diff options
111 files changed, 4305 insertions, 2390 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index dffcb651f4..c8221650b8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -617,6 +617,7 @@ F: hw/intc/gic_internal.h F: hw/misc/a9scu.c F: hw/misc/arm11scu.c F: hw/misc/arm_l2x0.c +F: hw/misc/armv7m_ras.c F: hw/timer/a9gtimer* F: hw/timer/arm* F: include/hw/arm/arm*.h @@ -626,6 +627,7 @@ F: include/hw/misc/arm11scu.h F: include/hw/timer/a9gtimer.h F: include/hw/timer/arm_mptimer.h F: include/hw/timer/armv7m_systick.h +F: include/hw/misc/armv7m_ras.h F: tests/qtest/test-arm-mptimer.c Exynos @@ -1660,6 +1662,16 @@ F: hw/net/opencores_eth.c Devices ------- +Overall Audio frontends +M: Gerd Hoffmann <kraxel@redhat.com> +S: Odd Fixes +F: hw/audio/ +F: include/hw/audio/ +F: tests/qtest/ac97-test.c +F: tests/qtest/es1370-test.c +F: tests/qtest/intel-hda-test.c +F: tests/qtest/fuzz-sb16-test.c + Xilinx CAN M: Vikram Garhwal <fnu.vikram@xilinx.com> M: Francisco Iglesias <francisco.iglesias@xilinx.com> @@ -2261,17 +2273,54 @@ F: include/net/can_*.h Subsystems ---------- -Audio +Overall Audio backends M: Gerd Hoffmann <kraxel@redhat.com> S: Odd Fixes F: audio/ -F: hw/audio/ -F: include/hw/audio/ +X: audio/alsaaudio.c +X: audio/coreaudio.c +X: audio/dsound* +X: audio/jackaudio.c +X: audio/ossaudio.c +X: audio/paaudio.c +X: audio/sdlaudio.c +X: audio/spiceaudio.c F: qapi/audio.json -F: tests/qtest/ac97-test.c -F: tests/qtest/es1370-test.c -F: tests/qtest/intel-hda-test.c -F: tests/qtest/fuzz-sb16-test.c + +ALSA Audio backend +M: Gerd Hoffmann <kraxel@redhat.com> +S: Odd Fixes +F: audio/alsaaudio.c + +Core Audio framework backend +M: Gerd Hoffmann <kraxel@redhat.com> +S: Odd Fixes +F: audio/coreaudio.c + +DSound Audio backend +M: Gerd Hoffmann <kraxel@redhat.com> +S: Odd Fixes +F: audio/dsound* + +JACK Audio Connection Kit backend +M: Gerd Hoffmann <kraxel@redhat.com> +S: Odd Fixes +F: audio/jackaudio.c + +Open Sound System (OSS) Audio backend +M: Gerd Hoffmann <kraxel@redhat.com> +S: Odd Fixes +F: audio/ossaudio.c + +PulseAudio backend +M: Gerd Hoffmann <kraxel@redhat.com> +S: Odd Fixes +F: audio/paaudio.c + +SDL Audio backend +M: Gerd Hoffmann <kraxel@redhat.com> +S: Odd Fixes +F: audio/sdlaudio.c Block layer core M: Kevin Wolf <kwolf@redhat.com> diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 8d4fd384a5..1e1a5e96ad 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -207,13 +207,6 @@ this CPU is also deprecated. System emulator machines ------------------------ -Raspberry Pi ``raspi2`` and ``raspi3`` machines (since 5.2) -''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' - -The Raspberry Pi machines come in various models (A, A+, B, B+). To be able -to distinguish which model QEMU is implementing, the ``raspi2`` and ``raspi3`` -machines have been renamed ``raspi2b`` and ``raspi3b``. - Aspeed ``swift-bmc`` machine (since 6.1) '''''''''''''''''''''''''''''''''''''''' diff --git a/docs/about/removed-features.rst b/docs/about/removed-features.rst index 08f9e625ce..9d0d90c90d 100644 --- a/docs/about/removed-features.rst +++ b/docs/about/removed-features.rst @@ -574,6 +574,13 @@ This machine has been renamed ``fuloong2e``. These machine types were very old and likely could not be used for live migration from old QEMU versions anymore. Use a newer machine type instead. +Raspberry Pi ``raspi2`` and ``raspi3`` machines (removed in 6.2) +'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The Raspberry Pi machines come in various models (A, A+, B, B+). To be able +to distinguish which model QEMU is implementing, the ``raspi2`` and ``raspi3`` +machines have been renamed ``raspi2b`` and ``raspi3b``. + linux-user mode CPUs -------------------- diff --git a/docs/devel/clocks.rst b/docs/devel/clocks.rst index 956bd147ea..675fbeb6ab 100644 --- a/docs/devel/clocks.rst +++ b/docs/devel/clocks.rst @@ -260,6 +260,29 @@ clocks get the new clock period value: *Clock 2*, *Clock 3* and *Clock 4*. It is not possible to disconnect a clock or to change the clock connection after it is connected. +Clock multiplier and divider settings +------------------------------------- + +By default, when clocks are connected together, the child +clocks run with the same period as their source (parent) clock. +The Clock API supports a built-in period multiplier/divider +mechanism so you can configure a clock to make its children +run at a different period from its own. If you call the +``clock_set_mul_div()`` function you can specify the clock's +multiplier and divider values. The children of that clock +will all run with a period of ``parent_period * multiplier / divider``. +For instance, if the clock has a frequency of 8MHz and you set its +multiplier to 2 and its divider to 3, the child clocks will run +at 12MHz. + +You can change the multiplier and divider of a clock at runtime, +so you can use this to model clock controller devices which +have guest-programmable frequency multipliers or dividers. + +Note that ``clock_set_mul_div()`` does not automatically call +``clock_propagate()``. If you make a runtime change to the +multiplier or divider you must call clock_propagate() yourself. + Unconnected input clocks ------------------------ diff --git a/docs/devel/qgraph.rst b/docs/devel/qgraph.rst index 39e293687e..c2882c3a33 100644 --- a/docs/devel/qgraph.rst +++ b/docs/devel/qgraph.rst @@ -41,7 +41,7 @@ Nodes A node can be of four types: -- **QNODE_MACHINE**: for example ``arm/raspi2`` +- **QNODE_MACHINE**: for example ``arm/raspi2b`` - **QNODE_DRIVER**: for example ``generic-sdhci`` - **QNODE_INTERFACE**: for example ``sdhci`` (interface for all ``-sdhci`` drivers). @@ -119,12 +119,12 @@ It is possible to troubleshoot unavailable tests by running:: # |-> dest='i440FX-pcihost' type=0 (node=0x5591421117f0) # src='' # |-> dest='x86_64/pc' type=0 (node=0x559142111600) - # |-> dest='arm/raspi2' type=0 (node=0x559142110740) + # |-> dest='arm/raspi2b' type=0 (node=0x559142110740) ... # } # ALL QGRAPH NODES: { # name='virtio-net-tests/announce-self' type=3 cmd_line='(null)' [available] - # name='arm/raspi2' type=0 cmd_line='-M raspi2 ' [UNAVAILABLE] + # name='arm/raspi2b' type=0 cmd_line='-M raspi2b ' [UNAVAILABLE] ... # } @@ -135,8 +135,8 @@ qgraph path in the "ALL QGRAPH EDGES" output as follows: '' -> 'x86_64/pc' -> 'virtio-net'. The root of the qgraph is '' and the depth first search begins there. -The ``arm/raspi`` machine node is listed as "UNAVAILABLE". Although it is -reachable from the root via '' -> 'arm/raspi2' the node is unavailable because +The ``arm/raspi2b`` machine node is listed as "UNAVAILABLE". Although it is +reachable from the root via '' -> 'arm/raspi2b' the node is unavailable because the QEMU binary did not list it when queried by the framework. This is expected because we used the ``qemu-system-x86_64`` binary which does not support ARM machine types. @@ -158,7 +158,7 @@ Here we continue the ``sdhci`` use case, with the following scenario: - ``sdhci-test`` aims to test the ``read[q,w], writeq`` functions offered by the ``sdhci`` drivers. - The current ``sdhci`` device is supported by both ``x86_64/pc`` and ``ARM`` - (in this example we focus on the ``arm-raspi2``) machines. + (in this example we focus on the ``arm-raspi2b``) machines. - QEMU offers 2 types of drivers: ``QSDHCI_MemoryMapped`` for ``ARM`` and ``QSDHCI_PCI`` for ``x86_64/pc``. Both implement the ``read[q,w], writeq`` functions. @@ -180,11 +180,11 @@ In order to implement such scenario in qgraph, the test developer needs to: all the pci drivers available) ``sdhci-pci --consumes--> pci-bus`` -- Create an ``arm/raspi2`` machine node. This machine ``contains`` +- Create an ``arm/raspi2b`` machine node. This machine ``contains`` a ``generic-sdhci`` memory mapped ``sdhci`` driver node, representing ``QSDHCI_MemoryMapped``. - ``arm/raspi2 --contains--> generic-sdhci`` + ``arm/raspi2b --contains--> generic-sdhci`` - Create the ``sdhci`` interface node. This interface offers the functions that are shared by all ``sdhci`` devices. The interface is produced by ``sdhci-pci`` and ``generic-sdhci``, @@ -199,7 +199,7 @@ In order to implement such scenario in qgraph, the test developer needs to: ``sdhci-test --consumes--> sdhci`` -``arm-raspi2`` machine, simplified from +``arm-raspi2b`` machine, simplified from ``tests/qtest/libqos/arm-raspi2-machine.c``:: #include "qgraph.h" @@ -217,7 +217,7 @@ In order to implement such scenario in qgraph, the test developer needs to: return &machine->alloc; } - fprintf(stderr, "%s not present in arm/raspi2\n", interface); + fprintf(stderr, "%s not present in arm/raspi2b\n", interface); g_assert_not_reached(); } @@ -229,7 +229,7 @@ In order to implement such scenario in qgraph, the test developer needs to: return &machine->sdhci.obj; } - fprintf(stderr, "%s not present in arm/raspi2\n", device); + fprintf(stderr, "%s not present in arm/raspi2b\n", device); g_assert_not_reached(); } @@ -253,10 +253,10 @@ In order to implement such scenario in qgraph, the test developer needs to: static void raspi2_register_nodes(void) { - /* arm/raspi2 --contains--> generic-sdhci */ - qos_node_create_machine("arm/raspi2", + /* arm/raspi2b --contains--> generic-sdhci */ + qos_node_create_machine("arm/raspi2b", qos_create_machine_arm_raspi2); - qos_node_contains("arm/raspi2", "generic-sdhci", NULL); + qos_node_contains("arm/raspi2b", "generic-sdhci", NULL); } libqos_init(raspi2_register_nodes); @@ -470,7 +470,7 @@ In the above example, all possible types of relations are created:: | +--produces-- + | - arm/raspi2 --contains--> generic-sdhci + arm/raspi2b --contains--> generic-sdhci or inverting the consumes edge in consumed_by:: @@ -486,7 +486,7 @@ or inverting the consumes edge in consumed_by:: | +--produces-- + | - arm/raspi2 --contains--> generic-sdhci + arm/raspi2b --contains--> generic-sdhci Adding a new test """"""""""""""""" @@ -536,7 +536,7 @@ Final graph will be like this:: | +--produces-- + | - arm/raspi2 --contains--> generic-sdhci + arm/raspi2b --contains--> generic-sdhci or inverting the consumes edge in consumed_by:: @@ -552,7 +552,7 @@ or inverting the consumes edge in consumed_by:: | +--produces-- + | - arm/raspi2 --contains--> generic-sdhci + arm/raspi2b --contains--> generic-sdhci Assuming there the binary is ``QTEST_QEMU_BINARY=./qemu-system-x86_64`` @@ -561,7 +561,7 @@ a valid test path will be: and for the binary ``QTEST_QEMU_BINARY=./qemu-system-arm``: -``/arm/raspi2/generic-sdhci/sdhci/sdhci-test`` +``/arm/raspi2b/generic-sdhci/sdhci/sdhci-test`` Additional examples are also in ``test-qgraph.c`` diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index 59acf0eeaf..850787495b 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -55,6 +55,7 @@ Supported guest CPU types: - ``cortex-a53`` (64-bit) - ``cortex-a57`` (64-bit) - ``cortex-a72`` (64-bit) +- ``a64fx`` (64-bit) - ``host`` (with KVM only) - ``max`` (same as ``host`` for KVM; best possible emulation with TCG) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index 12467bb9bb..f2ad0f335e 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -198,7 +198,6 @@ static void parts128_default_nan(FloatParts128 *p, float_status *status) static uint64_t parts_silence_nan_frac(uint64_t frac, float_status *status) { g_assert(!no_signaling_nans(status)); - g_assert(!status->default_nan_mode); /* The only snan_bit_is_one target without default_nan_mode is HPPA. */ if (snan_bit_is_one(status)) { diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index dc050b5c37..78fdd1b935 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -235,6 +235,7 @@ config STELLARIS select SSI_SD select STELLARIS_INPUT select STELLARIS_ENET # ethernet + select STELLARIS_GPTM # general purpose timer module select UNIMP config STM32VLDISCOVERY diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index a1456cb0f4..aecdeb9815 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -689,17 +689,6 @@ static void armsse_forward_sec_resp_cfg(ARMSSE *s) qdev_connect_gpio_out(dev_splitter, 2, s->sec_resp_cfg_in); } -static void armsse_mainclk_update(void *opaque, ClockEvent event) -{ - ARMSSE *s = ARM_SSE(opaque); - - /* - * Set system_clock_scale from our Clock input; this is what - * controls the tick rate of the CPU SysTick timer. - */ - system_clock_scale = clock_ticks_to_ns(s->mainclk, 1); -} - static void armsse_init(Object *obj) { ARMSSE *s = ARM_SSE(obj); @@ -711,8 +700,7 @@ static void armsse_init(Object *obj) assert(info->sram_banks <= MAX_SRAM_BANKS); assert(info->num_cpus <= SSE_MAX_CPUS); - s->mainclk = qdev_init_clock_in(DEVICE(s), "MAINCLK", - armsse_mainclk_update, s, ClockUpdate); + s->mainclk = qdev_init_clock_in(DEVICE(s), "MAINCLK", NULL, NULL, 0); s->s32kclk = qdev_init_clock_in(DEVICE(s), "S32KCLK", NULL, NULL, 0); memory_region_init(&s->container, obj, "armsse-container", UINT64_MAX); @@ -995,6 +983,9 @@ static void armsse_realize(DeviceState *dev, Error **errp) int j; char *gpioname; + qdev_connect_clock_in(cpudev, "cpuclk", s->mainclk); + /* The SSE subsystems do not wire up a systick refclk */ + qdev_prop_set_uint32(cpudev, "num-irq", s->exp_numirq + NUM_SSE_IRQS); /* * In real hardware the initial Secure VTOR is set from the INITSVTOR* @@ -1651,9 +1642,6 @@ static void armsse_realize(DeviceState *dev, Error **errp) * devices in the ARMSSE. */ sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->container); - - /* Set initial system_clock_scale from MAINCLK */ - armsse_mainclk_update(s, ClockUpdate); } static void armsse_idau_check(IDAUInterface *ii, uint32_t address, diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index 9ce5c30cd5..8d08db80be 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -14,11 +14,14 @@ #include "hw/arm/boot.h" #include "hw/loader.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "elf.h" #include "sysemu/reset.h" #include "qemu/error-report.h" #include "qemu/module.h" +#include "qemu/log.h" #include "target/arm/idau.h" +#include "migration/vmstate.h" /* Bitbanded IO. Each word corresponds to a single bit. */ @@ -124,6 +127,122 @@ static const hwaddr bitband_output_addr[ARMV7M_NUM_BITBANDS] = { 0x22000000, 0x42000000 }; +static MemTxResult v7m_sysreg_ns_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + MemoryRegion *mr = opaque; + + if (attrs.secure) { + /* S accesses to the alias act like NS accesses to the real region */ + attrs.secure = 0; + return memory_region_dispatch_write(mr, addr, value, + size_memop(size) | MO_TE, attrs); + } else { + /* NS attrs are RAZ/WI for privileged, and BusFault for user */ + if (attrs.user) { + return MEMTX_ERROR; + } + return MEMTX_OK; + } +} + +static MemTxResult v7m_sysreg_ns_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + MemoryRegion *mr = opaque; + + if (attrs.secure) { + /* S accesses to the alias act like NS accesses to the real region */ + attrs.secure = 0; + return memory_region_dispatch_read(mr, addr, data, + size_memop(size) | MO_TE, attrs); + } else { + /* NS attrs are RAZ/WI for privileged, and BusFault for user */ + if (attrs.user) { + return MEMTX_ERROR; + } + *data = 0; + return MEMTX_OK; + } +} + +static const MemoryRegionOps v7m_sysreg_ns_ops = { + .read_with_attrs = v7m_sysreg_ns_read, + .write_with_attrs = v7m_sysreg_ns_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static MemTxResult v7m_systick_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + ARMv7MState *s = opaque; + MemoryRegion *mr; + + /* Direct the access to the correct systick */ + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0); + return memory_region_dispatch_write(mr, addr, value, + size_memop(size) | MO_TE, attrs); +} + +static MemTxResult v7m_systick_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + ARMv7MState *s = opaque; + MemoryRegion *mr; + + /* Direct the access to the correct systick */ + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0); + return memory_region_dispatch_read(mr, addr, data, size_memop(size) | MO_TE, + attrs); +} + +static const MemoryRegionOps v7m_systick_ops = { + .read_with_attrs = v7m_systick_read, + .write_with_attrs = v7m_systick_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +/* + * Unassigned portions of the PPB space are RAZ/WI for privileged + * accesses, and fault for non-privileged accesses. + */ +static MemTxResult ppb_default_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + qemu_log_mask(LOG_UNIMP, "Read of unassigned area of PPB: offset 0x%x\n", + (uint32_t)addr); + if (attrs.user) { + return MEMTX_ERROR; + } + *data = 0; + return MEMTX_OK; +} + +static MemTxResult ppb_default_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + qemu_log_mask(LOG_UNIMP, "Write of unassigned area of PPB: offset 0x%x\n", + (uint32_t)addr); + if (attrs.user) { + return MEMTX_ERROR; + } + return MEMTX_OK; +} + +static const MemoryRegionOps ppb_default_ops = { + .read_with_attrs = ppb_default_read, + .write_with_attrs = ppb_default_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid.min_access_size = 1, + .valid.max_access_size = 8, +}; + static void armv7m_instance_init(Object *obj) { ARMv7MState *s = ARMV7M(obj); @@ -137,10 +256,20 @@ static void armv7m_instance_init(Object *obj) object_property_add_alias(obj, "num-irq", OBJECT(&s->nvic), "num-irq"); + object_initialize_child(obj, "systick-reg-ns", &s->systick[M_REG_NS], + TYPE_SYSTICK); + /* + * We can't initialize the secure systick here, as we don't know + * yet if we need it. + */ + for (i = 0; i < ARRAY_SIZE(s->bitband); i++) { object_initialize_child(obj, "bitband[*]", &s->bitband[i], TYPE_BITBAND); } + + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", NULL, NULL, 0); + s->cpuclk = qdev_init_clock_in(DEVICE(obj), "cpuclk", NULL, NULL, 