diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2020-06-23 18:57:05 +0100 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2020-06-23 18:57:05 +0100 |
commit | d4b78317b7cf8c0c635b70086503813f79ff21ec (patch) | |
tree | bab8d849b983bcc72e9680acf23470679fb9e251 | |
parent | d88d5a3806d78dcfca648c62dae9d88d3e803bd2 (diff) | |
parent | 539533b85fbd269f777bed931de8ccae1dd837e9 (diff) | |
download | qemu-d4b78317b7cf8c0c635b70086503813f79ff21ec.zip |
Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20200623' into staging
target-arm queue:
* util/oslib-posix : qemu_init_exec_dir implementation for Mac
* target/arm: Last parts of neon decodetree conversion
* hw/arm/virt: Add 5.0 HW compat props
* hw/watchdog/cmsdk-apb-watchdog: Add trace event for lock status
* mps2: Add CMSDK APB watchdog, FPGAIO block, S2I devices and I2C devices
* mps2: Add some unimplemented-device stubs for audio and GPIO
* mps2-tz: Use the ARM SBCon two-wire serial bus interface
* target/arm: Check supported KVM features globally (not per vCPU)
* tests/qtest/arm-cpu-features: Add feature setting tests
* arm/virt: Add memory hot remove support
# gpg: Signature made Tue 23 Jun 2020 12:38:31 BST
# gpg: using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg: issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [ultimate]
# gpg: aka "Peter Maydell <pmaydell@gmail.com>" [ultimate]
# gpg: aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83 15CF 3C25 25ED 1436 0CDE
* remotes/pmaydell/tags/pull-target-arm-20200623: (42 commits)
arm/virt: Add memory hot remove support
tests/qtest/arm-cpu-features: Add feature setting tests
target/arm: Check supported KVM features globally (not per vCPU)
hw/arm/mps2-tz: Use the ARM SBCon two-wire serial bus interface
hw/arm/mps2: Add audio I2S interface as unimplemented device
hw/arm/mps2: Add I2C devices
hw/arm/mps2: Add SPI devices
hw/arm/mps2: Map the FPGA I/O block
hw/arm/mps2: Add CMSDK AHB GPIO peripherals as unimplemented devices
hw/arm/mps2: Add CMSDK APB watchdog device
hw/arm/mps2: Rename CMSDK AHB peripheral region
hw/arm/mps2: Document CMSDK/FPGA APB subsystem sections
hw/arm: Use TYPE_VERSATILE_I2C instead of hardcoded string
hw/i2c: Add header for ARM SBCon two-wire serial bus interface
hw/i2c/versatile_i2c: Add SCL/SDA definitions
hw/i2c/versatile_i2c: Add definitions for register addresses
hw/watchdog/cmsdk-apb-watchdog: Add trace event for lock status
target/arm: Remove dead code relating to SABA and UABA
target/arm: Remove unnecessary gen_io_end() calls
target/arm: Move some functions used only in translate-neon.inc.c to that file
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
-rw-r--r-- | MAINTAINERS | 1 | ||||
-rw-r--r-- | hw/acpi/generic_event_device.c | 29 | ||||
-rw-r--r-- | hw/arm/Kconfig | 8 | ||||
-rw-r--r-- | hw/arm/mps2-tz.c | 23 | ||||
-rw-r--r-- | hw/arm/mps2.c | 67 | ||||
-rw-r--r-- | hw/arm/realview.c | 3 | ||||
-rw-r--r-- | hw/arm/versatilepb.c | 3 | ||||
-rw-r--r-- | hw/arm/vexpress.c | 3 | ||||
-rw-r--r-- | hw/arm/virt.c | 63 | ||||
-rw-r--r-- | hw/i2c/versatile_i2c.c | 38 | ||||
-rw-r--r-- | hw/watchdog/cmsdk-apb-watchdog.c | 1 | ||||
-rw-r--r-- | hw/watchdog/trace-events | 1 | ||||
-rw-r--r-- | include/hw/i2c/arm_sbcon_i2c.h | 35 | ||||
-rw-r--r-- | target/arm/cpu.c | 2 | ||||
-rw-r--r-- | target/arm/cpu.h | 2 | ||||
-rw-r--r-- | target/arm/cpu64.c | 10 | ||||
-rw-r--r-- | target/arm/kvm.c | 4 | ||||
-rw-r--r-- | target/arm/kvm64.c | 14 | ||||
-rw-r--r-- | target/arm/kvm_arm.h | 21 | ||||
-rw-r--r-- | target/arm/neon-dp.decode | 106 | ||||
-rw-r--r-- | target/arm/translate-a64.c | 20 | ||||
-rw-r--r-- | target/arm/translate-neon.inc.c | 1191 | ||||
-rw-r--r-- | target/arm/translate-vfp.inc.c | 7 | ||||
-rw-r--r-- | target/arm/translate.c | 1064 | ||||
-rw-r--r-- | target/arm/translate.h | 8 | ||||
-rw-r--r-- | tests/qtest/arm-cpu-features.c | 38 | ||||
-rw-r--r-- | util/oslib-posix.c | 15 |
27 files changed, 1625 insertions, 1152 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 51a45703b8..01e6b3fefe 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -842,6 +842,7 @@ M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Maintained F: hw/*/versatile* +F: include/hw/i2c/arm_sbcon_i2c.h F: hw/misc/arm_sysctl.c F: docs/system/arm/versatile.rst diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c index 1cb34111e5..b8abdefa1c 100644 --- a/hw/acpi/generic_event_device.c +++ b/hw/acpi/generic_event_device.c @@ -193,6 +193,33 @@ static void acpi_ged_device_plug_cb(HotplugHandler *hotplug_dev, } } +static void acpi_ged_unplug_request_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + AcpiGedState *s = ACPI_GED(hotplug_dev); + + if ((object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) && + !(object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM)))) { + acpi_memory_unplug_request_cb(hotplug_dev, &s->memhp_state, dev, errp); + } else { + error_setg(errp, "acpi: device unplug request for unsupported device" + " type: %s", object_get_typename(OBJECT(dev))); + } +} + +static void acpi_ged_unplug_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + AcpiGedState *s = ACPI_GED(hotplug_dev); + + if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { + acpi_memory_unplug_cb(&s->memhp_state, dev, errp); + } else { + error_setg(errp, "acpi: device unplug for unsupported device" + " type: %s", object_get_typename(OBJECT(dev))); + } +} + static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev) { AcpiGedState *s = ACPI_GED(adev); @@ -318,6 +345,8 @@ static void acpi_ged_class_init(ObjectClass *class, void *data) dc->vmsd = &vmstate_acpi_ged; hc->plug = acpi_ged_device_plug_cb; + hc->unplug_request = acpi_ged_unplug_request_cb; + hc->unplug = acpi_ged_unplug_cb; adevc->send_event = acpi_ged_send_event; } diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index 9afa6eee79..4a224a6351 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -59,7 +59,7 @@ config HIGHBANK select ARM_TIMER # sp804 select ARM_V7M select PL011 # UART - select PL022 # Serial port + select PL022 # SPI select PL031 # RTC select PL061 # GPIO select PL310 # cache controller @@ -222,7 +222,7 @@ config STELLARIS select CMSDK_APB_WATCHDOG select I2C select PL011 # UART - select PL022 # Serial port + select PL022 # SPI select PL061 # GPIO select SSD0303 # OLED display select SSD0323 # OLED display @@ -401,10 +401,12 @@ config MPS2 select MPS2_FPGAIO select MPS2_SCC select OR_IRQ - select PL022 # Serial port + select PL022 # SPI select PL080 # DMA controller select SPLIT_IRQ select UNIMP + select CMSDK_APB_WATCHDOG + select VERSATILE_I2C config FSL_IMX7 bool diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index 8155c35418..a4fd5ddede 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -58,6 +58,7 @@ #include "hw/arm/armsse.h" #include "hw/dma/pl080.h" #include "hw/ssi/pl022.h" +#include "hw/i2c/arm_sbcon_i2c.h" #include "hw/net/lan9118.h" #include "net/net.h" #include "hw/core/split-irq.h" @@ -87,7 +88,7 @@ typedef struct { TZPPC ppc[5]; TZMPC ssram_mpc[3]; PL022State spi[5]; - UnimplementedDeviceState i2c[4]; + ArmSbconI2CState i2c[4]; UnimplementedDeviceState i2s_audio; UnimplementedDeviceState gpio[4]; UnimplementedDeviceState gfx; @@ -365,6 +366,18 @@ static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(s, 0); } +static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, + const char *name, hwaddr size) +{ + ArmSbconI2CState *i2c = opaque; + SysBusDevice *s; + + object_initialize_child(OBJECT(mms), name, i2c, TYPE_ARM_SBCON_I2C); + s = SYS_BUS_DEVICE(i2c); + sysbus_realize(s, &error_fatal); + return sysbus_mmio_get_region(s, 0); +} + static void mps2tz_common_init(MachineState *machine) { MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); @@ -499,10 +512,10 @@ static void mps2tz_common_init(MachineState *machine) { "uart2", make_uart, &mms->uart[2], 0x40202000, 0x1000 }, { "uart3", make_uart, &mms->uart[3], 0x40203000, 0x1000 }, { "uart4", make_uart, &mms->uart[4], 0x40204000, 0x1000 }, - { "i2c0", make_unimp_dev, &mms->i2c[0], 0x40207000, 0x1000 }, - { "i2c1", make_unimp_dev, &mms->i2c[1], 0x40208000, 0x1000 }, - { "i2c2", make_unimp_dev, &mms->i2c[2], 0x4020c000, 0x1000 }, - { "i2c3", make_unimp_dev, &mms->i2c[3], 0x4020d000, 0x1000 }, + { "i2c0", make_i2c, &mms->i2c[0], 0x40207000, 0x1000 }, + { "i2c1", make_i2c, &mms->i2c[1], 0x40208000, 0x1000 }, + { "i2c2", make_i2c, &mms->i2c[2], 0x4020c000, 0x1000 }, + { "i2c3", make_i2c, &mms->i2c[3], 0x4020d000, 0x1000 }, }, }, { .name = "apb_ppcexp2", diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index daa55f730b..d1653a7e6e 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -38,8 +38,12 @@ #include "hw/timer/cmsdk-apb-timer.h" #include "hw/timer/cmsdk-apb-dualtimer.h" #include "hw/misc/mps2-scc.h" +#include "hw/misc/mps2-fpgaio.h" +#include "hw/ssi/pl022.h" +#include "hw/i2c/arm_sbcon_i2c.h" #include "hw/net/lan9118.h" #include "net/net.h" +#include "hw/watchdog/cmsdk-apb-watchdog.h" typedef enum MPS2FPGAType { FPGA_AN385, @@ -65,8 +69,12 @@ typedef struct { MemoryRegion blockram_m2; MemoryRegion blockram_m3; MemoryRegion sram; + /* FPGA APB subsystem */ MPS2SCC scc; + MPS2FPGAIO fpgaio; + /* CMSDK APB subsystem */ CMSDKAPBDualTimer dualtimer; + CMSDKAPBWatchdog watchdog; } MPS2MachineState; #define TYPE_MPS2_MACHINE "mps2" @@ -111,6 +119,7 @@ static void mps2_common_init(MachineState *machine) MemoryRegion *system_memory = get_system_memory(); MachineClass *mc = MACHINE_GET_CLASS(machine); DeviceState *armv7m, *sccdev; + int i; if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { error_report("This board can only be used with CPU %s", @@ -210,10 +219,11 @@ static void mps2_common_init(MachineState *machine) */ create_unimplemented_device("CMSDK APB peripheral region @0x40000000", 0x40000000, 0x00010000); - create_unimplemented_device("CMSDK peripheral region @0x40010000", + create_unimplemented_device("CMSDK AHB peripheral region @0x40010000", 0x40010000, 0x00010000); create_unimplemented_device("Extra peripheral region @0x40020000", 0x40020000, 0x00010000); + create_unimplemented_device("RESERVED 4", 0x40030000, 0x001D0000); create_unimplemented_device("VGA", 0x41000000, 0x0200000); @@ -225,7 +235,6 @@ static void mps2_common_init(MachineState *machine) */ Object *orgate; DeviceState *orgate_dev; - int i; orgate = object_new(TYPE_OR_IRQ); object_property_set_int(orgate, 6, "num-lines", &error_fatal); @@ -262,7 +271,6 @@ static void mps2_common_init(MachineState *machine) */ Object *orgate; DeviceState *orgate_dev; - int i; orgate = object_new(TYPE_OR_IRQ); object_property_set_int(orgate, 10, "num-lines", &error_fatal); @@ -298,10 +306,15 @@ static void mps2_common_init(MachineState *machine) default: g_assert_not_reached(); } + for (i = 0; i < 4; i++) { + static const hwaddr gpiobase[] = {0x40010000, 0x40011000, + 0x40012000, 0x40013000}; + create_unimplemented_device("cmsdk-ahb-gpio", gpiobase[i], 0x1000); + } + /* CMSDK APB subsystem */ cmsdk_apb_timer_create(0x40000000, qdev_get_gpio_in(armv7m, 8), SYSCLK_FRQ); cmsdk_apb_timer_create(0x40001000, qdev_get_gpio_in(armv7m, 9), SYSCLK_FRQ); - object_initialize_child(OBJECT(mms), "dualtimer", &mms->dualtimer, TYPE_CMSDK_APB_DUALTIMER); qdev_prop_set_uint32(DEVICE(&mms->dualtimer), "pclk-frq", SYSCLK_FRQ); @@ -309,7 +322,15 @@ static void mps2_common_init(MachineState *machine) sysbus_connect_irq(SYS_BUS_DEVICE(&mms->dualtimer), 0, qdev_get_gpio_in(armv7m, 10)); sysbus_mmio_map(SYS_BUS_DEVICE(&mms->dualtimer), 0, 0x40002000); - + object_initialize_child(OBJECT(mms), "watchdog", &mms->watchdog, + TYPE_CMSDK_APB_WATCHDOG); + qdev_prop_set_uint32(DEVICE(&mms->watchdog), "wdogclk-frq", SYSCLK_FRQ); + sysbus_realize(SYS_BUS_DEVICE(&mms->watchdog), &error_fatal); + sysbus_connect_irq(SYS_BUS_DEVICE(&mms->watchdog), 