i Family') + exec_command_and_wait_for_pattern(self, 'cat /proc/iomem', + 'system-control@1c00000') + def test_arm_orangepi(self): """ :avocado: tags=arch:arm -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> Add documents for Banana Pi M2U Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> [PMM: Minor format fixes to correct sphinx errors] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/bananapi_m2u.rst | 139 +++++++++++++++++++++++++++++++ docs/system/target-arm.rst | 1 + 2 files changed, 140 insertions(+) create mode 100644 docs/system/arm/bananapi_m2u.rst diff --git a/docs/system/arm/bananapi_m2u.rst b/docs/system/arm/bananapi_m2u.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/arm/bananapi_m2u.rst @@ -XXX,XX +XXX,XX @@ +Banana Pi BPI-M2U (``bpim2u``) +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Banana Pi BPI-M2 Ultra is a quad-core mini single board computer built with +Allwinner A40i/R40/V40 SoC. It features 2GB of RAM and 8GB eMMC. It also +has onboard WiFi and BT. On the ports side, the BPI-M2 Ultra has 2 USB A +2.0 ports, 1 USB OTG port, 1 HDMI port, 1 audio jack, a DC power port, +and last but not least, a SATA port. + +Supported devices +""""""""""""""""" + +The Banana Pi M2U machine supports the following devices: + + * SMP (Quad Core Cortex-A7) + * Generic Interrupt Controller configuration + * SRAM mappings + * SDRAM controller + * Timer device (re-used from Allwinner A10) + * UART + * SD/MMC storage controller + * EMAC ethernet + * GMAC ethernet + * Clock Control Unit + * TWI (I2C) + +Limitations +""""""""""" + +Currently, Banana Pi M2U does *not* support the following features: + +- Graphical output via HDMI, GPU and/or the Display Engine +- Audio output +- Hardware Watchdog +- Real Time Clock +- USB 2.0 interfaces + +Also see the 'unimplemented' array in the Allwinner R40 SoC module +for a complete list of unimplemented I/O devices: ``./hw/arm/allwinner-r40.c`` + +Boot options +"""""""""""" + +The Banana Pi M2U machine can start using the standard -kernel functionality +for loading a Linux kernel or ELF executable. Additionally, the Banana Pi M2U +machine can also emulate the BootROM which is present on an actual Allwinner R40 +based SoC, which loads the bootloader from a SD card, specified via the -sd +argument to qemu-system-arm. + +Running mainline Linux +"""""""""""""""""""""" + +To build a Linux mainline kernel that can be booted by the Banana Pi M2U machine, +simply configure the kernel using the sunxi_defconfig configuration: + +.. code-block:: bash + + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make mrproper + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make sunxi_defconfig + +To boot the newly build linux kernel in QEMU with the Banana Pi M2U machine, use: + +.. code-block:: bash + + $ qemu-system-arm -M bpim2u -nographic \ + -kernel /path/to/linux/arch/arm/boot/zImage \ + -append 'console=ttyS0,115200' \ + -dtb /path/to/linux/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dtb + +Banana Pi M2U images +"""""""""""""""""""" + +Note that the mainline kernel does not have a root filesystem. You can choose +to build you own image with buildroot using the bananapi_m2_ultra_defconfig. +Also see https://buildroot.org for more information. + +Another possibility is to run an OpenWrt image for Banana Pi M2U which +can be downloaded from: + + https://downloads.openwrt.org/releases/22.03.3/targets/sunxi/cortexa7/ + +When using an image as an SD card, it must be resized to a power of two. This can be +done with the ``qemu-img`` command. It is recommended to only increase the image size +instead of shrinking it to a power of two, to avoid loss of data. For example, +to prepare a downloaded Armbian image, first extract it and then increase +its size to one gigabyte as follows: + +.. code-block:: bash + + $ qemu-img resize \ + openwrt-22.03.3-sunxi-cortexa7-sinovoip_bananapi-m2-ultra-ext4-sdcard.img \ + 1G + +Instead of providing a custom Linux kernel via the -kernel command you may also +choose to let the Banana Pi M2U machine load the bootloader from SD card, just like +a real board would do using the BootROM. Simply pass the selected image via the -sd +argument and remove the -kernel, -append, -dbt and -initrd arguments: + +.. code-block:: bash + + $ qemu-system-arm -M bpim2u -nic user -nographic \ + -sd openwrt-22.03.3-sunxi-cortexa7-sinovoip_bananapi-m2-ultra-ext4-sdcard.img + +Running U-Boot +"""""""""""""" + +U-Boot mainline can be build and configured using the Bananapi_M2_Ultra_defconfig +using similar commands as describe above for Linux. Note that it is recommended +for development/testing to select the following configuration setting in U-Boot: + + Device Tree Control > Provider for DTB for DT Control > Embedded DTB + +The BootROM of allwinner R40 loading u-boot from the 8KiB offset of sdcard. +Let's create an bootable disk image: + +.. code-block:: bash + + $ dd if=/dev/zero of=sd.img bs=32M count=1 + $ dd if=u-boot-sunxi-with-spl.bin of=sd.img bs=1k seek=8 conv=notrunc + +And then boot it. + +.. code-block:: bash + + $ qemu-system-arm -M bpim2u -nographic -sd sd.img + +Banana Pi M2U integration tests +""""""""""""""""""""""""""""""" + +The Banana Pi M2U machine has several integration tests included. +To run the whole set of tests, build QEMU from source and simply +provide the following command: + +.. code-block:: bash + + $ cd qemu-build-dir + $ AVOCADO_ALLOW_LARGE_STORAGE=yes tests/venv/bin/avocado \ + --verbose --show=app,console run -t machine:bpim2u \ + ../tests/avocado/boot_linux_console.py diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/versatile arm/vexpress arm/aspeed + arm/bananapi_m2u.rst arm/sabrelite arm/digic arm/cubieboard -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Document the meaning of exclusive_high in a big-endian context, and why we can't change it now. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { uint64_t zcr_el[4]; /* ZCR_EL[1-3] */ uint64_t smcr_el[4]; /* SMCR_EL[1-3] */ } vfp; + uint64_t exclusive_addr; uint64_t exclusive_val; + /* + * Contains the 'val' for the second 64-bit register of LDXP, which comes + * from the higher address, not the high part of a complete 128-bit value. + * In some ways it might be more convenient to record the exclusive value + * as the low and high halves of a 128 bit data value, but the current + * semantics of these fields are baked into the migration format. + */ uint64_t exclusive_high; /* iwMMXt coprocessor state. */ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_st(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, ST) != 0; } +static inline bool isar_feature_aa64_lse2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, AT) != 0; +} + static inline bool isar_feature_aa64_fwb(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, FWB) != 0; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Let finalize_memop_atom be the new basic function, with finalize_memop and finalize_memop_pair testing FEAT_LSE2 to apply the appropriate atomicity. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate.h | 39 +++++++++++++++++++++++++++++----- target/arm/tcg/translate-a64.c | 2 ++ target/arm/tcg/translate.c | 1 + 3 files changed, 37 insertions(+), 5 deletions(-) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { uint64_t features; /* CPU features bits */ bool aarch64; bool thumb; + bool lse2; /* Because unallocated encodings generate different exception syndrome * information from traps due to FP being disabled, we can't do a single * "is fp access disabled" check at a high level in the decode tree. @@ -XXX,XX +XXX,XX @@ static inline TCGv_ptr fpstatus_ptr(ARMFPStatusFlavour flavour) } /** - * finalize_memop: + * finalize_memop_atom: * @s: DisasContext * @opc: size+sign+align of the memory operation + * @atom: atomicity of the memory operation * - * Build the complete MemOp for a memory operation, including alignment - * and endianness. + * Build the complete MemOp for a memory operation, including alignment, + * endianness, and atomicity. * * If (op & MO_AMASK) then the operation already contains the required * alignment, e.g. for AccType_ATOMIC. Otherwise, this an optionally @@ -XXX,XX +XXX,XX @@ static inline TCGv_ptr fpstatus_ptr(ARMFPStatusFlavour flavour) * and this is applied here. Note that there is no way to indicate that * no alignment should ever be enforced; this must be handled manually. */ -static inline MemOp finalize_memop(DisasContext *s, MemOp opc) +static inline MemOp finalize_memop_atom(DisasContext *s, MemOp opc, MemOp atom) { if (s->align_mem && !(opc & MO_AMASK)) { opc |= MO_ALIGN; } - return opc | s->be_data; + return opc | atom | s->be_data; +} + +/** + * finalize_memop: + * @s: DisasContext + * @opc: size+sign+align of the memory operation + * + * Like finalize_memop_atom, but with default atomicity. + */ +static inline MemOp finalize_memop(DisasContext *s, MemOp opc) +{ + MemOp atom = s->lse2 ? MO_ATOM_WITHIN16 : MO_ATOM_IFALIGN; + return finalize_memop_atom(s, opc, atom); +} + +/** + * finalize_memop_pair: + * @s: DisasContext + * @opc: size+sign+align of the memory operation + * + * Like finalize_memop_atom, but with atomicity for a pair. + * C.f. Pseudocode for Mem[], operand ispair. + */ +static inline MemOp finalize_memop_pair(DisasContext *s, MemOp opc) +{ + MemOp atom = s->lse2 ? MO_ATOM_WITHIN16_PAIR : MO_ATOM_IFALIGN_PAIR; + return finalize_memop_atom(s, opc, atom); } /** diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, tcg_debug_assert(dc->tbid & 1); #endif + dc->lse2 = dc_isar_feature(aa64_lse2, dc); + /* Single step state. The code-generation logic here is: * SS_ACTIVE == 0: * generate code with no special handling for single-stepping (except diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->sme_trap_nonstreaming = EX_TBFLAG_A32(tb_flags, SME_TRAP_NONSTREAMING); } + dc->lse2 = false; /* applies only to aarch64 */ dc->cp_regs = cpu->cp_regs; dc->features = env->features; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> While we don't require 16-byte atomicity here, using a single larger load simplifies the code, and makes it a closer match to STXP. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, TCGv_i64 addr, int size, bool is_pair) { int idx = get_mem_index(s); - MemOp memop = s->be_data; + MemOp memop; g_assert(size <= 3); if (is_pair) { g_assert(size >= 2); if (size == 2) { /* The pair must be single-copy atomic for the doubleword. */ - memop |= MO_64 | MO_ALIGN; + memop = finalize_memop(s, MO_64 | MO_ALIGN); tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop); if (s->be_data == MO_LE) { tcg_gen_extract_i64(cpu_reg(s, rt), cpu_exclusive_val, 0, 32); @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, tcg_gen_extract_i64(cpu_reg(s, rt2), cpu_exclusive_val, 0, 32); } } else { - /* The pair must be single-copy atomic for *each* doubleword, not - the entire quadword, however it must be quadword aligned. */ - memop |= MO_64; - tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, - memop | MO_ALIGN_16); + /* + * The pair must be single-copy atomic for *each* doubleword, not + * the entire quadword, however it must be quadword aligned. + * Expose the complete load to tcg, for ease of tlb lookup, + * but indicate that only 8-byte atomicity is required. + */ + TCGv_i128 t16 = tcg_temp_new_i128(); - TCGv_i64 addr2 = tcg_temp_new_i64(); - tcg_gen_addi_i64(addr2, addr, 8); - tcg_gen_qemu_ld_i64(cpu_exclusive_high, addr2, idx, memop); + memop = finalize_memop_atom(s, MO_128 | MO_ALIGN_16, + MO_ATOM_IFALIGN_PAIR); + tcg_gen_qemu_ld_i128(t16, addr, idx, memop); + if (s->be_data == MO_LE) { + tcg_gen_extr_i128_i64(cpu_exclusive_val, + cpu_exclusive_high, t16); + } else { + tcg_gen_extr_i128_i64(cpu_exclusive_high, + cpu_exclusive_val, t16); + } tcg_gen_mov_i64(cpu_reg(s, rt), cpu_exclusive_val); tcg_gen_mov_i64(cpu_reg(s, rt2), cpu_exclusive_high); } } else { - memop |= size | MO_ALIGN; + memop = finalize_memop(s, size | MO_ALIGN); tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop); tcg_gen_mov_i64(cpu_reg(s, rt), cpu_exclusive_val); } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> While we don't require 16-byte atomicity here, using a single larger operation simplifies the code. Introduce finalize_memop_asimd for this. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate.h | 24 +++++++++++++++++++++++ target/arm/tcg/translate-a64.c | 35 +++++++++++----------------------- 2 files changed, 35 insertions(+), 24 deletions(-) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop_pair(DisasContext *s, MemOp opc) return finalize_memop_atom(s, opc, atom); } +/** + * finalize_memop_asimd: + * @s: DisasContext + * @opc: size+sign+align of the memory operation + * + * Like finalize_memop_atom, but with atomicity of AccessType_ASIMD. + */ +static inline MemOp finalize_memop_asimd(DisasContext *s, MemOp opc) +{ + /* + * In the pseudocode for Mem[], with AccessType_ASIMD, size == 16, + * if IsAligned(8), the first case provides separate atomicity for + * the pair of 64-bit accesses. If !IsAligned(8), the middle cases + * do not apply, and we're left with the final case of no atomicity. + * Thus MO_ATOM_IFALIGN_PAIR. + * + * For other sizes, normal LSE2 rules apply. + */ + if ((opc & MO_SIZE) == MO_128) { + return finalize_memop_atom(s, opc, MO_ATOM_IFALIGN_PAIR); + } + return finalize_memop(s, opc); +} + /** * asimd_imm_const: Expand an encoded SIMD constant value * diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size) { /* This writes the bottom N bits of a 128 bit wide vector to memory */ TCGv_i64 tmplo = tcg_temp_new_i64(); - MemOp mop; + MemOp mop = finalize_memop_asimd(s, size); tcg_gen_ld_i64(tmplo, cpu_env, fp_reg_offset(s, srcidx, MO_64)); - if (size < 4) { - mop = finalize_memop(s, size); + if (size < MO_128) { tcg_gen_qemu_st_i64(tmplo, tcg_addr, get_mem_index(s), mop); } else { - bool be = s->be_data == MO_BE; - TCGv_i64 tcg_hiaddr = tcg_temp_new_i64(); TCGv_i64 tmphi = tcg_temp_new_i64(); + TCGv_i128 t16 = tcg_temp_new_i128(); tcg_gen_ld_i64(tmphi, cpu_env, fp_reg_hi_offset(s, srcidx)); + tcg_gen_concat_i64_i128(t16, tmplo, tmphi); - mop = s->be_data | MO_UQ; - tcg_gen_qemu_st_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s), - mop | (s->align_mem ? MO_ALIGN_16 : 0)); - tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8); - tcg_gen_qemu_st_i64(be ? tmplo : tmphi, tcg_hiaddr, - get_mem_index(s), mop); + tcg_gen_qemu_st_i128(t16, tcg_addr, get_mem_index(s), mop); } } @@ -XXX,XX +XXX,XX @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size) /* This always zero-extends and writes to a full 128 bit wide vector */ TCGv_i64 tmplo = tcg_temp_new_i64(); TCGv_i64 tmphi = NULL; - MemOp mop; + MemOp mop = finalize_memop_asimd(s, size); - if (size < 4) { - mop = finalize_memop(s, size); + if (size < MO_128) { tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), mop); } else { - bool be = s->be_data == MO_BE; - TCGv_i64 tcg_hiaddr; + TCGv_i128 t16 = tcg_temp_new_i128(); + + tcg_gen_qemu_ld_i128(t16, tcg_addr, get_mem_index(s), mop); tmphi = tcg_temp_new_i64(); - tcg_hiaddr = tcg_temp_new_i64(); - - mop = s->be_data | MO_UQ; - tcg_gen_qemu_ld_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s), - mop | (s->align_mem ? MO_ALIGN_16 : 0)); - tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8); - tcg_gen_qemu_ld_i64(be ? tmplo : tmphi, tcg_hiaddr, - get_mem_index(s), mop); + tcg_gen_extr_i128_i64(tmplo, tmphi, t16); } tcg_gen_st_i64(tmplo, cpu_env, fp_reg_offset(s, destidx, MO_64)); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This fixes a bug in that these two insns should have been using atomic 16-byte stores, since MTE is ARMv8.5 and LSE2 is mandatory from ARMv8.4. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn) if (is_zero) { TCGv_i64 clean_addr = clean_data_tbi(s, addr); - TCGv_i64 tcg_zero = tcg_constant_i64(0); + TCGv_i64 zero64 = tcg_constant_i64(0); + TCGv_i128 zero128 = tcg_temp_new_i128(); int mem_index = get_mem_index(s); - int i, n = (1 + is_pair) << LOG2_TAG_GRANULE; + MemOp mop = finalize_memop(s, MO_128 | MO_ALIGN); - tcg_gen_qemu_st_i64(tcg_zero, clean_addr, mem_index, - MO_UQ | MO_ALIGN_16); - for (i = 8; i < n; i += 8) { - tcg_gen_addi_i64(clean_addr, clean_addr, 8); - tcg_gen_qemu_st_i64(tcg_zero, clean_addr, mem_index, MO_UQ); + tcg_gen_concat_i64_i128(zero128, zero64, zero64); + + /* This is 1 or 2 atomic 16-byte operations. */ + tcg_gen_qemu_st_i128(zero128, clean_addr, mem_index, mop); + if (is_pair) { + tcg_gen_addi_i64(clean_addr, clean_addr, 16); + tcg_gen_qemu_st_i128(zero128, clean_addr, mem_index, mop); } } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Round len_align to 16 instead of 8, handling an odd 8-byte as part of the tail. Use MO_ATOM_NONE to indicate that all of these memory ops have only byte atomicity. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-sve.c | 95 +++++++++++++++++++++++++--------- 1 file changed, 70 insertions(+), 25 deletions(-) diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, int len, int rn, int imm) { - int len_align = QEMU_ALIGN_DOWN(len, 8); - int len_remain = len % 8; - int nparts = len / 8 + ctpop8(len_remain); + int len_align = QEMU_ALIGN_DOWN(len, 16); + int len_remain = len % 16; + int nparts = len / 16 + ctpop8(len_remain); int midx = get_mem_index(s); TCGv_i64 dirty_addr, clean_addr, t0, t1; + TCGv_i128 t16; dirty_addr = tcg_temp_new_i64(); tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm); @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, int i; t0 = tcg_temp_new_i64(); - for (i = 0; i < len_align; i += 8) { - tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ); + t1 = tcg_temp_new_i64(); + t16 = tcg_temp_new_i128(); + + for (i = 0; i < len_align; i += 16) { + tcg_gen_qemu_ld_i128(t16, clean_addr, midx, + MO_LE | MO_128 | MO_ATOM_NONE); + tcg_gen_extr_i128_i64(t0, t1, t16); tcg_gen_st_i64(t0, base, vofs + i); - tcg_gen_addi_i64(clean_addr, clean_addr, 8); + tcg_gen_st_i64(t1, base, vofs + i + 8); + tcg_gen_addi_i64(clean_addr, clean_addr, 16); } } else { TCGLabel *loop = gen_new_label(); @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, tcg_gen_movi_ptr(i, 0); gen_set_label(loop); - t0 = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ); - tcg_gen_addi_i64(clean_addr, clean_addr, 8); + t16 = tcg_temp_new_i128(); + tcg_gen_qemu_ld_i128(t16, clean_addr, midx, + MO_LE | MO_128 | MO_ATOM_NONE); + tcg_gen_addi_i64(clean_addr, clean_addr, 16); tp = tcg_temp_new_ptr(); tcg_gen_add_ptr(tp, base, i); - tcg_gen_addi_ptr(i, i, 8); + tcg_gen_addi_ptr(i, i, 16); + + t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + tcg_gen_extr_i128_i64(t0, t1, t16); + tcg_gen_st_i64(t0, tp, vofs); + tcg_gen_st_i64(t1, tp, vofs + 8); tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); } @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, * Predicate register loads can be any multiple of 2. * Note that we still store the entire 64-bit unit into cpu_env. */ + if (len_remain >= 8) { + t0 = tcg_temp_new_i64(); + tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE); + tcg_gen_st_i64(t0, base, vofs + len_align); + len_remain -= 8; + len_align += 8; + if (len_remain) { + tcg_gen_addi_i64(clean_addr, clean_addr, 8); + } + } if (len_remain) { t0 = tcg_temp_new_i64(); switch (len_remain) { @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, case 4: case 8: tcg_gen_qemu_ld_i64(t0, clean_addr, midx, - MO_LE | ctz32(len_remain)); + MO_LE | ctz32(len_remain) | MO_ATOM_NONE); break; case 6: t1 = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUL); + tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE); tcg_gen_addi_i64(clean_addr, clean_addr, 4); - tcg_gen_qemu_ld_i64(t1, clean_addr, midx, MO_LEUW); + tcg_gen_qemu_ld_i64(t1, clean_addr, midx, MO_LEUW | MO_ATOM_NONE); tcg_gen_deposit_i64(t0, t0, t1, 32, 32); break; @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, int len, int rn, int imm) { - int len_align = QEMU_ALIGN_DOWN(len, 8); - int len_remain = len % 8; - int nparts = len / 8 + ctpop8(len_remain); + int len_align = QEMU_ALIGN_DOWN(len, 16); + int len_remain = len % 16; + int nparts = len / 16 + ctpop8(len_remain); int midx = get_mem_index(s); - TCGv_i64 dirty_addr, clean_addr, t0; + TCGv_i64 dirty_addr, clean_addr, t0, t1; + TCGv_i128 t16; dirty_addr = tcg_temp_new_i64(); tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm); @@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, int i; t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + t16 = tcg_temp_new_i128(); for (i = 0; i < len_align; i += 8) { tcg_gen_ld_i64(t0, base, vofs + i); - tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ); - tcg_gen_addi_i64(clean_addr, clean_addr, 8); + tcg_gen_ld_i64(t1, base, vofs + i + 8); + tcg_gen_concat_i64_i128(t16, t0, t1); + tcg_gen_qemu_st_i128(t16, clean_addr, midx, + MO_LE | MO_128 | MO_ATOM_NONE); + tcg_gen_addi_i64(clean_addr, clean_addr, 16); } } else { TCGLabel *loop = gen_new_label(); @@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, gen_set_label(loop); t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); tp = tcg_temp_new_ptr(); tcg_gen_add_ptr(tp, base, i); tcg_gen_ld_i64(t0, tp, vofs); - tcg_gen_addi_ptr(i, i, 8); + tcg_gen_ld_i64(t1, tp, vofs + 8); + tcg_gen_addi_ptr(i, i, 16); - tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ); - tcg_gen_addi_i64(clean_addr, clean_addr, 8); + t16 = tcg_temp_new_i128(); + tcg_gen_concat_i64_i128(t16, t0, t1); + + tcg_gen_qemu_st_i128(t16, clean_addr, midx, MO_LEUQ); + tcg_gen_addi_i64(clean_addr, clean_addr, 16); tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); } /* Predicate register stores can be any multiple of 2. */ + if (len_remain >= 8) { + t0 = tcg_temp_new_i64(); + tcg_gen_st_i64(t0, base, vofs + len_align); + tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE); + len_remain -= 8; + len_align += 8; + if (len_remain) { + tcg_gen_addi_i64(clean_addr, clean_addr, 8); + } + } if (len_remain) { t0 = tcg_temp_new_i64(); tcg_gen_ld_i64(t0, base, vofs + len_align); @@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, case 4: case 8: tcg_gen_qemu_st_i64(t0, clean_addr, midx, - MO_LE | ctz32(len_remain)); + MO_LE | ctz32(len_remain) | MO_ATOM_NONE); break; case 6: - tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUL); + tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE); tcg_gen_addi_i64(clean_addr, clean_addr, 4); tcg_gen_shri_i64(t0, t0, 32); - tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUW); + tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUW | MO_ATOM_NONE); break; default: -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> No need to duplicate this check across multiple call sites. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 44 ++++++++++++++++------------------ 1 file changed, 21 insertions(+), 23 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_b_exc_sys(DisasContext *s, uint32_t insn) * races in multi-threaded linux-user and when MTTCG softmmu is * enabled. */ -static void gen_load_exclusive(DisasContext *s, int rt, int rt2, - TCGv_i64 addr, int size, bool is_pair) +static void gen_load_exclusive(DisasContext *s, int rt, int rt2, int rn, + int size, bool is_pair) { int idx = get_mem_index(s); MemOp memop; + TCGv_i64 dirty_addr, clean_addr; + + s->is_ldex = true; + dirty_addr = cpu_reg_sp(s, rn); + clean_addr = gen_mte_check1(s, dirty_addr, false, rn != 31, size); g_assert(size <= 3); if (is_pair) { @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, if (size == 2) { /* The pair must be single-copy atomic for the doubleword. */ memop = finalize_memop(s, MO_64 | MO_ALIGN); - tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop); + tcg_gen_qemu_ld_i64(cpu_exclusive_val, clean_addr, idx, memop); if (s->be_data == MO_LE) { tcg_gen_extract_i64(cpu_reg(s, rt), cpu_exclusive_val, 0, 32); tcg_gen_extract_i64(cpu_reg(s, rt2), cpu_exclusive_val, 32, 32); @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, memop = finalize_memop_atom(s, MO_128 | MO_ALIGN_16, MO_ATOM_IFALIGN_PAIR); - tcg_gen_qemu_ld_i128(t16, addr, idx, memop); + tcg_gen_qemu_ld_i128(t16, clean_addr, idx, memop); if (s->be_data == MO_LE) { tcg_gen_extr_i128_i64(cpu_exclusive_val, @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, } } else { memop = finalize_memop(s, size | MO_ALIGN); - tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop); + tcg_gen_qemu_ld_i64(cpu_exclusive_val, clean_addr, idx, memop); tcg_gen_mov_i64(cpu_reg(s, rt), cpu_exclusive_val); } - tcg_gen_mov_i64(cpu_exclusive_addr, addr); + tcg_gen_mov_i64(cpu_exclusive_addr, clean_addr); } static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, - TCGv_i64 addr, int size, int is_pair) + int rn, int size, int is_pair) { /* if (env->exclusive_addr == addr && env->exclusive_val == [addr] * && (!is_pair || env->exclusive_high == [addr + datasize])) { @@ -XXX,XX +XXX,XX @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, */ TCGLabel *fail_label = gen_new_label(); TCGLabel *done_label = gen_new_label(); - TCGv_i64 tmp; + TCGv_i64 tmp, dirty_addr, clean_addr; - tcg_gen_brcond_i64(TCG_COND_NE, addr, cpu_exclusive_addr, fail_label); + dirty_addr = cpu_reg_sp(s, rn); + clean_addr = gen_mte_check1(s, dirty_addr, true, rn != 31, size); + + tcg_gen_brcond_i64(TCG_COND_NE, clean_addr, cpu_exclusive_addr, fail_label); tmp = tcg_temp_new_i64(); if (is_pair) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (is_lasr) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); } - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), - true, rn != 31, size); - gen_store_exclusive(s, rs, rt, rt2, clean_addr, size, false); + gen_store_exclusive(s, rs, rt, rt2, rn, size, false); return; case 0x4: /* LDXR */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (rn == 31) { gen_check_sp_alignment(s); } - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), - false, rn != 31, size); - s->is_ldex = true; - gen_load_exclusive(s, rt, rt2, clean_addr, size, false); + gen_load_exclusive(s, rt, rt2, rn, size, false); if (is_lasr) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (is_lasr) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); } - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), - true, rn != 31, size); - gen_store_exclusive(s, rs, rt, rt2, clean_addr, size, true); + gen_store_exclusive(s, rs, rt, rt2, rn, size, true); return; } if (rt2 == 31 @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (rn == 31) { gen_check_sp_alignment(s); } - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), - false, rn != 31, size); - s->is_ldex = true; - gen_load_exclusive(s, rt, rt2, clean_addr, size, true); + gen_load_exclusive(s, rt, rt2, rn, size, true); if (is_lasr) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This is required for LSE2, where the pair must be treated atomically if it does not cross a 16-byte boundary. But it simplifies the code to do this always. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 70 ++++++++++++++++++++++++++-------- 1 file changed, 55 insertions(+), 15 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); TCGv_i64 tcg_rt2 = cpu_reg(s, rt2); + MemOp mop = size + 1; + + /* + * With LSE2, non-sign-extending pairs are treated atomically if + * aligned, and if unaligned one of the pair will be completely + * within a 16-byte block and that element will be atomic. + * Otherwise each element is separately atomic. + * In all cases, issue one operation with the correct atomicity. + * + * This treats sign-extending loads like zero-extending loads, + * since that reuses the most code below. + */ + if (s->align_mem) { + mop |= (size == 2 ? MO_ALIGN_4 : MO_ALIGN_8); + } + mop = finalize_memop_pair(s, mop); if (is_load) { - TCGv_i64 tmp = tcg_temp_new_i64(); + if (size == 2) { + int o2 = s->be_data == MO_LE ? 32 : 0; + int o1 = o2 ^ 32; - /* Do not modify tcg_rt before recognizing any exception - * from the second load. - */ - do_gpr_ld(s, tmp, clean_addr, size + is_signed * MO_SIGN, - false, false, 0, false, false); - tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size); - do_gpr_ld(s, tcg_rt2, clean_addr, size + is_signed * MO_SIGN, - false, false, 0, false, false); + tcg_gen_qemu_ld_i64(tcg_rt, clean_addr, get_mem_index(s), mop); + if (is_signed) { + tcg_gen_sextract_i64(tcg_rt2, tcg_rt, o2, 32); + tcg_gen_sextract_i64(tcg_rt, tcg_rt, o1, 32); + } else { + tcg_gen_extract_i64(tcg_rt2, tcg_rt, o2, 32); + tcg_gen_extract_i64(tcg_rt, tcg_rt, o1, 32); + } + } else { + TCGv_i128 tmp = tcg_temp_new_i128(); - tcg_gen_mov_i64(tcg_rt, tmp); + tcg_gen_qemu_ld_i128(tmp, clean_addr, get_mem_index(s), mop); + if (s->be_data == MO_LE) { + tcg_gen_extr_i128_i64(tcg_rt, tcg_rt2, tmp); + } else { + tcg_gen_extr_i128_i64(tcg_rt2, tcg_rt, tmp); + } + } } else { - do_gpr_st(s, tcg_rt, clean_addr, size, - false, 0, false, false); - tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size); - do_gpr_st(s, tcg_rt2, clean_addr, size, - false, 0, false, false); + if (size == 2) { + TCGv_i64 tmp = tcg_temp_new_i64(); + + if (s->be_data == MO_LE) { + tcg_gen_concat32_i64(tmp, tcg_rt, tcg_rt2); + } else { + tcg_gen_concat32_i64(tmp, tcg_rt2, tcg_rt); + } + tcg_gen_qemu_st_i64(tmp, clean_addr, get_mem_index(s), mop); + } else { + TCGv_i128 tmp = tcg_temp_new_i128(); + + if (s->be_data == MO_LE) { + tcg_gen_concat_i64_i128(tmp, tcg_rt, tcg_rt2); + } else { + tcg_gen_concat_i64_i128(tmp, tcg_rt2, tcg_rt); + } + tcg_gen_qemu_st_i128(tmp, clean_addr, get_mem_index(s), mop); + } } } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> We are going to need the complete memop beforehand, so let's not compute it twice. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 61 +++++++++++++++++++--------------- 1 file changed, 35 insertions(+), 26 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void do_gpr_st_memidx(DisasContext *s, TCGv_i64 source, unsigned int iss_srt, bool iss_sf, bool iss_ar) { - memop = finalize_memop(s, memop); tcg_gen_qemu_st_i64(source, tcg_addr, memidx, memop); if (iss_valid) { @@ -XXX,XX +XXX,XX @@ static void do_gpr_ld_memidx(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, bool iss_valid, unsigned int iss_srt, bool iss_sf, bool iss_ar) { - memop = finalize_memop(s, memop); tcg_gen_qemu_ld_i64(dest, tcg_addr, memidx, memop); if (extend && (memop & MO_SIGN)) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) int o2_L_o1_o0 = extract32(insn, 21, 3) * 2 | is_lasr; int size = extract32(insn, 30, 2); TCGv_i64 clean_addr; + MemOp memop; switch (o2_L_o1_o0) { case 0x0: /* STXR */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) gen_check_sp_alignment(s); } tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); + /* TODO: ARMv8.4-LSE SCTLR.nAA */ + memop = finalize_memop(s, size | MO_ALIGN); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, size); - /* TODO: ARMv8.4-LSE SCTLR.nAA */ - do_gpr_st(s, cpu_reg(s, rt), clean_addr, size | MO_ALIGN, true, rt, + do_gpr_st(s, cpu_reg(s, rt), clean_addr, memop, true, rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (rn == 31) { gen_check_sp_alignment(s); } + /* TODO: ARMv8.4-LSE SCTLR.nAA */ + memop = finalize_memop(s, size | MO_ALIGN); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), false, rn != 31, size); - /* TODO: ARMv8.4-LSE SCTLR.nAA */ - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size | MO_ALIGN, false, true, + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, memop, false, true, rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); return; @@ -XXX,XX +XXX,XX @@ static void disas_ld_lit(DisasContext *s, uint32_t insn) } else { /* Only unsigned 32bit loads target 32bit registers. */ bool iss_sf = opc != 0; + MemOp memop = finalize_memop(s, size + is_signed * MO_SIGN); - do_gpr_ld(s, tcg_rt, clean_addr, size + is_signed * MO_SIGN, - false, true, rt, iss_sf, false); + do_gpr_ld(s, tcg_rt, clean_addr, memop, false, true, rt, iss_sf, false); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, bool post_index; bool writeback; int memidx; - + MemOp memop; TCGv_i64 clean_addr, dirty_addr; if (is_vector) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, return; } is_store = (opc == 0); - is_signed = extract32(opc, 1, 1); + is_signed = !is_store && extract32(opc, 1, 1); is_extended = (size < 3) && extract32(opc, 0, 1); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, } memidx = is_unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); + memop = finalize_memop(s, size + is_signed * MO_SIGN); + clean_addr = gen_mte_check1_mmuidx(s, dirty_addr, is_store, writeback || rn != 31, size, is_unpriv, memidx); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); if (is_store) { - do_gpr_st_memidx(s, tcg_rt, clean_addr, size, memidx, + do_gpr_st_memidx(s, tcg_rt, clean_addr, memop, memidx, iss_valid, rt, iss_sf, false); } else { - do_gpr_ld_memidx(s, tcg_rt, clean_addr, size + is_signed * MO_SIGN, + do_gpr_ld_memidx(s, tcg_rt, clean_addr, memop, is_extended, memidx, iss_valid, rt, iss_sf, false); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, bool is_signed = false; bool is_store = false; bool is_extended = false; - TCGv_i64 tcg_rm, clean_addr, dirty_addr; + MemOp memop; if (extract32(opt, 1, 1) == 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, return; } is_store = (opc == 0); - is_signed = extract32(opc, 1, 1); + is_signed = !is_store && extract32(opc, 1, 1); is_extended = (size < 3) && extract32(opc, 0, 1); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, ext_and_shift_reg(tcg_rm, tcg_rm, opt, shift ? size : 0); tcg_gen_add_i64(dirty_addr, dirty_addr, tcg_rm); + + memop = finalize_memop(s, size + is_signed * MO_SIGN); clean_addr = gen_mte_check1(s, dirty_addr, is_store, true, size); if (is_vector) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); + if (is_store) { - do_gpr_st(s, tcg_rt, clean_addr, size, + do_gpr_st(s, tcg_rt, clean_addr, memop, true, rt, iss_sf, false); } else { - do_gpr_ld(s, tcg_rt, clean_addr, size + is_signed * MO_SIGN, + do_gpr_ld(s, tcg_rt, clean_addr, memop, is_extended, true, rt, iss_sf, false); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, int rn = extract32(insn, 5, 5); unsigned int imm12 = extract32(insn, 10, 12); unsigned int offset; - TCGv_i64 clean_addr, dirty_addr; - bool is_store; bool is_signed = false; bool is_extended = false; + MemOp memop; if (is_vector) { size |= (opc & 2) << 1; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, return; } is_store = (opc == 0); - is_signed = extract32(opc, 1, 1); + is_signed = !is_store && extract32(opc, 1, 1); is_extended = (size < 3) && extract32(opc, 0, 1); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, dirty_addr = read_cpu_reg_sp(s, rn, 1); offset = imm12 << size; tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); + + memop = finalize_memop(s, size + is_signed * MO_SIGN); clean_addr = gen_mte_check1(s, dirty_addr, is_store, rn != 31, size); if (is_vector) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, TCGv_i64 tcg_rt = cpu_reg(s, rt); bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); if (is_store) { - do_gpr_st(s, tcg_rt, clean_addr, size, - true, rt, iss_sf, false); + do_gpr_st(s, tcg_rt, clean_addr, memop, true, rt, iss_sf, false); } else { - do_gpr_ld(s, tcg_rt, clean_addr, size + is_signed * MO_SIGN, + do_gpr_ld(s, tcg_rt, clean_addr, memop, is_extended, true, rt, iss_sf, false); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, bool a = extract32(insn, 23, 1); TCGv_i64 tcg_rs, tcg_rt, clean_addr; AtomicThreeOpFn *fn = NULL; - MemOp mop = s->be_data | size | MO_ALIGN; + MemOp mop = finalize_memop(s, size | MO_ALIGN); if (is_vector || !dc_isar_feature(aa64_atomics, s)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, * full load-acquire (we only need "load-acquire processor consistent"), * but we choose to implement them as full LDAQ. */ - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, false, + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, mop, false, true, rt, disas_ldst_compute_iss_sf(size, false, 0), true); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pac(DisasContext *s, uint32_t insn, bool use_key_a = !extract32(insn, 23, 1); int offset; TCGv_i64 clean_addr, dirty_addr, tcg_rt; + MemOp memop; if (size != 3 || is_vector || !dc_isar_feature(aa64_pauth, s)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pac(DisasContext *s, uint32_t insn, offset = sextract32(offset << size, 0, 10 + size); tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); + memop = finalize_memop(s, size); + /* Note that "clean" and "dirty" here refer to TBI not PAC. */ clean_addr = gen_mte_check1(s, dirty_addr, false, is_wback || rn != 31, size); tcg_rt = cpu_reg(s, rt); - do_gpr_ld(s, tcg_rt, clean_addr, size, + do_gpr_ld(s, tcg_rt, clean_addr, memop, /* extend */ false, /* iss_valid */ !is_wback, /* iss_srt */ rt, /* iss_sf */ true, /* iss_ar */ false); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) } /* TODO: ARMv8.4-LSE SCTLR.nAA */ - mop = size | MO_ALIGN; + mop = finalize_memop(s, size | MO_ALIGN); switch (opc) { case 0: /* STLURB */ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> We are going to need the complete memop beforehand, so let's not compute it twice. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 43 ++++++++++++++++++---------------- 1 file changed, 23 insertions(+), 20 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, /* * Store from FP register to memory */ -static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size) +static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, MemOp mop) { /* This writes the bottom N bits of a 128 bit wide vector to memory */ TCGv_i64 tmplo = tcg_temp_new_i64(); - MemOp mop = finalize_memop_asimd(s, size); tcg_gen_ld_i64(tmplo, cpu_env, fp_reg_offset(s, srcidx, MO_64)); - if (size < MO_128) { + if ((mop & MO_SIZE) < MO_128) { tcg_gen_qemu_st_i64(tmplo, tcg_addr, get_mem_index(s), mop); } else { TCGv_i64 tmphi = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size) /* * Load from memory to FP register */ -static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size) +static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, MemOp mop) { /* This always zero-extends and writes to a full 128 bit wide vector */ TCGv_i64 tmplo = tcg_temp_new_i64(); TCGv_i64 tmphi = NULL; - MemOp mop = finalize_memop_asimd(s, size); - if (size < MO_128) { + if ((mop & MO_SIZE) < MO_128) { tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), mop); } else { TCGv_i128 t16 = tcg_temp_new_i128(); @@ -XXX,XX +XXX,XX @@ static void disas_ld_lit(DisasContext *s, uint32_t insn) bool is_signed = false; int size = 2; TCGv_i64 tcg_rt, clean_addr; + MemOp memop; if (is_vector) { if (opc == 3) { @@ -XXX,XX +XXX,XX @@ static void disas_ld_lit(DisasContext *s, uint32_t insn) if (!fp_access_check(s)) { return; } + memop = finalize_memop_asimd(s, size); } else { if (opc == 3) { /* PRFM (literal) : prefetch */ @@ -XXX,XX +XXX,XX @@ static void disas_ld_lit(DisasContext *s, uint32_t insn) } size = 2 + extract32(opc, 0, 1); is_signed = extract32(opc, 1, 1); + memop = finalize_memop(s, size + is_signed * MO_SIGN); } tcg_rt = cpu_reg(s, rt); clean_addr = tcg_temp_new_i64(); gen_pc_plus_diff(s, clean_addr, imm); + if (is_vector) { - do_fp_ld(s, rt, clean_addr, size); + do_fp_ld(s, rt, clean_addr, memop); } else { /* Only unsigned 32bit loads target 32bit registers. */ bool iss_sf = opc != 0; - MemOp memop = finalize_memop(s, size + is_signed * MO_SIGN); - do_gpr_ld(s, tcg_rt, clean_addr, memop, false, true, rt, iss_sf, false); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) (wback || rn != 31) && !set_tag, 2 << size); if (is_vector) { + MemOp mop = finalize_memop_asimd(s, size); + if (is_load) { - do_fp_ld(s, rt, clean_addr, size); + do_fp_ld(s, rt, clean_addr, mop); } else { - do_fp_st(s, rt, clean_addr, size); + do_fp_st(s, rt, clean_addr, mop); } tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size); if (is_load) { - do_fp_ld(s, rt2, clean_addr, size); + do_fp_ld(s, rt2, clean_addr, mop); } else { - do_fp_st(s, rt2, clean_addr, size); + do_fp_st(s, rt2, clean_addr, mop); } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, if (!fp_access_check(s)) { return; } + memop = finalize_memop_asimd(s, size); } else { if (size == 3 && opc == 2) { /* PRFM - prefetch */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, is_store = (opc == 0); is_signed = !is_store && extract32(opc, 1, 1); is_extended = (size < 3) && extract32(opc, 0, 1); + memop = finalize_memop(s, size + is_signed * MO_SIGN); } switch (idx) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, } memidx = is_unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); - memop = finalize_memop(s, size + is_signed * MO_SIGN); clean_addr = gen_mte_check1_mmuidx(s, dirty_addr, is_store, writeback || rn != 31, @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, if (is_vector) { if (is_store) { - do_fp_st(s, rt, clean_addr, size); + do_fp_st(s, rt, clean_addr, memop); } else { - do_fp_ld(s, rt, clean_addr, size); + do_fp_ld(s, rt, clean_addr, memop); } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, if (is_vector) { if (is_store) { - do_fp_st(s, rt, clean_addr, size); + do_fp_st(s, rt, clean_addr, memop); } else { - do_fp_ld(s, rt, clean_addr, size); + do_fp_ld(s, rt, clean_addr, memop); } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, if (is_vector) { if (is_store) { - do_fp_st(s, rt, clean_addr, size); + do_fp_st(s, rt, clean_addr, memop); } else { - do_fp_ld(s, rt, clean_addr, size); + do_fp_ld(s, rt, clean_addr, memop); } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Pass the completed memop to gen_mte_check1_mmuidx. For the moment, do nothing more than extract the size. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.h | 2 +- target/arm/tcg/translate-a64.c | 82 ++++++++++++++++++---------------- target/arm/tcg/translate-sve.c | 7 +-- 3 files changed, 49 insertions(+), 42 deletions(-) diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.h +++ b/target/arm/tcg/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline bool sme_smza_enabled_check(DisasContext *s) TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr); TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write, - bool tag_checked, int log2_size); + bool tag_checked, MemOp memop); TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, bool tag_checked, int size); diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_probe_access(DisasContext *s, TCGv_i64 ptr, */ static TCGv_i64 gen_mte_check1_mmuidx(DisasContext *s, TCGv_i64 addr, bool is_write, bool tag_checked, - int log2_size, bool is_unpriv, + MemOp memop, bool is_unpriv, int core_idx) { if (tag_checked && s->mte_active[is_unpriv]) { @@ -XXX,XX +XXX,XX @@ static TCGv_i64 gen_mte_check1_mmuidx(DisasContext *s, TCGv_i64 addr, desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write); - desc = FIELD_DP32(desc, MTEDESC, SIZEM1, (1 << log2_size) - 1); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, memop_size(memop) - 1); ret = tcg_temp_new_i64(); gen_helper_mte_check(ret, cpu_env, tcg_constant_i32(desc), addr); @@ -XXX,XX +XXX,XX @@ static TCGv_i64 gen_mte_check1_mmuidx(DisasContext *s, TCGv_i64 addr, } TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write, - bool tag_checked, int log2_size) + bool tag_checked, MemOp memop) { - return gen_mte_check1_mmuidx(s, addr, is_write, tag_checked, log2_size, + return gen_mte_check1_mmuidx(s, addr, is_write, tag_checked, memop, false, get_mem_index(s)); } @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, int rn, int size, bool is_pair) { int idx = get_mem_index(s); - MemOp memop; TCGv_i64 dirty_addr, clean_addr; + MemOp memop; + + /* + * For pairs: + * if size == 2, the operation is single-copy atomic for the doubleword. + * if size == 3, the operation is single-copy atomic for *each* doubleword, + * not the entire quadword, however it must be quadword aligned. + */ + memop = size + is_pair; + if (memop == MO_128) { + memop = finalize_memop_atom(s, MO_128 | MO_ALIGN, + MO_ATOM_IFALIGN_PAIR); + } else { + memop = finalize_memop(s, memop | MO_ALIGN); + } s->is_ldex = true; dirty_addr = cpu_reg_sp(s, rn); - clean_addr = gen_mte_check1(s, dirty_addr, false, rn != 31, size); + clean_addr = gen_mte_check1(s, dirty_addr, false, rn != 31, memop); g_assert(size <= 3); if (is_pair) { g_assert(size >= 2); if (size == 2) { - /* The pair must be single-copy atomic for the doubleword. */ - memop = finalize_memop(s, MO_64 | MO_ALIGN); tcg_gen_qemu_ld_i64(cpu_exclusive_val, clean_addr, idx, memop); if (s->be_data == MO_LE) { tcg_gen_extract_i64(cpu_reg(s, rt), cpu_exclusive_val, 0, 32); @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, int rn, tcg_gen_extract_i64(cpu_reg(s, rt2), cpu_exclusive_val, 0, 32); } } else { - /* - * The pair must be single-copy atomic for *each* doubleword, not - * the entire quadword, however it must be quadword aligned. - * Expose the complete load to tcg, for ease of tlb lookup, - * but indicate that only 8-byte atomicity is required. - */ TCGv_i128 t16 = tcg_temp_new_i128(); - memop = finalize_memop_atom(s, MO_128 | MO_ALIGN_16, - MO_ATOM_IFALIGN_PAIR); tcg_gen_qemu_ld_i128(t16, clean_addr, idx, memop); if (s->be_data == MO_LE) { @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, int rn, tcg_gen_mov_i64(cpu_reg(s, rt2), cpu_exclusive_high); } } else { - memop = finalize_memop(s, size | MO_ALIGN); tcg_gen_qemu_ld_i64(cpu_exclusive_val, clean_addr, idx, memop); tcg_gen_mov_i64(cpu_reg(s, rt), cpu_exclusive_val); } @@ -XXX,XX +XXX,XX @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, TCGLabel *fail_label = gen_new_label(); TCGLabel *done_label = gen_new_label(); TCGv_i64 tmp, dirty_addr, clean_addr; + MemOp memop; + + memop = (size + is_pair) | MO_ALIGN; + memop = finalize_memop(s, memop); dirty_addr = cpu_reg_sp(s, rn); - clean_addr = gen_mte_check1(s, dirty_addr, true, rn != 31, size); + clean_addr = gen_mte_check1(s, dirty_addr, true, rn != 31, memop); tcg_gen_brcond_i64(TCG_COND_NE, clean_addr, cpu_exclusive_addr, fail_label); @@ -XXX,XX +XXX,XX @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, } tcg_gen_atomic_cmpxchg_i64(tmp, cpu_exclusive_addr, cpu_exclusive_val, tmp, - get_mem_index(s), - MO_64 | MO_ALIGN | s->be_data); + get_mem_index(s), memop); tcg_gen_setcond_i64(TCG_COND_NE, tmp, tmp, cpu_exclusive_val); } else { TCGv_i128 t16 = tcg_temp_new_i128(); @@ -XXX,XX +XXX,XX @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, } tcg_gen_atomic_cmpxchg_i128(t16, cpu_exclusive_addr, c16, t16, - get_mem_index(s), - MO_128 | MO_ALIGN | s->be_data); + get_mem_index(s), memop); a = tcg_temp_new_i64(); b = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, } } else { tcg_gen_atomic_cmpxchg_i64(tmp, cpu_exclusive_addr, cpu_exclusive_val, - cpu_reg(s, rt), get_mem_index(s), - size | MO_ALIGN | s->be_data); + cpu_reg(s, rt), get_mem_index(s), memop); tcg_gen_setcond_i64(TCG_COND_NE, tmp, tmp, cpu_exclusive_val); } tcg_gen_mov_i64(cpu_reg(s, rd), tmp); @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap(DisasContext *s, int rs, int rt, TCGv_i64 tcg_rt = cpu_reg(s, rt); int memidx = get_mem_index(s); TCGv_i64 clean_addr; + MemOp memop; if (rn == 31) { gen_check_sp_alignment(s); } - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, size); - tcg_gen_atomic_cmpxchg_i64(tcg_rs, clean_addr, tcg_rs, tcg_rt, memidx, - size | MO_ALIGN | s->be_data); + memop = finalize_memop(s, size | MO_ALIGN); + clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, memop); + tcg_gen_atomic_cmpxchg_i64(tcg_rs, clean_addr, tcg_rs, tcg_rt, + memidx, memop); } static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, TCGv_i64 t2 = cpu_reg(s, rt + 1); TCGv_i64 clean_addr; int memidx = get_mem_index(s); + MemOp memop; if (rn == 31) { gen_check_sp_alignment(s); } /* This is a single atomic access, despite the "pair". */ - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, size + 1); + memop = finalize_memop(s, (size + 1) | MO_ALIGN); + clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, memop); if (size == 2) { TCGv_i64 cmp = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, tcg_gen_concat32_i64(cmp, s2, s1); } - tcg_gen_atomic_cmpxchg_i64(cmp, clean_addr, cmp, val, memidx, - MO_64 | MO_ALIGN | s->be_data); + tcg_gen_atomic_cmpxchg_i64(cmp, clean_addr, cmp, val, memidx, memop); if (s->be_data == MO_LE) { tcg_gen_extr32_i64(s1, s2, cmp); @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, tcg_gen_concat_i64_i128(cmp, s2, s1); } - tcg_gen_atomic_cmpxchg_i128(cmp, clean_addr, cmp, val, memidx, - MO_128 | MO_ALIGN | s->be_data); + tcg_gen_atomic_cmpxchg_i128(cmp, clean_addr, cmp, val, memidx, memop); if (s->be_data == MO_LE) { tcg_gen_extr_i128_i64(s1, s2, cmp); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) /* TODO: ARMv8.4-LSE SCTLR.nAA */ memop = finalize_memop(s, size | MO_ALIGN); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), - true, rn != 31, size); + true, rn != 31, memop); do_gpr_st(s, cpu_reg(s, rt), clean_addr, memop, true, rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) /* TODO: ARMv8.4-LSE SCTLR.nAA */ memop = finalize_memop(s, size | MO_ALIGN); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), - false, rn != 31, size); + false, rn != 31, memop); do_gpr_ld(s, cpu_reg(s, rt), clean_addr, memop, false, true, rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, tcg_gen_add_i64(dirty_addr, dirty_addr, tcg_rm); memop = finalize_memop(s, size + is_signed * MO_SIGN); - clean_addr = gen_mte_check1(s, dirty_addr, is_store, true, size); + clean_addr = gen_mte_check1(s, dirty_addr, is_store, true, memop); if (is_vector) { if (is_store) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); memop = finalize_memop(s, size + is_signed * MO_SIGN); - clean_addr = gen_mte_check1(s, dirty_addr, is_store, rn != 31, size); + clean_addr = gen_mte_check1(s, dirty_addr, is_store, rn != 31, memop); if (is_vector) { if (is_store) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, if (rn == 31) { gen_check_sp_alignment(s); } - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), false, rn != 31, size); + clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), false, rn != 31, mop); if (o3_opc == 014) { /* @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pac(DisasContext *s, uint32_t insn, /* Note that "clean" and "dirty" here refer to TBI not PAC. */ clean_addr = gen_mte_check1(s, dirty_addr, false, - is_wback || rn != 31, size); + is_wback || rn != 31, memop); tcg_rt = cpu_reg(s, rt); do_gpr_ld(s, tcg_rt, clean_addr, memop, diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a) unsigned msz = dtype_msz(a->dtype); TCGLabel *over; TCGv_i64 temp, clean_addr; + MemOp memop; if (!dc_isar_feature(aa64_sve, s)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a) /* Load the data. */ temp = tcg_temp_new_i64(); tcg_gen_addi_i64(temp, cpu_reg_sp(s, a->rn), a->imm << msz); - clean_addr = gen_mte_check1(s, temp, false, true, msz); - tcg_gen_qemu_ld_i64(temp, clean_addr, get_mem_index(s), - finalize_memop(s, dtype_mop[a->dtype])); + memop = finalize_memop(s, dtype_mop[a->dtype]); + clean_addr = gen_mte_check1(s, temp, false, true, memop); + tcg_gen_qemu_ld_i64(temp, clean_addr, get_mem_index(s), memop); /* Broadcast to *all* elements. */ tcg_gen_gvec_dup_i64(esz, vec_full_reg_offset(s, a->rd), -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Pass the individual memop to gen_mte_checkN. For the moment, do nothing with it. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.h | 2 +- target/arm/tcg/translate-a64.c | 31 +++++++++++++++++++------------ target/arm/tcg/translate-sve.c | 4 ++-- 3 files changed, 22 insertions(+), 15 deletions(-) diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.h +++ b/target/arm/tcg/translate-a64.h @@ -XXX,XX +XXX,XX @@ TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr); TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write, bool tag_checked, MemOp memop); TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, - bool tag_checked, int size); + bool tag_checked, int total_size, MemOp memop); /* We should have at some point before trying to access an FP register * done the necessary access check, so assert that diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write, * For MTE, check multiple logical sequential accesses. */ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, - bool tag_checked, int size) + bool tag_checked, int total_size, MemOp single_mop) { if (tag_checked && s->mte_active[0]) { TCGv_i64 ret; @@ -XXX,XX +XXX,XX @@ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write); - desc = FIELD_DP32(desc, MTEDESC, SIZEM1, size - 1); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, total_size - 1); ret = tcg_temp_new_i64(); gen_helper_mte_check(ret, cpu_env, tcg_constant_i32(desc), addr); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) bool is_vector = extract32(insn, 26, 1); bool is_load = extract32(insn, 22, 1); int opc = extract32(insn, 30, 2); - bool is_signed = false; bool postindex = false; bool wback = false; bool set_tag = false; - TCGv_i64 clean_addr, dirty_addr; - + MemOp mop; int size; if (opc == 3) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) } } + if (is_vector) { + mop = finalize_memop_asimd(s, size); + } else { + mop = finalize_memop(s, size); + } clean_addr = gen_mte_checkN(s, dirty_addr, !is_load, - (wback || rn != 31) && !set_tag, 2 << size); + (wback || rn != 31) && !set_tag, + 2 << size, mop); if (is_vector) { - MemOp mop = finalize_memop_asimd(s, size); - + /* LSE2 does not merge FP pairs; leave these as separate operations. */ if (is_load) { do_fp_ld(s, rt, clean_addr, mop); } else { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); TCGv_i64 tcg_rt2 = cpu_reg(s, rt2); - MemOp mop = size + 1; /* + * We built mop above for the single logical access -- rebuild it + * now for the paired operation. + * * With LSE2, non-sign-extending pairs are treated atomically if * aligned, and if unaligned one of the pair will be completely * within a 16-byte block and that element will be atomic. @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) * This treats sign-extending loads like zero-extending loads, * since that reuses the most code below. */ + mop = size + 1; if (s->align_mem) { mop |= (size == 2 ? MO_ALIGN_4 : MO_ALIGN_8); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) * promote consecutive little-endian elements below. */ clean_addr = gen_mte_checkN(s, tcg_rn, is_store, is_postidx || rn != 31, - total); + total, finalize_memop(s, size)); /* * Consecutive little-endian elements from a single register @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) total = selem << scale; tcg_rn = cpu_reg_sp(s, rn); - clean_addr = gen_mte_checkN(s, tcg_rn, !is_load, is_postidx || rn != 31, - total); mop = finalize_memop(s, scale); + clean_addr = gen_mte_checkN(s, tcg_rn, !is_load, is_postidx || rn != 31, + total, mop); + tcg_ebytes = tcg_constant_i64(1 << scale); for (xs = 0; xs < selem; xs++) { if (replicate) { diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, dirty_addr = tcg_temp_new_i64(); tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm); - clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len); + clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len, MO_8); /* * Note that unpredicated load/store of vector/predicate registers @@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, dirty_addr = tcg_temp_new_i64(); tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm); - clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len); + clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len, MO_8); /* Note that unpredicated load/store of vector/predicate registers * are defined as a stream of bytes, which equates to little-endian -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Fixes a bug in that with SCTLR.A set, we should raise any alignment fault before raising any MTE check fault. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 3 ++- target/arm/tcg/mte_helper.c | 18 ++++++++++++++++++ target/arm/tcg/translate-a64.c | 2 ++ 3 files changed, 22 insertions(+), 1 deletion(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ FIELD(MTEDESC, MIDX, 0, 4) FIELD(MTEDESC, TBI, 4, 2) FIELD(MTEDESC, TCMA, 6, 2) FIELD(MTEDESC, WRITE, 8, 1) -FIELD(MTEDESC, SIZEM1, 9, SIMD_DATA_BITS - 9) /* size - 1 */ +FIELD(MTEDESC, ALIGN, 9, 3) +FIELD(MTEDESC, SIZEM1, 12, SIMD_DATA_BITS - 12) /* size - 1 */ bool mte_probe(CPUARMState *env, uint32_t desc, uint64_t ptr); uint64_t mte_check(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra); diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mte_helper.c +++ b/target/arm/tcg/mte_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t mte_check(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra) uint64_t HELPER(mte_check)(CPUARMState *env, uint32_t desc, uint64_t ptr) { + /* + * R_XCHFJ: Alignment check not caused by memory type is priority 1, + * higher than any translation fault. When MTE is disabled, tcg + * performs the alignment check during the code generated for the + * memory access. With MTE enabled, we must check this here before + * raising any translation fault in allocation_tag_mem. + */ + unsigned align = FIELD_EX32(desc, MTEDESC, ALIGN); + if (unlikely(align)) { + align = (1u << align) - 1; + if (unlikely(ptr & align)) { + int idx = FIELD_EX32(desc, MTEDESC, MIDX); + bool w = FIELD_EX32(desc, MTEDESC, WRITE); + MMUAccessType type = w ? MMU_DATA_STORE : MMU_DATA_LOAD; + arm_cpu_do_unaligned_access(env_cpu(env), ptr, type, idx, GETPC()); + } + } + return mte_check(env, desc, ptr, GETPC()); } diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static TCGv_i64 gen_mte_check1_mmuidx(DisasContext *s, TCGv_i64 addr, desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write); + desc = FIELD_DP32(desc, MTEDESC, ALIGN, get_alignment_bits(memop)); desc = FIELD_DP32(desc, MTEDESC, SIZEM1, memop_size(memop) - 1); ret = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write); + desc = FIELD_DP32(desc, MTEDESC, ALIGN, get_alignment_bits(single_mop)); desc = FIELD_DP32(desc, MTEDESC, SIZEM1, total_size - 1); ret = tcg_temp_new_i64(); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 3 ++- target/arm/tcg/translate.h | 2 ++ target/arm/tcg/hflags.c | 6 ++++++ target/arm/tcg/translate-a64.c | 1 + 4 files changed, 11 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define SCTLR_D (1U << 5) /* up to v5; RAO in v6 */ #define SCTLR_CP15BEN (1U << 5) /* v7 onward */ #define SCTLR_L (1U << 6) /* up to v5; RAO in v6 and v7; RAZ in v8 */ -#define SCTLR_nAA (1U << 6) /* when v8.4-LSE is implemented */ +#define SCTLR_nAA (1U << 6) /* when FEAT_LSE2 is implemented */ #define SCTLR_B (1U << 7) /* up to v6; RAZ in v7 */ #define SCTLR_ITD (1U << 7) /* v8 onward */ #define SCTLR_S (1U << 8) /* up to v6; RAZ in v7 */ @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, SVL, 24, 4) /* Indicates that SME Streaming mode is active, and SMCR_ELx.FA64 is not. */ FIELD(TBFLAG_A64, SME_TRAP_NONSTREAMING, 28, 1) FIELD(TBFLAG_A64, FGT_ERET, 29, 1) +FIELD(TBFLAG_A64, NAA, 30, 1) /* * Helpers for using the above. diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { bool fgt_eret; /* True if fine-grained trap on SVC is enabled */ bool fgt_svc; + /* True if FEAT_LSE2 SCTLR_ELx.nAA is set */ + bool naa; /* * >= 0, a copy of PSTATE.BTYPE, which will be 0 without v8.5-BTI. * < 0, set by the current instruction. diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/hflags.c +++ b/target/arm/tcg/hflags.c @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, } } + if (cpu_isar_feature(aa64_lse2, env_archcpu(env))) { + if (sctlr & SCTLR_nAA) { + DP_TBFLAG_A64(flags, NAA, 1); + } + } + /* Compute the condition for using AccType_UNPRIV for LDTR et al. */ if (!(env->pstate & PSTATE_UAO)) { switch (mmu_idx) { diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->pstate_sm = EX_TBFLAG_A64(tb_flags, PSTATE_SM); dc->pstate_za = EX_TBFLAG_A64(tb_flags, PSTATE_ZA); dc->sme_trap_nonstreaming = EX_TBFLAG_A64(tb_flags, SME_TRAP_NONSTREAMING); + dc->naa = EX_TBFLAG_A64(tb_flags, NAA); dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = arm_cpu->cp_regs; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> FEAT_LSE2 only requires that atomic operations not cross a 16-byte boundary. Ordered operations may be completely unaligned if SCTLR.nAA is set. Because this alignment check is so special, do it by hand. Make sure not to keep TCG temps live across the branch. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-17-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-a64.h | 3 + target/arm/tcg/helper-a64.c | 7 ++ target/arm/tcg/translate-a64.c | 120 ++++++++++++++++++++++++++------- 3 files changed, 104 insertions(+), 26 deletions(-) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(st2g_stub, TCG_CALL_NO_WG, void, env, i64) DEF_HELPER_FLAGS_2(ldgm, TCG_CALL_NO_WG, i64, env, i64) DEF_HELPER_FLAGS_3(stgm, TCG_CALL_NO_WG, void, env, i64, i64) DEF_HELPER_FLAGS_3(stzgm_tags, TCG_CALL_NO_WG, void, env, i64, i64) + +DEF_HELPER_FLAGS_4(unaligned_access, TCG_CALL_NO_WG, + noreturn, env, i64, i32, i32) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) memset(mem, 0, blocklen); } + +void HELPER(unaligned_access)(CPUARMState *env, uint64_t addr, + uint32_t access_type, uint32_t mmu_idx) +{ + arm_cpu_do_unaligned_access(env_cpu(env), addr, access_type, + mmu_idx, GETPC()); +} diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, return clean_data_tbi(s, addr); } +/* + * Generate the special alignment check that applies to AccType_ATOMIC + * and AccType_ORDERED insns under FEAT_LSE2: the access need not be + * naturally aligned, but it must not cross a 16-byte boundary. + * See AArch64.CheckAlignment(). + */ +static void check_lse2_align(DisasContext *s, int rn, int imm, + bool is_write, MemOp mop) +{ + TCGv_i32 tmp; + TCGv_i64 addr; + TCGLabel *over_label; + MMUAccessType type; + int mmu_idx; + + tmp = tcg_temp_new_i32(); + tcg_gen_extrl_i64_i32(tmp, cpu_reg_sp(s, rn)); + tcg_gen_addi_i32(tmp, tmp, imm & 15); + tcg_gen_andi_i32(tmp, tmp, 15); + tcg_gen_addi_i32(tmp, tmp, memop_size(mop)); + + over_label = gen_new_label(); + tcg_gen_brcondi_i32(TCG_COND_LEU, tmp, 16, over_label); + + addr = tcg_temp_new_i64(); + tcg_gen_addi_i64(addr, cpu_reg_sp(s, rn), imm); + + type = is_write ? MMU_DATA_STORE : MMU_DATA_LOAD, + mmu_idx = get_mem_index(s); + gen_helper_unaligned_access(cpu_env, addr, tcg_constant_i32(type), + tcg_constant_i32(mmu_idx)); + + gen_set_label(over_label); + +} + +/* Handle the alignment check for AccType_ATOMIC instructions. */ +static MemOp check_atomic_align(DisasContext *s, int rn, MemOp mop) +{ + MemOp size = mop & MO_SIZE; + + if (size == MO_8) { + return mop; + } + + /* + * If size == MO_128, this is a LDXP, and the operation is single-copy + * atomic for each doubleword, not the entire quadword; it still must + * be quadword aligned. + */ + if (size == MO_128) { + return finalize_memop_atom(s, MO_128 | MO_ALIGN, + MO_ATOM_IFALIGN_PAIR); + } + if (dc_isar_feature(aa64_lse2, s)) { + check_lse2_align(s, rn, 0, true, mop); + } else { + mop |= MO_ALIGN; + } + return finalize_memop(s, mop); +} + +/* Handle the alignment check for AccType_ORDERED instructions. */ +static MemOp check_ordered_align(DisasContext *s, int rn, int imm, + bool is_write, MemOp mop) +{ + MemOp size = mop & MO_SIZE; + + if (size == MO_8) { + return mop; + } + if (size == MO_128) { + return finalize_memop_atom(s, MO_128 | MO_ALIGN, + MO_ATOM_IFALIGN_PAIR); + } + if (!dc_isar_feature(aa64_lse2, s)) { + mop |= MO_ALIGN; + } else if (!s->naa) { + check_lse2_align(s, rn, imm, is_write, mop); + } + return finalize_memop(s, mop); +} + typedef struct DisasCompare64 { TCGCond cond; TCGv_i64 value; @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, int rn, { int idx = get_mem_index(s); TCGv_i64 dirty_addr, clean_addr; - MemOp memop; - - /* - * For pairs: - * if size == 2, the operation is single-copy atomic for the doubleword. - * if size == 3, the operation is single-copy atomic for *each* doubleword, - * not the entire quadword, however it must be quadword aligned. - */ - memop = size + is_pair; - if (memop == MO_128) { - memop = finalize_memop_atom(s, MO_128 | MO_ALIGN, - MO_ATOM_IFALIGN_PAIR); - } else { - memop = finalize_memop(s, memop | MO_ALIGN); - } + MemOp memop = check_atomic_align(s, rn, size + is_pair); s->is_ldex = true; dirty_addr = cpu_reg_sp(s, rn); @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap(DisasContext *s, int rs, int rt, if (rn == 31) { gen_check_sp_alignment(s); } - memop = finalize_memop(s, size | MO_ALIGN); + memop = check_atomic_align(s, rn, size); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, memop); tcg_gen_atomic_cmpxchg_i64(tcg_rs, clean_addr, tcg_rs, tcg_rt, memidx, memop); @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, } /* This is a single atomic access, despite the "pair". */ - memop = finalize_memop(s, (size + 1) | MO_ALIGN); + memop = check_atomic_align(s, rn, size + 1); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, memop); if (size == 2) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) gen_check_sp_alignment(s); } tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); - /* TODO: ARMv8.4-LSE SCTLR.nAA */ - memop = finalize_memop(s, size | MO_ALIGN); + memop = check_ordered_align(s, rn, 0, true, size); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, memop); do_gpr_st(s, cpu_reg(s, rt), clean_addr, memop, true, rt, @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (rn == 31) { gen_check_sp_alignment(s); } - /* TODO: ARMv8.4-LSE SCTLR.nAA */ - memop = finalize_memop(s, size | MO_ALIGN); + memop = check_ordered_align(s, rn, 0, false, size); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), false, rn != 31, memop); do_gpr_ld(s, cpu_reg(s, rt), clean_addr, memop, false, true, @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, bool a = extract32(insn, 23, 1); TCGv_i64 tcg_rs, tcg_rt, clean_addr; AtomicThreeOpFn *fn = NULL; - MemOp mop = finalize_memop(s, size | MO_ALIGN); + MemOp mop = size; if (is_vector || !dc_isar_feature(aa64_atomics, s)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, if (rn == 31) { gen_check_sp_alignment(s); } + + mop = check_atomic_align(s, rn, mop); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), false, rn != 31, mop); if (o3_opc == 014) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) bool is_store = false; bool extend = false; bool iss_sf; - MemOp mop; + MemOp mop = size; if (!dc_isar_feature(aa64_rcpc_8_4, s)) { unallocated_encoding(s); return; } - /* TODO: ARMv8.4-LSE SCTLR.nAA */ - mop = finalize_memop(s, size | MO_ALIGN); - switch (opc) { case 0: /* STLURB */ is_store = true; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) gen_check_sp_alignment(s); } + mop = check_ordered_align(s, rn, offset, is_store, mop); + dirty_addr = read_cpu_reg_sp(s, rn, 1); tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); clean_addr = clean_data_tbi(s, dirty_addr); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Push the mte check behind the exclusive_addr check. Document the several ways that we are still out of spec with this implementation. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 42 +++++++++++++++++++++++++++++----- 1 file changed, 36 insertions(+), 6 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, */ TCGLabel *fail_label = gen_new_label(); TCGLabel *done_label = gen_new_label(); - TCGv_i64 tmp, dirty_addr, clean_addr; + TCGv_i64 tmp, clean_addr; MemOp memop; - memop = (size + is_pair) | MO_ALIGN; - memop = finalize_memop(s, memop); - - dirty_addr = cpu_reg_sp(s, rn); - clean_addr = gen_mte_check1(s, dirty_addr, true, rn != 31, memop); + /* + * FIXME: We are out of spec here. We have recorded only the address + * from load_exclusive, not the entire range, and we assume that the + * size of the access on both sides match. The architecture allows the + * store to be smaller than the load, so long as the stored bytes are + * within the range recorded by the load. + */ + /* See AArch64.ExclusiveMonitorsPass() and AArch64.IsExclusiveVA(). */ + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); tcg_gen_brcond_i64(TCG_COND_NE, clean_addr, cpu_exclusive_addr, fail_label); + /* + * The write, and any associated faults, only happen if the virtual + * and physical addresses pass the exclusive monitor check. These + * faults are exceedingly unlikely, because normally the guest uses + * the exact same address register for the load_exclusive, and we + * would have recognized these faults there. + * + * It is possible to trigger an alignment fault pre-LSE2, e.g. with an + * unaligned 4-byte write within the range of an aligned 8-byte load. + * With LSE2, the store would need to cross a 16-byte boundary when the + * load did not, which would mean the store is outside the range + * recorded for the monitor, which would have failed a corrected monitor + * check above. For now, we assume no size change and retain the + * MO_ALIGN to let tcg know what we checked in the load_exclusive. + * + * It is possible to trigger an MTE fault, by performing the load with + * a virtual address with a valid tag and performing the store with the + * same virtual address and a different invalid tag. + */ + memop = size + is_pair; + if (memop == MO_128 || !dc_isar_feature(aa64_lse2, s)) { + memop |= MO_ALIGN; + } + memop = finalize_memop(s, memop); + gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, memop); + tmp = tcg_temp_new_i64(); if (is_pair) { if (size == 2) { -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> We have many other instances of stg in the testsuite; change these to provide an instance of stz2g. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/tcg/aarch64/mte-7.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tests/tcg/aarch64/mte-7.c b/tests/tcg/aarch64/mte-7.c index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/aarch64/mte-7.c +++ b/tests/tcg/aarch64/mte-7.c @@ -XXX,XX +XXX,XX @@ int main(int ac, char **av) p = (void *)((unsigned long)p | (1ul << 56)); /* Store tag in sequential granules. */ - asm("stg %0, [%0]" : : "r"(p + 0x0ff0)); - asm("stg %0, [%0]" : : "r"(p + 0x1000)); + asm("stz2g %0, [%0]" : : "r"(p + 0x0ff0)); /* * Perform an unaligned store with tag 1 crossing the pages. -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> With -cpu max and FEAT_LSE2, the __aarch64__ section will only raise an alignment exception when the load crosses a 16-byte boundary. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/tcg/multiarch/sigbus.