0); } static void armv7m_realize(DeviceState *dev, Error **errp) @@ -223,13 +352,130 @@ static void armv7m_realize(DeviceState *dev, Error **errp) qdev_pass_gpios(DEVICE(&s->nvic), dev, "SYSRESETREQ"); qdev_pass_gpios(DEVICE(&s->nvic), dev, "NMI"); + /* + * We map various devices into the container MR at their architected + * addresses. In particular, we map everything corresponding to the + * "System PPB" space. This is the range from 0xe0000000 to 0xe00fffff + * and includes the NVIC, the System Control Space (system registers), + * the systick timer, and for CPUs with the Security extension an NS + * banked version of all of these. + * + * The default behaviour for unimplemented registers/ranges + * (for instance the Data Watchpoint and Trace unit at 0xe0001000) + * is to RAZ/WI for privileged access and BusFault for non-privileged + * access. + * + * The NVIC and System Control Space (SCS) starts at 0xe000e000 + * and looks like this: + * 0x004 - ICTR + * 0x010 - 0xff - systick + * 0x100..0x7ec - NVIC + * 0x7f0..0xcff - Reserved + * 0xd00..0xd3c - SCS registers + * 0xd40..0xeff - Reserved or Not implemented + * 0xf00 - STIR + * + * Some registers within this space are banked between security states. + * In v8M there is a second range 0xe002e000..0xe002efff which is the + * NonSecure alias SCS; secure accesses to this behave like NS accesses + * to the main SCS range, and non-secure accesses (including when + * the security extension is not implemented) are RAZ/WI. + * Note that both the main SCS range and the alias range are defined + * to be exempt from memory attribution (R_BLJT) and so the memory + * transaction attribute always matches the current CPU security + * state (attrs.secure == env->v7m.secure). In the v7m_sysreg_ns_ops + * wrappers we change attrs.secure to indicate the NS access; so + * generally code determining which banked register to use should + * use attrs.secure; code determining actual behaviour of the system + * should use env->v7m.secure. + * + * Within the PPB space, some MRs overlap, and the priority + * of overlapping regions is: + * - default region (for RAZ/WI and BusFault) : -1 + * - system register regions (provided by the NVIC) : 0 + * - systick : 1 + * This is because the systick device is a small block of registers + * in the middle of the other system control registers. + */ + + memory_region_init_io(&s->defaultmem, OBJECT(s), &ppb_default_ops, s, + "nvic-default", 0x100000); + memory_region_add_subregion_overlap(&s->container, 0xe0000000, + &s->defaultmem, -1); + /* Wire the NVIC up to the CPU */ sbd = SYS_BUS_DEVICE(&s->nvic); sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ)); - memory_region_add_subregion(&s->container, 0xe0000000, + memory_region_add_subregion(&s->container, 0xe000e000, sysbus_mmio_get_region(sbd, 0)); + if (arm_feature(&s->cpu->env, ARM_FEATURE_V8)) { + /* Create the NS alias region for the NVIC sysregs */ + memory_region_init_io(&s->sysreg_ns_mem, OBJECT(s), + &v7m_sysreg_ns_ops, + sysbus_mmio_get_region(sbd, 0), + "nvic_sysregs_ns", 0x1000); + memory_region_add_subregion(&s->container, 0xe002e000, + &s->sysreg_ns_mem); + } + + /* Create and map the systick devices */ + qdev_connect_clock_in(DEVICE(&s->systick[M_REG_NS]), "refclk", s->refclk); + qdev_connect_clock_in(DEVICE(&s->systick[M_REG_NS]), "cpuclk", s->cpuclk); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), errp)) { + return; + } + sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), 0, + qdev_get_gpio_in_named(DEVICE(&s->nvic), + "systick-trigger", M_REG_NS)); + + if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY)) { + /* + * We couldn't init the secure systick device in instance_init + * as we didn't know then if the CPU had the security extensions; + * so we have to do it here. + */ + object_initialize_child(OBJECT(dev), "systick-reg-s", + &s->systick[M_REG_S], TYPE_SYSTICK); + qdev_connect_clock_in(DEVICE(&s->systick[M_REG_S]), "refclk", + s->refclk); + qdev_connect_clock_in(DEVICE(&s->systick[M_REG_S]), "cpuclk", + s->cpuclk); + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_S]), errp)) { + return; + } + sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_S]), 0, + qdev_get_gpio_in_named(DEVICE(&s->nvic), + "systick-trigger", M_REG_S)); + } + + memory_region_init_io(&s->systickmem, OBJECT(s), + &v7m_systick_ops, s, + "v7m_systick", 0xe0); + + memory_region_add_subregion_overlap(&s->container, 0xe000e010, + &s->systickmem, 1); + if (arm_feature(&s->cpu->env, ARM_FEATURE_V8)) { + memory_region_init_io(&s->systick_ns_mem, OBJECT(s), + &v7m_sysreg_ns_ops, &s->systickmem, + "v7m_systick_ns", 0xe0); + memory_region_add_subregion_overlap(&s->container, 0xe002e010, + &s->systick_ns_mem, 1); + } + + /* If the CPU has RAS support, create the RAS register block */ + if (cpu_isar_feature(aa32_ras, s->cpu)) { + object_initialize_child(OBJECT(dev), "armv7m-ras", + &s->ras, TYPE_ARMV7M_RAS); + sbd = SYS_BUS_DEVICE(&s->ras); + if (!sysbus_realize(sbd, errp)) { + return; + } + memory_region_add_subregion_overlap(&s->container, 0xe0005000, + sysbus_mmio_get_region(sbd, 0), 1); + } for (i = 0; i < ARRAY_SIZE(s->bitband); i++) { if (s->enable_bitband) { @@ -269,11 +515,23 @@ static Property armv7m_properties[] = { DEFINE_PROP_END_OF_LIST(), }; +static const VMStateDescription vmstate_armv7m = { + .name = "armv7m", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_CLOCK(refclk, SysTickState), + VMSTATE_CLOCK(cpuclk, SysTickState), + VMSTATE_END_OF_LIST() + } +}; + static void armv7m_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); dc->realize = armv7m_realize; + dc->vmsd = &vmstate_armv7m; device_class_set_props(dc, armv7m_properties); } diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index 81413b7133..4634aa1a1c 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -86,6 +86,7 @@ struct MPS2MachineState { CMSDKAPBWatchdog watchdog; CMSDKAPBTimer timer[2]; Clock *sysclk; + Clock *refclk; }; #define TYPE_MPS2_MACHINE "mps2" @@ -99,6 +100,15 @@ OBJECT_DECLARE_TYPE(MPS2MachineState, MPS2MachineClass, MPS2_MACHINE) /* Main SYSCLK frequency in Hz */ #define SYSCLK_FRQ 25000000 +/* + * The Application Notes don't say anything about how the + * systick reference clock is configured. (Quite possibly + * they don't have one at all.) This 1MHz clock matches the + * pre-existing behaviour that used to be hardcoded in the + * armv7m_systick implementation. + */ +#define REFCLK_FRQ (1 * 1000 * 1000) + /* Initialize the auxiliary RAM region @mr and map it into * the memory map at @base. */ @@ -146,6 +156,9 @@ static void mps2_common_init(MachineState *machine) mms->sysclk = clock_new(OBJECT(machine), "SYSCLK"); clock_set_hz(mms->sysclk, SYSCLK_FRQ); + mms->refclk = clock_new(OBJECT(machine), "REFCLK"); + clock_set_hz(mms->refclk, REFCLK_FRQ); + /* The FPGA images have an odd combination of different RAMs, * because in hardware they are different implementations and * connected to different buses, giving varying performance/size @@ -223,6 +236,8 @@ static void mps2_common_init(MachineState *machine) default: g_assert_not_reached(); } + qdev_connect_clock_in(armv7m, "cpuclk", mms->sysclk); + qdev_connect_clock_in(armv7m, "refclk", mms->refclk); qdev_prop_set_string(armv7m, "cpu-type", machine->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); object_property_set_link(OBJECT(&mms->armv7m), "memory", @@ -424,8 +439,6 @@ static void mps2_common_init(MachineState *machine) qdev_get_gpio_in(armv7m, mmc->fpga_type == FPGA_AN511 ? 47 : 13)); - system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0x400000); } diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c index 5cfe7caf83..b5fe9f364d 100644 --- a/hw/arm/msf2-soc.c +++ b/hw/arm/msf2-soc.c @@ -29,6 +29,7 @@ #include "hw/char/serial.h" #include "hw/arm/msf2-soc.h" #include "hw/misc/unimp.h" +#include "hw/qdev-clock.h" #include "sysemu/sysemu.h" #define MSF2_TIMER_BASE 0x40004000 @@ -73,6 +74,9 @@ static void m2sxxx_soc_initfn(Object *obj) } object_initialize_child(obj, "emac", &s->emac, TYPE_MSS_EMAC); + + s->m3clk = qdev_init_clock_in(DEVICE(obj), "m3clk", NULL, NULL, 0); + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", NULL, NULL, 0); } static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) @@ -83,11 +87,34 @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) int i; MemoryRegion *system_memory = get_system_memory(); - MemoryRegion *nvm = g_new(MemoryRegion, 1); - MemoryRegion *nvm_alias = g_new(MemoryRegion, 1); - MemoryRegion *sram = g_new(MemoryRegion, 1); - memory_region_init_rom(nvm, OBJECT(dev_soc), "MSF2.eNVM", s->envm_size, + if (!clock_has_source(s->m3clk)) { + error_setg(errp, "m3clk must be wired up by the board code"); + return; + } + + /* + * We use s->refclk internally and only define it with qdev_init_clock_in() + * so it is correctly parented and not leaked on an init/deinit; it is not + * intended as an externally exposed clock. + */ + if (clock_has_source(s->refclk)) { + error_setg(errp, "refclk must not be wired up by the board code"); + return; + } + + /* + * TODO: ideally we should model the SoC SYSTICK_CR register at 0xe0042038, + * which allows the guest to program the divisor between the m3clk and + * the systick refclk to either /4, /8, /16 or /32, as well as setting + * the value the guest can read in the STCALIB register. Currently we + * implement the divisor as a fixed /32, which matches the reset value + * of SYSTICK_CR. + */ + clock_set_mul_div(s->refclk, 32, 1); + clock_set_source(s->refclk, s->m3clk); + + memory_region_init_rom(&s->nvm, OBJECT(dev_soc), "MSF2.eNVM", s->envm_size, &error_fatal); /* * On power-on, the eNVM region 0x60000000 is automatically @@ -95,34 +122,28 @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) * start address (0x0). We do not support remapping other eNVM, * eSRAM and DDR regions by guest(via Sysreg) currently. */ - memory_region_init_alias(nvm_alias, OBJECT(dev_soc), "MSF2.eNVM", nvm, 0, - s->envm_size); + memory_region_init_alias(&s->nvm_alias, OBJECT(dev_soc), "MSF2.eNVM", + &s->nvm, 0, s->envm_size); - memory_region_add_subregion(system_memory, ENVM_BASE_ADDRESS, nvm); - memory_region_add_subregion(system_memory, 0, nvm_alias); + memory_region_add_subregion(system_memory, ENVM_BASE_ADDRESS, &s->nvm); + memory_region_add_subregion(system_memory, 0, &s->nvm_alias); - memory_region_init_ram(sram, NULL, "MSF2.eSRAM", s->esram_size, + memory_region_init_ram(&s->sram, NULL, "MSF2.eSRAM", s->esram_size, &error_fatal); - memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); + memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, &s->sram); armv7m = DEVICE(&s->armv7m); qdev_prop_set_uint32(armv7m, "num-irq", 81); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); + qdev_connect_clock_in(armv7m, "cpuclk", s->m3clk); + qdev_connect_clock_in(armv7m, "refclk", s->refclk); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(get_system_memory()), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { return; } - if (!s->m3clk) { - error_setg(errp, "Invalid m3clk value"); - error_append_hint(errp, "m3clk can not be zero\n"); - return; - } - - system_clock_scale = NANOSECONDS_PER_SECOND / s->m3clk; - for (i = 0; i < MSF2_NUM_UARTS; i++) { if (serial_hd(i)) { serial_mm_init(get_system_memory(), uart_addr[i], 2, @@ -132,8 +153,13 @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) } dev = DEVICE(&s->timer); - /* APB0 clock is the timer input clock */ - qdev_prop_set_uint32(dev, "clock-frequency", s->m3clk / s->apb0div); + /* + * APB0 clock is the timer input clock. + * TODO: ideally the MSF2 timer device should use a Clock rather than a + * clock-frequency integer property. + */ + qdev_prop_set_uint32(dev, "clock-frequency", + clock_get_hz(s->m3clk) / s->apb0div); if (!sysbus_realize(SYS_BUS_DEVICE(&s->timer), errp)) { return; } @@ -210,8 +236,6 @@ static Property m2sxxx_soc_properties[] = { DEFINE_PROP_UINT64("eNVM-size", MSF2State, envm_size, MSF2_ENVM_MAX_SIZE), DEFINE_PROP_UINT64("eSRAM-size", MSF2State, esram_size, MSF2_ESRAM_MAX_SIZE), - /* Libero GUI shows 100Mhz as default for clocks */ - DEFINE_PROP_UINT32("m3clk", MSF2State, m3clk, 100 * 1000000), /* default divisors in Libero GUI */ DEFINE_PROP_UINT8("apb0div", MSF2State, apb0div, 2), DEFINE_PROP_UINT8("apb1div", MSF2State, apb1div, 2), diff --git a/hw/arm/msf2-som.c b/hw/arm/msf2-som.c index 343ec977c0..396e8b9913 100644 --- a/hw/arm/msf2-som.c +++ b/hw/arm/msf2-som.c @@ -29,6 +29,7 @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/boot.h" +#include "hw/qdev-clock.h" #include "exec/address-spaces.h" #include "hw/arm/msf2-soc.h" @@ -49,6 +50,7 @@ static void emcraft_sf2_s2s010_init(MachineState *machine) BusState *spi_bus; MemoryRegion *sysmem = get_system_memory(); MemoryRegion *ddr = g_new(MemoryRegion, 1); + Clock *m3clk; if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { error_report("This board can only be used with CPU %s", @@ -72,7 +74,10 @@ static void emcraft_sf2_s2s010_init(MachineState *machine) * in Libero. CPU clock is divided by APB0 and APB1 divisors for * peripherals. Emcraft's SoM kit comes with these settings by default. */ - qdev_prop_set_uint32(dev, "m3clk", 142 * 1000000); + /* This clock doesn't need migration because it is fixed-frequency */ + m3clk = clock_new(OBJECT(machine), "m3clk"); + clock_set_hz(m3clk, 142 * 1000000); + qdev_connect_clock_in(dev, "m3clk", m3clk); qdev_prop_set_uint32(dev, "apb0div", 2); qdev_prop_set_uint32(dev, "apb1div", 2); diff --git a/hw/arm/netduino2.c b/hw/arm/netduino2.c index 1733b71507..3365da11bf 100644 --- a/hw/arm/netduino2.c +++ b/hw/arm/netduino2.c @@ -26,6 +26,7 @@ #include "qapi/error.h" #include "hw/boards.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "qemu/error-report.h" #include "hw/arm/stm32f205_soc.h" #include "hw/arm/boot.h" @@ -36,16 +37,15 @@ static void netduino2_init(MachineState *machine) { DeviceState *dev; + Clock *sysclk; - /* - * TODO: ideally we would model the SoC RCC and let it handle - * system_clock_scale, including its ability to define different - * possible SYSCLK sources. - */ - system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; + /* This clock doesn't need migration because it is fixed-frequency */ + sysclk = clock_new(OBJECT(machine), "SYSCLK"); + clock_set_hz(sysclk, SYSCLK_FRQ); dev = qdev_new(TYPE_STM32F205_SOC); qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m3")); + qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, diff --git a/hw/arm/netduinoplus2.c b/hw/arm/netduinoplus2.c index d3ad7a2b67..76cea8e489 100644 --- a/hw/arm/netduinoplus2.c +++ b/hw/arm/netduinoplus2.c @@ -26,6 +26,7 @@ #include "qapi/error.h" #include "hw/boards.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "qemu/error-report.h" #include "hw/arm/stm32f405_soc.h" #include "hw/arm/boot.h" @@ -36,16 +37,15 @@ static void netduinoplus2_init(MachineState *machine) { DeviceState *dev; + Clock *sysclk; - /* - * TODO: ideally we would model the SoC RCC and let it handle - * system_clock_scale, including its ability to define different - * possible SYSCLK sources. - */ - system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; + /* This clock doesn't need migration because it is fixed-frequency */ + sysclk = clock_new(OBJECT(machine), "SYSCLK"); + clock_set_hz(sysclk, SYSCLK_FRQ); dev = qdev_new(TYPE_STM32F405_SOC); qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m4")); + qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); armv7m_load_kernel(ARM_CPU(first_cpu), diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c index 9407c2f268..34da0d62f0 100644 --- a/hw/arm/nrf51_soc.c +++ b/hw/arm/nrf51_soc.c @@ -12,6 +12,7 @@ #include "qapi/error.h" #include "hw/arm/boot.h" #include "hw/sysbus.h" +#include "hw/qdev-clock.h" #include "hw/misc/unimp.h" #include "qemu/log.h" @@ -66,7 +67,22 @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) return; } - system_clock_scale = NANOSECONDS_PER_SECOND / HCLK_FRQ; + /* + * HCLK on this SoC is fixed, so we set up sysclk ourselves and + * the board shouldn't connect it. + */ + if (clock_has_source(s->sysclk)) { + error_setg(errp, "sysclk clock must not be wired up by the board code"); + return; + } + /* This clock doesn't need migration because it is fixed-frequency */ + clock_set_hz(s->sysclk, HCLK_FRQ); + qdev_connect_clock_in(DEVICE(&s->cpu), "cpuclk", s->sysclk); + /* + * This SoC has no systick device, so don't connect refclk. + * TODO: model the lack of systick (currently the armv7m object + * will always provide one). + */ object_property_set_link(OBJECT(&s->cpu), "memory", OBJECT(&s->container), &error_abort); @@ -191,6 +207,8 @@ static void nrf51_soc_init(Object *obj) TYPE_NRF51_TIMER); } + + s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); } static Property nrf51_soc_properties[] = { diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c index 0ada91c05e..146d35382b 100644 --- a/hw/arm/raspi.c +++ b/hw/arm/raspi.c @@ -340,7 +340,6 @@ static void raspi2b_machine_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); RaspiMachineClass *rmc = RASPI_MACHINE_CLASS(oc); - mc->alias = "raspi2"; rmc->board_rev = 0xa21041; raspi_machine_class_common_init(mc, rmc->board_rev); }; @@ -360,7 +359,6 @@ static void raspi3b_machine_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); RaspiMachineClass *rmc = RASPI_MACHINE_CLASS(oc); - mc->alias = "raspi3"; rmc->board_rev = 0xa02082; raspi_machine_class_common_init(mc, rmc->board_rev); }; diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index ad48cf2605..78827ace6b 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -26,6 +26,7 @@ #include "hw/watchdog/cmsdk-apb-watchdog.h" #include "migration/vmstate.h" #include "hw/misc/unimp.h" +#include "hw/timer/stellaris-gptm.h" #include "hw/qdev-clock.h" #include "qom/object.h" @@ -55,306 +56,6 @@ typedef const struct { uint32_t peripherals; } stellaris_board_info; -/* General purpose timer module. */ - -#define TYPE_STELLARIS_GPTM "stellaris-gptm" -OBJECT_DECLARE_SIMPLE_TYPE(gptm_state, STELLARIS_GPTM) - -struct gptm_state { - SysBusDevice parent_obj; - - MemoryRegion iomem; - uint32_t config; - uint32_t mode[2]; - uint32_t control; - uint32_t state; - uint32_t mask; - uint32_t load[2]; - uint32_t match[2]; - uint32_t prescale[2]; - uint32_t match_prescale[2]; - uint32_t rtc; - int64_t tick[2]; - struct gptm_state *opaque[2]; - QEMUTimer *timer[2]; - /* The timers have an alternate output used to trigger the ADC. */ - qemu_irq trigger; - qemu_irq irq; -}; - -static void gptm_update_irq(gptm_state *s) -{ - int level; - level = (s->state & s->mask) != 0; - qemu_set_irq(s->irq, level); -} - -static void gptm_stop(gptm_state *s, int n) -{ - timer_del(s->timer[n]); -} - -static void gptm_reload(gptm_state *s, int n, int reset) -{ - int64_t tick; - if (reset) - tick = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - else - tick = s->tick[n]; - - if (s->config == 0) { - /* 32-bit CountDown. */ - uint32_t count; - count = s->load[0] | (s->load[1] << 16); - tick += (int64_t)count * system_clock_scale; - } else if (s->config == 1) { - /* 32-bit RTC. 1Hz tick. */ - tick += NANOSECONDS_PER_SECOND; - } else if (s->mode[n] == 0xa) { - /* PWM mode. Not implemented. */ - } else { - qemu_log_mask(LOG_UNIMP, - "GPTM: 16-bit timer mode unimplemented: 0x%x\n", - s->mode[n]); - return; - } - s->tick[n] = tick; - timer_mod(s->timer[n], tick); -} - -static void gptm_tick(void *opaque) -{ - gptm_state **p = (gptm_state **)opaque; - gptm_state *s; - int n; - - s = *p; - n = p - s->opaque; - if (s->config == 0) { - s->state |= 1; - if ((s->control & 0x20)) { - /* Output trigger. */ - qemu_irq_pulse(s->trigger); - } - if (s->mode[0] & 1) { - /* One-shot. */ - s->control &= ~1; - } else { - /* Periodic. */ - gptm_reload(s, 0, 0); - } - } else if (s->config == 1) { - /* RTC. */ - uint32_t match; - s->rtc++; - match = s->match[0] | (s->match[1] << 16); - if (s->rtc > match) - s->rtc = 0; - if (s->rtc == 0) { - s->state |= 8; - } - gptm_reload(s, 0, 0); - } else if (s->mode[n] == 0xa) { - /* PWM mode. Not implemented. */ - } else { - qemu_log_mask(LOG_UNIMP, - "GPTM: 16-bit timer mode unimplemented: 0x%x\n", - s->mode[n]); - } - gptm_update_irq(s); -} - -static uint64_t gptm_read(void *opaque, hwaddr offset, - unsigned size) -{ - gptm_state *s = (gptm_state *)opaque; - - switch (offset) { - case 0x00: /* CFG */ - return s->config; - case 0x04: /* TAMR */ - return s->mode[0]; - case 0x08: /* TBMR */ - return s->mode[1]; - case 0x0c: /* CTL */ - return s->control; - case 0x18: /* IMR */ - return s->mask; - case 0x1c: /* RIS */ - return s->state; - case 0x20: /* MIS */ - return s->state & s->mask; - case 0x24: /* CR */ - return 0; - case 0x28: /* TAILR */ - return s->load[0] | ((s->config < 4) ? (s->load[1] << 16) : 0); - case 0x2c: /* TBILR */ - return s->load[1]; - case 0x30: /* TAMARCHR */ - return s->match[0] | ((s->config < 4) ? (s->match[1] << 16) : 0); - case 0x34: /* TBMATCHR */ - return s->match[1]; - case 0x38: /* TAPR */ - return s->prescale[0]; - case 0x3c: /* TBPR */ - return s->prescale[1]; - case 0x40: /* TAPMR */ - return s->match_prescale[0]; - case 0x44: /* TBPMR */ - return s->match_prescale[1]; - case 0x48: /* TAR */ - if (s->config == 1) { - return s->rtc; - } - qemu_log_mask(LOG_UNIMP, - "GPTM: read of TAR but timer read not supported\n"); - return 0; - case 0x4c: /* TBR */ - qemu_log_mask(LOG_UNIMP, - "GPTM: read of TBR but timer read not supported\n"); - return 0; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "GPTM: read at bad offset 0x02%" HWADDR_PRIx "\n", - offset); - return 0; - } -} - -static void gptm_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - gptm_state *s = (gptm_state *)opaque; - uint32_t oldval; - - /* The timers should be disabled before changing the configuration. - We take advantage of this and defer everything until the timer - is enabled. */ - switch (offset) { - case 0x00: /* CFG */ - s->config = value; - break; - case 0x04: /* TAMR */ - s->mode[0] = value; - break; - case 0x08: /* TBMR */ - s->mode[1] = value; - break; - case 0x0c: /* CTL */ - oldval = s->control; - s->control = value; - /* TODO: Implement pause. */ - if ((oldval ^ value) & 1) { - if (value & 1) { - gptm_reload(s, 0, 1); - } else { - gptm_stop(s, 0); - } - } - if (((oldval ^ value) & 0x100) && s->config >= 4) { - if (value & 0x100) { - gptm_reload(s, 1, 1); - } else { - gptm_stop(s, 1); - } - } - break; - case 0x18: /* IMR */ - s->mask = value & 0x77; - gptm_update_irq(s); - break; - case 0x24: /* CR */ - s->state &= ~value; - break; - case 0x28: /* TAILR */ - s->load[0] = value & 0xffff; - if (s->config < 4) { - s->load[1] = value >> 16; - } - break; - case 0x2c: /* TBILR */ - s->load[1] = value & 0xffff; - break; - case 0x30: /* TAMARCHR */ - s->match[0] = value & 0xffff; - if (s->config < 4) { - s->match[1] = value >> 16; - } - break; - case 0x34: /* TBMATCHR */ - s->match[1] = value >> 16; - break; - case 0x38: /* TAPR */ - s->prescale[0] = value; - break; - case 0x3c: /* TBPR */ - s->prescale[1] = value; - break; - case 0x40: /* TAPMR */ - s->match_prescale[0] = value; - break; - case 0x44: /* TBPMR */ - s->match_prescale[0] = value; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "GPTM: write at bad offset 0x02%" HWADDR_PRIx "\n", - offset); - } - gptm_update_irq(s); -} - -static const MemoryRegionOps gptm_ops = { - .read = gptm_read, - .write = gptm_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static const VMStateDescription vmstate_stellaris_gptm = { - .name = "stellaris_gptm", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32(config, gptm_state), - VMSTATE_UINT32_ARRAY(mode, gptm_state, 2), - VMSTATE_UINT32(control, gptm_state), - VMSTATE_UINT32(state, gptm_state), - VMSTATE_UINT32(mask, gptm_state), - VMSTATE_UNUSED(8), - VMSTATE_UINT32_ARRAY(load, gptm_state, 2), - VMSTATE_UINT32_ARRAY(match, gptm_state, 2), - VMSTATE_UINT32_ARRAY(prescale, gptm_state, 2), - VMSTATE_UINT32_ARRAY(match_prescale, gptm_state, 2), - VMSTATE_UINT32(rtc, gptm_state), - VMSTATE_INT64_ARRAY(tick, gptm_state, 2), - VMSTATE_TIMER_PTR_ARRAY(timer, gptm_state, 2), - VMSTATE_END_OF_LIST() - } -}; - -static void stellaris_gptm_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - gptm_state *s = STELLARIS_GPTM(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - sysbus_init_irq(sbd, &s->irq); - qdev_init_gpio_out(dev, &s->trigger, 1); - - memory_region_init_io(&s->iomem, obj, &gptm_ops, s, - "gptm", 0x1000); - sysbus_init_mmio(sbd, &s->iomem); - - s->opaque[0] = s->opaque[1] = s; -} - -static void stellaris_gptm_realize(DeviceState *dev, Error **errp) -{ - gptm_state *s = STELLARIS_GPTM(dev); - s->timer[0] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[0]); - s->timer[1] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[1]); -} - /* System controller. */ #define TYPE_STELLARIS_SYS "stellaris-sys" @@ -562,17 +263,18 @@ static bool ssys_use_rcc2(ssys_state *s) */ static void ssys_calculate_system_clock(ssys_state *s, bool propagate_clock) { + int period_ns; /* * SYSDIV field specifies divisor: 0 == /1, 1 == /2, etc. Input * clock is 200MHz, which is a period of 5 ns. Dividing the clock * frequency by X is the same as multiplying the period by X. */ if (ssys_use_rcc2(s)) { - system_clock_scale = 5 * (((s->rcc2 >> 23) & 0x3f) + 1); + period_ns = 5 * (((s->rcc2 >> 23) & 0x3f) + 1); } else { - system_clock_scale = 5 * (((s->rcc >> 23) & 0xf) + 1); + period_ns = 5 * (((s->rcc >> 23) & 0xf) + 1); } - clock_set_ns(s->sysclk, system_clock_scale); + clock_set_ns(s->sysclk, period_ns); if (propagate_clock) { clock_propagate(s->sysclk); } @@ -755,33 +457,6 @@ static void stellaris_sys_instance_init(Object *obj) s->sysclk = qdev_init_clock_out(DEVICE(s), "SYSCLK"); } -static DeviceState *stellaris_sys_init(uint32_t base, qemu_irq irq, - stellaris_board_info *board, - uint8_t *macaddr) -{ - DeviceState *dev = qdev_new(TYPE_STELLARIS_SYS); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - - /* Most devices come preprogrammed with a MAC address in the user data. */ - qdev_prop_set_uint32(dev, "user0", - macaddr[0] | (macaddr[1] << 8) | (macaddr[2] << 16)); - qdev_prop_set_uint32(dev, "user1", - macaddr[3] | (macaddr[4] << 8) | (macaddr[5] << 16)); - qdev_prop_set_uint32(dev, "did0", board->did0); - qdev_prop_set_uint32(dev, "did1", board->did1); - qdev_prop_set_uint32(dev, "dc0", board->dc0); - qdev_prop_set_uint32(dev, "dc1", board->dc1); - qdev_prop_set_uint32(dev, "dc2", board->dc2); - qdev_prop_set_uint32(dev, "dc3", board->dc3); - qdev_prop_set_uint32(dev, "dc4", board->dc4); - - sysbus_realize_and_unref(sbd, &error_fatal); - sysbus_mmio_map(sbd, 0, base); - sysbus_connect_irq(sbd, 0, irq); - - return dev; -} - /* I2C controller. */ #define TYPE_STELLARIS_I2C "stellaris-i2c" @@ -1349,6 +1024,7 @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) DeviceState *ssys_dev; int i; int j; + const uint8_t *macaddr; MemoryRegion *sram = g_new(MemoryRegion, 1); MemoryRegion *flash = g_new(MemoryRegion, 1); @@ -1366,15 +1042,42 @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) &error_fatal); memory_region_add_subregion(system_memory, 0x20000000, sram); + /* + * Create the system-registers object early, because we will + * need its sysclk output. + */ + ssys_dev = qdev_new(TYPE_STELLARIS_SYS); + /* Most devices come preprogrammed with a MAC address in the user data. */ + macaddr = nd_table[0].macaddr.a; + qdev_prop_set_uint32(ssys_dev, "user0", + macaddr[0] | (macaddr[1] << 8) | (macaddr[2] << 16)); + qdev_prop_set_uint32(ssys_dev, "user1", + macaddr[3] | (macaddr[4] << 8) | (macaddr[5] << 16)); + qdev_prop_set_uint32(ssys_dev, "did0", board->did0); + qdev_prop_set_uint32(ssys_dev, "did1", board->did1); + qdev_prop_set_uint32(ssys_dev, "dc0", board->dc0); + qdev_prop_set_uint32(ssys_dev, "dc1", board->dc1); + qdev_prop_set_uint32(ssys_dev, "dc2", board->dc2); + qdev_prop_set_uint32(ssys_dev, "dc3", board->dc3); + qdev_prop_set_uint32(ssys_dev, "dc4", board->dc4); + sysbus_realize_and_unref(SYS_BUS_DEVICE(ssys_dev), &error_fatal); + nvic = qdev_new(TYPE_ARMV7M); qdev_prop_set_uint32(nvic, "num-irq", NUM_IRQ_LINES); qdev_prop_set_string(nvic, "cpu-type", ms->cpu_type); qdev_prop_set_bit(nvic, "enable-bitband", true); + qdev_connect_clock_in(nvic, "cpuclk", + qdev_get_clock_out(ssys_dev, "SYSCLK")); + /* This SoC does not connect the systick reference clock */ object_property_set_link(OBJECT(nvic), "memory", OBJECT(get_system_memory()), &error_abort); /* This will exit with an error if the user passed us a bad cpu_type */ sysbus_realize_and_unref(SYS_BUS_DEVICE(nvic), &error_fatal); + /* Now we can wire up the IRQ and MMIO of the system registers */ + sysbus_mmio_map(SYS_BUS_DEVICE(ssys_dev), 0, 0x400fe000); + sysbus_connect_irq(SYS_BUS_DEVICE(ssys_dev), 0, qdev_get_gpio_in(nvic, 28)); + if (board->dc1 & (1 << 16)) { dev = sysbus_create_varargs(TYPE_STELLARIS_ADC, 0x40038000, qdev_get_gpio_in(nvic, 14), @@ -1388,19 +1091,21 @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } for (i = 0; i < 4; i++) { if (board->dc2 & (0x10000 << i)) { - dev = sysbus_create_simple(TYPE_STELLARIS_GPTM, - 0x40030000 + i * 0x1000, - qdev_get_gpio_in(nvic, timer_irq[i])); + SysBusDevice *sbd; + + dev = qdev_new(TYPE_STELLARIS_GPTM); + sbd = SYS_BUS_DEVICE(dev); + qdev_connect_clock_in(dev, "clk", + qdev_get_clock_out(ssys_dev, "SYSCLK")); + sysbus_realize_and_unref(sbd, &error_fatal); + sysbus_mmio_map(sbd, 0, 0x40030000 + i * 0x1000); + sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(nvic, timer_irq[i])); /* TODO: This is incorrect, but we get away with it because the ADC output is only ever pulsed. */ qdev_connect_gpio_out(dev, 0, adc); } } - ssys_dev = stellaris_sys_init(0x400fe000, qdev_get_gpio_in(nvic, 28), - board, nd_table[0].macaddr.a); - - if (board->dc1 & (1 << 3)) { /* watchdog present */ dev = qdev_new(TYPE_LUMINARY_WATCHDOG); @@ -1642,22 +1347,6 @@ static const TypeInfo stellaris_i2c_info = { .class_init = stellaris_i2c_class_init, }; -static void stellaris_gptm_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->vmsd = &vmstate_stellaris_gptm; - dc->realize = stellaris_gptm_realize; -} - -static const TypeInfo stellaris_gptm_info = { - .name = TYPE_STELLARIS_GPTM, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(gptm_state), - .instance_init = stellaris_gptm_init, - .class_init = stellaris_gptm_class_init, -}; - static void stellaris_adc_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -1696,7 +1385,6 @@ static const TypeInfo stellaris_sys_info = { static void stellaris_register_types(void) { type_register_static(&stellaris_i2c_info); - type_register_static(&stellaris_gptm_info); type_register_static(&stellaris_adc_info); type_register_static(&stellaris_sys_info); } diff --git a/hw/arm/stm32f100_soc.c b/hw/arm/stm32f100_soc.c index 0c4a5c6645..f7b344ba9f 100644 --- a/hw/arm/stm32f100_soc.c +++ b/hw/arm/stm32f100_soc.c @@ -30,6 +30,7 @@ #include "exec/address-spaces.h" #include "hw/arm/stm32f100_soc.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "hw/misc/unimp.h" #include "sysemu/sysemu.h" @@ -57,6 +58,9 @@ static void stm32f100_soc_initfn(Object *obj) for (i = 0; i < STM_NUM_SPIS; i++) { object_initialize_child(obj, "spi[*]", &s->spi[i], TYPE_STM32F2XX_SPI); } + + s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); + s->refclk = qdev_init_clock_in(DEVICE(s), "refclk", NULL, NULL, 0); } static void stm32f100_soc_realize(DeviceState *dev_soc, Error **errp) @@ -67,31 +71,54 @@ static void stm32f100_soc_realize(DeviceState *dev_soc, Error **errp) int i; MemoryRegion *system_memory = get_system_memory(); - MemoryRegion *sram = g_new(MemoryRegion, 1); - MemoryRegion *flash = g_new(MemoryRegion, 1); - MemoryRegion *flash_alias = g_new(MemoryRegion, 1); + + /* + * We use s->refclk internally and only define it with qdev_init_clock_in() + * so it is correctly parented and not leaked on an init/deinit; it is not + * intended as an externally exposed clock. + */ + if (clock_has_source(s->refclk)) { + error_setg(errp, "refclk clock must not be wired up by the board code"); + return; + } + + if (!clock_has_source(s->sysclk)) { + error_setg(errp, "sysclk clock must be wired up by the board code"); + return; + } + + /* + * TODO: ideally we should model the SoC RCC and its ability to + * change the sysclk frequency and define different sysclk sources. + */ + + /* The refclk always runs at frequency HCLK / 8 */ + clock_set_mul_div(s->refclk, 8, 1); + clock_set_source(s->refclk, s->sysclk); /* * Init flash region * Flash starts at 0x08000000 and then is aliased to boot memory at 0x0 */ - memory_region_init_rom(flash, OBJECT(dev_soc), "STM32F100.flash", + memory_region_init_rom(&s->flash, OBJECT(dev_soc), "STM32F100.flash", FLASH_SIZE, &error_fatal); - memory_region_init_alias(flash_alias, OBJECT(dev_soc), - "STM32F100.flash.alias", flash, 0, FLASH_SIZE); - memory_region_add_subregion(system_memory, FLASH_BASE_ADDRESS, flash); - memory_region_add_subregion(system_memory, 0, flash_alias); + memory_region_init_alias(&s->flash_alias, OBJECT(dev_soc), + "STM32F100.flash.alias", &s->flash, 0, FLASH_SIZE); + memory_region_add_subregion(system_memory, FLASH_BASE_ADDRESS, &s->flash); + memory_region_add_subregion(system_memory, 0, &s->flash_alias); /* Init SRAM region */ - memory_region_init_ram(sram, NULL, "STM32F100.sram", SRAM_SIZE, + memory_region_init_ram(&s->sram, NULL, "STM32F100.sram", SRAM_SIZE, &error_fatal); - memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); + memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, &s->sram); /* Init ARMv7m */ armv7m = DEVICE(&s->armv7m); qdev_prop_set_uint32(armv7m, "num-irq", 61); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); + qdev_connect_clock_in(armv7m, "cpuclk", s->sysclk); + qdev_connect_clock_in(armv7m, "refclk", s->refclk); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(get_system_memory()), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { diff --git a/hw/arm/stm32f205_soc.c b/hw/arm/stm32f205_soc.c index 9cd41bf56d..c6b75a381d 100644 --- a/hw/arm/stm32f205_soc.c +++ b/hw/arm/stm32f205_soc.c @@ -29,6 +29,7 @@ #include "exec/address-spaces.h" #include "hw/arm/stm32f205_soc.