0, + qdev_get_gpio_in_named(armv7m, "NMI", 0)); + sysbus_mmio_map(SYS_BUS_DEVICE(&mms->watchdog), 0, 0x40008000); + + /* FPGA APB subsystem */ object_initialize_child(OBJECT(mms), "scc", &mms->scc, TYPE_MPS2_SCC); sccdev = DEVICE(&mms->scc); qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); @@ -317,6 +338,42 @@ static void mps2_common_init(MachineState *machine) qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); sysbus_realize(SYS_BUS_DEVICE(&mms->scc), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(sccdev), 0, 0x4002f000); + object_initialize_child(OBJECT(mms), "fpgaio", + &mms->fpgaio, TYPE_MPS2_FPGAIO); + qdev_prop_set_uint32(DEVICE(&mms->fpgaio), "prescale-clk", 25000000); + sysbus_realize(SYS_BUS_DEVICE(&mms->fpgaio), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&mms->fpgaio), 0, 0x40028000); + sysbus_create_simple(TYPE_PL022, 0x40025000, /* External ADC */ + qdev_get_gpio_in(armv7m, 22)); + for (i = 0; i < 2; i++) { + static const int spi_irqno[] = {11, 24}; + static const hwaddr spibase[] = {0x40020000, /* APB */ + 0x40021000, /* LCD */ + 0x40026000, /* Shield0 */ + 0x40027000}; /* Shield1 */ + DeviceState *orgate_dev; + Object *orgate; + int j; + + orgate = object_new(TYPE_OR_IRQ); + object_property_set_int(orgate, 2, "num-lines", &error_fatal); + orgate_dev = DEVICE(orgate); + qdev_realize(orgate_dev, NULL, &error_fatal); + qdev_connect_gpio_out(orgate_dev, 0, + qdev_get_gpio_in(armv7m, spi_irqno[i])); + for (j = 0; j < 2; j++) { + sysbus_create_simple(TYPE_PL022, spibase[2 * i + j], + qdev_get_gpio_in(orgate_dev, j)); + } + } + for (i = 0; i < 4; i++) { + static const hwaddr i2cbase[] = {0x40022000, /* Touch */ + 0x40023000, /* Audio */ + 0x40029000, /* Shield0 */ + 0x4002a000}; /* Shield1 */ + sysbus_create_simple(TYPE_ARM_SBCON_I2C, i2cbase[i], NULL); + } + create_unimplemented_device("i2s", 0x40024000, 0x400); /* In hardware this is a LAN9220; the LAN9118 is software compatible * except that it doesn't support the checksum-offload feature. diff --git a/hw/arm/realview.c b/hw/arm/realview.c index f3c00fe00c..b6c0a1adb9 100644 --- a/hw/arm/realview.c +++ b/hw/arm/realview.c @@ -26,6 +26,7 @@ #include "hw/cpu/a9mpcore.h" #include "hw/intc/realview_gic.h" #include "hw/irq.h" +#include "hw/i2c/arm_sbcon_i2c.h" #define SMP_BOOT_ADDR 0xe0000000 #define SMP_BOOTREG_ADDR 0x10000030 @@ -282,7 +283,7 @@ static void realview_init(MachineState *machine, } } - dev = sysbus_create_simple("versatile_i2c", 0x10002000, NULL); + dev = sysbus_create_simple(TYPE_VERSATILE_I2C, 0x10002000, NULL); i2c = (I2CBus *)qdev_get_child_bus(dev, "i2c"); i2c_create_slave(i2c, "ds1338", 0x68); diff --git a/hw/arm/versatilepb.c b/hw/arm/versatilepb.c index 2ebdcbd8ac..e596b8170f 100644 --- a/hw/arm/versatilepb.c +++ b/hw/arm/versatilepb.c @@ -18,6 +18,7 @@ #include "sysemu/sysemu.h" #include "hw/pci/pci.h" #include "hw/i2c/i2c.h" +#include "hw/i2c/arm_sbcon_i2c.h" #include "hw/irq.h" #include "hw/boards.h" #include "exec/address-spaces.h" @@ -314,7 +315,7 @@ static void versatile_init(MachineState *machine, int board_id) /* Add PL031 Real Time Clock. */ sysbus_create_simple("pl031", 0x101e8000, pic[10]); - dev = sysbus_create_simple("versatile_i2c", 0x10002000, NULL); + dev = sysbus_create_simple(TYPE_VERSATILE_I2C, 0x10002000, NULL); i2c = (I2CBus *)qdev_get_child_bus(dev, "i2c"); i2c_create_slave(i2c, "ds1338", 0x68); diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c index 7ca5d523a4..24d656e653 100644 --- a/hw/arm/vexpress.c +++ b/hw/arm/vexpress.c @@ -42,6 +42,7 @@ #include "hw/char/pl011.h" #include "hw/cpu/a9mpcore.h" #include "hw/cpu/a15mpcore.h" +#include "hw/i2c/arm_sbcon_i2c.h" #define VEXPRESS_BOARD_ID 0x8e0 #define VEXPRESS_FLASH_SIZE (64 * 1024 * 1024) @@ -640,7 +641,7 @@ static void vexpress_common_init(MachineState *machine) sysbus_create_simple("sp804", map[VE_TIMER01], pic[2]); sysbus_create_simple("sp804", map[VE_TIMER23], pic[3]); - dev = sysbus_create_simple("versatile_i2c", map[VE_SERIALDVI], NULL); + dev = sysbus_create_simple(TYPE_VERSATILE_I2C, map[VE_SERIALDVI], NULL); i2c = (I2CBus *)qdev_get_child_bus(dev, "i2c"); i2c_create_slave(i2c, "sii9022", 0x39); diff --git a/hw/arm/virt.c b/hw/arm/virt.c index caceb1e4a0..402c362c14 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -2177,11 +2177,68 @@ static void virt_machine_device_plug_cb(HotplugHandler *hotplug_dev, } } +static void virt_dimm_unplug_request(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(hotplug_dev); + Error *local_err = NULL; + + if (!vms->acpi_dev) { + error_setg(&local_err, + "memory hotplug is not enabled: missing acpi-ged device"); + goto out; + } + + if (object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM)) { + error_setg(&local_err, + "nvdimm device hot unplug is not supported yet."); + goto out; + } + + hotplug_handler_unplug_request(HOTPLUG_HANDLER(vms->acpi_dev), dev, + &local_err); +out: + error_propagate(errp, local_err); +} + +static void virt_dimm_unplug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(hotplug_dev); + Error *local_err = NULL; + + hotplug_handler_unplug(HOTPLUG_HANDLER(vms->acpi_dev), dev, &local_err); + if (local_err) { + goto out; + } + + pc_dimm_unplug(PC_DIMM(dev), MACHINE(vms)); + qdev_unrealize(dev); + +out: + error_propagate(errp, local_err); +} + static void virt_machine_device_unplug_request_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { - error_setg(errp, "device unplug request for unsupported device" - " type: %s", object_get_typename(OBJECT(dev))); + if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { + virt_dimm_unplug_request(hotplug_dev, dev, errp); + } else { + error_setg(errp, "device unplug request for unsupported device" + " type: %s", object_get_typename(OBJECT(dev))); + } +} + +static void virt_machine_device_unplug_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { + virt_dimm_unplug(hotplug_dev, dev, errp); + } else { + error_setg(errp, "virt: device unplug for unsupported device" + " type: %s", object_get_typename(OBJECT(dev))); + } } static HotplugHandler *virt_machine_get_hotplug_handler(MachineState *machine, @@ -2262,6 +2319,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) hc->pre_plug = virt_machine_device_pre_plug_cb; hc->plug = virt_machine_device_plug_cb; hc->unplug_request = virt_machine_device_unplug_request_cb; + hc->unplug = virt_machine_device_unplug_cb; mc->numa_mem_supported = true; mc->nvdimm_supported = true; mc->auto_enable_numa_with_memhp = true; @@ -2375,6 +2433,7 @@ DEFINE_VIRT_MACHINE_AS_LATEST(5, 1) static void virt_machine_5_0_options(MachineClass *mc) { virt_machine_5_1_options(mc); + compat_props_add(mc->compat_props, hw_compat_5_0, hw_compat_5_0_len); } DEFINE_VIRT_MACHINE(5, 0) diff --git a/hw/i2c/versatile_i2c.c b/hw/i2c/versatile_i2c.c index 1ac2a6f59a..da8cda2ec1 100644 --- a/hw/i2c/versatile_i2c.c +++ b/hw/i2c/versatile_i2c.c @@ -1,5 +1,6 @@ /* - * ARM Versatile I2C controller + * ARM SBCon two-wire serial bus interface (I2C bitbang) + * a.k.a. ARM Versatile I2C controller * * Copyright (c) 2006-2007 CodeSourcery. * Copyright (c) 2012 Oskar Andero <oskar.andero@gmail.com> @@ -22,32 +23,33 @@ */ #include "qemu/osdep.h" -#include "hw/sysbus.h" -#include "hw/i2c/bitbang_i2c.h" +#include "hw/i2c/arm_sbcon_i2c.h" +#include "hw/registerfields.h" #include "qemu/log.h" #include "qemu/module.h" -#define TYPE_VERSATILE_I2C "versatile_i2c" #define VERSATILE_I2C(obj) \ OBJECT_CHECK(VersatileI2CState, (obj), TYPE_VERSATILE_I2C) -typedef struct VersatileI2CState { - SysBusDevice parent_obj; +typedef ArmSbconI2CState VersatileI2CState; - MemoryRegion iomem; - bitbang_i2c_interface bitbang; - int out; - int in; -} VersatileI2CState; + +REG32(CONTROL_GET, 0) +REG32(CONTROL_SET, 0) +REG32(CONTROL_CLR, 4) + +#define SCL BIT(0) +#define SDA BIT(1) static uint64_t versatile_i2c_read(void *opaque, hwaddr offset, unsigned size) { VersatileI2CState *s = (VersatileI2CState *)opaque; - if (offset == 0) { + switch (offset) { + case A_CONTROL_SET: return (s->out & 1) | (s->in << 1); - } else { + default: qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%x\n", __func__, (int)offset); return -1; @@ -60,18 +62,18 @@ static void versatile_i2c_write(void *opaque, hwaddr offset, VersatileI2CState *s = (VersatileI2CState *)opaque; switch (offset) { - case 0: + case A_CONTROL_SET: s->out |= value & 3; break; - case 4: + case A_CONTROL_CLR: s->out &= ~value; break; default: qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%x\n", __func__, (int)offset); } - bitbang_i2c_set(&s->bitbang, BITBANG_I2C_SCL, (s->out & 1) != 0); - s->in = bitbang_i2c_set(&s->bitbang, BITBANG_I2C_SDA, (s->out & 2) != 0); + bitbang_i2c_set(&s->bitbang, BITBANG_I2C_SCL, (s->out & SCL) != 0); + s->in = bitbang_i2c_set(&s->bitbang, BITBANG_I2C_SDA, (s->out & SDA) != 0); } static const MemoryRegionOps versatile_i2c_ops = { @@ -90,7 +92,7 @@ static void versatile_i2c_init(Object *obj) bus = i2c_init_bus(dev, "i2c"); bitbang_i2c_init(&s->bitbang, bus); memory_region_init_io(&s->iomem, obj, &versatile_i2c_ops, s, - "versatile_i2c", 0x1000); + "arm_sbcon_i2c", 0x1000); sysbus_init_mmio(sbd, &s->iomem); } diff --git a/hw/watchdog/cmsdk-apb-watchdog.c b/hw/watchdog/cmsdk-apb-watchdog.c index 1541365914..5bbadadfa6 100644 --- a/hw/watchdog/cmsdk-apb-watchdog.c +++ b/hw/watchdog/cmsdk-apb-watchdog.c @@ -225,6 +225,7 @@ static void cmsdk_apb_watchdog_write(void *opaque, hwaddr offset, break; case A_WDOGLOCK: s->lock = (value != WDOG_UNLOCK_VALUE); + trace_cmsdk_apb_watchdog_lock(s->lock); break; case A_WDOGITCR: if (s->is_luminary) { diff --git a/hw/watchdog/trace-events b/hw/watchdog/trace-events index ab94d7df50..3124ca1f1b 100644 --- a/hw/watchdog/trace-events +++ b/hw/watchdog/trace-events @@ -4,3 +4,4 @@ cmsdk_apb_watchdog_read(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB watchdog read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" cmsdk_apb_watchdog_write(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB watchdog write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" cmsdk_apb_watchdog_reset(void) "CMSDK APB watchdog: reset" +cmsdk_apb_watchdog_lock(uint32_t lock) "CMSDK APB watchdog: lock %" PRIu32 diff --git a/include/hw/i2c/arm_sbcon_i2c.h b/include/hw/i2c/arm_sbcon_i2c.h new file mode 100644 index 0000000000..5d96507ab6 --- /dev/null +++ b/include/hw/i2c/arm_sbcon_i2c.h @@ -0,0 +1,35 @@ +/* + * ARM SBCon two-wire serial bus interface (I2C bitbang) + * a.k.a. + * ARM Versatile I2C controller + * + * Copyright (c) 2006-2007 CodeSourcery. + * Copyright (c) 2012 Oskar Andero <oskar.andero@gmail.com> + * Copyright (C) 2020 Philippe Mathieu-Daudé <f4bug@amsat.org> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef HW_I2C_ARM_SBCON_H +#define HW_I2C_ARM_SBCON_H + +#include "hw/sysbus.h" +#include "hw/i2c/bitbang_i2c.h" + +#define TYPE_VERSATILE_I2C "versatile_i2c" +#define TYPE_ARM_SBCON_I2C TYPE_VERSATILE_I2C + +#define ARM_SBCON_I2C(obj) \ + OBJECT_CHECK(ArmSbconI2CState, (obj), TYPE_ARM_SBCON_I2C) + +typedef struct ArmSbconI2CState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + MemoryRegion iomem; + bitbang_i2c_interface bitbang; + int out; + int in; +} ArmSbconI2CState; + +#endif /* HW_I2C_ARM_SBCON_H */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index 5b7a36b5d7..e44e18062c 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -1108,7 +1108,7 @@ static void arm_set_pmu(Object *obj, bool value, Error **errp) ARMCPU *cpu = ARM_CPU(obj); if (value) { - if (kvm_enabled() && !kvm_arm_pmu_supported(CPU(cpu))) { + if (kvm_enabled() && !kvm_arm_pmu_supported()) { error_setg(errp, "'pmu' feature not supported by KVM on this host"); return; } diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 