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/tests/tcg/multiarch/sigbus.c b/tests/tcg/multiarch/sigbus.c index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/multiarch/sigbus.c +++ b/tests/tcg/multiarch/sigbus.c @@ -XXX,XX +XXX,XX @@ #include <endian.h> -unsigned long long x = 0x8877665544332211ull; -void * volatile p = (void *)&x + 1; +char x[32] __attribute__((aligned(16))) = { + 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, + 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 0x10, + 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, + 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, +}; +void * volatile p = (void *)&x + 15; void sigbus(int sig, siginfo_t *info, void *uc) { @@ -XXX,XX +XXX,XX @@ int main() * We might as well validate the unaligned load worked. */ if (BYTE_ORDER == LITTLE_ENDIAN) { - assert(tmp == 0x55443322); + assert(tmp == 0x13121110); } else { - assert(tmp == 0x77665544); + assert(tmp == 0x10111213); } return EXIT_SUCCESS; } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230530191438.411344-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu64.c | 1 + 2 files changed, 2 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_LRCPC (Load-acquire RCpc instructions) - FEAT_LRCPC2 (Load-acquire RCpc instructions v2) - FEAT_LSE (Large System Extensions) +- FEAT_LSE2 (Large System Extensions v2) - FEAT_LVA (Large Virtual Address space) - FEAT_MTE (Memory Tagging Extension) - FEAT_MTE2 (Memory Tagging Extension) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64MMFR2, IESB, 1); /* FEAT_IESB */ t = FIELD_DP64(t, ID_AA64MMFR2, VARANGE, 1); /* FEAT_LVA */ t = FIELD_DP64(t, ID_AA64MMFR2, ST, 1); /* FEAT_TTST */ + t = FIELD_DP64(t, ID_AA64MMFR2, AT, 1); /* FEAT_LSE2 */ t = FIELD_DP64(t, ID_AA64MMFR2, IDS, 1); /* FEAT_IDST */ t = FIELD_DP64(t, ID_AA64MMFR2, FWB, 1); /* FEAT_S2FWB */ t = FIELD_DP64(t, ID_AA64MMFR2, TTL, 1); /* FEAT_TTL */ -- 2.34.1 From: Zhuojia Shen <chaosdefinition@hotmail.com> DC CVAP and DC CVADP instructions can be executed in EL0 on Linux, either directly when SCTLR_EL1.UCI == 1 or emulated by the kernel (see user_cache_maint_handler() in arch/arm64/kernel/traps.c). This patch enables execution of the two instructions in user mode emulation. Signed-off-by: Zhuojia Shen <chaosdefinition@hotmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo rndr_reginfo[] = { .access = PL0_R, .readfn = rndr_readfn }, }; -#ifndef CONFIG_USER_ONLY static void dccvap_writefn(CPUARMState *env, const ARMCPRegInfo *opaque, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static void dccvap_writefn(CPUARMState *env, const ARMCPRegInfo *opaque, /* This won't be crossing page boundaries */ haddr = probe_read(env, vaddr, dline_size, mem_idx, GETPC()); if (haddr) { +#ifndef CONFIG_USER_ONLY ram_addr_t offset; MemoryRegion *mr; @@ -XXX,XX +XXX,XX @@ static void dccvap_writefn(CPUARMState *env, const ARMCPRegInfo *opaque, if (mr) { memory_region_writeback(mr, offset, dline_size); } +#endif /*CONFIG_USER_ONLY*/ } } @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo dcpodp_reg[] = { .fgt = FGT_DCCVADP, .accessfn = aa64_cacheop_poc_access, .writefn = dccvap_writefn }, }; -#endif /*CONFIG_USER_ONLY*/ static CPAccessResult access_aa64_tid5(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_tlbios, cpu)) { define_arm_cp_regs(cpu, tlbios_reginfo); } -#ifndef CONFIG_USER_ONLY /* Data Cache clean instructions up to PoP */ if (cpu_isar_feature(aa64_dcpop, cpu)) { define_one_arm_cp_reg(cpu, dcpop_reg); @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_one_arm_cp_reg(cpu, dcpodp_reg); } } -#endif /*CONFIG_USER_ONLY*/ /* * If full MTE is enabled, add all of the system registers. -- 2.34.1 From: Zhuojia Shen <chaosdefinition@hotmail.com> Test execution of DC CVAP and DC CVADP instructions under user mode emulation. Signed-off-by: Zhuojia Shen <chaosdefinition@hotmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/tcg/aarch64/dcpodp.c | 63 +++++++++++++++++++++++++++++++ tests/tcg/aarch64/dcpop.c | 63 +++++++++++++++++++++++++++++++ tests/tcg/aarch64/Makefile.target | 11 ++++++ 3 files changed, 137 insertions(+) create mode 100644 tests/tcg/aarch64/dcpodp.c create mode 100644 tests/tcg/aarch64/dcpop.c diff --git a/tests/tcg/aarch64/dcpodp.c b/tests/tcg/aarch64/dcpodp.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/dcpodp.c @@ -XXX,XX +XXX,XX @@ +/* + * Test execution of DC CVADP instruction. + * + * Copyright (c) 2023 Zhuojia Shen <chaosdefinition@hotmail.com> + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include <asm/hwcap.h> +#include <sys/auxv.h> + +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> + +#ifndef HWCAP2_DCPODP +#define HWCAP2_DCPODP (1 << 0) +#endif + +bool should_fail = false; + +static void signal_handler(int sig, siginfo_t *si, void *data) +{ + ucontext_t *uc = (ucontext_t *)data; + + if (should_fail) { + uc->uc_mcontext.pc += 4; + } else { + exit(EXIT_FAILURE); + } +} + +static int do_dc_cvadp(void) +{ + struct sigaction sa = { + .sa_flags = SA_SIGINFO, + .sa_sigaction = signal_handler, + }; + + sigemptyset(&sa.sa_mask); + if (sigaction(SIGSEGV, &sa, NULL) < 0) { + perror("sigaction"); + return EXIT_FAILURE; + } + + asm volatile("dc cvadp, %0\n\t" :: "r"(&sa)); + + should_fail = true; + asm volatile("dc cvadp, %0\n\t" :: "r"(NULL)); + should_fail = false; + + return EXIT_SUCCESS; +} + +int main(void) +{ + if (getauxval(AT_HWCAP2) & HWCAP2_DCPODP) { + return do_dc_cvadp(); + } else { + printf("SKIP: no HWCAP2_DCPODP on this system\n"); + return EXIT_SUCCESS; + } +} diff --git a/tests/tcg/aarch64/dcpop.c b/tests/tcg/aarch64/dcpop.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/dcpop.c @@ -XXX,XX +XXX,XX @@ +/* + * Test execution of DC CVAP instruction. + * + * Copyright (c) 2023 Zhuojia Shen <chaosdefinition@hotmail.com> + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include <asm/hwcap.h> +#include <sys/auxv.h> + +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> + +#ifndef HWCAP_DCPOP +#define HWCAP_DCPOP (1 << 16) +#endif + +bool should_fail = false; + +static void signal_handler(int sig, siginfo_t *si, void *data) +{ + ucontext_t *uc = (ucontext_t *)data; + + if (should_fail) { + uc->uc_mcontext.pc += 4; + } else { + exit(EXIT_FAILURE); + } +} + +static int do_dc_cvap(void) +{ + struct sigaction sa = { + .sa_flags = SA_SIGINFO, + .sa_sigaction = signal_handler, + }; + + sigemptyset(&sa.sa_mask); + if (sigaction(SIGSEGV, &sa, NULL) < 0) { + perror("sigaction"); + return EXIT_FAILURE; + } + + asm volatile("dc cvap, %0\n\t" :: "r"(&sa)); + + should_fail = true; + asm volatile("dc cvap, %0\n\t" :: "r"(NULL)); + should_fail = false; + + return EXIT_SUCCESS; +} + +int main(void) +{ + if (getauxval(AT_HWCAP) & HWCAP_DCPOP) { + return do_dc_cvap(); + } else { + printf("SKIP: no HWCAP_DCPOP on this system\n"); + return EXIT_SUCCESS; + } +} diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -XXX,XX +XXX,XX @@ config-cc.mak: Makefile $(quiet-@)( \ $(call cc-option,-march=armv8.1-a+sve, CROSS_CC_HAS_SVE); \ $(call cc-option,-march=armv8.1-a+sve2, CROSS_CC_HAS_SVE2); \ + $(call cc-option,-march=armv8.2-a, CROSS_CC_HAS_ARMV8_2); \ $(call cc-option,-march=armv8.3-a, CROSS_CC_HAS_ARMV8_3); \ + $(call cc-option,-march=armv8.5-a, CROSS_CC_HAS_ARMV8_5); \ $(call cc-option,-mbranch-protection=standard, CROSS_CC_HAS_ARMV8_BTI); \ $(call cc-option,-march=armv8.5-a+memtag, CROSS_CC_HAS_ARMV8_MTE); \ $(call cc-option,-march=armv9-a+sme, CROSS_CC_HAS_ARMV9_SME)) 3> config-cc.mak -include config-cc.mak +ifneq ($(CROSS_CC_HAS_ARMV8_2),) +AARCH64_TESTS += dcpop +dcpop: CFLAGS += -march=armv8.2-a +endif +ifneq ($(CROSS_CC_HAS_ARMV8_5),) +AARCH64_TESTS += dcpodp +dcpodp: CFLAGS += -march=armv8.5-a +endif + # Pauth Tests ifneq ($(CROSS_CC_HAS_ARMV8_3),) AARCH64_TESTS += pauth-1 pauth-2 pauth-4 pauth-5 -- 2.34.1 From: Zhuojia Shen <chaosdefinition@hotmail.com> Accessing EL0-accessible Debug Communication Channel (DCC) registers in user mode emulation is currently enabled. However, it does not match Linux behavior as Linux sets MDSCR_EL1.TDCC on startup to disable EL0 access to DCC (see __cpu_setup() in arch/arm64/mm/proc.S). This patch fixes access_tdcc() to check MDSCR_EL1.TDCC for EL0 and sets MDSCR_EL1.TDCC for user mode emulation to match Linux. Signed-off-by: Zhuojia Shen <chaosdefinition@hotmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: DS7PR12MB630905198DD8E69F6817544CAC4EA@DS7PR12MB6309.namprd12.prod.outlook.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 2 ++ target/arm/debug_helper.c | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset_hold(Object *obj) * This is not yet exposed from the Linux kernel in any way. */ env->cp15.sctlr_el[1] |= SCTLR_TSCXT; + /* Disable access to Debug Communication Channel (DCC). */ + env->cp15.mdscr_el1 |= 1 << 12; #else /* Reset into the highest available EL */ if (arm_feature(env, ARM_FEATURE_EL3)) { diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/debug_helper.c +++ b/target/arm/debug_helper.c @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_tda(CPUARMState *env, const ARMCPRegInfo *ri, * is implemented then these are controlled by MDCR_EL2.TDCC for * EL2 and MDCR_EL3.TDCC for EL3. They are also controlled by * the general debug access trap bits MDCR_EL2.TDA and MDCR_EL3.TDA. + * For EL0, they are also controlled by MDSCR_EL1.TDCC. */ static CPAccessResult access_tdcc(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { int el = arm_current_el(env); uint64_t mdcr_el2 = arm_mdcr_el2_eff(env); + bool mdscr_el1_tdcc = extract32(env->cp15.mdscr_el1, 12, 1); bool mdcr_el2_tda = (mdcr_el2 & MDCR_TDA) || (mdcr_el2 & MDCR_TDE) || (arm_hcr_el2_eff(env) & HCR_TGE); bool mdcr_el2_tdcc = cpu_isar_feature(aa64_fgt, env_archcpu(env)) && @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_tdcc(CPUARMState *env, const ARMCPRegInfo *ri, bool mdcr_el3_tdcc = cpu_isar_feature(aa64_fgt, env_archcpu(env)) && (env->cp15.mdcr_el3 & MDCR_TDCC); + if (el < 1 && mdscr_el1_tdcc) { + return CP_ACCESS_TRAP; + } if (el < 2 && (mdcr_el2_tda || mdcr_el2_tdcc)) { return CP_ACCESS_TRAP_EL2; } -- 2.34.1