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "sysemu/sysemu.h" /* At the moment only Timer 2 to 5 are modelled */ @@ -74,6 +75,9 @@ static void stm32f205_soc_initfn(Object *obj) for (i = 0; i < STM_NUM_SPIS; i++) { object_initialize_child(obj, "spi[*]", &s->spi[i], TYPE_STM32F2XX_SPI); } + + s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); + s->refclk = qdev_init_clock_in(DEVICE(s), "refclk", NULL, NULL, 0); } static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) @@ -84,26 +88,49 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) int i; MemoryRegion *system_memory = get_system_memory(); - MemoryRegion *sram = g_new(MemoryRegion, 1); - MemoryRegion *flash = g_new(MemoryRegion, 1); - MemoryRegion *flash_alias = g_new(MemoryRegion, 1); - memory_region_init_rom(flash, OBJECT(dev_soc), "STM32F205.flash", + /* + * We use s->refclk internally and only define it with qdev_init_clock_in() + * so it is correctly parented and not leaked on an init/deinit; it is not + * intended as an externally exposed clock. + */ + if (clock_has_source(s->refclk)) { + error_setg(errp, "refclk clock must not be wired up by the board code"); + return; + } + + if (!clock_has_source(s->sysclk)) { + error_setg(errp, "sysclk clock must be wired up by the board code"); + return; + } + + /* + * TODO: ideally we should model the SoC RCC and its ability to + * change the sysclk frequency and define different sysclk sources. + */ + + /* The refclk always runs at frequency HCLK / 8 */ + clock_set_mul_div(s->refclk, 8, 1); + clock_set_source(s->refclk, s->sysclk); + + memory_region_init_rom(&s->flash, OBJECT(dev_soc), "STM32F205.flash", FLASH_SIZE, &error_fatal); - memory_region_init_alias(flash_alias, OBJECT(dev_soc), - "STM32F205.flash.alias", flash, 0, FLASH_SIZE); + memory_region_init_alias(&s->flash_alias, OBJECT(dev_soc), + "STM32F205.flash.alias", &s->flash, 0, FLASH_SIZE); - memory_region_add_subregion(system_memory, FLASH_BASE_ADDRESS, flash); - memory_region_add_subregion(system_memory, 0, flash_alias); + memory_region_add_subregion(system_memory, FLASH_BASE_ADDRESS, &s->flash); + memory_region_add_subregion(system_memory, 0, &s->flash_alias); - memory_region_init_ram(sram, NULL, "STM32F205.sram", SRAM_SIZE, + memory_region_init_ram(&s->sram, NULL, "STM32F205.sram", SRAM_SIZE, &error_fatal); - memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); + memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, &s->sram); armv7m = DEVICE(&s->armv7m); qdev_prop_set_uint32(armv7m, "num-irq", 96); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); + qdev_connect_clock_in(armv7m, "cpuclk", s->sysclk); + qdev_connect_clock_in(armv7m, "refclk", s->refclk); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(get_system_memory()), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { diff --git a/hw/arm/stm32f405_soc.c b/hw/arm/stm32f405_soc.c index cb04c11198..0019b7f478 100644 --- a/hw/arm/stm32f405_soc.c +++ b/hw/arm/stm32f405_soc.c @@ -28,6 +28,7 @@ #include "exec/address-spaces.h" #include "sysemu/sysemu.h" #include "hw/arm/stm32f405_soc.h" +#include "hw/qdev-clock.h" #include "hw/misc/unimp.h" #define SYSCFG_ADD 0x40013800 @@ -80,6 +81,9 @@ static void stm32f405_soc_initfn(Object *obj) } object_initialize_child(obj, "exti", &s->exti, TYPE_STM32F4XX_EXTI); + + s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); + s->refclk = qdev_init_clock_in(DEVICE(s), "refclk", NULL, NULL, 0); } static void stm32f405_soc_realize(DeviceState *dev_soc, Error **errp) @@ -91,6 +95,30 @@ static void stm32f405_soc_realize(DeviceState *dev_soc, Error **errp) Error *err = NULL; int i; + /* + * We use s->refclk internally and only define it with qdev_init_clock_in() + * so it is correctly parented and not leaked on an init/deinit; it is not + * intended as an externally exposed clock. + */ + if (clock_has_source(s->refclk)) { + error_setg(errp, "refclk clock must not be wired up by the board code"); + return; + } + + if (!clock_has_source(s->sysclk)) { + error_setg(errp, "sysclk clock must be wired up by the board code"); + return; + } + + /* + * TODO: ideally we should model the SoC RCC and its ability to + * change the sysclk frequency and define different sysclk sources. + */ + + /* The refclk always runs at frequency HCLK / 8 */ + clock_set_mul_div(s->refclk, 8, 1); + clock_set_source(s->refclk, s->sysclk); + memory_region_init_rom(&s->flash, OBJECT(dev_soc), "STM32F405.flash", FLASH_SIZE, &err); if (err != NULL) { @@ -116,6 +144,8 @@ static void stm32f405_soc_realize(DeviceState *dev_soc, Error **errp) qdev_prop_set_uint32(armv7m, "num-irq", 96); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); + qdev_connect_clock_in(armv7m, "cpuclk", s->sysclk); + qdev_connect_clock_in(armv7m, "refclk", s->refclk); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(system_memory), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { diff --git a/hw/arm/stm32vldiscovery.c b/hw/arm/stm32vldiscovery.c index 7e8191ebf5..04036da3ee 100644 --- a/hw/arm/stm32vldiscovery.c +++ b/hw/arm/stm32vldiscovery.c @@ -27,6 +27,7 @@ #include "qapi/error.h" #include "hw/boards.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "qemu/error-report.h" #include "hw/arm/stm32f100_soc.h" #include "hw/arm/boot.h" @@ -39,16 +40,15 @@ static void stm32vldiscovery_init(MachineState *machine) { DeviceState *dev; + Clock *sysclk; - /* - * TODO: ideally we would model the SoC RCC and let it handle - * system_clock_scale, including its ability to define different - * possible SYSCLK sources. - */ - system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; + /* This clock doesn't need migration because it is fixed-frequency */ + sysclk = clock_new(OBJECT(machine), "SYSCLK"); + clock_set_hz(sysclk, SYSCLK_FRQ); dev = qdev_new(TYPE_STM32F100_SOC); qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m3")); + qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); armv7m_load_kernel(ARM_CPU(first_cpu), @@ -63,4 +63,3 @@ static void stm32vldiscovery_machine_init(MachineClass *mc) } DEFINE_MACHINE("stm32vldiscovery", stm32vldiscovery_machine_init) - diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 86c8a4ca3d..73e9c6bb7c 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -200,6 +200,7 @@ static const char *valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a53"), ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), + ARM_CPU_TYPE_NAME("a64fx"), ARM_CPU_TYPE_NAME("host"), ARM_CPU_TYPE_NAME("max"), }; @@ -2783,10 +2784,17 @@ static void machvirt_machine_init(void) } type_init(machvirt_machine_init); +static void virt_machine_6_2_options(MachineClass *mc) +{ +} +DEFINE_VIRT_MACHINE_AS_LATEST(6, 2) + static void virt_machine_6_1_options(MachineClass *mc) { + virt_machine_6_2_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); } -DEFINE_VIRT_MACHINE_AS_LATEST(6, 1) +DEFINE_VIRT_MACHINE(6, 1) static void virt_machine_6_0_options(MachineClass *mc) { diff --git a/hw/char/Kconfig b/hw/char/Kconfig index 2e4f620b13..6b6cf2fc1d 100644 --- a/hw/char/Kconfig +++ b/hw/char/Kconfig @@ -68,3 +68,6 @@ config SIFIVE_UART config GOLDFISH_TTY bool + +config SHAKTI_UART + bool diff --git a/hw/char/meson.build b/hw/char/meson.build index 8361d0ab28..7b594f51b8 100644 --- a/hw/char/meson.build +++ b/hw/char/meson.build @@ -16,7 +16,7 @@ softmmu_ss.add(when: 'CONFIG_SERIAL', if_true: files('serial.c')) softmmu_ss.add(when: 'CONFIG_SERIAL_ISA', if_true: files('serial-isa.c')) softmmu_ss.add(when: 'CONFIG_SERIAL_PCI', if_true: files('serial-pci.c')) softmmu_ss.add(when: 'CONFIG_SERIAL_PCI_MULTI', if_true: files('serial-pci-multi.c')) -softmmu_ss.add(when: 'CONFIG_SHAKTI', if_true: files('shakti_uart.c')) +softmmu_ss.add(when: 'CONFIG_SHAKTI_UART', if_true: files('shakti_uart.c')) softmmu_ss.add(when: 'CONFIG_VIRTIO_SERIAL', if_true: files('virtio-console.c')) softmmu_ss.add(when: 'CONFIG_XEN', if_true: files('xen_console.c')) softmmu_ss.add(when: 'CONFIG_XILINX', if_true: files('xilinx_uartlite.c')) diff --git a/hw/core/clock-vmstate.c b/hw/core/clock-vmstate.c index 260b13fc2c..9d9174ffbd 100644 --- a/hw/core/clock-vmstate.c +++ b/hw/core/clock-vmstate.c @@ -14,12 +14,50 @@ #include "migration/vmstate.h" #include "hw/clock.h" +static bool muldiv_needed(void *opaque) +{ + Clock *clk = opaque; + + return clk->multiplier != 1 || clk->divider != 1; +} + +static int clock_pre_load(void *opaque) +{ + Clock *clk = opaque; + /* + * The initial out-of-reset settings of the Clock might have been + * configured by the device to be different from what we set + * in clock_initfn(), so we must here set the default values to + * be used if they are not in the inbound migration state. + */ + clk->multiplier = 1; + clk->divider = 1; + + return 0; +} + +const VMStateDescription vmstate_muldiv = { + .name = "clock/muldiv", + .version_id = 1, + .minimum_version_id = 1, + .needed = muldiv_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT32(multiplier, Clock), + VMSTATE_UINT32(divider, Clock), + }, +}; + const VMStateDescription vmstate_clock = { .name = "clock", .version_id = 0, .minimum_version_id = 0, + .pre_load = clock_pre_load, .fields = (VMStateField[]) { VMSTATE_UINT64(period, Clock), VMSTATE_END_OF_LIST() - } + }, + .subsections = (const VMStateDescription*[]) { + &vmstate_muldiv, + NULL + }, }; diff --git a/hw/core/clock.c b/hw/core/clock.c index fc5a99683f..916875e07a 100644 --- a/hw/core/clock.c +++ b/hw/core/clock.c @@ -64,6 +64,15 @@ bool clock_set(Clock *clk, uint64_t period) return true; } +static uint64_t clock_get_child_period(Clock *clk) +{ + /* + * Return the period to be used for child clocks, which is the parent + * clock period adjusted for for multiplier and divider effects. + */ + return muldiv64(clk->period, clk->multiplier, clk->divider); +} + static void clock_call_callback(Clock *clk, ClockEvent event) { /* @@ -78,15 +87,16 @@ static void clock_call_callback(Clock *clk, ClockEvent event) static void clock_propagate_period(Clock *clk, bool call_callbacks) { Clock *child; + uint64_t child_period = clock_get_child_period(clk); QLIST_FOREACH(child, &clk->children, sibling) { - if (child->period != clk->period) { + if (child->period != child_period) { if (call_callbacks) { clock_call_callback(child, ClockPreUpdate); } - child->period = clk->period; + child->period = child_period; trace_clock_update(CLOCK_PATH(child), CLOCK_PATH(clk), - CLOCK_PERIOD_TO_HZ(clk->period), + CLOCK_PERIOD_TO_HZ(child->period), call_callbacks); if (call_callbacks) { clock_call_callback(child, ClockUpdate); @@ -110,7 +120,7 @@ void clock_set_source(Clock *clk, Clock *src) trace_clock_set_source(CLOCK_PATH(clk), CLOCK_PATH(src)); - clk->period = src->period; + clk->period = clock_get_child_period(src); QLIST_INSERT_HEAD(&src->children, clk, sibling); clk->source = src; clock_propagate_period(clk, false); @@ -133,10 +143,23 @@ char *clock_display_freq(Clock *clk) return freq_to_str(clock_get_hz(clk)); } +void clock_set_mul_div(Clock *clk, uint32_t multiplier, uint32_t divider) +{ + assert(divider != 0); + + trace_clock_set_mul_div(CLOCK_PATH(clk), clk->multiplier, multiplier, + clk->divider, divider); + clk->multiplier = multiplier; + clk->divider = divider; +} + static void clock_initfn(Object *obj) { Clock *clk = CLOCK(obj); + clk->multiplier = 1; + clk->divider = 1; + QLIST_INIT(&clk->children); } diff --git a/hw/core/machine.c b/hw/core/machine.c index 54e040587d..067f42b528 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -37,6 +37,9 @@ #include "hw/virtio/virtio.h" #include "hw/virtio/virtio-pci.h" +GlobalProperty hw_compat_6_1[] = {}; +const size_t hw_compat_6_1_len = G_N_ELEMENTS(hw_compat_6_1); + GlobalProperty hw_compat_6_0[] = { { "gpex-pcihost", "allow-unmapped-accesses", "false" }, { "i8042", "extended-state", "false"}, diff --git a/hw/core/register.c b/hw/core/register.c index d6f8c20816..95b0150c0a 100644 --- a/hw/core/register.c +++ b/hw/core/register.c @@ -300,6 +300,18 @@ RegisterInfoArray *register_init_block32(DeviceState *owner, data, ops, debug_enabled, memory_size, 32); } +RegisterInfoArray *register_init_block64(DeviceState *owner, + const RegisterAccessInfo *rae, + int num, RegisterInfo *ri, + uint64_t *data, + const MemoryRegionOps *ops, + bool debug_enabled, + uint64_t memory_size) +{ + return register_init_block(owner, rae, num, ri, (void *) + data, ops, debug_enabled, memory_size, 64); +} + void register_finalize_block(RegisterInfoArray *r_array) { object_unparent(OBJECT(&r_array->mem)); diff --git a/hw/core/trace-events b/hw/core/trace-events index 360ddeb2c8..9b3ecce3b2 100644 --- a/hw/core/trace-events +++ b/hw/core/trace-events @@ -34,3 +34,4 @@ clock_disconnect(const char *clk) "'%s'" clock_set(const char *clk, uint64_t old, uint64_t new) "'%s', %"PRIu64"Hz->%"PRIu64"Hz" clock_propagate(const char *clk) "'%s'" clock_update(const char *clk, const char *src, uint64_t hz, int cb) "'%s', src='%s', val=%"PRIu64"Hz cb=%d" +clock_set_mul_div(const char *clk, uint32_t oldmul, uint32_t mul, uint32_t olddiv, uint32_t div) "'%s', mul: %u -> %u, div: %u -> %u" diff --git a/hw/display/artist.c b/hw/display/artist.c index aa7bd594aa..21b7fd1b44 100644 --- a/hw/display/artist.c +++ b/hw/display/artist.c @@ -1170,8 +1170,8 @@ static void artist_vram_write(void *opaque, hwaddr addr, uint64_t val, } buf = vram_write_buffer(s); - posy = ADDR_TO_Y(addr); - posx = ADDR_TO_X(addr); + posy = ADDR_TO_Y(addr >> 2); + posx = ADDR_TO_X(addr >> 2); if (!buf->size) { return; @@ -1232,8 +1232,8 @@ static uint64_t artist_vram_read(void *opaque, hwaddr addr, unsigned size) return 0; } - posy = ADDR_TO_Y(addr); - posx = ADDR_TO_X(addr); + posy = ADDR_TO_Y(addr >> 2); + posx = ADDR_TO_X(addr >> 2); if (posy > buf->height || posx > buf->width) { return 0; diff --git a/hw/display/meson.build b/hw/display/meson.build index 1e6b707d3c..861c43ff98 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -56,7 +56,8 @@ if config_all_devices.has_key('CONFIG_VIRTIO_GPU') virtio_gpu_ss = ss.source_set() virtio_gpu_ss.add(when: 'CONFIG_VIRTIO_GPU', if_true: [files('virtio-gpu-base.c', 'virtio-gpu.c'), pixman]) - virtio_gpu_ss.add(when: 'CONFIG_LINUX', if_true: files('virtio-gpu-udmabuf.c')) + virtio_gpu_ss.add(when: 'CONFIG_LINUX', if_true: files('virtio-gpu-udmabuf.c'), + if_false: files('virtio-gpu-udmabuf-stubs.c')) virtio_gpu_ss.add(when: 'CONFIG_VHOST_USER_GPU', if_true: files('vhost-user-gpu.c')) hw_display_modules += {'virtio-gpu': virtio_gpu_ss} diff --git a/hw/display/vga-isa.c b/hw/display/vga-isa.c index 90851e730b..8cea84f2be 100644 --- a/hw/display/vga-isa.c +++ b/hw/display/vga-isa.c @@ -33,6 +33,7 @@ #include "hw/loader.h" #include "hw/qdev-properties.h" #include "qom/object.h" +#include "qapi/error.h" #define TYPE_ISA_VGA "isa-vga" OBJECT_DECLARE_SIMPLE_TYPE(ISAVGAState, ISA_VGA) @@ -61,6 +62,15 @@ static void vga_isa_realizefn(DeviceState *dev, Error **errp) MemoryRegion *vga_io_memory; const MemoryRegionPortio *vga_ports, *vbe_ports; + /* + * make sure this device is not being added twice, if so + * exit without crashing qemu + */ + if (object_resolve_path_type("", TYPE_ISA_VGA, NULL)) { + error_setg(errp, "at most one %s device is permitted", TYPE_ISA_VGA); + return; + } + s->global_vmstate = true; vga_common_init(s, OBJECT(dev)); s->legacy_address_space = isa_address_space(isadev); diff --git a/stubs/virtio-gpu-udmabuf.c b/hw/display/virtio-gpu-udmabuf-stubs.c index 81f661441a..81f661441a 100644 --- a/stubs/virtio-gpu-udmabuf.c +++ b/hw/display/virtio-gpu-udmabuf-stubs.c diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c index 990e71fd40..72da5bf500 100644 --- a/hw/display/virtio-gpu.c +++ b/hw/display/virtio-gpu.c @@ -362,7 +362,7 @@ static void virtio_gpu_resource_create_blob(VirtIOGPU *g, ret = virtio_gpu_create_mapping_iov(g, cblob.nr_entries, sizeof(cblob), cmd, &res->addrs, &res->iov, &res->iov_cnt); - if (ret != 0 || res->iov) { + if (ret != 0) { cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; g_free(res); return; diff --git a/hw/display/xlnx_dp.c b/hw/display/xlnx_dp.c index 2bb7a5441a..9bb781e312 100644 --- a/hw/display/xlnx_dp.c +++ b/hw/display/xlnx_dp.c @@ -714,7 +714,11 @@ static uint64_t xlnx_dp_read(void *opaque, hwaddr offset, unsigned size) break; default: assert(offset <= (0x3AC >> 2)); - ret = s->core_registers[offset]; + if (offset == (0x3A8 >> 2) || offset == (0x3AC >> 2)) { + ret = s->core_registers[DP_INT_MASK]; + } else { + ret = s->core_registers[offset]; + } break; } diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 102b223946..1276bfeee4 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -93,6 +93,9 @@ #include "trace.h" #include CONFIG_DEVICES +GlobalProperty pc_compat_6_1[] = {}; +const size_t pc_compat_6_1_len = G_N_ELEMENTS(pc_compat_6_1); + GlobalProperty pc_compat_6_0[] = { { "qemu64" "-" TYPE_X86_CPU, "family", "6" }, { "qemu64" "-" TYPE_X86_CPU, "model", "6" }, diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 1bc30167ac..c5da7739ce 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -412,7 +412,7 @@ static void pc_i440fx_machine_options(MachineClass *m) machine_class_allow_dynamic_sysbus_dev(m, TYPE_VMBUS_BRIDGE); } -static void pc_i440fx_6_1_machine_options(MachineClass *m) +static void pc_i440fx_6_2_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_i440fx_machine_options(m); @@ -421,6 +421,18 @@ static void pc_i440fx_6_1_machine_options(MachineClass *m) pcmc->default_cpu_version = 1; } +DEFINE_I440FX_MACHINE(v6_2, "pc-i440fx-6.2", NULL, + pc_i440fx_6_2_machine_options); + +static void pc_i440fx_6_1_machine_options(MachineClass *m) +{ + pc_i440fx_6_2_machine_options(m); + m->alias = NULL; + m->is_default = false; + compat_props_add(m->compat_props, hw_compat_6_1, hw_compat_6_1_len); + compat_props_add(m->compat_props, pc_compat_6_1, pc_compat_6_1_len); +} + DEFINE_I440FX_MACHINE(v6_1, "pc-i440fx-6.1", NULL, pc_i440fx_6_1_machine_options); diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index eeb0b185b1..565fadce54 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -354,7 +354,7 @@ static void pc_q35_machine_options(MachineClass *m) m->max_cpus = 288; } -static void pc_q35_6_1_machine_options(MachineClass *m) +static void pc_q35_6_2_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_q35_machine_options(m); @@ -362,6 +362,17 @@ static void pc_q35_6_1_machine_options(MachineClass *m) pcmc->default_cpu_version = 1; } +DEFINE_Q35_MACHINE(v6_2, "pc-q35-6.2", NULL, + pc_q35_6_2_machine_options); + +static void pc_q35_6_1_machine_options(MachineClass *m) +{ + pc_q35_6_2_machine_options(m); + m->alias = NULL; + compat_props_add(m->compat_props, hw_compat_6_1, hw_compat_6_1_len); + compat_props_add(m->compat_props, pc_compat_6_1, pc_compat_6_1_len); +} + DEFINE_Q35_MACHINE(v6_1, "pc-q35-6.1", NULL, pc_q35_6_1_machine_options); diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c index