677584e5da..cf66b8c7fb 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -2334,7 +2334,7 @@ static inline uint64_t cpreg_to_kvm_id(uint32_t cpregid) * migration or KVM state synchronization. (Typically this is for "registers" * which are actually used as instructions for cache maintenance and so on.) * IO indicates that this register does I/O and therefore its accesses - * need to be surrounded by gen_io_start()/gen_io_end(). In particular, + * need to be marked with gen_io_start() and also end the TB. In particular, * registers which implement clocks or timers require this. * RAISES_EXC is for when the read or write hook might raise an exception; * the generated code will synchronize the CPU state before calling the hook diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index 778cecc2e6..a0c1d8894b 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -266,7 +266,7 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) /* Collect the set of vector lengths supported by KVM. */ bitmap_zero(kvm_supported, ARM_MAX_VQ); - if (kvm_enabled() && kvm_arm_sve_supported(CPU(cpu))) { + if (kvm_enabled() && kvm_arm_sve_supported()) { kvm_arm_sve_get_vls(CPU(cpu), kvm_supported); } else if (kvm_enabled()) { assert(!cpu_isar_feature(aa64_sve, cpu)); @@ -473,7 +473,7 @@ static void cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name, return; } - if (kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) { + if (kvm_enabled() && !kvm_arm_sve_supported()) { error_setg(errp, "cannot set sve-max-vq"); error_append_hint(errp, "SVE not supported by KVM on this host\n"); return; @@ -519,7 +519,7 @@ static void cpu_arm_set_sve_vq(Object *obj, Visitor *v, const char *name, return; } - if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) { + if (value && kvm_enabled() && !kvm_arm_sve_supported()) { error_setg(errp, "cannot enable %s", name); error_append_hint(errp, "SVE not supported by KVM on this host\n"); return; @@ -556,7 +556,7 @@ static void cpu_arm_set_sve(Object *obj, Visitor *v, const char *name, return; } - if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) { + if (value && kvm_enabled() && !kvm_arm_sve_supported()) { error_setg(errp, "'sve' feature not supported by KVM on this host"); return; } @@ -751,7 +751,7 @@ static void aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp) * uniform execution state like do_interrupt. */ if (value == false) { - if (!kvm_enabled() || !kvm_arm_aarch32_supported(CPU(cpu))) { + if (!kvm_enabled() || !kvm_arm_aarch32_supported()) { error_setg(errp, "'aarch64' feature cannot be disabled " "unless KVM is enabled and 32-bit EL1 " "is supported"); diff --git a/target/arm/kvm.c b/target/arm/kvm.c index eef3bbd1cc..7c672c78b8 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -208,9 +208,9 @@ void kvm_arm_add_vcpu_properties(Object *obj) } } -bool kvm_arm_pmu_supported(CPUState *cpu) +bool kvm_arm_pmu_supported(void) { - return kvm_check_extension(cpu->kvm_state, KVM_CAP_ARM_PMU_V3); + return kvm_check_extension(kvm_state, KVM_CAP_ARM_PMU_V3); } int kvm_arm_get_max_vm_ipa_size(MachineState *ms) diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index f09ed9f4df..3dc494aaa7 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -652,18 +652,14 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) return true; } -bool kvm_arm_aarch32_supported(CPUState *cpu) +bool kvm_arm_aarch32_supported(void) { - KVMState *s = KVM_STATE(current_accel()); - - return kvm_check_extension(s, KVM_CAP_ARM_EL1_32BIT); + return kvm_check_extension(kvm_state, KVM_CAP_ARM_EL1_32BIT); } -bool kvm_arm_sve_supported(CPUState *cpu) +bool kvm_arm_sve_supported(void) { - KVMState *s = KVM_STATE(current_accel()); - - return kvm_check_extension(s, KVM_CAP_ARM_SVE); + return kvm_check_extension(kvm_state, KVM_CAP_ARM_SVE); } QEMU_BUILD_BUG_ON(KVM_ARM64_SVE_VQ_MIN != 1); @@ -798,7 +794,7 @@ int kvm_arch_init_vcpu(CPUState *cs) env->features &= ~(1ULL << ARM_FEATURE_PMU); } if (cpu_isar_feature(aa64_sve, cpu)) { - assert(kvm_arm_sve_supported(cs)); + assert(kvm_arm_sve_supported()); cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_SVE; } diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index 48bf5e16d5..a4ce4fd93d 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -269,29 +269,26 @@ void kvm_arm_add_vcpu_properties(Object *obj); /** * kvm_arm_aarch32_supported: - * @cs: CPUState * - * Returns: true if the KVM VCPU can enable AArch32 mode + * Returns: true if KVM can enable AArch32 mode * and false otherwise. */ -bool kvm_arm_aarch32_supported(CPUState *cs); +bool kvm_arm_aarch32_supported(void); /** * kvm_arm_pmu_supported: - * @cs: CPUState * - * Returns: true if the KVM VCPU can enable its PMU + * Returns: true if KVM can enable the PMU * and false otherwise. */ -bool kvm_arm_pmu_supported(CPUState *cs); +bool kvm_arm_pmu_supported(void); /** * kvm_arm_sve_supported: - * @cs: CPUState * - * Returns true if the KVM VCPU can enable SVE and false otherwise. + * Returns true if KVM can enable SVE and false otherwise. */ -bool kvm_arm_sve_supported(CPUState *cs); +bool kvm_arm_sve_supported(void); /** * kvm_arm_get_max_vm_ipa_size: @@ -359,17 +356,17 @@ static inline void kvm_arm_set_cpu_features_from_host(ARMCPU *cpu) static inline void kvm_arm_add_vcpu_properties(Object *obj) {} -static inline bool kvm_arm_aarch32_supported(CPUState *cs) +static inline bool kvm_arm_aarch32_supported(void) { return false; } -static inline bool kvm_arm_pmu_supported(CPUState *cs) +static inline bool kvm_arm_pmu_supported(void) { return false; } -static inline bool kvm_arm_sve_supported(CPUState *cs) +static inline bool kvm_arm_sve_supported(void) { return false; } diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index 6d890b2161..686f9fbf46 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -429,6 +429,112 @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm vm=%vm_dp vd=%vd_dp size=1 VDUP_scalar 1111 001 1 1 . 11 index:1 100 .... 11 000 q:1 . 0 .... \ vm=%vm_dp vd=%vd_dp size=2 + + ################################################################## + # 2-reg-misc grouping: + # 1111 001 11 D 11 size:2 opc1:2 Vd:4 0 opc2:4 q:1 M 0 Vm:4 + ################################################################## + + &2misc vd vm q size + + @2misc .... ... .. . .. size:2 .. .... . .... q:1 . . .... \ + &2misc vm=%vm_dp vd=%vd_dp + @2misc_q0 .... ... .. . .. size:2 .. .... . .... . . . .... \ + &2misc vm=%vm_dp vd=%vd_dp q=0 + @2misc_q1 .... ... .. . .. size:2 .. .... . .... . . . .... \ + &2misc vm=%vm_dp vd=%vd_dp q=1 + + VREV64 1111 001 11 . 11 .. 00 .... 0 0000 . . 0 .... @2misc + VREV32 1111 001 11 . 11 .. 00 .... 0 0001 . . 0 .... @2misc + VREV16 1111 001 11 . 11 .. 00 .... 0 0010 . . 0 .... @2misc + + VPADDL_S 1111 001 11 . 11 .. 00 .... 0 0100 . . 0 .... @2misc + VPADDL_U 1111 001 11 . 11 .. 00 .... 0 0101 . . 0 .... @2misc + + AESE 1111 001 11 . 11 .. 00 .... 0 0110 0 . 0 .... @2misc_q1 + AESD 1111 001 11 . 11 .. 00 .... 0 0110 1 . 0 .... @2misc_q1 + AESMC 1111 001 11 . 11 .. 00 .... 0 0111 0 . 0 .... @2misc_q1 + AESIMC 1111 001 11 . 11 .. 00 .... 0 0111 1 . 0 .... @2misc_q1 + + VCLS 1111 001 11 . 11 .. 00 .... 0 1000 . . 0 .... @2misc + VCLZ 1111 001 11 . 11 .. 00 .... 0 1001 . . 0 .... @2misc + VCNT 1111 001 11 . 11 .. 00 .... 0 1010 . . 0 .... @2misc + + VMVN 1111 001 11 . 11 .. 00 .... 0 1011 . . 0 .... @2misc + + VPADAL_S 1111 001 11 . 11 .. 00 .... 0 1100 . . 0 .... @2misc + VPADAL_U 1111 001 11 . 11 .. 00 .... 0 1101 . . 0 .... @2misc + + VQABS 1111 001 11 . 11 .. 00 .... 0 1110 . . 0 .... @2misc + VQNEG 1111 001 11 . 11 .. 00 .... 0 1111 . . 0 .... @2misc + + VCGT0 1111 001 11 . 11 .. 01 .... 0 0000 . . 0 .... @2misc + VCGE0 1111 001 11 . 11 .. 01 .... 0 0001 . . 0 .... @2misc + VCEQ0 1111 001 11 . 11 .. 01 .... 0 0010 . . 0 .... @2misc + VCLE0 1111 001 11 . 11 .. 01 .... 0 0011 . . 0 .... @2misc + VCLT0 1111 001 11 . 11 .. 01 .... 0 0100 . . 0 .... @2misc + + SHA1H 1111 001 11 . 11 .. 01 .... 0 0101 1 . 0 .... @2misc_q1 + + VABS 1111 001 11 . 11 .. 01 .... 0 0110 . . 0 .... @2misc + VNEG 1111 001 11 . 11 .. 01 .... 0 0111 . . 0 .... @2misc + + VCGT0_F 1111 001 11 . 11 .. 01 .... 0 1000 . . 0 .... @2misc + VCGE0_F 1111 001 11 . 11 .. 01 .... 0 1001 . . 0 .... @2misc + VCEQ0_F 1111 001 11 . 11 .. 01 .... 0 1010 . . 0 .... @2misc + VCLE0_F 1111 001 11 . 11 .. 01 .... 0 1011 . . 0 .... @2misc + VCLT0_F 1111 001 11 . 11 .. 01 .... 0 1100 . . 0 .... @2misc + + VABS_F 1111 001 11 . 11 .. 01 .... 0 1110 . . 0 .... @2misc + VNEG_F 1111 001 11 . 11 .. 01 .... 0 1111 . . 0 .... @2misc + + VSWP 1111 001 11 . 11 .. 10 .... 0 0000 . . 0 .... @2misc + VTRN 1111 001 11 . 11 .. 10 .... 0 0001 . . 0 .... @2misc + VUZP 1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc + VZIP 1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc + + VMOVN 1111 001 11 . 11 .. 10 .... 0 0100 0 . 0 .... @2misc_q0 + # VQMOVUN: unsigned result (source is always signed) + VQMOVUN 1111 001 11 . 11 .. 10 .... 0 0100 1 . 0 .... @2misc_q0 + # VQMOVN: signed result, source may be signed (_S) or unsigned (_U) + VQMOVN_S 1111 001 11 . 11 .. 10 .... 0 0101 0 . 0 .... @2misc_q0 + VQMOVN_U 1111 001 11 . 11 .. 10 .... 0 0101 1 . 0 .... @2misc_q0 + + VSHLL 1111 001 11 . 11 .. 10 .... 0 0110 0 . 0 .... @2misc_q0 + + SHA1SU1 1111 001 11 . 11 .. 10 .... 0 0111 0 . 0 .... @2misc_q1 + SHA256SU0 1111 001 11 . 11 .. 10 .... 0 0111 1 . 0 .... @2misc_q1 + + VRINTN 1111 001 11 . 11 .. 10 .... 0 1000 . . 0 .... @2misc + VRINTX 1111 001 11 . 11 .. 10 .... 0 1001 . . 0 .... @2misc + VRINTA 1111 001 11 . 11 .. 10 .... 0 1010 . . 0 .... @2misc + VRINTZ 1111 001 11 . 11 .. 10 .... 0 1011 . . 0 .... @2misc + + VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0 + + VRINTM 1111 001 11 . 11 .. 10 .... 0 1101 . . 0 .... @2misc + + VCVT_F32_F16 1111 001 11 . 11 .. 10 .... 0 1110 0 . 0 .... @2misc_q0 + + VRINTP 1111 001 11 . 11 .. 10 .... 0 1111 . . 0 .... @2misc + + VCVTAS 1111 001 11 . 11 .. 11 .... 0 0000 . . 0 .... @2misc + VCVTAU 1111 001 11 . 11 .. 11 .... 0 0001 . . 0 .... @2misc + VCVTNS 1111 001 11 . 11 .. 11 .... 0 0010 . . 0 .... @2misc + VCVTNU 1111 001 11 . 11 .. 11 .... 0 0011 . . 0 .... @2misc + VCVTPS 1111 001 11 . 11 .. 11 .... 0 0100 . . 0 .... @2misc + VCVTPU 1111 001 11 . 11 .. 11 .... 0 0101 . . 0 .... @2misc + VCVTMS 1111 001 11 . 11 .. 11 .... 0 0110 . . 0 .... @2misc + VCVTMU 1111 001 11 . 11 .. 11 .... 0 0111 . . 0 .... @2misc + + VRECPE 1111 001 11 . 11 .. 11 .... 0 1000 . . 0 .... @2misc + VRSQRTE 1111 001 11 . 11 .. 11 .... 0 1001 . . 0 .... @2misc + VRECPE_F 1111 001 11 . 11 .. 11 .... 0 1010 . . 0 .... @2misc + VRSQRTE_F 1111 001 11 . 11 .. 11 .... 0 1011 . . 0 .... @2misc + VCVT_FS 1111 001 11 . 11 .. 11 .... 0 1100 . . 0 .... @2misc + VCVT_FU 1111 001 11 . 11 .. 11 .... 0 1101 . . 0 .... @2misc + VCVT_SF 1111 001 11 . 11 .. 11 .... 0 1110 . . 0 .... @2misc + VCVT_UF 1111 001 11 . 11 .. 11 .... 0 1111 . . 0 .... @2misc ] # Subgroup for size != 0b11 diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index a0e72ad694..4cef862c41 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -9534,7 +9534,7 @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, TCGv_i64 tcg_op = tcg_temp_new_i64(); TCGv_i64 tcg_zero = tcg_const_i64(0); TCGv_i64 tcg_res = tcg_temp_new_i64(); - NeonGenTwoDoubleOPFn *genfn; + NeonGenTwoDoubleOpFn *genfn; bool swap = false; int pass; @@ -9576,7 +9576,7 @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, TCGv_i32 tcg_op = tcg_temp_new_i32(); TCGv_i32 tcg_zero = tcg_const_i32(0); TCGv_i32 tcg_res = tcg_temp_new_i32(); - NeonGenTwoSingleOPFn *genfn; + NeonGenTwoSingleOpFn *genfn; bool swap = false; int pass, maxpasses; @@ -11370,18 +11370,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn(tcg_res, tcg_op1, tcg_op2); } - if (opcode == 0xf) { - /* SABA, UABA: accumulating ops */ - static NeonGenTwoOpFn * const fns[3] = { - gen_helper_neon_add_u8, - gen_helper_neon_add_u16, - tcg_gen_add_i32, - }; - - read_vec_element_i32(s, tcg_op1, rd, pass, MO_32); - fns[size](tcg_res, tcg_op1, tcg_res); - } - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); tcg_temp_free_i32(tcg_res); @@ -11917,8 +11905,8 @@ static void handle_2misc_pairwise(DisasContext *s, int opcode, bool u, } else { for (pass = 0; pass < maxpass; pass++) { TCGv_i64 tcg_op = tcg_temp_new_i64(); - NeonGenOneOpFn *genfn; - static NeonGenOneOpFn * const fns[2][2] = { + NeonGenOne64OpFn *genfn; + static NeonGenOne64OpFn * const fns[2][2] = { { gen_helper_neon_addlp_s8, gen_helper_neon_addlp_u8 }, { gen_helper_neon_addlp_s16, gen_helper_neon_addlp_u16 }, }; diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index a5aa56bbde..f6cb921573 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -54,6 +54,107 @@ static inline int rsub_8(DisasContext *s, int x) #include "decode-neon-ls.inc.c" #include "decode-neon-shared.inc.c" +/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE, + * where 0 is the least significant end of the register. + */ +static inline long +neon_element_offset(int reg, int element, MemOp size) +{ + int element_size = 1 << size; + int ofs = element * element_size; +#ifdef HOST_WORDS_BIGENDIAN + /* Calculate the offset assuming fully little-endian, + * then XOR to account for the order of the 8-byte units. + */ + if (element_size < 8) { + ofs ^= 8 - element_size; + } +#endif + return neon_reg_offset(reg, 0) + ofs; +} + +static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) +{ + long offset = neon_element_offset(reg, ele, mop & MO_SIZE); + + switch (mop) { + case MO_UB: + tcg_gen_ld8u_i32(var, cpu_env, offset); + break; + case MO_UW: + tcg_gen_ld16u_i32(var, cpu_env, offset); + break; + case MO_UL: + tcg_gen_ld_i32(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + +static void neon_load_element64(TCGv_i64 var, int reg, int ele, MemOp mop) +{ + long offset = neon_element_offset(reg, ele, mop & MO_SIZE); + + switch (mop) { + case MO_UB: + tcg_gen_ld8u_i64(var, cpu_env, offset); + break; + case MO_UW: + tcg_gen_ld16u_i64(var, cpu_env, offset); + break; + case MO_UL: + tcg_gen_ld32u_i64(var, cpu_env, offset); + break; + case MO_Q: + tcg_gen_ld_i64(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + +static void neon_store_element(int reg, int ele, MemOp size, TCGv_i32 var) +{ + long offset = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_8: + tcg_gen_st8_i32(var, cpu_env, offset); + break; + case MO_16: + tcg_gen_st16_i32(var, cpu_env, offset); + break; + case MO_32: + tcg_gen_st_i32(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + +static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var) +{ + long offset = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_8: + tcg_gen_st8_i64(var, cpu_env, offset); + break; + case MO_16: + tcg_gen_st16_i64(var, cpu_env, offset); + break; + case MO_32: + tcg_gen_st32_i64(var, cpu_env, offset); + break; + case MO_64: + tcg_gen_st_i64(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) { int opr_sz; @@ -1664,7 +1765,7 @@ static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a) } static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, - NeonGenTwoSingleOPFn *fn) + NeonGenTwoSingleOpFn *fn) { /* FP operations in 2-reg-and-shift group */ TCGv_i32 tmp, shiftv; @@ -2970,3 +3071,1091 @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) a->q ? 16 : 8, a->q ? 16 : 8); return true; } + +static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) +{ + int pass, half; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (a->size == 3) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + for (pass = 0; pass < (a->q ? 2 : 1); pass++) { + TCGv_i32 tmp[2]; + + for (half = 0; half < 2; half++) { + tmp[half] = neon_load_reg(a->vm, pass * 2 + half); + switch (a->size) { + case 0: + tcg_gen_bswap32_i32(tmp[half], tmp[half]); + break; + case 1: + gen_swap_half(tmp[half], tmp[half]); + break; + case 2: + break; + default: + g_assert_not_reached(); + } + } + neon_store_reg(a->vd, pass * 2, tmp[1]); + neon_store_reg(a->vd, pass * 2 + 1, tmp[0]); + } + return true; +} + +static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a, + NeonGenWidenFn *widenfn, + NeonGenTwo64OpFn *opfn, + NeonGenTwo64OpFn *accfn) +{ + /* + * Pairwise long operations: widen both halves of the pair, + * combine the pairs with the opfn, and then possibly accumulate + * into the destination with the accfn. + */ + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!widenfn) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + for (pass = 0; pass < a->q + 1; pass++) { + TCGv_i32 tmp; + TCGv_i64 rm0_64, rm1_64, rd_64; + + rm0_64 = tcg_temp_new_i64(); + rm1_64 = tcg_temp_new_i64(); + rd_64 = tcg_temp_new_i64(); + tmp = neon_load_reg(a->vm, pass * 2); + widenfn(rm0_64, tmp); + tcg_temp_free_i32(tmp); + tmp = neon_load_reg(a->vm, pass * 2 + 1); + widenfn(rm1_64, tmp); + tcg_temp_free_i32(tmp); + opfn(rd_64, rm0_64, rm1_64); + tcg_temp_free_i64(rm0_64); + tcg_temp_free_i64(rm1_64); + + if (accfn) { + TCGv_i64 tmp64 = tcg_temp_new_i64(); + neon_load_reg64(tmp64, a->vd + pass); + accfn(rd_64, tmp64, rd_64); + tcg_temp_free_i64(tmp64); + } + neon_store_reg64(rd_64, a->vd + pass); + tcg_temp_free_i64(rd_64); + } + return true; +} + +static bool trans_VPADDL_S(DisasContext *s, arg_2misc *a) +{ + static NeonGenWidenFn * const widenfn[] = { + gen_helper_neon_widen_s8, + gen_helper_neon_widen_s16, + tcg_gen_ext_i32_i64, + NULL, + }; + static NeonGenTwo64OpFn * const opfn[] = { + gen_helper_neon_paddl_u16, + gen_helper_neon_paddl_u32, + tcg_gen_add_i64, + NULL, + }; + + return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], NULL); +} + +static bool trans_VPADDL_U(DisasContext *s, arg_2misc *a) +{ + static NeonGenWidenFn * const widenfn[] = { + gen_helper_neon_widen_u8, + gen_helper_neon_widen_u16, + tcg_gen_extu_i32_i64, + NULL, + }; + static NeonGenTwo64OpFn * const opfn[] = { + gen_helper_neon_paddl_u16, + gen_helper_neon_paddl_u32, + tcg_gen_add_i64, + NULL, + }; + + return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], NULL); +} + +static bool trans_VPADAL_S(DisasContext *s, arg_2misc *a) +{ + static NeonGenWidenFn * const widenfn[] = { + gen_helper_neon_widen_s8, + gen_helper_neon_widen_s16, + tcg_gen_ext_i32_i64, + NULL, + }; + static NeonGenTwo64OpFn * const opfn[] = { + gen_helper_neon_paddl_u16, + gen_helper_neon_paddl_u32, + tcg_gen_add_i64, + NULL, + }; + static NeonGenTwo64OpFn * const accfn[] = { + gen_helper_neon_addl_u16, + gen_helper_neon_addl_u32, + tcg_gen_add_i64, + NULL, + }; + + return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], + accfn[a->size]); +} + +static bool trans_VPADAL_U(DisasContext *s, arg_2misc *a) +{ + static NeonGenWidenFn * const widenfn[] = { + gen_helper_neon_widen_u8, + gen_helper_neon_widen_u16, + tcg_gen_extu_i32_i64, + NULL, + }; + static NeonGenTwo64OpFn * const opfn[] = { + gen_helper_neon_paddl_u16, + gen_helper_neon_paddl_u32, + tcg_gen_add_i64, + NULL, + }; + static NeonGenTwo64OpFn * const accfn[] = { + gen_helper_neon_addl_u16, + gen_helper_neon_addl_u32, + tcg_gen_add_i64, + NULL, + }; + + return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], + accfn[a->size]); +} + +typedef void ZipFn(TCGv_ptr, TCGv_ptr); + +static bool do_zip_uzp(DisasContext *s, arg_2misc *a, + ZipFn *fn) +{ + TCGv_ptr pd, pm; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!fn) { + /* Bad size or size/q combination */ + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + pd = vfp_reg_ptr(true, a->vd); + pm = vfp_reg_ptr(true, a->vm); + fn(pd, pm); + tcg_temp_free_ptr(pd); + tcg_temp_free_ptr(pm); + return true; +} + +static bool trans_VUZP(DisasContext *s, arg_2misc *a) +{ + static ZipFn * const fn[2][4] = { + { + gen_helper_neon_unzip8, + gen_helper_neon_unzip16, + NULL, + NULL, + }, { + gen_helper_neon_qunzip8, + gen_helper_neon_qunzip16, + gen_helper_neon_qunzip32, + NULL, + } + }; + return do_zip_uzp(s, a, fn[a->q][a->size]); +} + +static bool trans_VZIP(DisasContext *s, arg_2misc *a) +{ + static ZipFn * const fn[2][4] = { + { + gen_helper_neon_zip8, + gen_helper_neon_zip16, + NULL, + NULL, + }, { + gen_helper_neon_qzip8, + gen_helper_neon_qzip16, + gen_helper_neon_qzip32, + NULL, + } + }; + return do_zip_uzp(s, a, fn[a->q][a->size]); +} + +static bool do_vmovn(DisasContext *s, arg_2misc *a, + NeonGenNarrowEnvFn *narrowfn) +{ + TCGv_i64 rm; + TCGv_i32 rd0, rd1; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->vm & 1) { + return false; + } + + if (!narrowfn) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + rm = tcg_temp_new_i64(); + rd0 = tcg_temp_new_i32(); + rd1 = tcg_temp_new_i32(); + + neon_load_reg64(rm, a->vm); + narrowfn(rd0, cpu_env, rm); + neon_load_reg64(rm, a->vm + 1); + narrowfn(rd1, cpu_env, rm); + neon_store_reg(a->vd, 0, rd0); + neon_store_reg(a->vd, 1, rd1); + tcg_temp_free_i64(rm); + return true; +} + +#define DO_VMOVN(INSN, FUNC) \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + static NeonGenNarrowEnvFn * const narrowfn[] = { \ + FUNC##8, \ + FUNC##16, \ + FUNC##32, \ + NULL, \ + }; \ + return do_vmovn(s, a, narrowfn[a->size]); \ + } + +DO_VMOVN(VMOVN, gen_neon_narrow_u) +DO_VMOVN(VQMOVUN, gen_helper_neon_unarrow_sat) +DO_VMOVN(VQMOVN_S, gen_helper_neon_narrow_sat_s) +DO_VMOVN(VQMOVN_U, gen_helper_neon_narrow_sat_u) + +static bool trans_VSHLL(DisasContext *s, arg_2misc *a) +{ + TCGv_i32 rm0, rm1; + TCGv_i64 rd; + static NeonGenWidenFn * const widenfns[] = { + gen_helper_neon_widen_u8, + gen_helper_neon_widen_u16, + tcg_gen_extu_i32_i64, + NULL, + }; + NeonGenWidenFn *widenfn = widenfns[a->size]; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->vd & 1) { + return false; + } + + if (!widenfn) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + rd = tcg_temp_new_i64(); + + rm0 = neon_load_reg(a->vm, 0); + rm1 = neon_load_reg(a->vm, 1); + + widenfn(rd, rm0); + tcg_gen_shli_i64(rd, rd, 8 << a->size); + neon_store_reg64(rd, a->vd); + widenfn(rd, rm1); + tcg_gen_shli_i64(rd, rd, 8 << a->size); + neon_store_reg64(rd, a->vd + 1); + + tcg_temp_free_i64(rd); + tcg_temp_free_i32(rm0); + tcg_temp_free_i32(rm1); + return true; +} + +static bool trans_VCVT_F16_F32(DisasContext *s, arg_2misc *a) +{ + TCGv_ptr fpst; + TCGv_i32 ahp, tmp, tmp2, tmp3; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON) || + !dc_isar_feature(aa32_fp16_spconv, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm & 1) || (a->size != 1)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = get_fpstatus_ptr(true); + ahp = get_ahp_flag(); + tmp = neon_load_reg(a->vm, 0); + gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); + tmp2 = neon_load_reg(a->vm, 1); + gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp); + tcg_gen_shli_i32(tmp2, tmp2, 16); + tcg_gen_or_i32(tmp2, tmp2, tmp); + tcg_temp_free_i32(tmp); + tmp = neon_load_reg(a->vm, 2); + gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); + tmp3 = neon_load_reg(a->vm, 3); + neon_store_reg(a->vd, 0, tmp2); + gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp); + tcg_gen_shli_i32(tmp3, tmp3, 16); + tcg_gen_or_i32(tmp3, tmp3, tmp); + neon_store_reg(a->vd, 1, tmp3); + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); + + return true; +} + +static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a) +{ + TCGv_ptr fpst; + TCGv_i32 ahp, tmp, tmp2, tmp3; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON) || + !dc_isar_feature(aa32_fp16_spconv, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vd & 1) || (a->size != 1)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = get_fpstatus_ptr(true); + ahp = get_ahp_flag(); + tmp3 = tcg_temp_new_i32(); + tmp = neon_load_reg(a->vm, 0); + tmp2 = neon_load_reg(a->vm, 1); + tcg_gen_ext16u_i32(tmp3, tmp); + gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); + neon_store_reg(a->vd, 0, tmp3); + tcg_gen_shri_i32(tmp, tmp, 16); + gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp); + neon_store_reg(a->vd, 1, tmp); + tmp3 = tcg_temp_new_i32(); + tcg_gen_ext16u_i32(tmp3, tmp2); + gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); + neon_store_reg(a->vd, 2, tmp3); + tcg_gen_shri_i32(tmp2, tmp2, 16); + gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp); + neon_store_reg(a->vd, 3, tmp2); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); + + return true; +} + +static bool do_2misc_vec(DisasContext *s, arg_2misc *a, GVecGen2Fn *fn) +{ + int vec_size = a->q ? 