b65f56f903..5beb7c4235 100644 --- a/hw/intc/arm_gicv3_dist.c +++ b/hw/intc/arm_gicv3_dist.c @@ -262,8 +262,21 @@ static void gicd_write_irouter(GICv3State *s, MemTxAttrs attrs, int irq, gicv3_update(s, irq, 1); } -static MemTxResult gicd_readb(GICv3State *s, hwaddr offset, - uint64_t *data, MemTxAttrs attrs) +/** + * gicd_readb + * gicd_readw + * gicd_readl + * gicd_readq + * gicd_writeb + * gicd_writew + * gicd_writel + * gicd_writeq + * + * Return %true if the operation succeeded, %false otherwise. + */ + +static bool gicd_readb(GICv3State *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) { /* Most GICv3 distributor registers do not support byte accesses. */ switch (offset) { @@ -273,17 +286,17 @@ static MemTxResult gicd_readb(GICv3State *s, hwaddr offset, /* This GIC implementation always has affinity routing enabled, * so these registers are all RAZ/WI. */ - return MEMTX_OK; + return true; case GICD_IPRIORITYR ... GICD_IPRIORITYR + 0x3ff: *data = gicd_read_ipriorityr(s, attrs, offset - GICD_IPRIORITYR); - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_writeb(GICv3State *s, hwaddr offset, - uint64_t value, MemTxAttrs attrs) +static bool gicd_writeb(GICv3State *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) { /* Most GICv3 distributor registers do not support byte accesses. */ switch (offset) { @@ -293,25 +306,25 @@ static MemTxResult gicd_writeb(GICv3State *s, hwaddr offset, /* This GIC implementation always has affinity routing enabled, * so these registers are all RAZ/WI. */ - return MEMTX_OK; + return true; case GICD_IPRIORITYR ... GICD_IPRIORITYR + 0x3ff: { int irq = offset - GICD_IPRIORITYR; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } gicd_write_ipriorityr(s, attrs, irq, value); gicv3_update(s, irq, 1); - return MEMTX_OK; + return true; } default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_readw(GICv3State *s, hwaddr offset, - uint64_t *data, MemTxAttrs attrs) +static bool gicd_readw(GICv3State *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) { /* Only GICD_SETSPI_NSR, GICD_CLRSPI_NSR, GICD_SETSPI_SR and GICD_SETSPI_NSR * support 16 bit accesses, and those registers are all part of the @@ -319,11 +332,11 @@ static MemTxResult gicd_readw(GICv3State *s, hwaddr offset, * implement (ie for us GICD_TYPER.MBIS == 0), so for us they are * reserved. */ - return MEMTX_ERROR; + return false; } -static MemTxResult gicd_writew(GICv3State *s, hwaddr offset, - uint64_t value, MemTxAttrs attrs) +static bool gicd_writew(GICv3State *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) { /* Only GICD_SETSPI_NSR, GICD_CLRSPI_NSR, GICD_SETSPI_SR and GICD_SETSPI_NSR * support 16 bit accesses, and those registers are all part of the @@ -331,11 +344,11 @@ static MemTxResult gicd_writew(GICv3State *s, hwaddr offset, * implement (ie for us GICD_TYPER.MBIS == 0), so for us they are * reserved. */ - return MEMTX_ERROR; + return false; } -static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, - uint64_t *data, MemTxAttrs attrs) +static bool gicd_readl(GICv3State *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) { /* Almost all GICv3 distributor registers are 32-bit. * Note that WO registers must return an UNKNOWN value on reads, @@ -363,7 +376,7 @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, } else { *data = s->gicd_ctlr; } - return MEMTX_OK; + return true; case GICD_TYPER: { /* For this implementation: @@ -387,61 +400,61 @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, *data = (1 << 25) | (1 << 24) | (sec_extn << 10) | (0xf << 19) | itlinesnumber; - return MEMTX_OK; + return true; } case GICD_IIDR: /* We claim to be an ARM r0p0 with a zero ProductID. * This is the same as an r0p0 GIC-500. */ *data = gicv3_iidr(); - return MEMTX_OK; + return true; case GICD_STATUSR: /* RAZ/WI for us (this is an optional register and our implementation * does not track RO/WO/reserved violations to report them to the guest) */ *data = 0; - return MEMTX_OK; + return true; case GICD_IGROUPR ... GICD_IGROUPR + 0x7f: { int irq; if (!attrs.secure && !(s->gicd_ctlr & GICD_CTLR_DS)) { *data = 0; - return MEMTX_OK; + return true; } /* RAZ/WI for SGIs, PPIs, unimplemented irqs */ irq = (offset - GICD_IGROUPR) * 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { *data = 0; - return MEMTX_OK; + return true; } *data = *gic_bmp_ptr32(s->group, irq); - return MEMTX_OK; + return true; } case GICD_ISENABLER ... GICD_ISENABLER + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->enabled, NULL, offset - GICD_ISENABLER); - return MEMTX_OK; + return true; case GICD_ICENABLER ... GICD_ICENABLER + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->enabled, NULL, offset - GICD_ICENABLER); - return MEMTX_OK; + return true; case GICD_ISPENDR ... GICD_ISPENDR + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->pending, mask_nsacr_ge1, offset - GICD_ISPENDR); - return MEMTX_OK; + return true; case GICD_ICPENDR ... GICD_ICPENDR + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->pending, mask_nsacr_ge2, offset - GICD_ICPENDR); - return MEMTX_OK; + return true; case GICD_ISACTIVER ... GICD_ISACTIVER + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->active, mask_nsacr_ge2, offset - GICD_ISACTIVER); - return MEMTX_OK; + return true; case GICD_ICACTIVER ... GICD_ICACTIVER + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->active, mask_nsacr_ge2, offset - GICD_ICACTIVER); - return MEMTX_OK; + return true; case GICD_IPRIORITYR ... GICD_IPRIORITYR + 0x3ff: { int i, irq = offset - GICD_IPRIORITYR; @@ -452,12 +465,12 @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, value |= gicd_read_ipriorityr(s, attrs, i); } *data = value; - return MEMTX_OK; + return true; } case GICD_ITARGETSR ... GICD_ITARGETSR + 0x3ff: /* RAZ/WI since affinity routing is always enabled */ *data = 0; - return MEMTX_OK; + return true; case GICD_ICFGR ... GICD_ICFGR + 0xff: { /* Here only the even bits are used; odd bits are RES0 */ @@ -466,7 +479,7 @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, if (irq < GIC_INTERNAL || irq >= s->num_irq) { *data = 0; - return MEMTX_OK; + return true; } /* Since our edge_trigger bitmap is one bit per irq, we only need @@ -478,7 +491,7 @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, value = extract32(value, (irq & 0x1f) ? 16 : 0, 16); value = half_shuffle32(value) << 1; *data = value; - return MEMTX_OK; + return true; } case GICD_IGRPMODR ... GICD_IGRPMODR + 0xff: { @@ -489,16 +502,16 @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, * security enabled and this is an NS access */ *data = 0; - return MEMTX_OK; + return true; } /* RAZ/WI for SGIs, PPIs, unimplemented irqs */ irq = (offset - GICD_IGRPMODR) * 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { *data = 0; - return MEMTX_OK; + return true; } *data = *gic_bmp_ptr32(s->grpmod, irq); - return MEMTX_OK; + return true; } case GICD_NSACR ... GICD_NSACR + 0xff: { @@ -507,7 +520,7 @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, if (irq < GIC_INTERNAL || irq >= s->num_irq) { *data = 0; - return MEMTX_OK; + return true; } if ((s->gicd_ctlr & GICD_CTLR_DS) || !attrs.secure) { @@ -515,17 +528,17 @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, * security enabled and this is an NS access */ *data = 0; - return MEMTX_OK; + return true; } *data = s->gicd_nsacr[irq / 16]; - return MEMTX_OK; + return true; } case GICD_CPENDSGIR ... GICD_CPENDSGIR + 0xf: case GICD_SPENDSGIR ... GICD_SPENDSGIR + 0xf: /* RAZ/WI since affinity routing is always enabled */ *data = 0; - return MEMTX_OK; + return true; case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: { uint64_t r; @@ -537,26 +550,26 @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, } else { *data = (uint32_t)r; } - return MEMTX_OK; + return true; } case GICD_IDREGS ... GICD_IDREGS + 0x2f: /* ID registers */ *data = gicv3_idreg(offset - GICD_IDREGS); - return MEMTX_OK; + return true; case GICD_SGIR: /* WO registers, return unknown value */ qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest read from WO register at offset " TARGET_FMT_plx "\n", __func__, offset); *data = 0; - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, - uint64_t value, MemTxAttrs attrs) +static bool gicd_writel(GICv3State *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) { /* Almost all GICv3 distributor registers are 32-bit. Note that * RO registers must ignore writes, not abort. @@ -600,68 +613,68 @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, s->gicd_ctlr &= ~(GICD_CTLR_EN_GRP1S | GICD_CTLR_ARE_NS); } gicv3_full_update(s); - return MEMTX_OK; + return true; } case GICD_STATUSR: /* RAZ/WI for our implementation */ - return MEMTX_OK; + return true; case GICD_IGROUPR ... GICD_IGROUPR + 0x7f: { int irq; if (!attrs.secure && !(s->gicd_ctlr & GICD_CTLR_DS)) { - return MEMTX_OK; + return true; } /* RAZ/WI for SGIs, PPIs, unimplemented irqs */ irq = (offset - GICD_IGROUPR) * 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } *gic_bmp_ptr32(s->group, irq) = value; gicv3_update(s, irq, 32); - return MEMTX_OK; + return true; } case GICD_ISENABLER ... GICD_ISENABLER + 0x7f: gicd_write_set_bitmap_reg(s, attrs, s->enabled, NULL, offset - GICD_ISENABLER, value); - return MEMTX_OK; + return true; case GICD_ICENABLER ... GICD_ICENABLER + 0x7f: gicd_write_clear_bitmap_reg(s, attrs, s->enabled, NULL, offset - GICD_ICENABLER, value); - return MEMTX_OK; + return true; case GICD_ISPENDR ... GICD_ISPENDR + 0x7f: gicd_write_set_bitmap_reg(s, attrs, s->pending, mask_nsacr_ge1, offset - GICD_ISPENDR, value); - return MEMTX_OK; + return true; case GICD_ICPENDR ... GICD_ICPENDR + 0x7f: gicd_write_clear_bitmap_reg(s, attrs, s->pending, mask_nsacr_ge2, offset - GICD_ICPENDR, value); - return MEMTX_OK; + return true; case GICD_ISACTIVER ... GICD_ISACTIVER + 0x7f: gicd_write_set_bitmap_reg(s, attrs, s->active, NULL, offset - GICD_ISACTIVER, value); - return MEMTX_OK; + return true; case GICD_ICACTIVER ... GICD_ICACTIVER + 0x7f: gicd_write_clear_bitmap_reg(s, attrs, s->active, NULL, offset - GICD_ICACTIVER, value); - return MEMTX_OK; + return true; case GICD_IPRIORITYR ... GICD_IPRIORITYR + 0x3ff: { int i, irq = offset - GICD_IPRIORITYR; if (irq < GIC_INTERNAL || irq + 3 >= s->num_irq) { - return MEMTX_OK; + return true; } for (i = irq; i < irq + 4; i++, value >>= 8) { gicd_write_ipriorityr(s, attrs, i, value); } gicv3_update(s, irq, 4); - return MEMTX_OK; + return true; } case GICD_ITARGETSR ... GICD_ITARGETSR + 0x3ff: /* RAZ/WI since affinity routing is always enabled */ - return MEMTX_OK; + return true; case GICD_ICFGR ... GICD_ICFGR + 0xff: { /* Here only the odd bits are used; even bits are RES0 */ @@ -669,7 +682,7 @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, uint32_t mask, oldval; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } /* Since our edge_trigger bitmap is one bit per irq, our input @@ -687,7 +700,7 @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, oldval = *gic_bmp_ptr32(s->edge_trigger, (irq & ~0x1f)); value = (oldval & ~mask) | (value & mask); *gic_bmp_ptr32(s->edge_trigger, irq & ~0x1f) = value; - return MEMTX_OK; + return true; } case GICD_IGRPMODR ... GICD_IGRPMODR + 0xff: { @@ -697,16 +710,16 @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, /* RAZ/WI if security disabled, or if * security enabled and this is an NS access */ - return MEMTX_OK; + return true; } /* RAZ/WI for SGIs, PPIs, unimplemented irqs */ irq = (offset - GICD_IGRPMODR) * 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } *gic_bmp_ptr32(s->grpmod, irq) = value; gicv3_update(s, irq, 32); - return MEMTX_OK; + return true; } case GICD_NSACR ... GICD_NSACR + 0xff: { @@ -714,41 +727,41 @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, int irq = (offset - GICD_NSACR) * 4; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } if ((s->gicd_ctlr & GICD_CTLR_DS) || !attrs.secure) { /* RAZ/WI if security disabled, or if * security enabled and this is an NS access */ - return MEMTX_OK; + return true; } s->gicd_nsacr[irq / 16] = value; /* No update required as this only affects access permission checks */ - return MEMTX_OK; + return true; } case GICD_SGIR: /* RES0 if affinity routing is enabled */ - return MEMTX_OK; + return true; case GICD_CPENDSGIR ... GICD_CPENDSGIR + 0xf: case GICD_SPENDSGIR ... GICD_SPENDSGIR + 0xf: /* RAZ/WI since affinity routing is always enabled */ - return MEMTX_OK; + return true; case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: { uint64_t r; int irq = (offset - GICD_IROUTER) / 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } /* Write half of the 64-bit register */ r = gicd_read_irouter(s, attrs, irq); r = deposit64(r, (offset & 7) ? 32 : 0, 32, value); gicd_write_irouter(s, attrs, irq, r); - return MEMTX_OK; + return true; } case GICD_IDREGS ... GICD_IDREGS + 0x2f: case GICD_TYPER: @@ -757,14 +770,14 @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest write to RO register at offset " TARGET_FMT_plx "\n", __func__, offset); - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_writell(GICv3State *s, hwaddr offset, - uint64_t value, MemTxAttrs attrs) +static bool gicd_writeq(GICv3State *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) { /* Our only 64-bit registers are GICD_IROUTER<n> */ int irq; @@ -773,14 +786,14 @@ static MemTxResult gicd_writell(GICv3State *s, hwaddr offset, case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: irq = (offset - GICD_IROUTER) / 8; gicd_write_irouter(s, attrs, irq, value); - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_readll(GICv3State *s, hwaddr offset, - uint64_t *data, MemTxAttrs attrs) +static bool gicd_readq(GICv3State *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) { /* Our only 64-bit registers are GICD_IROUTER<n> */ int irq; @@ -789,9 +802,9 @@ static MemTxResult gicd_readll(GICv3State *s, hwaddr offset, case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: irq = (offset - GICD_IROUTER) / 8; *data = gicd_read_irouter(s, attrs, irq); - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } @@ -799,7 +812,7 @@ MemTxResult gicv3_dist_read(void *opaque, hwaddr offset, uint64_t *data, unsigned size, MemTxAttrs attrs) { GICv3State *s = (GICv3State *)opaque; - MemTxResult r; + bool r; switch (size) { case 1: @@ -812,14 +825,14 @@ MemTxResult gicv3_dist_read(void *opaque, hwaddr offset, uint64_t *data, r = gicd_readl(s, offset, data, attrs); break; case 8: - r = gicd_readll(s, offset, data, attrs); + r = gicd_readq(s, offset, data, attrs); break; default: - r = MEMTX_ERROR; + r = false; break; } - if (r == MEMTX_ERROR) { + if (!r) { qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest read at offset " TARGET_FMT_plx "size %u\n", __func__, offset, size); @@ -829,19 +842,18 @@ MemTxResult gicv3_dist_read(void *opaque, hwaddr offset, uint64_t *data, * trigger the guest-error logging but don't return it to * the caller, or we'll cause a spurious guest data abort. */ - r = MEMTX_OK; *data = 0; } else { trace_gicv3_dist_read(offset, *data, size, attrs.secure); } - return r; + return MEMTX_OK; } MemTxResult gicv3_dist_write(void *opaque, hwaddr offset, uint64_t data, unsigned size, MemTxAttrs attrs) { GICv3State *s = (GICv3State *)opaque; - MemTxResult r; + bool r; switch (size) { case 1: @@ -854,14 +866,14 @@ MemTxResult gicv3_dist_write(void *opaque, hwaddr offset, uint64_t data, r = gicd_writel(s, offset, data, attrs); break; case 8: - r = gicd_writell(s, offset, data, attrs); + r = gicd_writeq(s, offset, data, attrs); break; default: - r = MEMTX_ERROR; + r = false; break; } - if (r == MEMTX_ERROR) { + if (!r) { qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest write at offset " TARGET_FMT_plx "size %u\n", __func__, offset, size); @@ -871,11 +883,10 @@ MemTxResult gicv3_dist_write(void *opaque, hwaddr offset, uint64_t data, * trigger the guest-error logging but don't return it to * the caller, or we'll cause a spurious guest data abort. */ - r = MEMTX_OK; } else { trace_gicv3_dist_write(offset, data, size, attrs.secure); } - return r; + return MEMTX_OK; } void gicv3_dist_set_irq(GICv3State *s, int irq, int level) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index 1e7ddcb94c..13df002ce4 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -2470,172 +2470,6 @@ static const MemoryRegionOps nvic_sysreg_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static MemTxResult nvic_sysreg_ns_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size, - MemTxAttrs attrs) -{ - MemoryRegion *mr = opaque; - - if (attrs.secure) { - /* S accesses to the alias act like NS accesses to the real region */ - attrs.secure = 0; - return memory_region_dispatch_write(mr, addr, value, - size_memop(size) | MO_TE, attrs); - } else { - /* NS attrs are RAZ/WI for privileged, and BusFault for user */ - if (attrs.user) { - return MEMTX_ERROR; - } - return MEMTX_OK; - } -} - -static MemTxResult nvic_sysreg_ns_read(void *opaque, hwaddr addr, - uint64_t *data, unsigned size, - MemTxAttrs attrs) -{ - MemoryRegion *mr = opaque; - - if (attrs.secure) { - /* S accesses to the alias act like NS accesses to the real region */ - attrs.secure = 0; - return memory_region_dispatch_read(mr, addr, data, - size_memop(size) | MO_TE, attrs); - } else { - /* NS attrs are RAZ/WI for privileged, and BusFault for user */ - if (attrs.user) { - return MEMTX_ERROR; - } - *data = 0; - return MEMTX_OK; - } -} - -static const MemoryRegionOps nvic_sysreg_ns_ops = { - .read_with_attrs = nvic_sysreg_ns_read, - .write_with_attrs = nvic_sysreg_ns_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static MemTxResult nvic_systick_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size, - MemTxAttrs attrs) -{ - NVICState *s = opaque; - MemoryRegion *mr; - - /* Direct the access to the correct systick */ - mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0); - return memory_region_dispatch_write(mr, addr, value, - size_memop(size) | MO_TE, attrs); -} - -static MemTxResult nvic_systick_read(void *opaque, hwaddr addr, - uint64_t *data, unsigned size, - MemTxAttrs attrs) -{ - NVICState *s = opaque; - MemoryRegion *mr; - - /* Direct the access to the correct systick */ - mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0); - return memory_region_dispatch_read(mr, addr, data, size_memop(size) | MO_TE, - attrs); -} - -static const MemoryRegionOps nvic_systick_ops = { - .read_with_attrs = nvic_systick_read, - .write_with_attrs = nvic_systick_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - - -static MemTxResult ras_read(void *opaque, hwaddr addr, - uint64_t *data, unsigned size, - MemTxAttrs attrs) -{ - if (attrs.user) { - return MEMTX_ERROR; - } - - switch (addr) { - case 0xe10: /* ERRIIDR */ - /* architect field = Arm; product/variant/revision 0 */ - *data = 0x43b; - break; - case 0xfc8: /* ERRDEVID */ - /* Minimal RAS: we implement 0 error record indexes */ - *data = 0; - break; - default: - qemu_log_mask(LOG_UNIMP, "Read RAS register offset 0x%x\n", - (uint32_t)addr); - *data = 0; - break; - } - return MEMTX_OK; -} - -static MemTxResult ras_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size, - MemTxAttrs attrs) -{ - if (attrs.user) { - return MEMTX_ERROR; - } - - switch (addr) { - default: - qemu_log_mask(LOG_UNIMP, "Write to RAS register offset 0x%x\n", - (uint32_t)addr); - break; - } - return MEMTX_OK; -} - -static const MemoryRegionOps ras_ops = { - .read_with_attrs = ras_read, - .write_with_attrs = ras_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -/* - * Unassigned portions of the PPB space are RAZ/WI for privileged - * accesses, and fault for non-privileged accesses. - */ -static MemTxResult ppb_default_read(void *opaque, hwaddr addr, - uint64_t *data, unsigned size, - MemTxAttrs attrs) -{ - qemu_log_mask(LOG_UNIMP, "Read of unassigned area of PPB: offset 0x%x\n", - (uint32_t)addr); - if (attrs.user) { - return MEMTX_ERROR; - } - *data = 0; - return MEMTX_OK; -} - -static MemTxResult ppb_default_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size, - MemTxAttrs attrs) -{ - qemu_log_mask(LOG_UNIMP, "Write of unassigned area of PPB: offset 0x%x\n", - (uint32_t)addr); - if (attrs.user) { - return MEMTX_ERROR; - } - return MEMTX_OK; -} - -static const MemoryRegionOps ppb_default_ops = { - .read_with_attrs = ppb_default_read, - .write_with_attrs = ppb_default_write, - .endianness = DEVICE_NATIVE_ENDIAN, - .valid.min_access_size = 1, - .valid.max_access_size = 8, -}; - static int nvic_post_load(void *opaque, int version_id) { NVICState *s = opaque; @@ -2851,108 +2685,14 @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) s->num_prio_bits = arm_feature(&s->cpu->env, ARM_FEATURE_V7) ? 8 : 2; - if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), errp)) { - return; - } - sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), 0, - qdev_get_gpio_in_named(dev, "systick-trigger", - M_REG_NS)); - - if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY)) { - /* We couldn't init the secure systick device in instance_init - * as we didn't know then if the CPU had the security extensions; - * so we have to do it here. - */ - object_initialize_child(OBJECT(dev), "systick-reg-s", - &s->systick[M_REG_S], TYPE_SYSTICK); - - if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_S]), errp)) { - return; - } - sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_S]), 0, - qdev_get_gpio_in_named(dev, "systick-trigger", - M_REG_S)); - } - /* - * This device provides a single sysbus memory region which - * represents the whole of the "System PPB" space. This is the - * range from 0xe0000000 to 0xe00fffff and includes the NVIC, - * the System Control Space (system registers), the systick timer, - * and for CPUs with the Security extension an NS banked version - * of all of these. - * - * The default behaviour for unimplemented registers/ranges - * (for instance the Data Watchpoint and Trace unit at 0xe0001000) - * is to RAZ/WI for privileged access and BusFault for non-privileged - * access. - * - * The NVIC and System Control Space (SCS) starts at 0xe000e000 - * and looks like this: - * 0x004 - ICTR - * 0x010 - 0xff - systick - * 0x100..0x7ec - NVIC - * 0x7f0..0xcff - Reserved - * 0xd00..0xd3c - SCS registers - * 0xd40..0xeff - Reserved or Not implemented - * 0xf00 - STIR - * - * Some registers within this space are banked between security states. - * In v8M there is a second range 0xe002e000..0xe002efff which is the - * NonSecure alias SCS; secure accesses to this behave like NS accesses - * to the main SCS range, and non-secure accesses (including when - * the security extension is not implemented) are RAZ/WI. - * Note that both the main SCS range and the alias range are defined - * to be exempt from memory attribution (R_BLJT) and so the memory - * transaction attribute always matches the current CPU security - * state (attrs.secure == env->v7m.secure). In the nvic_sysreg_ns_ops - * wrappers we change attrs.secure to indicate the NS access; so - * generally code determining which banked register to use should - * use attrs.secure; code determining actual behaviour of the system - * should use env->v7m.secure. - * - * The container covers the whole PPB space. Within it the priority - * of overlapping regions is: - * - default region (for RAZ/WI and BusFault) : -1 - * - system register regions : 0 - * - systick : 1 - * This is because the systick device is a small block of registers - * in the middle of the other system control registers. + * This device provides a single memory region which covers the + * sysreg/NVIC registers from 0xE000E000 .. 0xE000EFFF, with the + * exception of the systick timer registers 0xE000E010 .. 0xE000E0FF. */ - memory_region_init(&s->container, OBJECT(s), "nvic", 0x100000); - memory_region_init_io(&s->defaultmem, OBJECT(s), &ppb_default_ops, s, - "nvic-default", 0x100000); - memory_region_add_subregion_overlap(&s->container, 0, &s->defaultmem, -1); memory_region_init_io(&s->sysregmem, OBJECT(s), &nvic_sysreg_ops, s, "nvic_sysregs", 0x1000); - memory_region_add_subregion(&s->container, 0xe000, &s->sysregmem); - - memory_region_init_io(&s->systickmem, OBJECT(s), - &nvic_systick_ops, s, - "nvic_systick", 0xe0); - - memory_region_add_subregion_overlap(&s->container, 0xe010, - &s->systickmem, 1); - - if (arm_feature(&s->cpu->env, ARM_FEATURE_V8)) { - memory_region_init_io(&s->sysreg_ns_mem, OBJECT(s), - &nvic_sysreg_ns_ops, &s->sysregmem, - "nvic_sysregs_ns", 0x1000); - memory_region_add_subregion(&s->container, 0x2e000, &s->sysreg_ns_mem); - memory_region_init_io(&s->systick_ns_mem, OBJECT(s), - &nvic_sysreg_ns_ops, &s->systickmem, - "nvic_systick_ns", 0xe0); - memory_region_add_subregion_overlap(&s->container, 0x2e010, - &s->systick_ns_mem, 1); - } - - if (cpu_isar_feature(aa32_ras, s->cpu)) { - memory_region_init_io(&s->ras_mem, OBJECT(s), - &ras_ops, s, "nvic_ras", 0x1000); - memory_region_add_subregion(&s->container, 0x5000, &s->ras_mem); - } - - sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->sysregmem); } static void armv7m_nvic_instance_init(Object *obj) @@ -2961,12 +2701,6 @@ static void armv7m_nvic_instance_init(Object *obj) NVICState *nvic = NVIC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - object_initialize_child(obj, "systick-reg-ns", &nvic->systick[M_REG_NS], - TYPE_SYSTICK); - /* We can't initialize the secure systick here, as we don't know - * yet if we need it. - */ - sysbus_init_irq(sbd, &nvic->excpout); qdev_init_gpio_out_named(dev, &nvic->sysresetreq, "SYSRESETREQ", 1); qdev_init_gpio_in_named(dev, nvic_systick_trigger, "systick-trigger", diff --git a/hw/intc/sifive_clint.c b/hw/intc/sifive_clint.c index 0f41e5ea1c..99c870ced2 100644 --- a/hw/intc/sifive_clint.c +++ b/hw/intc/sifive_clint.c @@ -59,8 +59,29 @@ static void sifive_clint_write_timecmp(RISCVCPU *cpu, uint64_t value, riscv_cpu_update_mip(cpu, MIP_MTIP, BOOL_TO_MASK(0)); diff = cpu->env.timecmp - rtc_r; /* back to ns (note args switched in muldiv64) */ - next = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + - muldiv64(diff, NANOSECONDS_PER_SECOND, timebase_freq); + uint64_t ns_diff = muldiv64(diff, NANOSECONDS_PER_SECOND, timebase_freq); + + /* + * check if ns_diff overflowed and check if the addition would potentially + * overflow + */ + if ((NANOSECONDS_PER_SECOND > timebase_freq && ns_diff < diff) || + ns_diff > INT64_MAX) { + next = INT64_MAX; + } else { + /* + * as it is very unlikely qemu_clock_get_ns will return a value + * greater than INT64_MAX, no additional check is needed for an + * unsigned integer overflow. + */ + next = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + ns_diff; + /* + * if ns_diff is INT64_MAX next may still be outside the range + * of a signed integer. + */ + next = MIN(next, INT64_MAX); + } + timer_mod(cpu->env.timer, next); } diff --git a/hw/misc/armv7m_ras.c b/hw/misc/armv7m_ras.c new file mode 100644 index 0000000000..de24922c94 --- /dev/null +++ b/hw/misc/armv7m_ras.c @@ -0,0 +1,93 @@ +/* + * Arm M-profile RAS (Reliability, Availability and Serviceability) block + * + * Copyright (c) 2021 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 or + * (at your option) any later version. + */ + +#include "qemu/osdep.h" +#include "hw/misc/armv7m_ras.h" +#include "qemu/log.h" + +static MemTxResult ras_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + if (attrs.user) { + return MEMTX_ERROR; + } + + switch (addr) { + case 0xe10: /* ERRIIDR */ + /* architect field = Arm; product/variant/revision 0 */ + *data = 0x43b; + break; + case 0xfc8: /* ERRDEVID */ + /* Minimal RAS: we implement 0 error record indexes */ + *data = 0; + break; + default: + qemu_log_mask(LOG_UNIMP, "Read RAS register offset 0x%x\n", + (uint32_t)addr); + *data = 0; + break; + } + return MEMTX_OK; +} + +static MemTxResult ras_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + if (attrs.user) { + return MEMTX_ERROR; + } + + switch (addr) { + default: + qemu_log_mask(LOG_UNIMP, "Write to RAS register offset 0x%x\n", + (uint32_t)addr); + break; + } + return MEMTX_OK; +} + +static const MemoryRegionOps ras_ops = { + .read_with_attrs = ras_read, + .write_with_attrs = ras_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + + +static void armv7m_ras_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + ARMv7MRAS *s = ARMV7M_RAS(obj); + + memory_region_init_io(&s->iomem, obj, &ras_ops, + s, "armv7m-ras", 0x1000); + sysbus_init_mmio(sbd, &s->iomem); +} + +static void armv7m_ras_class_init(ObjectClass *klass, void *data) +{ + /* This device has no state: no need for vmstate or reset */ +} + +static const TypeInfo armv7m_ras_info = { + .name = TYPE_ARMV7M_RAS, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(ARMv7MRAS), + .instance_init = armv7m_ras_init, + .class_init = armv7m_ras_class_init, +}; + +static void armv7m_ras_register_types(void) +{ + type_register_static(&armv7m_ras_info); +} + +type_init(armv7m_ras_register_types); diff --git a/hw/misc/meson.build b/hw/misc/meson.build index a53b849a5a..3f41a3a5b2 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -17,6 +17,8 @@ softmmu_ss.add(when: 'CONFIG_INTEGRATOR_DEBUG', if_true: files('arm_integrator_d softmmu_ss.add(when: 'CONFIG_A9SCU', if_true: files('a9scu.c')) softmmu_ss.add(when: 'CONFIG_ARM11SCU', if_true: files('arm11scu.c')) +softmmu_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m_ras.c')) + # Mac devices softmmu_ss.add(when: 'CONFIG_MOS6522', if_true: files('mos6522.c')) diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 81699d4f8b..d39fd4e644 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -4686,14 +4686,25 @@ static void spapr_machine_latest_class_options(MachineClass *mc) type_init(spapr_machine_register_##suffix) /* + * pseries-6.2 + */ +static void spapr_machine_6_2_class_options(MachineClass *mc) +{ + /* Defaults for the latest behaviour inherited from the base class */ +} + +DEFINE_SPAPR_MACHINE(6_2, "6.2", true); + +/* * pseries-6.1 */ static void spapr_machine_6_1_class_options(MachineClass *mc) { - /* Defaults for the latest behaviour inherited from the base class */ + spapr_machine_6_2_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); } -DEFINE_SPAPR_MACHINE(6_1, "6.1", true); +DEFINE_SPAPR_MACHINE(6_1, "6.1", false); /* * pseries-6.0 diff --git a/hw/riscv/Kconfig b/hw/riscv/Kconfig index 0590f443fd..ff75add6f3 100644 --- a/hw/riscv/Kconfig +++ b/hw/riscv/Kconfig @@ -22,13 +22,10 @@ config OPENTITAN select IBEX select UNIMP -config SHAKTI - bool - config SHAKTI_C bool select UNIMP - select SHAKTI + select SHAKTI_UART select SIFIVE_CLINT select SIFIVE_PLIC diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c index 0e55411045..5624adda58 100644 --- a/hw/riscv/virt.c +++ b/hw/riscv/virt.c @@ -454,7 +454,7 @@ static void create_fdt(RISCVVirtState *s, const MemMapEntry *memmap, qemu_fdt_setprop_cell(fdt, name, "interrupts", RTC_IRQ); g_free(name); - name = g_strdup_printf("/soc/flash@%" PRIx64, flashbase); + name = g_strdup_printf("/flash@%" PRIx64, flashbase); qemu_fdt_add_subnode(mc->fdt, name); qemu_fdt_setprop_string(mc->fdt, name, "compatible", "cfi-flash"); qemu_fdt_setprop_sized_cells(mc->fdt, name, "reg", @@ -540,6 +540,24 @@ static FWCfgState *create_fw_cfg(const MachineState *mc) return fw_cfg; } +/* + * Return the per-socket PLIC hart topology configuration string + * (caller must free with g_free()) + */ +static char *plic_hart_config_string(int hart_count) +{ + g_autofree const char **vals = g_new(const char *, hart_count + 1); + int i; + + for (i = 0; i < hart_count; i++) { + vals[i] = VIRT_PLIC_HART_CONFIG; + } + vals[i] = NULL; + + /* g_strjoinv() obliges us to cast away const here */ + return g_strjoinv(",", (char **)vals); +} + static void virt_machine_init(MachineState *machine) { const MemMapEntry *memmap = virt_memmap; @@ -548,13 +566,12 @@ static void virt_machine_init(MachineState *machine) MemoryRegion *main_mem = g_new(MemoryRegion, 1); MemoryRegion *mask_rom = g_new(MemoryRegion, 1); char *plic_hart_config, *soc_name; - size_t plic_hart_config_len; target_ulong start_addr = memmap[VIRT_DRAM].base; target_ulong firmware_end_addr, kernel_start_addr; uint32_t fdt_load_addr; uint64_t kernel_entry; DeviceState *mmio_plic, *virtio_plic, *pcie_plic; - int i, j, base_hartid, hart_count; + int i, base_hartid, hart_count; /* Check socket count limit */ if (VIRT_SOCKETS_MAX < riscv_socket_count(machine)) { @@ -603,17 +620,7 @@ static void virt_machine_init(MachineState *machine) SIFIVE_CLINT_TIMEBASE_FREQ, true); /* Per-socket PLIC hart topology configuration string */ - plic_hart_config_len = - (strlen(VIRT_PLIC_HART_CONFIG) + 1) * hart_count; - plic_hart_config = g_malloc0(plic_hart_config_len); - for (j = 0; j < hart_count; j++) { - if (j != 0) { - strncat(plic_hart_config, ",", plic_hart_config_len); - } - strncat(plic_hart_config, VIRT_PLIC_HART_CONFIG, - plic_hart_config_len); - plic_hart_config_len -= (strlen(VIRT_PLIC_HART_CONFIG) + 1); - } + plic_hart_config = plic_hart_config_string(hart_count); /* Per-socket PLIC */ s->plic[i] = sifive_plic_create( diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index e4b18aef49..4d25278cf2 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -791,14 +791,26 @@ bool css_migration_enabled(void) } \ type_init(ccw_machine_register_##suffix) +static void ccw_machine_6_2_instance_options(MachineState *machine) +{ +} + +static void ccw_machine_6_2_class_options(MachineClass *mc) +{ +} +DEFINE_CCW_MACHINE(6_2, "6.2", true); + static void ccw_machine_6_1_instance_options(MachineState *machine) { + ccw_machine_6_2_instance_options(machine); } static void ccw_machine_6_1_class_options(MachineClass *mc) { + ccw_machine_6_2_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); } -DEFINE_CCW_MACHINE(6_1, "6.1", true); +DEFINE_CCW_MACHINE(6_1, "6.1", false); static void ccw_machine_6_0_instance_options(MachineState *machine) { diff --git a/hw/timer/Kconfig b/hw/timer/Kconfig index bac2511715..1e73da7e12 100644 --- a/hw/timer/Kconfig +++ b/hw/timer/Kconfig @@ -52,5 +52,8 @@ config SSE_COUNTER config SSE_TIMER bool +config STELLARIS_GPTM + bool + config AVR_TIMER16 bool diff --git a/hw/timer/armv7m_systick.c b/hw/timer/armv7m_systick.c index 2f192011eb..3bd951dd04 100644 --- a/hw/timer/armv7m_systick.c +++ b/hw/timer/armv7m_systick.c @@ -14,28 +14,32 @@ #include "migration/vmstate.h" #include "hw/irq.h" #include "hw/sysbus.h" +#include "hw/qdev-clock.h" #include "qemu/timer.h" #include "qemu/log.h" #include "qemu/module.h" +#include "qapi/error.h" #include "trace.h" -/* qemu timers run at 1GHz. We want something closer to 1MHz. */ -#define SYSTICK_SCALE 1000ULL - #define SYSTICK_ENABLE (1 << 0) #define SYSTICK_TICKINT (1 << 1) #define SYSTICK_CLKSOURCE (1 << 2) #define SYSTICK_COUNTFLAG (1 << 16) -int system_clock_scale; +#define SYSCALIB_NOREF (1U << 31) +#define SYSCALIB_SKEW (1U << 30) +#define SYSCALIB_TENMS ((1U << 24) - 1) -/* Conversion factor from qemu timer to SysTick frequencies. */ -static inline int64_t systick_scale(SysTickState *s) +static void systick_set_period_from_clock(SysTickState *s) { + /* + * Set the ptimer period from whichever clock is selected. + * Must be called from within a ptimer transaction block. + */ if (s->control & SYSTICK_CLKSOURCE) { - return system_clock_scale; + ptimer_set_period_from_clock(s->ptimer, s->cpuclk, 1); } else { - return 1000; + ptimer_set_period_from_clock(s->ptimer, s->refclk, 1); } } @@ -82,7 +86,28 @@ static MemTxResult systick_read(void *opaque, hwaddr addr, uint64_t *data, val = ptimer_get_count(s->ptimer); break; case 0xc: /* SysTick Calibration Value. */ - val = 10000; + /* + * In real hardware it is possible to make this register report + * a different value from what the reference clock is actually + * running at. We don't model that (which usually happens due + * to integration errors in the real hardware) and instead always + * report the theoretical correct value as described in the + * knowledgebase article at + * https://developer.arm.com/documentation/ka001325/latest + * If necessary, we could implement an extra QOM property on this + * device to force the STCALIB value to something different from + * the "correct" value. + */ + if (!clock_has_source(s->refclk)) { + val = SYSCALIB_NOREF; + break; + } + val = clock_ns_to_ticks(s->refclk, 10 * SCALE_MS) - 1; + val &= SYSCALIB_TENMS; + if (clock_ticks_to_ns(s->refclk, val + 1) != 10 * SCALE_MS) { + /* report that tick count does not yield exactly 10ms */ + val |= SYSCALIB_SKEW; + } break; default: val = 0; @@ -114,6 +139,11 @@ static MemTxResult systick_write(void *opaque, hwaddr addr, { uint32_t oldval; + if (!clock_has_source(s->refclk)) { + /* This bit is always 1 if there is no external refclk */ + value |= SYSTICK_CLKSOURCE; + } + ptimer_transaction_begin(s->ptimer); oldval = s->control; s->control &= 0xfffffff8; @@ -121,19 +151,14 @@ static MemTxResult systick_write(void *opaque, hwaddr addr, if ((oldval ^ value) & SYSTICK_ENABLE) { if (value & SYSTICK_ENABLE) { - /* - * Always reload the period in case board code has - * changed system_clock_scale. If we ever replace that - * global with a more sensible API then we might be able - * to set the period only when it actually changes. - */ - ptimer_set_period(s->ptimer, systick_scale(s)); ptimer_run(s->ptimer, 0); } else { ptimer_stop(s->ptimer); } - } else if ((oldval ^ value) & SYSTICK_CLKSOURCE) { - ptimer_set_period(s->ptimer, systick_scale(s)); + } + + if ((oldval ^ value) & SYSTICK_CLKSOURCE) { + systick_set_period_from_clock(s); } ptimer_transaction_commit(s->ptimer); break; @@ -176,20 +201,42 @@ static void systick_reset(DeviceState *dev) { SysTickState *s = SYSTICK(dev); - /* - * Forgetting to set system_clock_scale is always a board code - * bug. We can't check this earlier because for some boards - * (like stellaris) it is not yet configured at the point where - * the systick device is realized. - */ - assert(system_clock_scale != 0); - ptimer_transaction_begin(s->ptimer); s->control = 0; + if (!clock_has_source(s->refclk)) { + /* This bit is always 1 if there is no external refclk */ + s->control |= SYSTICK_CLKSOURCE; + } ptimer_stop(s->ptimer); ptimer_set_count(s->ptimer, 0); ptimer_set_limit(s->ptimer, 0, 0); - ptimer_set_period(s->ptimer, systick_scale(s)); + systick_set_period_from_clock(s); + ptimer_transaction_commit(s->ptimer); +} + +static void systick_cpuclk_update(void *opaque, ClockEvent event) +{ + SysTickState *s = SYSTICK(opaque); + + if (!(s->control & SYSTICK_CLKSOURCE)) { + /* currently using refclk, we can ignore cpuclk changes */ + } + + ptimer_transaction_begin(s->ptimer); + ptimer_set_period_from_clock(s->ptimer, s->cpuclk, 1); + ptimer_transaction_commit(s->ptimer); +} + +static void systick_refclk_update(void *opaque, ClockEvent event) +{ + SysTickState *s = SYSTICK(opaque); + + if (s->control & SYSTICK_CLKSOURCE) { + /* currently using cpuclk, we can ignore refclk changes */ + } + + ptimer_transaction_begin(s->ptimer); + ptimer_set_period_from_clock(s->ptimer, s->refclk, 1); ptimer_transaction_commit(s->ptimer); } @@ -201,6 +248,11 @@ static void systick_instance_init(Object *obj) memory_region_init_io(&s->iomem, obj, &systick_ops, s, "systick", 0xe0); sysbus_init_mmio(sbd, &s->iomem); sysbus_init_irq(sbd, &s->irq); + + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", + systick_refclk_update, s, ClockUpdate); + s->cpuclk = qdev_init_clock_in(DEVICE(obj), "cpuclk", + systick_cpuclk_update, s, ClockUpdate); } static void systick_realize(DeviceState *dev, Error **errp) @@ -211,13 +263,21 @@ static void systick_realize(DeviceState *dev, Error **errp) PTIMER_POLICY_NO_COUNTER_ROUND_DOWN | PTIMER_POLICY_NO_IMMEDIATE_RELOAD | PTIMER_POLICY_TRIGGER_ONLY_ON_DECREMENT); + + if (!clock_has_source(s->cpuclk)) { + error_setg(errp, "systick: cpuclk must be connected"); + return; + } + /* It's OK not to connect the refclk */ } static const VMStateDescription vmstate_systick = { .name = "armv7m_systick", - .version_id = 2, - .minimum_version_id = 2, + .version_id = 3, + .minimum_version_id = 3, .fields = (VMStateField[]) { + VMSTATE_CLOCK(refclk, SysTickState), + VMSTATE_CLOCK(cpuclk, SysTickState), VMSTATE_UINT32(control, SysTickState), VMSTATE_INT64(tick, SysTickState), VMSTATE_PTIMER(ptimer, SysTickState), diff --git a/hw/timer/meson.build b/hw/timer/meson.build index 1aa3cd2284..e67478a8f1 100644 --- a/hw/timer/meson.build +++ b/hw/timer/meson.build @@ -31,6 +31,7 @@ softmmu_ss.add(when: 'CONFIG_SH_TIMER', if_true: files('sh_timer.c')) softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_timer.c')) softmmu_ss.add(when: 'CONFIG_SSE_COUNTER', if_true: files('sse-counter.c')) softmmu_ss.add(when: 'CONFIG_SSE_TIMER', if_true: files('sse-timer.c')) +softmmu_ss.add(when: 'CONFIG_STELLARIS_GPTM', if_true: files('stellaris-gptm.c')) softmmu_ss.add(when: 'CONFIG_STM32F2XX_TIMER', if_true: files('stm32f2xx_timer.c')) softmmu_ss.add(when: 'CONFIG_XILINX', if_true: files('xilinx_timer.c')) specific_ss.add(when: 'CONFIG_IBEX', if_true: files('ibex_timer.c')) diff --git a/hw/timer/stellaris-gptm.c b/hw/timer/stellaris-gptm.c new file mode 100644 index 0000000000..fd71c79be4 --- /dev/null +++ b/hw/timer/stellaris-gptm.c @@ -0,0 +1,332 @@ +/* + * Luminary Micro Stellaris General Purpose Timer Module + * + * Copyright (c) 2006 CodeSourcery. + * Written by Paul Brook + * + * This code is licensed under the GPL. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/timer.h" +#include "qapi/error.h" +#include "migration/vmstate.h" +#include "hw/qdev-clock.h" +#include "hw/timer/stellaris-gptm.h" + +static void gptm_update_irq(gptm_state *s) +{ + int level; + level = (s->state & s->mask) != 0; + qemu_set_irq(s->irq, level); +} + +static void gptm_stop(gptm_state *s, int n) +{ + timer_del(s->timer[n]); +} + +static void gptm_reload(gptm_state *s, int n, int reset) +{ + int64_t tick; + if (reset) { + tick = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + } else { + tick = s->tick[n]; + } + + if (s->config == 0) { + /* 32-bit CountDown. */ + uint32_t count; + count = s->load[0] | (s->load[1] << 16); + tick += clock_ticks_to_ns(s->clk, count); + } else if (s->config == 1) { + /* 32-bit RTC. 1Hz tick. */ + tick += NANOSECONDS_PER_SECOND; + } else if (s->mode[n] == 0xa) { + /* PWM mode. Not implemented. */ + } else { + qemu_log_mask(LOG_UNIMP, + "GPTM: 16-bit timer mode unimplemented: 0x%x\n", + s->mode[n]); + return; + } + s->tick[n] = tick; + timer_mod(s->timer[n], tick); +} + +static void gptm_tick(void *opaque) +{ + gptm_state **p = (gptm_state **)opaque; + gptm_state *s; + int n; + + s = *p; + n = p - s->opaque; + if (s->config == 0) { + s->state |= 1; + if ((s->control & 0x20)) { + /* Output trigger. */ + qemu_irq_pulse(s->trigger); + } + if (s->mode[0] & 1) { + /* One-shot. */ + s->control &= ~1; + } else { + /* Periodic. */ + gptm_reload(s, 0, 0); + } + } else if (s->config == 1) { + /* RTC. */ + uint32_t match; + s->rtc++; + match = s->match[0] | (s->match[1] << 16); + if (s->rtc > match) + s->rtc = 0; + if (s->rtc == 0) { + s->state |= 8; + } + gptm_reload(s, 0, 0); + } else if (s->mode[n] == 0xa) { + /* PWM mode. Not implemented. */ + } else { + qemu_log_mask(LOG_UNIMP, + "GPTM: 16-bit timer mode unimplemented: 0x%x\n", + s->mode[n]); + } + gptm_update_irq(s); +} + +static uint64_t gptm_read(void *opaque, hwaddr offset, + unsigned size) +{ + gptm_state *s = (gptm_state *)opaque; + + switch (offset) { + case 0x00: /* CFG */ + return s->config; + case 0x04: /* TAMR */ + return s->mode[0]; + case 0x08: /* TBMR */ + return s->mode[1]; + case 0x0c: /* CTL */ + return s->control; + case 0x18: /* IMR */ + return s->mask; + case 0x1c: /* RIS */ + return s->state; + case 0x20: /* MIS */ + return s->state & s->mask; + case 0x24: /* CR */ + return 0; + case 0x28: /* TAILR */ + return s->load[0] | ((s->config < 4) ? (s->load[1] << 16) : 0); + case 0x2c: /* TBILR */ + return s->load[1]; + case 0x30: /* TAMARCHR */ + return s->match[0] | ((s->config < 4) ? (s->match[1] << 16) : 0); + case 0x34: /* TBMATCHR */ + return s->match[1]; + case 0x38: /* TAPR */ + return s->prescale[0]; + case 0x3c: /* TBPR */ + return s->prescale[1]; + case 0x40: /* TAPMR */ + return s->match_prescale[0]; + case 0x44: /* TBPMR */ + return s->match_prescale[1]; + case 0x48: /* TAR */ + if (s->config == 1) { + return s->rtc; + } + qemu_log_mask(LOG_UNIMP, + "GPTM: read of TAR but timer read not supported\n"); + return 0; + case 0x4c: /* TBR */ + qemu_log_mask(LOG_UNIMP, + "GPTM: read of TBR but timer read not supported\n"); + return 0; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "GPTM: read at bad offset 0x02%" HWADDR_PRIx "\n", + offset); + return 0; + } +} + +static void gptm_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + gptm_state *s = (gptm_state *)opaque; + uint32_t oldval; + + /* + * The timers should be disabled before changing the configuration. + * We take advantage of this and defer everything until the timer + * is enabled. + */ + switch (offset) { + case 0x00: /* CFG */ + s->config = value; + break; + case 0x04: /* TAMR */ + s->mode[0] = value; + break; + case 0x08: /* TBMR */ + s->mode[1] = value; + break; + case 0x0c: /* CTL */ + oldval = s->control; + s->control = value; + /* TODO: Implement pause. */ + if ((oldval ^ value) & 1) { + if (value & 1) { + gptm_reload(s, 0, 1); + } else { + gptm_stop(s, 0); + } + } + if (((oldval ^ value) & 0x100) && s->config >= 4) { + if (value & 0x100) { + gptm_reload(s, 1, 1); + } else { + gptm_stop(s, 1); + } + } + break; + case 0x18: /* IMR */ + s->mask = value & 0x77; + gptm_update_irq(s); + break; + case 0x24: /* CR */ + s->state &= ~value; + break; + case 0x28: /* TAILR */ + s->load[0] = value & 0xffff; + if (s->config < 4) { + s->load[1] = value >> 16; + } + break; + case 0x2c: /* TBILR */ + s->load[1] = value & 0xffff; + break; + case 0x30: /* TAMARCHR */ + s->match[0] = value & 0xffff; + if (s->config < 4) { + s->match[1] = value >> 16; + } + break; + case 0x34: /* TBMATCHR */ + s->match[1] = value >> 16; + break; + case 0x38: /* TAPR */ + s->prescale[0] = value; + break; + case 0x3c: /* TBPR */ + s->prescale[1] = value; + break; + case 0x40: /* TAPMR */ + s->match_prescale[0] = value; + break; + case 0x44: /* TBPMR */ + s->match_prescale[0] = value; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "GPTM: write at bad offset 0x02%" HWADDR_PRIx "\n", + offset); + } + gptm_update_irq(s); +} + +static const MemoryRegionOps gptm_ops = { + .read = gptm_read, + .write = gptm_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const VMStateDescription vmstate_stellaris_gptm = { + .name = "stellaris_gptm", + .version_id = 2, + .minimum_version_id = 2, + .fields = (VMStateField[]) { + VMSTATE_UINT32(config, gptm_state), + VMSTATE_UINT32_ARRAY(mode, gptm_state, 2), + VMSTATE_UINT32(control, gptm_state), + VMSTATE_UINT32(state, gptm_state), + VMSTATE_UINT32(mask, gptm_state), + VMSTATE_UNUSED(8), + VMSTATE_UINT32_ARRAY(load, gptm_state, 2), + VMSTATE_UINT32_ARRAY(match, gptm_state, 2), + VMSTATE_UINT32_ARRAY(prescale, gptm_state, 2), + VMSTATE_UINT32_ARRAY(match_prescale, gptm_state, 2), + VMSTATE_UINT32(rtc, gptm_state), + VMSTATE_INT64_ARRAY(tick, gptm_state, 2), + VMSTATE_TIMER_PTR_ARRAY(timer, gptm_state, 2), + VMSTATE_CLOCK(clk, gptm_state), + VMSTATE_END_OF_LIST() + } +}; + +static void stellaris_gptm_init(Object *obj) +{ + DeviceState *dev = DEVICE(obj); + gptm_state *s = STELLARIS_GPTM(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + sysbus_init_irq(sbd, &s->irq); + qdev_init_gpio_out(dev, &s->trigger, 1); + + memory_region_init_io(&s->iomem, obj, &gptm_ops, s, + "gptm", 0x1000); + sysbus_init_mmio(sbd, &s->iomem); + + s->opaque[0] = s->opaque[1] = s; + + /* + * TODO: in an ideal world we would model the effects of changing + * the input clock frequency while the countdown timer is active. + * The best way to do this would be to convert the device to use + * ptimer instead of hand-rolling its own timer. This would also + * make it easy to implement reading the current count from the + * TAR and TBR registers. + */ + s->clk = qdev_init_clock_in(dev, "clk", NULL, NULL, 0); +} + +static void stellaris_gptm_realize(DeviceState *dev, Error **errp) +{ + gptm_state *s = STELLARIS_GPTM(dev); + + if (!clock_has_source(s->clk)) { + error_setg(errp, "stellaris-gptm: clk must be connected"); + return; + } + + s->timer[0] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[0]); + s->timer[1] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[1]); +} + +static void stellaris_gptm_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_stellaris_gptm; + dc->realize = stellaris_gptm_realize; +} + +static const TypeInfo stellaris_gptm_info = { + .name = TYPE_STELLARIS_GPTM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(gptm_state), + .instance_init = stellaris_gptm_init, + .class_init = stellaris_gptm_class_init, +}; + +static void stellaris_gptm_register_types(void) +{ + type_register_static(&stellaris_gptm_info); +} + +type_init(stellaris_gptm_register_types) diff --git a/hw/usb/desc-msos.c b/hw/usb/desc-msos.c index 836e38c67e..c72c65b650 100644 --- a/hw/usb/desc-msos.c +++ b/hw/usb/desc-msos.c @@ -5,12 +5,12 @@ /* * Microsoft OS Descriptors * - * Windows tries to fetch some special descriptors with informations + * Windows tries to fetch some special descriptors with information * specifically for windows. Presence is indicated using a special * string @ index 0xee. There are two kinds of descriptors: * * compatid descriptor - * Used to bind drivers, if usb class isn't specific enougth. + * Used to bind drivers, if usb class isn't specific enough. * Used for PTP/MTP for example (both share the same usb class). * * properties descriptor @@ -23,7 +23,7 @@ * HLM\SYSTEM\CurrentControlSet\Control\usbflags * HLM\SYSTEM\CurrentControlSet\Enum\USB * Windows will complain it can't delete entries on the second one. - * It has deleted everything it had permissions too, which is enouth + * It has deleted everything it had permissions too, which is enough * as this includes "Device Parameters". * * http://msdn.microsoft.com/en-us/library/windows/hardware/ff537430.aspx @@ -192,8 +192,8 @@ static int usb_desc_msos_prop(const USBDesc *desc, uint8_t *dest) if (desc->msos->SelectiveSuspendEnabled) { /* * Signaling remote wakeup capability in the standard usb - * descriptors isn't enouth to make windows actually use it. - * This is the "Yes, we really mean it" registy entry to flip + * descriptors isn't enough to make windows actually use it. + * This is the "Yes, we really mean it" registry entry to flip * the switch in the windows drivers. */ length += usb_desc_msos_prop_dword(dest+length, diff --git a/hw/usb/desc.h b/hw/usb/desc.h index 4d81c68e0e..3ac604ecfa 100644 --- a/hw/usb/desc.h +++ b/hw/usb/desc.h @@ -133,7 +133,7 @@ struct USBDescConfig { const USBDescIface *ifs; }; -/* conceptually an Interface Association Descriptor, and releated interfaces */ +/* conceptually an Interface Association Descriptor, and related interfaces */ struct USBDescIfaceAssoc { uint8_t bFirstInterface; uint8_t bInterfaceCount; diff --git a/hw/usb/dev-audio.c b/hw/usb/dev-audio.c index f5cb246792..8748c1ba04 100644 --- a/hw/usb/dev-audio.c +++ b/hw/usb/dev-audio.c @@ -168,7 +168,7 @@ static const USBDescIface desc_iface[] = { STRING_FEATURE_UNIT, /* u8 iFeature */ } },{ - /* Headphone Ouptut Terminal ID3 Descriptor */ + /* Headphone Output Terminal ID3 Descriptor */ .data = (uint8_t[]) { 0x09, /* u8 bLength */ USB_DT_CS_INTERFACE, /* u8 bDescriptorType */ @@ -332,7 +332,7 @@ static const USBDescIface desc_iface_multi[] = { STRING_FEATURE_UNIT, /* u8 iFeature */ } },{ - /* Headphone Ouptut Terminal ID3 Descriptor */ + /* Headphone Output Terminal ID3 Descriptor */ .data = (uint8_t[]) { 0x09, /* u8 bLength */ USB_DT_CS_INTERFACE, /* u8 bDescriptorType */ diff --git a/hw/usb/dev-uas.c b/hw/usb/dev-uas.c index 263056231c..f6309a5ebf 100644 --- a/hw/usb/dev-uas.c +++ b/hw/usb/dev-uas.c @@ -840,6 +840,9 @@ static void usb_uas_handle_data(USBDevice *dev, USBPacket *p) } break; case UAS_PIPE_ID_STATUS: + if (p->stream > UAS_MAX_STREAMS) { + goto err_stream; + } if (p->stream) { QTAILQ_FOREACH(st, &uas->results, next) { if (st->stream == p->stream) { @@ -867,6 +870,9 @@ static void usb_uas_handle_data(USBDevice *dev, USBPacket *p) break; case UAS_PIPE_ID_DATA_IN: case UAS_PIPE_ID_DATA_OUT: + if (p->stream > UAS_MAX_STREAMS) { + goto err_stream; + } if (p->stream) { req = usb_uas_find_request(uas, p->stream); } else { @@ -902,6 +908,11 @@ static void usb_uas_handle_data(USBDevice *dev, USBPacket *p) p->status = USB_RET_STALL; break; } + +err_stream: + error_report("%s: invalid stream %d", __func__, p->stream); + p->status = USB_RET_STALL; + return; } static void usb_uas_unrealize(USBDevice *dev) diff --git a/hw/usb/host-libusb.c b/hw/usb/host-libusb.c index 00f6fbb29b..d0d46dd0a4 100644 --- a/hw/usb/host-libusb.c +++ b/hw/usb/host-libusb.c @@ -1706,7 +1706,7 @@ static void usb_host_free_streams(USBDevice *udev, USBEndpoint **eps, /* * This is *NOT* about restoring state. We have absolutely no idea * what state the host device