16 : 8; + int rd_ofs = neon_reg_offset(a->vd, 0); + int rm_ofs = neon_reg_offset(a->vm, 0); + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->size == 3) { + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fn(a->size, rd_ofs, rm_ofs, vec_size, vec_size); + + return true; +} + +#define DO_2MISC_VEC(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + return do_2misc_vec(s, a, FN); \ + } + +DO_2MISC_VEC(VNEG, tcg_gen_gvec_neg) +DO_2MISC_VEC(VABS, tcg_gen_gvec_abs) +DO_2MISC_VEC(VCEQ0, gen_gvec_ceq0) +DO_2MISC_VEC(VCGT0, gen_gvec_cgt0) +DO_2MISC_VEC(VCLE0, gen_gvec_cle0) +DO_2MISC_VEC(VCGE0, gen_gvec_cge0) +DO_2MISC_VEC(VCLT0, gen_gvec_clt0) + +static bool trans_VMVN(DisasContext *s, arg_2misc *a) +{ + if (a->size != 0) { + return false; + } + return do_2misc_vec(s, a, tcg_gen_gvec_not); +} + +#define WRAP_2M_3_OOL_FN(WRAPNAME, FUNC, DATA) \ + static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \ + uint32_t rm_ofs, uint32_t oprsz, \ + uint32_t maxsz) \ + { \ + tcg_gen_gvec_3_ool(rd_ofs, rd_ofs, rm_ofs, oprsz, maxsz, \ + DATA, FUNC); \ + } + +#define WRAP_2M_2_OOL_FN(WRAPNAME, FUNC, DATA) \ + static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \ + uint32_t rm_ofs, uint32_t oprsz, \ + uint32_t maxsz) \ + { \ + tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, oprsz, maxsz, DATA, FUNC); \ + } + +WRAP_2M_3_OOL_FN(gen_AESE, gen_helper_crypto_aese, 0) +WRAP_2M_3_OOL_FN(gen_AESD, gen_helper_crypto_aese, 1) +WRAP_2M_2_OOL_FN(gen_AESMC, gen_helper_crypto_aesmc, 0) +WRAP_2M_2_OOL_FN(gen_AESIMC, gen_helper_crypto_aesmc, 1) +WRAP_2M_2_OOL_FN(gen_SHA1H, gen_helper_crypto_sha1h, 0) +WRAP_2M_2_OOL_FN(gen_SHA1SU1, gen_helper_crypto_sha1su1, 0) +WRAP_2M_2_OOL_FN(gen_SHA256SU0, gen_helper_crypto_sha256su0, 0) + +#define DO_2M_CRYPTO(INSN, FEATURE, SIZE) \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + if (!dc_isar_feature(FEATURE, s) || a->size != SIZE) { \ + return false; \ + } \ + return do_2misc_vec(s, a, gen_##INSN); \ + } + +DO_2M_CRYPTO(AESE, aa32_aes, 0) +DO_2M_CRYPTO(AESD, aa32_aes, 0) +DO_2M_CRYPTO(AESMC, aa32_aes, 0) +DO_2M_CRYPTO(AESIMC, aa32_aes, 0) +DO_2M_CRYPTO(SHA1H, aa32_sha1, 2) +DO_2M_CRYPTO(SHA1SU1, aa32_sha1, 2) +DO_2M_CRYPTO(SHA256SU0, aa32_sha2, 2) + +static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn) +{ + int pass; + + /* Handle a 2-reg-misc operation by iterating 32 bits at a time */ + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (!fn) { + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + TCGv_i32 tmp = neon_load_reg(a->vm, pass); + fn(tmp, tmp); + neon_store_reg(a->vd, pass, tmp); + } + + return true; +} + +static bool trans_VREV32(DisasContext *s, arg_2misc *a) +{ + static NeonGenOneOpFn * const fn[] = { + tcg_gen_bswap32_i32, + gen_swap_half, + NULL, + NULL, + }; + return do_2misc(s, a, fn[a->size]); +} + +static bool trans_VREV16(DisasContext *s, arg_2misc *a) +{ + if (a->size != 0) { + return false; + } + return do_2misc(s, a, gen_rev16); +} + +static bool trans_VCLS(DisasContext *s, arg_2misc *a) +{ + static NeonGenOneOpFn * const fn[] = { + gen_helper_neon_cls_s8, + gen_helper_neon_cls_s16, + gen_helper_neon_cls_s32, + NULL, + }; + return do_2misc(s, a, fn[a->size]); +} + +static void do_VCLZ_32(TCGv_i32 rd, TCGv_i32 rm) +{ + tcg_gen_clzi_i32(rd, rm, 32); +} + +static bool trans_VCLZ(DisasContext *s, arg_2misc *a) +{ + static NeonGenOneOpFn * const fn[] = { + gen_helper_neon_clz_u8, + gen_helper_neon_clz_u16, + do_VCLZ_32, + NULL, + }; + return do_2misc(s, a, fn[a->size]); +} + +static bool trans_VCNT(DisasContext *s, arg_2misc *a) +{ + if (a->size != 0) { + return false; + } + return do_2misc(s, a, gen_helper_neon_cnt_u8); +} + +static bool trans_VABS_F(DisasContext *s, arg_2misc *a) +{ + if (a->size != 2) { + return false; + } + /* TODO: FP16 : size == 1 */ + return do_2misc(s, a, gen_helper_vfp_abss); +} + +static bool trans_VNEG_F(DisasContext *s, arg_2misc *a) +{ + if (a->size != 2) { + return false; + } + /* TODO: FP16 : size == 1 */ + return do_2misc(s, a, gen_helper_vfp_negs); +} + +static bool trans_VRECPE(DisasContext *s, arg_2misc *a) +{ + if (a->size != 2) { + return false; + } + return do_2misc(s, a, gen_helper_recpe_u32); +} + +static bool trans_VRSQRTE(DisasContext *s, arg_2misc *a) +{ + if (a->size != 2) { + return false; + } + return do_2misc(s, a, gen_helper_rsqrte_u32); +} + +#define WRAP_1OP_ENV_FN(WRAPNAME, FUNC) \ + static void WRAPNAME(TCGv_i32 d, TCGv_i32 m) \ + { \ + FUNC(d, cpu_env, m); \ + } + +WRAP_1OP_ENV_FN(gen_VQABS_s8, gen_helper_neon_qabs_s8) +WRAP_1OP_ENV_FN(gen_VQABS_s16, gen_helper_neon_qabs_s16) +WRAP_1OP_ENV_FN(gen_VQABS_s32, gen_helper_neon_qabs_s32) +WRAP_1OP_ENV_FN(gen_VQNEG_s8, gen_helper_neon_qneg_s8) +WRAP_1OP_ENV_FN(gen_VQNEG_s16, gen_helper_neon_qneg_s16) +WRAP_1OP_ENV_FN(gen_VQNEG_s32, gen_helper_neon_qneg_s32) + +static bool trans_VQABS(DisasContext *s, arg_2misc *a) +{ + static NeonGenOneOpFn * const fn[] = { + gen_VQABS_s8, + gen_VQABS_s16, + gen_VQABS_s32, + NULL, + }; + return do_2misc(s, a, fn[a->size]); +} + +static bool trans_VQNEG(DisasContext *s, arg_2misc *a) +{ + static NeonGenOneOpFn * const fn[] = { + gen_VQNEG_s8, + gen_VQNEG_s16, + gen_VQNEG_s32, + NULL, + }; + return do_2misc(s, a, fn[a->size]); +} + +static bool do_2misc_fp(DisasContext *s, arg_2misc *a, + NeonGenOneSingleOpFn *fn) +{ + int pass; + TCGv_ptr fpst; + + /* Handle a 2-reg-misc operation by iterating 32 bits at a time */ + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->size != 2) { + /* TODO: FP16 will be the size == 1 case */ + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = get_fpstatus_ptr(1); + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + TCGv_i32 tmp = neon_load_reg(a->vm, pass); + fn(tmp, tmp, fpst); + neon_store_reg(a->vd, pass, tmp); + } + tcg_temp_free_ptr(fpst); + + return true; +} + +#define DO_2MISC_FP(INSN, FUNC) \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + return do_2misc_fp(s, a, FUNC); \ + } + +DO_2MISC_FP(VRECPE_F, gen_helper_recpe_f32) +DO_2MISC_FP(VRSQRTE_F, gen_helper_rsqrte_f32) +DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos) +DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos) +DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs) +DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs) + +static bool trans_VRINTX(DisasContext *s, arg_2misc *a) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8)) { + return false; + } + return do_2misc_fp(s, a, gen_helper_rints_exact); +} + +#define WRAP_FP_CMP0_FWD(WRAPNAME, FUNC) \ + static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \ + { \ + TCGv_i32 zero = tcg_const_i32(0); \ + FUNC(d, m, zero, fpst); \ + tcg_temp_free_i32(zero); \ + } +#define WRAP_FP_CMP0_REV(WRAPNAME, FUNC) \ + static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \ + { \ + TCGv_i32 zero = tcg_const_i32(0); \ + FUNC(d, zero, m, fpst); \ + tcg_temp_free_i32(zero); \ + } + +#define DO_FP_CMP0(INSN, FUNC, REV) \ + WRAP_FP_CMP0_##REV(gen_##INSN, FUNC) \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + return do_2misc_fp(s, a, gen_##INSN); \ + } + +DO_FP_CMP0(VCGT0_F, gen_helper_neon_cgt_f32, FWD) +DO_FP_CMP0(VCGE0_F, gen_helper_neon_cge_f32, FWD) +DO_FP_CMP0(VCEQ0_F, gen_helper_neon_ceq_f32, FWD) +DO_FP_CMP0(VCLE0_F, gen_helper_neon_cge_f32, REV) +DO_FP_CMP0(VCLT0_F, gen_helper_neon_cgt_f32, REV) + +static bool do_vrint(DisasContext *s, arg_2misc *a, int rmode) +{ + /* + * Handle a VRINT* operation by iterating 32 bits at a time, + * with a specified rounding mode in operation. + */ + int pass; + TCGv_ptr fpst; + TCGv_i32 tcg_rmode; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON) || + !arm_dc_feature(s, ARM_FEATURE_V8)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->size != 2) { + /* TODO: FP16 will be the size == 1 case */ + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = get_fpstatus_ptr(1); + tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); + gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + TCGv_i32 tmp = neon_load_reg(a->vm, pass); + gen_helper_rints(tmp, tmp, fpst); + neon_store_reg(a->vd, pass, tmp); + } + gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); + tcg_temp_free_i32(tcg_rmode); + tcg_temp_free_ptr(fpst); + + return true; +} + +#define DO_VRINT(INSN, RMODE) \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + return do_vrint(s, a, RMODE); \ + } + +DO_VRINT(VRINTN, FPROUNDING_TIEEVEN) +DO_VRINT(VRINTA, FPROUNDING_TIEAWAY) +DO_VRINT(VRINTZ, FPROUNDING_ZERO) +DO_VRINT(VRINTM, FPROUNDING_NEGINF) +DO_VRINT(VRINTP, FPROUNDING_POSINF) + +static bool do_vcvt(DisasContext *s, arg_2misc *a, int rmode, bool is_signed) +{ + /* + * Handle a VCVT* operation by iterating 32 bits at a time, + * with a specified rounding mode in operation. + */ + int pass; + TCGv_ptr fpst; + TCGv_i32 tcg_rmode, tcg_shift; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON) || + !arm_dc_feature(s, ARM_FEATURE_V8)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->size != 2) { + /* TODO: FP16 will be the size == 1 case */ + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = get_fpstatus_ptr(1); + tcg_shift = tcg_const_i32(0); + tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); + gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + TCGv_i32 tmp = neon_load_reg(a->vm, pass); + if (is_signed) { + gen_helper_vfp_tosls(tmp, tmp, tcg_shift, fpst); + } else { + gen_helper_vfp_touls(tmp, tmp, tcg_shift, fpst); + } + neon_store_reg(a->vd, pass, tmp); + } + gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); + tcg_temp_free_i32(tcg_rmode); + tcg_temp_free_i32(tcg_shift); + tcg_temp_free_ptr(fpst); + + return true; +} + +#define DO_VCVT(INSN, RMODE, SIGNED) \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + return do_vcvt(s, a, RMODE, SIGNED); \ + } + +DO_VCVT(VCVTAU, FPROUNDING_TIEAWAY, false) +DO_VCVT(VCVTAS, FPROUNDING_TIEAWAY, true) +DO_VCVT(VCVTNU, FPROUNDING_TIEEVEN, false) +DO_VCVT(VCVTNS, FPROUNDING_TIEEVEN, true) +DO_VCVT(VCVTPU, FPROUNDING_POSINF, false) +DO_VCVT(VCVTPS, FPROUNDING_POSINF, true) +DO_VCVT(VCVTMU, FPROUNDING_NEGINF, false) +DO_VCVT(VCVTMS, FPROUNDING_NEGINF, true) + +static bool trans_VSWP(DisasContext *s, arg_2misc *a) +{ + TCGv_i64 rm, rd; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->size != 0) { + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + rm = tcg_temp_new_i64(); + rd = tcg_temp_new_i64(); + for (pass = 0; pass < (a->q ? 2 : 1); pass++) { + neon_load_reg64(rm, a->vm + pass); + neon_load_reg64(rd, a->vd + pass); + neon_store_reg64(rm, a->vd + pass); + neon_store_reg64(rd, a->vm + pass); + } + tcg_temp_free_i64(rm); + tcg_temp_free_i64(rd); + + return true; +} +static void gen_neon_trn_u8(TCGv_i32 t0, TCGv_i32 t1) +{ + TCGv_i32 rd, tmp; + + rd = tcg_temp_new_i32(); + tmp = tcg_temp_new_i32(); + + tcg_gen_shli_i32(rd, t0, 8); + tcg_gen_andi_i32(rd, rd, 0xff00ff00); + tcg_gen_andi_i32(tmp, t1, 0x00ff00ff); + tcg_gen_or_i32(rd, rd, tmp); + + tcg_gen_shri_i32(t1, t1, 8); + tcg_gen_andi_i32(t1, t1, 0x00ff00ff); + tcg_gen_andi_i32(tmp, t0, 0xff00ff00); + tcg_gen_or_i32(t1, t1, tmp); + tcg_gen_mov_i32(t0, rd); + + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(rd); +} + +static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1) +{ + TCGv_i32 rd, tmp; + + rd = tcg_temp_new_i32(); + tmp = tcg_temp_new_i32(); + + tcg_gen_shli_i32(rd, t0, 16); + tcg_gen_andi_i32(tmp, t1, 0xffff); + tcg_gen_or_i32(rd, rd, tmp); + tcg_gen_shri_i32(t1, t1, 16); + tcg_gen_andi_i32(tmp, t0, 0xffff0000); + tcg_gen_or_i32(t1, t1, tmp); + tcg_gen_mov_i32(t0, rd); + + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(rd); +} + +static bool trans_VTRN(DisasContext *s, arg_2misc *a) +{ + TCGv_i32 tmp, tmp2; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (a->size == 3) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + if (a->size == 2) { + for (pass = 0; pass < (a->q ? 4 : 2); pass += 2) { + tmp = neon_load_reg(a->vm, pass); + tmp2 = neon_load_reg(a->vd, pass + 1); + neon_store_reg(a->vm, pass, tmp2); + neon_store_reg(a->vd, pass + 1, tmp); + } + } else { + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + tmp = neon_load_reg(a->vm, pass); + tmp2 = neon_load_reg(a->vd, pass); + if (a->size == 0) { + gen_neon_trn_u8(tmp, tmp2); + } else { + gen_neon_trn_u16(tmp, tmp2); + } + neon_store_reg(a->vm, pass, tmp2); + neon_store_reg(a->vd, pass, tmp); + } + } + return true; +} diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index e1a9017598..bf31b18657 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -119,15 +119,14 @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled) if (s->v7m_lspact) { /* * Lazy state saving affects external memory and also the NVIC, - * so we must mark it as an IO operation for icount. + * so we must mark it as an IO operation for icount (and cause + * this to be the last insn in the TB). */ if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { + s->base.is_jmp = DISAS_UPDATE; gen_io_start(); } gen_helper_v7m_preserve_fp_state(cpu_env); - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_end(); - } /* * If the preserve_fp_state helper doesn't throw an exception * then it will clear LSPACT; we don't need to repeat this for diff --git a/target/arm/translate.c b/target/arm/translate.c index 6d18892ade..795964da1f 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -378,9 +378,9 @@ static void gen_revsh(TCGv_i32 dest, TCGv_i32 var) } /* Swap low and high halfwords. */ -static void gen_swap_half(TCGv_i32 var) +static void gen_swap_half(TCGv_i32 dest, TCGv_i32 var) { - tcg_gen_rotri_i32(var, var, 16); + tcg_gen_rotri_i32(dest, var, 16); } /* Dual 16-bit add. Result placed in t0 and t1 is marked as dead. @@ -1133,25 +1133,6 @@ neon_reg_offset (int reg, int n) return vfp_reg_offset(0, sreg); } -/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE, - * where 0 is the least significant end of the register. - */ -static inline long -neon_element_offset(int reg, int element, MemOp size) -{ - int element_size = 1 << size; - int ofs = element * element_size; -#ifdef HOST_WORDS_BIGENDIAN - /* Calculate the offset assuming fully little-endian, - * then XOR to account for the order of the 8-byte units. - */ - if (element_size < 8) { - ofs ^= 8 - element_size; - } -#endif - return neon_reg_offset(reg, 0) + ofs; -} - static TCGv_i32 neon_load_reg(int reg, int pass) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -1159,94 +1140,12 @@ static TCGv_i32 neon_load_reg(int reg, int pass) return tmp; } -static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) -{ - long offset = neon_element_offset(reg, ele, mop & MO_SIZE); - - switch (mop) { - case MO_UB: - tcg_gen_ld8u_i32(var, cpu_env, offset); - break; - case MO_UW: - tcg_gen_ld16u_i32(var, cpu_env, offset); - break; - case MO_UL: - tcg_gen_ld_i32(var, cpu_env, offset); - break; - default: - g_assert_not_reached(); - } -} - -static void neon_load_element64(TCGv_i64 var, int reg, int ele, MemOp mop) -{ - long offset = neon_element_offset(reg, ele, mop & MO_SIZE); - - switch (mop) { - case MO_UB: - tcg_gen_ld8u_i64(var, cpu_env, offset); - break; - case MO_UW: - tcg_gen_ld16u_i64(var, cpu_env, offset); - break; - case MO_UL: - tcg_gen_ld32u_i64(var, cpu_env, offset); - break; - case MO_Q: - tcg_gen_ld_i64(var, cpu_env, offset); - break; - default: - g_assert_not_reached(); - } -} - static void neon_store_reg(int reg, int pass, TCGv_i32 var) { tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass)); tcg_temp_free_i32(var); } -static void neon_store_element(int reg, int ele, MemOp size, TCGv_i32 var) -{ - long offset = neon_element_offset(reg, ele, size); - - switch (size) { - case MO_8: - tcg_gen_st8_i32(var, cpu_env, offset); - break; - case MO_16: - tcg_gen_st16_i32(var, cpu_env, offset); - break; - case MO_32: - tcg_gen_st_i32(var, cpu_env, offset); - break; - default: - g_assert_not_reached(); - } -} - -static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var) -{ - long offset = neon_element_offset(reg, ele, size); - - switch (size) { - case MO_8: - tcg_gen_st8_i64(var, cpu_env, offset); - break; - case MO_16: - tcg_gen_st16_i64(var, cpu_env, offset); - break; - case MO_32: - tcg_gen_st32_i64(var, cpu_env, offset); - break; - case MO_64: - tcg_gen_st_i64(var, cpu_env, offset); - break; - default: - g_assert_not_reached(); - } -} - static inline void neon_load_reg64(TCGv_i64 var, int reg) { tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg)); @@ -2934,377 +2833,6 @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc) gen_rfe(s, pc, load_cpu_field(spsr)); } -#define CPU_V001 cpu_V0, cpu_V0, cpu_V1 - -static int gen_neon_unzip(int rd, int rm, int size, int q) -{ - TCGv_ptr pd, pm; - - if (!q && size == 2) { - return 1; - } - pd = vfp_reg_ptr(true, rd); - pm = vfp_reg_ptr(true, rm); - if (q) { - switch (size) { - case 0: - gen_helper_neon_qunzip8(pd, pm); - break; - case 1: - gen_helper_neon_qunzip16(pd, pm); - break; - case 2: - gen_helper_neon_qunzip32(pd, pm); - break; - default: - abort(); - } - } else { - switch (size) { - case 0: - gen_helper_neon_unzip8(pd, pm); - break; - case 1: - gen_helper_neon_unzip16(pd, pm); - break; - default: - abort(); - } - } - tcg_temp_free_ptr(pd); - tcg_temp_free_ptr(pm); - return 0; -} - -static int gen_neon_zip(int rd, int rm, int size, int q) -{ - TCGv_ptr pd, pm; - - if (!q && size == 2) { - return 1; - } - pd = vfp_reg_ptr(true, rd); - pm = vfp_reg_ptr(true, rm); - if (q) { - switch (size) { - case 0: - gen_helper_neon_qzip8(pd, pm); - break; - case 1: - gen_helper_neon_qzip16(pd, pm); - break; - case 2: - gen_helper_neon_qzip32(pd, pm); - break; - default: - abort(); - } - } else { - switch (size) { - case 0: - gen_helper_neon_zip8(pd, pm); - break; - case 1: - gen_helper_neon_zip16(pd, pm); - break; - default: - abort(); - } - } - tcg_temp_free_ptr(pd); - tcg_temp_free_ptr(pm); - return 0; -} - -static void gen_neon_trn_u8(TCGv_i32 t0, TCGv_i32 t1) -{ - TCGv_i32 rd, tmp; - - rd = tcg_temp_new_i32(); - tmp = tcg_temp_new_i32(); - - tcg_gen_shli_i32(rd, t0, 8); - tcg_gen_andi_i32(rd, rd, 0xff00ff00); - tcg_gen_andi_i32(tmp, t1, 0x00ff00ff); - tcg_gen_or_i32(rd, rd, tmp); - - tcg_gen_shri_i32(t1, t1, 8); - tcg_gen_andi_i32(t1, t1, 0x00ff00ff); - tcg_gen_andi_i32(tmp, t0, 0xff00ff00); - tcg_gen_or_i32(t1, t1, tmp); - tcg_gen_mov_i32(t0, rd); - - tcg_temp_free_i32(tmp); - tcg_temp_free_i32(rd); -} - -static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1) -{ - TCGv_i32 rd, tmp; - - rd = tcg_temp_new_i32(); - tmp = tcg_temp_new_i32(); - - tcg_gen_shli_i32(rd, t0, 16); - tcg_gen_andi_i32(tmp, t1, 0xffff); - tcg_gen_or_i32(rd, rd, tmp); - tcg_gen_shri_i32(t1, t1, 16); - tcg_gen_andi_i32(tmp, t0, 0xffff0000); - tcg_gen_or_i32(t1, t1, tmp); - tcg_gen_mov_i32(t0, rd); - - tcg_temp_free_i32(tmp); - tcg_temp_free_i32(rd); -} - -static inline void gen_neon_narrow(int size, TCGv_i32 dest, TCGv_i64 src) -{ - switch (size) { - case 0: gen_helper_neon_narrow_u8(dest, src); break; - case 1: gen_helper_neon_narrow_u16(dest, src); break; - case 2: tcg_gen_extrl_i64_i32(dest, src); break; - default: abort(); - } -} - -static inline void gen_neon_narrow_sats(int size, TCGv_i32 dest, TCGv_i64 src) -{ - switch (size) { - case 0: gen_helper_neon_narrow_sat_s8(dest, cpu_env, src); break; - case 1: gen_helper_neon_narrow_sat_s16(dest, cpu_env, src); break; - case 2: gen_helper_neon_narrow_sat_s32(dest, cpu_env, src); break; - default: abort(); - } -} - -static inline void gen_neon_narrow_satu(int size, TCGv_i32 dest, TCGv_i64 src) -{ - switch (size) { - case 0: gen_helper_neon_narrow_sat_u8(dest, cpu_env, src); break; - case 1: gen_helper_neon_narrow_sat_u16(dest, cpu_env, src); break; - case 2: gen_helper_neon_narrow_sat_u32(dest, cpu_env, src); break; - default: abort(); - } -} - -static inline void gen_neon_unarrow_sats(int size, TCGv_i32 dest, TCGv_i64 src) -{ - switch (size) { - case 0: gen_helper_neon_unarrow_sat8(dest, cpu_env, src); break; - case 1: gen_helper_neon_unarrow_sat16(dest, cpu_env, src); break; - case 2: gen_helper_neon_unarrow_sat32(dest, cpu_env, src); break; - default: abort(); - } -} - -static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u) -{ - if (u) { - switch (size) { - case 0: gen_helper_neon_widen_u8(dest, src); break; - case 1: gen_helper_neon_widen_u16(dest, src); break; - case 2: tcg_gen_extu_i32_i64(dest, src); break; - default: abort(); - } - } else { - switch (size) { - case 0: gen_helper_neon_widen_s8(dest, src); break; - case 1: gen_helper_neon_widen_s16(dest, src); break; - case 2: tcg_gen_ext_i32_i64(dest, src); break; - default: abort(); - } - } - tcg_temp_free_i32(src); -} - -static inline void gen_neon_addl(int size) -{ - switch (size) { - case 0: gen_helper_neon_addl_u16(CPU_V001); break; - case 1: gen_helper_neon_addl_u32(CPU_V001); break; - case 2: tcg_gen_add_i64(CPU_V001); break; - default: abort(); - } -} - -static void gen_neon_narrow_op(int op, int u, int size, - TCGv_i32 dest, TCGv_i64 src) -{ - if (op) { - if (u) { - gen_neon_unarrow_sats(size, dest, src); - } else { - gen_neon_narrow(size, dest, src); - } - } else { - if (u) { - gen_neon_narrow_satu(size, dest, src); - } else { - gen_neon_narrow_sats(size, dest, src); - } - } -} - -/* Symbolic constants for op fields for Neon 2-register miscellaneous. - * The values correspond to bits [17:16,10:7]; see the ARM ARM DDI0406B - * table A7-13. - */ -#define NEON_2RM_VREV64 0 -#define NEON_2RM_VREV32 1 -#define NEON_2RM_VREV16 2 -#define NEON_2RM_VPADDL 4 -#define NEON_2RM_VPADDL_U 5 -#define NEON_2RM_AESE 6 /* Includes AESD */ -#define NEON_2RM_AESMC 7 /* Includes AESIMC */ -#define NEON_2RM_VCLS 8 -#define NEON_2RM_VCLZ 9 -#define NEON_2RM_VCNT 10 -#define NEON_2RM_VMVN 11 -#define NEON_2RM_VPADAL 12 -#define NEON_2RM_VPADAL_U 13 -#define NEON_2RM_VQABS 14 -#define NEON_2RM_VQNEG 15 -#define NEON_2RM_VCGT0 16 -#define NEON_2RM_VCGE0 17 -#define NEON_2RM_VCEQ0 18 -#define NEON_2RM_VCLE0 19 -#define NEON_2RM_VCLT0 20 -#define NEON_2RM_SHA1H 21 -#define NEON_2RM_VABS 22 -#define NEON_2RM_VNEG 23 -#define NEON_2RM_VCGT0_F 24 -#define NEON_2RM_VCGE0_F 25 -#define NEON_2RM_VCEQ0_F 26 -#define NEON_2RM_VCLE0_F 27 -#define NEON_2RM_VCLT0_F 28 -#define NEON_2RM_VABS_F 30 -#define NEON_2RM_VNEG_F 31 -#define NEON_2RM_VSWP 32 -#define NEON_2RM_VTRN 33 -#define NEON_2RM_VUZP 34 -#define NEON_2RM_VZIP 35 -#define NEON_2RM_VMOVN 36 /* Includes VQMOVN, VQMOVUN */ -#define NEON_2RM_VQMOVN 37 /* Includes VQMOVUN */ -#define NEON_2RM_VSHLL 38 -#define NEON_2RM_SHA1SU1 39 /* Includes SHA256SU0 */ -#define NEON_2RM_VRINTN 40 -#define NEON_2RM_VRINTX 41 -#define NEON_2RM_VRINTA 42 -#define NEON_2RM_VRINTZ 43 -#define NEON_2RM_VCVT_F16_F32 44 -#define NEON_2RM_VRINTM 45 -#define NEON_2RM_VCVT_F32_F16 46 -#define NEON_2RM_VRINTP 47 -#define NEON_2RM_VCVTAU 48 -#define NEON_2RM_VCVTAS 49 -#define NEON_2RM_VCVTNU 50 -#define NEON_2RM_VCVTNS 51 -#define NEON_2RM_VCVTPU 52 -#define NEON_2RM_VCVTPS 53 -#define NEON_2RM_VCVTMU 54 -#define NEON_2RM_VCVTMS 55 -#define NEON_2RM_VRECPE 56 -#define NEON_2RM_VRSQRTE 57 -#define NEON_2RM_VRECPE_F 58 -#define NEON_2RM_VRSQRTE_F 59 -#define NEON_2RM_VCVT_FS 60 -#define NEON_2RM_VCVT_FU 61 -#define NEON_2RM_VCVT_SF 62 -#define NEON_2RM_VCVT_UF 63 - -static bool neon_2rm_is_v8_op(int op) -{ - /* Return true if this neon 2reg-misc op is ARMv8 and up */ - switch (op) { - case NEON_2RM_VRINTN: - case NEON_2RM_VRINTA: - case NEON_2RM_VRINTM: - case NEON_2RM_VRINTP: - case NEON_2RM_VRINTZ: - case NEON_2RM_VRINTX: - case NEON_2RM_VCVTAU: - case NEON_2RM_VCVTAS: - case NEON_2RM_VCVTNU: - case NEON_2RM_VCVTNS: - case NEON_2RM_VCVTPU: - case NEON_2RM_VCVTPS: - case NEON_2RM_VCVTMU: - case NEON_2RM_VCVTMS: - return true; - default: - return false; - } -} - -/* Each entry in this array has bit n set if the insn allows - * size value n (otherwise it will UNDEF). Since unallocated - * op values will have no bits set they always UNDEF. - */ -static const uint8_t neon_2rm_sizes[] = { - [NEON_2RM_VREV64] = 0x7, - [NEON_2RM_VREV32] = 0x3, - [NEON_2RM_VREV16] = 0x1, - [NEON_2RM_VPADDL] = 0x7, - [NEON_2RM_VPADDL_U] = 0x7, - [NEON_2RM_AESE] = 0x1, - [NEON_2RM_AESMC] = 0x1, - [NEON_2RM_VCLS] = 0x7, - [NEON_2RM_VCLZ] = 0x7, - [NEON_2RM_VCNT] = 0x1, - [NEON_2RM_VMVN] = 0x1, - [NEON_2RM_VPADAL] = 0x7, - [NEON_2RM_VPADAL_U] = 0x7, - [NEON_2RM_VQABS] = 0x7, - [NEON_2RM_VQNEG] = 0x7, - [NEON_2RM_VCGT0] = 0x7, - [NEON_2RM_VCGE0] = 0x7, - [NEON_2RM_VCEQ0] = 0x7, - [NEON_2RM_VCLE0] = 0x7, - [NEON_2RM_VCLT0] = 0x7, - [NEON_2RM_SHA1H] = 0x4, - [NEON_2RM_VABS] = 0x7, - [NEON_2RM_VNEG] = 0x7, - [NEON_2RM_VCGT0_F] = 0x4, - [NEON_2RM_VCGE0_F] = 0x4, - [NEON_2RM_VCEQ0_F] = 0x4, - [NEON_2RM_VCLE0_F] = 0x4, - [NEON_2RM_VCLT0_F] = 0x4, - [NEON_2RM_VABS_F] = 0x4, - [NEON_2RM_VNEG_F] = 0x4, - [NEON_2RM_VSWP] = 0x1, - [NEON_2RM_VTRN] = 0x7, - [NEON_2RM_VUZP] = 0x7, - [NEON_2RM_VZIP] = 0x7, - [NEON_2RM_VMOVN] = 0x7, - [NEON_2RM_VQMOVN] = 0x7, - [NEON_2RM_VSHLL] = 0x7, - [NEON_2RM_SHA1SU1] = 0x4, - [NEON_2RM_VRINTN] = 0x4, - [NEON_2RM_VRINTX] = 0x4, - [NEON_2RM_VRINTA] = 0x4, - [NEON_2RM_VRINTZ] = 0x4, - [NEON_2RM_VCVT_F16_F32] = 0x2, - [NEON_2RM_VRINTM] = 0x4, - [NEON_2RM_VCVT_F32_F16] = 0x2, - [NEON_2RM_VRINTP] = 0x4, - [NEON_2RM_VCVTAU] = 0x4, - [NEON_2RM_VCVTAS] = 0x4, - [NEON_2RM_VCVTNU] = 0x4, - [NEON_2RM_VCVTNS] = 0x4, - [NEON_2RM_VCVTPU] = 0x4, - [NEON_2RM_VCVTPS] = 0x4, - [NEON_2RM_VCVTMU] = 0x4, - [NEON_2RM_VCVTMS] = 0x4, - [NEON_2RM_VRECPE] = 0x4, - [NEON_2RM_VRSQRTE] = 0x4, - [NEON_2RM_VRECPE_F] = 0x4, - [NEON_2RM_VRSQRTE_F] = 0x4, - [NEON_2RM_VCVT_FS] = 0x4, - [NEON_2RM_VCVT_FU] = 0x4, - [NEON_2RM_VCVT_SF] = 0x4, - [NEON_2RM_VCVT_UF] = 0x4, -}; - static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz, gen_helper_gvec_3_ptr *fn) @@ -5016,573 +4544,6 @@ void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } -/* Translate a NEON data processing instruction. Return nonzero if the - instruction is invalid. - We process data in a mixture of 32-bit and 64-bit chunks. - Mostly we use 32-bit chunks so we can use normal scalar instructions. */ - -static int disas_neon_data_insn(DisasContext *s, uint32_t insn) -{ - int op; - int q; - int rd, rm, rd_ofs, rm_ofs; - int size; - int pass; - int u; - int vec_size; - TCGv_i32 tmp, tmp2, tmp3; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { - return 1; - } - - /* FIXME: this access check should not take precedence over UNDEF - * for invalid encodings; we will generate incorrect syndrome information - * for attempts to execute invalid vfp/neon encodings with FP disabled. - */ - if (s->fp_excp_el) { - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, - syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); - return 0; - } - - if (!s->vfp_enabled) - return 1; - q = (insn & (1 << 6)) != 0; - u = (insn >> 24) & 1; - VFP_DREG_D(rd, insn); - VFP_DREG_M(rm, insn); - size = (insn >> 20) & 3; - vec_size = q ? 16 : 8; - rd_ofs = neon_reg_offset(rd, 0); - rm_ofs = neon_reg_offset(rm, 0); - - if ((insn & (1 << 23)) == 0) { - /* Three register same length: handled by decodetree */ - return 1; - } else if (insn & (1 << 4)) { - /* Two registers and shift or reg and imm: handled by decodetree */ - return 1; - } else { /* (insn & 0x00800010 == 0x00800000) */ - if (size != 3) { - /* - * Three registers of different lengths, or two registers and - * a scalar: handled by decodetree - */ - return 1; - } else { /* size == 3 */ - if (!u) { - /* Extract: handled by decodetree */ - return 1; - } else if ((insn & (1 << 11)) == 0) { - /* Two register misc. */ - op = ((insn >> 12) & 0x30) | ((insn >> 7) & 0xf); - size = (insn >> 18) & 3; - /* UNDEF for unknown op values and bad op-size combinations */ - if ((neon_2rm_sizes[op] & (1 << size)) == 0) { - return 1; - } - if (neon_2rm_is_v8_op(op) && - !arm_dc_feature(s, ARM_FEATURE_V8)) { - return 1; - } - if ((op != NEON_2RM_VMOVN && op != NEON_2RM_VQMOVN) && - q && ((rm | rd) & 1)) { - return 1; - } - switch (op) { - case NEON_2RM_VREV64: - for (pass = 0; pass < (q ? 2 : 1); pass++) { - tmp = neon_load_reg(rm, pass * 2); - tmp2 = neon_load_reg(rm, pass * 2 + 1); - switch (size) { - case 0: tcg_gen_bswap32_i32(tmp, tmp); break; - case 1: gen_swap_half(tmp); break; - case 2: /* no-op */ break; - default: abort(); - } - neon_store_reg(rd, pass * 2 + 1, tmp); - if (size == 2) { - neon_store_reg(rd, pass * 2, tmp2); - } else { - switch (size) { - case 0: tcg_gen_bswap32_i32(tmp2, tmp2); break; - case 1: gen_swap_half(tmp2); break; - default: abort(); - } - neon_store_reg(rd, pass * 2, tmp2); - } - } - break; - case NEON_2RM_VPADDL: case NEON_2RM_VPADDL_U: - case NEON_2RM_VPADAL: case NEON_2RM_VPADAL_U: - for (pass = 0; pass < q + 1; pass++) { - tmp = neon_load_reg(rm, pass * 2); - gen_neon_widen(cpu_V0, tmp, size, op & 1); - tmp = neon_load_reg(rm, pass * 2 + 1); - gen_neon_widen(cpu_V1, tmp, size, op & 1); - switch (size) { - case 0: gen_helper_neon_paddl_u16(CPU_V001); break; - case 1: gen_helper_neon_paddl_u32(CPU_V001); break; - case 2: tcg_gen_add_i64(CPU_V001); break; - default: abort(); - } - if (op >= NEON_2RM_VPADAL) { - /* Accumulate. */ - neon_load_reg64(cpu_V1, rd + pass); - gen_neon_addl(size); - } - neon_store_reg64(cpu_V0, rd + pass); - } - break; - case NEON_2RM_VTRN: - if (size == 2) { - int n; - for (n = 0; n < (q ? 4 : 2); n += 2) { - tmp = neon_load_reg(rm, n); - tmp2 = neon_load_reg(rd, n + 1); - neon_store_reg(rm, n, tmp2); - neon_store_reg(rd, n + 1, tmp); - } - } else { - goto elementwise; - } - break; - case NEON_2RM_VUZP: - if (gen_neon_unzip(rd, rm, size, q)) { - return 1; - } - break; - case NEON_2RM_VZIP: - if (gen_neon_zip(rd, rm, size, q)) { - return 1; - } - break; - case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN: - /* also VQMOVUN; op field and mnemonics don't line up */ - if (rm & 1) { - return 1; - } - tmp2 = NULL; - for (pass = 0; pass < 2; pass++) { - neon_load_reg64(cpu_V0, rm + pass); - tmp = tcg_temp_new_i32(); - gen_neon_narrow_op(op == NEON_2RM_VMOVN, q, size, - tmp, cpu_V0); - if (pass == 0) { - tmp2 = tmp; - } else { - neon_store_reg(rd, 0, tmp2); - neon_store_reg(rd, 1, tmp); - } - } - break; - case NEON_2RM_VSHLL: - if (q || (rd & 1)) { - return 1; - } - tmp = neon_load_reg(rm, 0); - tmp2 = neon_load_reg(rm, 1); - for (pass = 0; pass < 2; pass++) { - if (pass == 1) - tmp = tmp2; - gen_neon_widen(cpu_V0, tmp, size, 1); - tcg_gen_shli_i64(cpu_V0, cpu_V0, 8 << size); - neon_store_reg64(cpu_V0, rd + pass); - } - break; - case NEON_2RM_VCVT_F16_F32: - { - TCGv_ptr fpst; - TCGv_i32 ahp; - - if (!dc_isar_feature(aa32_fp16_spconv, s) || - q || (rm & 1)) { - return 1; - } - fpst = get_fpstatus_ptr(true); - ahp = get_ahp_flag(); - tmp = neon_load_reg(rm, 0); - gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); - tmp2 = neon_load_reg(rm, 1); - gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp); - tcg_gen_shli_i32(tmp2, tmp2, 16); - tcg_gen_or_i32(tmp2, tmp2, tmp); - tcg_temp_free_i32(tmp); - tmp = neon_load_reg(rm, 2); - gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); - tmp3 = neon_load_reg(rm, 3); - neon_store_reg(rd, 0, tmp2); - gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp); - tcg_gen_shli_i32(tmp3, tmp3, 16); - tcg_gen_or_i32(tmp3, tmp3, tmp); - neon_store_reg(rd, 1, tmp3); - tcg_temp_free_i32(tmp); - tcg_temp_free_i32(ahp); - tcg_temp_free_ptr(fpst); - break; - } - case NEON_2RM_VCVT_F32_F16: - { - TCGv_ptr fpst; - TCGv_i32 ahp; - if (!dc_isar_feature(aa32_fp16_spconv, s) || - q || (rd & 1)) { - return 1; - } - fpst = get_fpstatus_ptr(true); - ahp = get_ahp_flag(); - tmp3 = tcg_temp_new_i32(); - tmp = neon_load_reg(rm, 0); - tmp2 = neon_load_reg(rm, 1); - tcg_gen_ext16u_i32(tmp3, tmp); - gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); - neon_store_reg(rd, 0, tmp3); - tcg_gen_shri_i32(tmp, tmp, 16); - gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp); - neon_store_reg(rd, 1, tmp); - tmp3 = tcg_temp_new_i32(); - tcg_gen_ext16u_i32(tmp3, tmp2); - gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); - neon_store_reg(rd, 2, tmp3); - tcg_gen_shri_i32(tmp2, tmp2, 16); - gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp); - neon_store_reg(rd, 3, tmp2); - tcg_temp_free_i32(ahp); - tcg_temp_free_ptr(fpst); - break; - } - case NEON_2RM_AESE: case NEON_2RM_AESMC: - if (!dc_isar_feature(aa32_aes, s) || ((rm | rd) & 1)) { - return 1; - } - /* - * Bit 6 is the lowest opcode bit; it distinguishes - * between encryption (AESE/AESMC) and decryption - * (AESD/AESIMC). - */ - if (op == NEON_2RM_AESE) { - tcg_gen_gvec_3_ool(vfp_reg_offset(true, rd), - vfp_reg_offset(true, rd), - vfp_reg_offset(true, rm), - 16, 16, extract32(insn, 6, 1), - gen_helper_crypto_aese); - } else { - tcg_gen_gvec_2_ool(vfp_reg_offset(true, rd), - vfp_reg_offset(true, rm), - 16, 16, extract32(insn, 6, 1), - gen_helper_crypto_aesmc); - } - break; - case NEON_2RM_SHA1H: - if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 1)) { - return 1; - } - tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0, - gen_helper_crypto_sha1h); - break; - case NEON_2RM_SHA1SU1: - if ((rm | rd) & 1) { - return 1; - } - /* bit 6 (q): set -> SHA256SU0, cleared -> SHA1SU1 */ - if (q) { - if (!dc_isar_feature(aa32_sha2, s)) { - return 1; - } - } else if (!dc_isar_feature(aa32_sha1, s)) { - return 1; - } - tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0, - q ? gen_helper_crypto_sha256su0 - : gen_helper_crypto_sha1su1); - break; - case NEON_2RM_VMVN: - tcg_gen_gvec_not(0, rd_ofs, rm_ofs, vec_size, vec_size); - break; - case NEON_2RM_VNEG: - tcg_gen_gvec_neg(size, rd_ofs, rm_ofs, vec_size, vec_size); - break; - case NEON_2RM_VABS: - tcg_gen_gvec_abs(size, rd_ofs, rm_ofs, vec_size, vec_size); - break; - - case NEON_2RM_VCEQ0: - gen_gvec_ceq0(size, rd_ofs, rm_ofs, vec_size, vec_size); - break; - case NEON_2RM_VCGT0: - gen_gvec_cgt0(size, rd_ofs, rm_ofs, vec_size, vec_size); - break; - case NEON_2RM_VCLE0: - gen_gvec_cle0(size, rd_ofs, rm_ofs, vec_size, vec_size); - break; - case NEON_2RM_VCGE0: - gen_gvec_cge0(size, rd_ofs, rm_ofs, vec_size, vec_size); - break; - case NEON_2RM_VCLT0: - gen_gvec_clt0(size, rd_ofs, rm_ofs, vec_size, vec_size); - break; - - default: - elementwise: - for (pass = 0; pass < (q ? 4 : 2); pass++) { - tmp = neon_load_reg(rm, pass); - switch (op) { - case NEON_2RM_VREV32: - switch (size) { - case 0: tcg_gen_bswap32_i32(tmp, tmp); break; - case 1: gen_swap_half(tmp); break; - default: abort(); - } - break; - case NEON_2RM_VREV16: - gen_rev16(tmp, tmp); - break; - case NEON_2RM_VCLS: - switch (size) { - case 0: gen_helper_neon_cls_s8(tmp, tmp); break; - case 1: gen_helper_neon_cls_s16(tmp, tmp); break; - case 2: gen_helper_neon_cls_s32(tmp, tmp); break; - default: abort(); - } - break; - case NEON_2RM_VCLZ: - switch (size) { - case 0: gen_helper_neon_clz_u8(tmp, tmp); break; - case 1: gen_helper_neon_clz_u16(tmp, tmp); break; - case 2: tcg_gen_clzi_i32(tmp, tmp, 32); break; - default: abort(); - } - break; - case NEON_2RM_VCNT: - gen_helper_neon_cnt_u8(tmp, tmp); - break; - case NEON_2RM_VQABS: - switch (size) { - case 0: - gen_helper_neon_qabs_s8(tmp, cpu_env, tmp); - break; - case 1: - gen_helper_neon_qabs_s16(tmp, cpu_env, tmp); - break; - case 2: - gen_helper_neon_qabs_s32(tmp, cpu_env, tmp); - break; - default: abort(); - } - break; - case NEON_2RM_VQNEG: - switch (size) { - case 0: - gen_helper_neon_qneg_s8(tmp, cpu_env, tmp); - break; - case 1: - gen_helper_neon_qneg_s16(tmp, cpu_env, tmp); - break; - case 2: - gen_helper_neon_qneg_s32(tmp, cpu_env, tmp); - break; - default: abort(); - } - break; - case NEON_2RM_VCGT0_F: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - tmp2 = tcg_const_i32(0); - gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus); - tcg_temp_free_i32(tmp2); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCGE0_F: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - tmp2 = tcg_const_i32(0); - gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus); - tcg_temp_free_i32(tmp2); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCEQ0_F: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - tmp2 = tcg_const_i32(0); - gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus); - tcg_temp_free_i32(tmp2); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCLE0_F: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - tmp2 = tcg_const_i32(0); - gen_helper_neon_cge_f32(tmp, tmp2, tmp, fpstatus); - tcg_temp_free_i32(tmp2); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCLT0_F: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - tmp2 = tcg_const_i32(0); - gen_helper_neon_cgt_f32(tmp, tmp2, tmp, fpstatus); - tcg_temp_free_i32(tmp2); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VABS_F: - gen_helper_vfp_abss(tmp, tmp); - break; - case NEON_2RM_VNEG_F: - gen_helper_vfp_negs(tmp, tmp); - break; - case NEON_2RM_VSWP: - tmp2 = neon_load_reg(rd, pass); - neon_store_reg(rm, pass, tmp2); - break; - case NEON_2RM_VTRN: - tmp2 = neon_load_reg(rd, pass); - switch (size) { - case 0: gen_neon_trn_u8(tmp, tmp2); break; - case 1: gen_neon_trn_u16(tmp, tmp2); break; - default: abort(); - } - neon_store_reg(rm, pass, tmp2); - break; - case NEON_2RM_VRINTN: - case NEON_2RM_VRINTA: - case NEON_2RM_VRINTM: - case NEON_2RM_VRINTP: - case NEON_2RM_VRINTZ: - { - TCGv_i32 tcg_rmode; - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - int rmode; - - if (op == NEON_2RM_VRINTZ) { - rmode = FPROUNDING_ZERO; - } else { - rmode = fp_decode_rm[((op & 0x6) >> 1) ^ 1]; - } - - tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, - cpu_env); - gen_helper_rints(tmp, tmp, fpstatus); - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, - cpu_env); - tcg_temp_free_ptr(fpstatus); - tcg_temp_free_i32(tcg_rmode); - break; - } - case NEON_2RM_VRINTX: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_rints_exact(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCVTAU: - case NEON_2RM_VCVTAS: - case NEON_2RM_VCVTNU: - case NEON_2RM_VCVTNS: - case NEON_2RM_VCVTPU: - case NEON_2RM_VCVTPS: - case NEON_2RM_VCVTMU: - case NEON_2RM_VCVTMS: - { - bool is_signed = !extract32(insn, 7, 1); - TCGv_ptr fpst = get_fpstatus_ptr(1); - TCGv_i32 tcg_rmode, tcg_shift; - int rmode = fp_decode_rm[extract32(insn, 8, 2)]; - - tcg_shift = tcg_const_i32(0); - tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, - cpu_env); - - if (is_signed) { - gen_helper_vfp_tosls(tmp, tmp, - tcg_shift, fpst); - } else { - gen_helper_vfp_touls(tmp, tmp, - tcg_shift, fpst); - } - - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, - cpu_env); - tcg_temp_free_i32(tcg_rmode); - tcg_temp_free_i32(tcg_shift); - tcg_temp_free_ptr(fpst); - break; - } - case NEON_2RM_VRECPE: - gen_helper_recpe_u32(tmp, tmp); - break; - case NEON_2RM_VRSQRTE: - gen_helper_rsqrte_u32(tmp, tmp); - break; - case NEON_2RM_VRECPE_F: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_recpe_f32(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VRSQRTE_F: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_rsqrte_f32(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCVT_FS: /* VCVT.F32.S32 */ - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_sitos(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCVT_FU: /* VCVT.F32.U32 */ - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_uitos(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCVT_SF: /* VCVT.S32.F32 */ - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_tosizs(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCVT_UF: /* VCVT.U32.F32 */ - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_touizs(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - default: - /* Reserved op values were caught by the - * neon_2rm_sizes[] check earlier. - */ - abort(); - } - neon_store_reg(rd, pass, tmp); - } - break; - } - } else { - /* VTBL, VTBX, VDUP: handled by decodetree */ - return 1; - } - } - } - return 0; -} - static int disas_coproc_insn(DisasContext *s, uint32_t insn) { int cpnum, is64, crn, crm, opc1, opc2, isread, rt, rt2; @@ -8417,7 +7378,7 @@ static bool op_smlad(DisasContext *s, arg_rrrr *a, bool m_swap, bool sub) t1 = load_reg(s, a->rn); t2 = load_reg(s, a->rm); if (m_swap) { - gen_swap_half(t2); + gen_swap_half(t2, t2); } gen_smul_dual(t1, t2); @@ -8475,7 +7436,7 @@ static bool op_smlald(DisasContext *s, arg_rrrr *a, bool m_swap, bool sub) t1 = load_reg(s, a->rn); t2 = load_reg(s, a->rm); if (m_swap) { - gen_swap_half(t2); + gen_swap_half(t2, t2); } gen_smul_dual(t1, t2); @@ -8824,9 +7785,6 @@ static bool do_ldm(DisasContext *s, arg_ldst_block *a, int min_n) gen_io_start(); } gen_helper_cpsr_write_eret(cpu_env, tmp); - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - gen_io_end(); - } tcg_temp_free_i32(tmp); /* Must exit loop to check un-masked IRQs */ s->base.is_jmp = DISAS_EXIT; @@ -9283,13 +8241,6 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } /* fall back to legacy decoder */ - if (((insn >> 25) & 7) == 1) { - /* NEON Data processing. */ - if (disas_neon_data_insn(s, insn)) { - goto illegal_op; - } - return; - } if ((insn & 0x0e000f00) == 0x0c000100) { if (arm_dc_feature(s, ARM_FEATURE_IWMMXT)) { /* iWMMXt register transfer. */ @@ -9477,11 +8428,8 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) break; } if (((insn >> 24) & 3) == 3) { - /* Translate into the equivalent ARM encoding. */ - insn = (insn & 0xe2ffffff) | ((insn & (1 << 28)) >> 4) | (1 << 28); - if (disas_neon_data_insn(s, insn)) { - goto illegal_op; - } + /* Neon DP, but failed disas_neon_dp() */ + goto illegal_op; } else if (((insn >> 8) & 0xe) == 10) { /* VFP, but failed disas_vfp. */ goto illegal_op; diff --git a/target/arm/translate.h b/target/arm/translate.h index 62ed5c4780..19650a9e2d 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -363,6 +363,7 @@ typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t); /* Function prototype for gen_ functions for calling Neon helpers */ +typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32); typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32); typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32); typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); @@ -372,9 +373,10 @@ typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64); typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32); typedef void NeonGenTwoOpWidenFn(TCGv_i64, TCGv_i32, TCGv_i32); -typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); -typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); -typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64); +typedef void NeonGenOneSingleOpFn(TCGv_i32, TCGv_i32, TCGv_ptr); +typedef void NeonGenTwoSingleOpFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); +typedef void NeonGenTwoDoubleOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); +typedef void NeonGenOne64OpFn(TCGv_i64, TCGv_i64); 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); diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c index 4692173676..f7e062c189 100644 --- a/tests/qtest/arm-cpu-features.c +++ b/tests/qtest/arm-cpu-features.c @@ -159,16 +159,35 @@ static bool resp_get_feature(QDict *resp, const char *feature) qobject_unref(_resp); \ }) -#define assert_feature(qts, cpu_type, feature, expected_value) \ +#define resp_assert_feature(resp, feature, expected_value) \ ({ \ - QDict *_resp, *_props; \ + QDict *_props; \ \ - _resp = do_query_no_props(qts, cpu_type); \ g_assert(_resp); \ g_assert(resp_has_props(_resp)); \ _props = resp_get_props(_resp); \ g_assert(qdict_get(_props, feature)); \ g_assert(qdict_get_bool(_props, feature) == (expected_value)); \ +}) + +#define assert_feature(qts, cpu_type, feature, expected_value) \ +({ \ + QDict *_resp; \ + \ + _resp = do_query_no_props(qts, cpu_type); \ + g_assert(_resp); \ + resp_assert_feature(_resp, feature, expected_value); \ + qobject_unref(_resp); \ +}) + +#define assert_set_feature(qts, cpu_type, feature, value) \ +({ \ + const char *_fmt = (value) ? "{ %s: true }" : "{ %s: false }"; \ + QDict *_resp; \ + \ + _resp = do_query(qts, cpu_type, _fmt, feature); \ + g_assert(_resp); \ + resp_assert_feature(_resp, feature, value); \ qobject_unref(_resp); \ }) @@ -424,10 +443,14 @@ static void test_query_cpu_model_expansion(const void *data) assert_error(qts, "host", "The CPU type 'host' requires KVM", NULL); /* Test expected feature presence/absence for some cpu types */ - assert_has_feature_enabled(qts, "max", "pmu"); assert_has_feature_enabled(qts, "cortex-a15", "pmu"); assert_has_not_feature(qts, "cortex-a15", "aarch64"); + /* Enabling and disabling pmu should always work. */ + assert_has_feature_enabled(qts, "max", "pmu"); + assert_set_feature(qts, "max", "pmu", false); + assert_set_feature(qts, "max", "pmu", true); + assert_has_not_feature(qts, "max", "kvm-no-adjvtime"); if (g_str_equal(qtest_get_arch(), "aarch64")) { @@ -464,7 +487,10 @@ static void test_query_cpu_model_expansion_kvm(const void *data) return; } + /* Enabling and disabling kvm-no-adjvtime should always work. */ assert_has_feature_disabled(qts, "host", "kvm-no-adjvtime"); + assert_set_feature(qts, "host", "kvm-no-adjvtime", true); + assert_set_feature(qts, "host", "kvm-no-adjvtime", false); if (g_str_equal(qtest_get_arch(), "aarch64")) { bool kvm_supports_sve; @@ -475,7 +501,11 @@ static void test_query_cpu_model_expansion_kvm(const void *data) char *error; assert_has_feature_enabled(qts, "host", "aarch64"); + + /* Enabling and disabling pmu should always work. */ assert_has_feature_enabled(qts, "host", "pmu"); + assert_set_feature(qts, "host", "pmu", false); + assert_set_feature(qts, "host", "pmu", true); assert_error(qts, "cortex-a15", "We cannot guarantee the CPU type 'cortex-a15' works " diff --git a/util/oslib-posix.c b/util/oslib-posix.c index 916f1be224..39ddc77c85 100644 --- a/util/oslib-posix.c +++ b/util/oslib-posix.c @@ -57,6 +57,10 @@ #include <lwp.h> #endif +#ifdef __APPLE__ +#include <mach-o/dyld.h> +#endif + #include "qemu/mmap-alloc.h" #ifdef CONFIG_DEBUG_STACK_USAGE @@ -375,6 +379,17 @@ void qemu_init_exec_dir(const char *argv0) p = buf; } } +#elif defined(__APPLE__) + { + char fpath[PATH_MAX]; + uint32_t len = sizeof(fpath); + if (_NSGetExecutablePath(fpath, &len) == 0) { + p = realpath(fpath, buf); + if (!p) { + return; + } + } + } #endif /* If we don't have any way of figuring out the actual executable location then try argv[0]. */ |