is in at the moment and whenever it is - * still present in the first place. Attemping to contine where we + * still present in the first place. Attempting to continue where we * left off is impossible. * * What we are going to do here is emulate a surprise removal of diff --git a/hw/usb/quirks-ftdi-ids.h b/hw/usb/quirks-ftdi-ids.h index 01aca55ca7..f3cb157d6f 100644 --- a/hw/usb/quirks-ftdi-ids.h +++ b/hw/usb/quirks-ftdi-ids.h @@ -625,9 +625,9 @@ * Definitions for Icom Inc. devices */ #define ICOM_VID 0x0C26 /* Icom vendor ID */ -/* Note: ID-1 is a communications tranceiver for HAM-radio operators */ +/* Note: ID-1 is a communications transceiver for HAM-radio operators */ #define ICOM_ID_1_PID 0x0004 /* ID-1 USB to RS-232 */ -/* Note: OPC is an Optional cable to connect an Icom Tranceiver */ +/* Note: OPC is an Optional cable to connect an Icom Transceiver */ #define ICOM_OPC_U_UC_PID 0x0018 /* OPC-478UC, OPC-1122U cloning cable */ /* Note: ID-RP* devices are Icom Repeater Devices for HAM-radio */ #define ICOM_ID_RP2C1_PID 0x0009 /* ID-RP2C Asset 1 to RS-232 */ diff --git a/hw/usb/u2f-emulated.c b/hw/usb/u2f-emulated.c index 9151feb63d..63cceaa5fc 100644 --- a/hw/usb/u2f-emulated.c +++ b/hw/usb/u2f-emulated.c @@ -307,7 +307,7 @@ static void u2f_emulated_realize(U2FKeyState *base, Error **errp) rc = u2f_emulated_setup_vdev_manualy(key); } else { error_setg(errp, "%s: cert, priv, entropy and counter " - "parameters must be provided to manualy configure " + "parameters must be provided to manually configure " "the emulated device", TYPE_U2F_EMULATED); return; } diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index bc6733c518..b7ba0ff409 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -12,8 +12,10 @@ #include "hw/sysbus.h" #include "hw/intc/armv7m_nvic.h" +#include "hw/misc/armv7m_ras.h" #include "target/arm/idau.h" #include "qom/object.h" +#include "hw/clock.h" #define TYPE_BITBAND "ARM-bitband-memory" OBJECT_DECLARE_SIMPLE_TYPE(BitBandState, BITBAND) @@ -50,6 +52,8 @@ OBJECT_DECLARE_SIMPLE_TYPE(ARMv7MState, ARMV7M) * + Property "vfp": enable VFP (forwarded to CPU object) * + Property "dsp": enable DSP (forwarded to CPU object) * + Property "enable-bitband": expose bitbanded IO + * + Clock input "refclk" is the external reference clock for the systick timers + * + Clock input "cpuclk" is the main CPU clock */ struct ARMv7MState { /*< private >*/ @@ -58,11 +62,31 @@ struct ARMv7MState { NVICState nvic; BitBandState bitband[ARMV7M_NUM_BITBANDS]; ARMCPU *cpu; + ARMv7MRAS ras; + SysTickState systick[M_REG_NUM_BANKS]; /* MemoryRegion we pass to the CPU, with our devices layered on * top of the ones the board provides in board_memory. */ MemoryRegion container; + /* + * MemoryRegion which passes the transaction to either the S or the + * NS systick device depending on the transaction attributes + */ + MemoryRegion systickmem; + /* + * MemoryRegion which enforces the S/NS handling of the systick + * device NS alias region and passes the transaction to the + * NS systick device if appropriate. + */ + MemoryRegion systick_ns_mem; + /* Ditto, for the sysregs region provided by the NVIC */ + MemoryRegion sysreg_ns_mem; + /* MR providing default PPB behaviour */ + MemoryRegion defaultmem; + + Clock *refclk; + Clock *cpuclk; /* Properties */ char *cpu_type; diff --git a/include/hw/arm/msf2-soc.h b/include/hw/arm/msf2-soc.h index d406184685..ce417a6266 100644 --- a/include/hw/arm/msf2-soc.h +++ b/include/hw/arm/msf2-soc.h @@ -30,6 +30,7 @@ #include "hw/misc/msf2-sysreg.h" #include "hw/ssi/mss-spi.h" #include "hw/net/msf2-emac.h" +#include "hw/clock.h" #include "qom/object.h" #define TYPE_MSF2_SOC "msf2-soc" @@ -57,7 +58,8 @@ struct MSF2State { uint64_t envm_size; uint64_t esram_size; - uint32_t m3clk; + Clock *m3clk; + Clock *refclk; uint8_t apb0div; uint8_t apb1div; @@ -65,6 +67,10 @@ struct MSF2State { MSSTimerState timer; MSSSpiState spi[MSF2_NUM_SPIS]; MSF2EmacState emac; + + MemoryRegion nvm; + MemoryRegion nvm_alias; + MemoryRegion sram; }; #endif diff --git a/include/hw/arm/nrf51_soc.h b/include/hw/arm/nrf51_soc.h index f8a6725b77..e52a56e75e 100644 --- a/include/hw/arm/nrf51_soc.h +++ b/include/hw/arm/nrf51_soc.h @@ -17,6 +17,7 @@ #include "hw/gpio/nrf51_gpio.h" #include "hw/nvram/nrf51_nvm.h" #include "hw/timer/nrf51_timer.h" +#include "hw/clock.h" #include "qom/object.h" #define TYPE_NRF51_SOC "nrf51-soc" @@ -50,6 +51,7 @@ struct NRF51State { MemoryRegion container; + Clock *sysclk; }; #endif diff --git a/include/hw/arm/stm32f100_soc.h b/include/hw/arm/stm32f100_soc.h index 71bffcf4fd..40cd415b28 100644 --- a/include/hw/arm/stm32f100_soc.h +++ b/include/hw/arm/stm32f100_soc.h @@ -29,6 +29,7 @@ #include "hw/ssi/stm32f2xx_spi.h" #include "hw/arm/armv7m.h" #include "qom/object.h" +#include "hw/clock.h" #define TYPE_STM32F100_SOC "stm32f100-soc" OBJECT_DECLARE_SIMPLE_TYPE(STM32F100State, STM32F100_SOC) @@ -52,6 +53,13 @@ struct STM32F100State { STM32F2XXUsartState usart[STM_NUM_USARTS]; STM32F2XXSPIState spi[STM_NUM_SPIS]; + + MemoryRegion sram; + MemoryRegion flash; + MemoryRegion flash_alias; + + Clock *sysclk; + Clock *refclk; }; #endif diff --git a/include/hw/arm/stm32f205_soc.h b/include/hw/arm/stm32f205_soc.h index 985ff63aa9..849d3ed889 100644 --- a/include/hw/arm/stm32f205_soc.h +++ b/include/hw/arm/stm32f205_soc.h @@ -32,6 +32,7 @@ #include "hw/or-irq.h" #include "hw/ssi/stm32f2xx_spi.h" #include "hw/arm/armv7m.h" +#include "hw/clock.h" #include "qom/object.h" #define TYPE_STM32F205_SOC "stm32f205-soc" @@ -63,6 +64,13 @@ struct STM32F205State { STM32F2XXSPIState spi[STM_NUM_SPIS]; qemu_or_irq *adc_irqs; + + MemoryRegion sram; + MemoryRegion flash; + MemoryRegion flash_alias; + + Clock *sysclk; + Clock *refclk; }; #endif diff --git a/include/hw/arm/stm32f405_soc.h b/include/hw/arm/stm32f405_soc.h index 347105e709..5bb0c8d569 100644 --- a/include/hw/arm/stm32f405_soc.h +++ b/include/hw/arm/stm32f405_soc.h @@ -68,6 +68,9 @@ struct STM32F405State { MemoryRegion sram; MemoryRegion flash; MemoryRegion flash_alias; + + Clock *sysclk; + Clock *refclk; }; #endif diff --git a/include/hw/boards.h b/include/hw/boards.h index accd6eff35..463a5514f9 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -353,6 +353,9 @@ struct MachineState { } \ type_init(machine_initfn##_register_types) +extern GlobalProperty hw_compat_6_1[]; +extern const size_t hw_compat_6_1_len; + extern GlobalProperty hw_compat_6_0[]; extern const size_t hw_compat_6_0_len; diff --git a/include/hw/clock.h b/include/hw/clock.h index a7187eab95..11f67fb970 100644 --- a/include/hw/clock.h +++ b/include/hw/clock.h @@ -81,6 +81,10 @@ struct Clock { void *callback_opaque; unsigned int callback_events; + /* Ratio of the parent clock to run the child clocks at */ + uint32_t multiplier; + uint32_t divider; + /* Clocks are organized in a clock tree */ Clock *source; QLIST_HEAD(, Clock) children; @@ -350,4 +354,29 @@ static inline bool clock_is_enabled(const Clock *clk) */ char *clock_display_freq(Clock *clk); +/** + * clock_set_mul_div: set multiplier/divider for child clocks + * @clk: clock + * @multiplier: multiplier value + * @divider: divider value + * + * By default, a Clock's children will all run with the same period + * as their parent. This function allows you to adjust the multiplier + * and divider used to derive the child clock frequency. + * For example, setting a multiplier of 2 and a divider of 3 + * will run child clocks with a period 2/3 of the parent clock, + * so if the parent clock is an 8MHz clock the children will + * be 12MHz. + * + * Setting the multiplier to 0 will stop the child clocks. + * Setting the divider to 0 is a programming error (diagnosed with + * an assertion failure). + * Setting a multiplier value that results in the child period + * overflowing is not diagnosed. + * + * Note that this function does not call clock_propagate(); the + * caller should do that if necessary. + */ +void clock_set_mul_div(Clock *clk, uint32_t multiplier, uint32_t divider); + #endif /* QEMU_HW_CLOCK_H */ diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 88dffe7517..97b4ab79b5 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -196,6 +196,9 @@ void pc_system_parse_ovmf_flash(uint8_t *flash_ptr, size_t flash_size); void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, const CPUArchIdList *apic_ids, GArray *entry); +extern GlobalProperty pc_compat_6_1[]; +extern const size_t pc_compat_6_1_len; + extern GlobalProperty pc_compat_6_0[]; extern const size_t pc_compat_6_0_len; diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index 39c71e1593..0180c7b0ca 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -80,18 +80,10 @@ struct NVICState { int vectpending_prio; /* group prio of the exeception in vectpending */ MemoryRegion sysregmem; - MemoryRegion sysreg_ns_mem; - MemoryRegion systickmem; - MemoryRegion systick_ns_mem; - MemoryRegion ras_mem; - MemoryRegion container; - MemoryRegion defaultmem; uint32_t num_irq; qemu_irq excpout; qemu_irq sysresetreq; - - SysTickState systick[M_REG_NUM_BANKS]; }; #endif diff --git a/include/hw/misc/armv7m_ras.h b/include/hw/misc/armv7m_ras.h new file mode 100644 index 0000000000..ba6daccf3f --- /dev/null +++ b/include/hw/misc/armv7m_ras.h @@ -0,0 +1,37 @@ +/* + * Arm M-profile RAS (Reliability, Availability and Serviceability) block + * + * Copyright (c) 2021 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 or + * (at your option) any later version. + */ + +/* + * This is a model of the RAS register block of an M-profile CPU + * (the registers starting at 0xE0005000 with ERRFRn). + * + * QEMU interface: + * + sysbus MMIO region 0: the register bank + * + * The QEMU implementation currently provides "minimal RAS" only. + */ + +#ifndef HW_MISC_ARMV7M_RAS_H +#define HW_MISC_ARMV7M_RAS_H + +#include "hw/sysbus.h" + +#define TYPE_ARMV7M_RAS "armv7m-ras" +OBJECT_DECLARE_SIMPLE_TYPE(ARMv7MRAS, ARMV7M_RAS) + +struct ARMv7MRAS { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + MemoryRegion iomem; +}; + +#endif diff --git a/include/hw/register.h b/include/hw/register.h index b480e3882c..6a076cfcdf 100644 --- a/include/hw/register.h +++ b/include/hw/register.h @@ -204,6 +204,14 @@ RegisterInfoArray *register_init_block32(DeviceState *owner, bool debug_enabled, uint64_t memory_size); +RegisterInfoArray *register_init_block64(DeviceState *owner, + const RegisterAccessInfo *rae, + int num, RegisterInfo *ri, + uint64_t *data, + const MemoryRegionOps *ops, + bool debug_enabled, + uint64_t memory_size); + /** * This function should be called to cleanup the registers that were initialized * when calling register_init_block32(). This function should only be called diff --git a/include/hw/registerfields.h b/include/hw/registerfields.h index 93fa4a84c2..f2a3c9c41f 100644 --- a/include/hw/registerfields.h +++ b/include/hw/registerfields.h @@ -30,6 +30,10 @@ enum { A_ ## reg = (addr) }; \ enum { R_ ## reg = (addr) / 2 }; +#define REG64(reg, addr) \ + enum { A_ ## reg = (addr) }; \ + enum { R_ ## reg = (addr) / 8 }; + /* Define SHIFT, LENGTH and MASK constants for a field within a register */ /* This macro will define R_FOO_BAR_MASK, R_FOO_BAR_SHIFT and R_FOO_BAR_LENGTH @@ -58,6 +62,8 @@ /* Extract a field from an array of registers */ #define ARRAY_FIELD_EX32(regs, reg, field) \ FIELD_EX32((regs)[R_ ## reg], reg, field) +#define ARRAY_FIELD_EX64(regs, reg, field) \ + FIELD_EX64((regs)[R_ ## reg], reg, field) /* Deposit a register field. * Assigning values larger then the target field will result in @@ -89,7 +95,7 @@ _d; }) #define FIELD_DP64(storage, reg, field, val) ({ \ struct { \ - unsigned int v:R_ ## reg ## _ ## field ## _LENGTH; \ + uint64_t v:R_ ## reg ## _ ## field ## _LENGTH; \ } _v = { .v = val }; \ uint64_t _d; \ _d = deposit64((storage), R_ ## reg ## _ ## field ## _SHIFT, \ @@ -99,5 +105,7 @@ /* Deposit a field to array of registers. */ #define ARRAY_FIELD_DP32(regs, reg, field, val) \ (regs)[R_ ## reg] = FIELD_DP32((regs)[R_ ## reg], reg, field, val); +#define ARRAY_FIELD_DP64(regs, reg, field, val) \ + (regs)[R_ ## reg] = FIELD_DP64((regs)[R_ ## reg], reg, field, val); #endif diff --git a/include/hw/timer/armv7m_systick.h b/include/hw/timer/armv7m_systick.h index 84496faaf9..ee09b13881 100644 --- a/include/hw/timer/armv7m_systick.h +++ b/include/hw/timer/armv7m_systick.h @@ -15,11 +15,23 @@ #include "hw/sysbus.h" #include "qom/object.h" #include "hw/ptimer.h" +#include "hw/clock.h" #define TYPE_SYSTICK "armv7m_systick" OBJECT_DECLARE_SIMPLE_TYPE(SysTickState, SYSTICK) +/* + * QEMU interface: + * + sysbus MMIO region 0 is the register interface (covering + * the registers which are mapped at address 0xE000E010) + * + sysbus IRQ 0 is the interrupt line to the NVIC + * + Clock input "refclk" is the external reference clock + * (used when SYST_CSR.CLKSOURCE == 0) + * + Clock input "cpuclk" is the main CPU clock + * (used when SYST_CSR.CLKSOURCE == 1) + */ + struct SysTickState { /*< private >*/ SysBusDevice parent_obj; @@ -31,28 +43,8 @@ struct SysTickState { ptimer_state *ptimer; MemoryRegion iomem; qemu_irq irq; + Clock *refclk; + Clock *cpuclk; }; -/* - * Multiplication factor to convert from system clock ticks to qemu timer - * ticks. This should be set (by board code, usually) to a value - * equal to NANOSECONDS_PER_SECOND / frq, where frq is the clock frequency - * in Hz of the CPU. - * - * This value is used by the systick device when it is running in - * its "use the CPU clock" mode (ie when SYST_CSR.CLKSOURCE == 1) to - * set how fast the timer should tick. - * - * TODO: we should refactor this so that rather than using a global - * we use a device property or something similar. This is complicated - * because (a) the property would need to be plumbed through from the - * board code down through various layers to the systick device - * and (b) the property needs to be modifiable after realize, because - * the stellaris board uses this to implement the behaviour where the - * guest can reprogram the PLL registers to downclock the CPU, and the - * systick device needs to react accordingly. Possibly this should - * be deferred until we have a good API for modelling clock trees. - */ -extern int system_clock_scale; - #endif diff --git a/include/hw/timer/stellaris-gptm.h b/include/hw/timer/stellaris-gptm.h new file mode 100644 index 0000000000..fde1fc6f0c --- /dev/null +++ b/include/hw/timer/stellaris-gptm.h @@ -0,0 +1,51 @@ +/* + * Luminary Micro Stellaris General Purpose Timer Module + * + * Copyright (c) 2006 CodeSourcery. + * Written by Paul Brook + * + * This code is licensed under the GPL. + */ + +#ifndef HW_TIMER_STELLARIS_GPTM_H +#define HW_TIMER_STELLARIS_GPTM_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "hw/irq.h" +#include "hw/clock.h" + +#define TYPE_STELLARIS_GPTM "stellaris-gptm" +OBJECT_DECLARE_SIMPLE_TYPE(gptm_state, STELLARIS_GPTM) + +/* + * QEMU interface: + * + sysbus MMIO region 0: register bank + * + sysbus IRQ 0: timer interrupt + * + unnamed GPIO output 0: trigger output for the ADC + * + Clock input "clk": the 32-bit countdown timer runs at this speed + */ +struct gptm_state { + SysBusDevice parent_obj; + + MemoryRegion iomem; + uint32_t config; + uint32_t mode[2]; + uint32_t control; + uint32_t state; + uint32_t mask; + uint32_t load[2]; + uint32_t match[2]; + uint32_t prescale[2]; + uint32_t match_prescale[2]; + uint32_t rtc; + int64_t tick[2]; + struct gptm_state *opaque[2]; + QEMUTimer *timer[2]; + /* The timers have an alternate output used to trigger the ADC. */ + qemu_irq trigger; + qemu_irq irq; + Clock *clk; +}; + +#endif diff --git a/include/ui/console.h b/include/ui/console.h index b30b63976a..3be21497a2 100644 --- a/include/ui/console.h +++ b/include/ui/console.h @@ -471,7 +471,9 @@ bool vnc_display_reload_certs(const char *id, Error **errp); /* input.c */ int index_from_key(const char *key, size_t key_length); +#ifdef CONFIG_LINUX /* udmabuf.c */ int udmabuf_fd(void); +#endif #endif diff --git a/stubs/meson.build b/stubs/meson.build index 717bfa9a99..275ac89c16 100644 --- a/stubs/meson.build +++ b/stubs/meson.build @@ -52,7 +52,6 @@ if have_system stub_ss.add(files('semihost.c')) stub_ss.add(files('usb-dev-stub.c')) stub_ss.add(files('xen-hw-stub.c')) - stub_ss.add(files('virtio-gpu-udmabuf.c')) else stub_ss.add(files('qdev.c')) endif diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index 2f0cbddab5..15245a60a8 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -841,10 +841,58 @@ static void aarch64_max_initfn(Object *obj) cpu_max_set_sve_max_vq, NULL, NULL); } +static void aarch64_a64fx_initfn(Object *obj) +{ + ARMCPU *cpu = ARM_CPU(obj); + + cpu->dtb_compatible = "arm,a64fx"; + set_feature(&cpu->env, ARM_FEATURE_V8); + set_feature(&cpu->env, ARM_FEATURE_NEON); + set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_AARCH64); + set_feature(&cpu->env, ARM_FEATURE_EL2); + set_feature(&cpu->env, ARM_FEATURE_EL3); + set_feature(&cpu->env, ARM_FEATURE_PMU); + cpu->midr = 0x461f0010; + cpu->revidr = 0x00000000; + cpu->ctr = 0x86668006; + cpu->reset_sctlr = 0x30000180; + cpu->isar.id_aa64pfr0 = 0x0000000101111111; /* No RAS Extensions */ + cpu->isar.id_aa64pfr1 = 0x0000000000000000; + cpu->isar.id_aa64dfr0 = 0x0000000010305408; + cpu->isar.id_aa64dfr1 = 0x0000000000000000; + cpu->id_aa64afr0 = 0x0000000000000000; + cpu->id_aa64afr1 = 0x0000000000000000; + cpu->isar.id_aa64mmfr0 = 0x0000000000001122; + cpu->isar.id_aa64mmfr1 = 0x0000000011212100; + cpu->isar.id_aa64mmfr2 = 0x0000000000001011; + cpu->isar.id_aa64isar0 = 0x0000000010211120; + cpu->isar.id_aa64isar1 = 0x0000000000010001; + cpu->isar.id_aa64zfr0 = 0x0000000000000000; + cpu->clidr = 0x0000000080000023; + cpu->ccsidr[0] = 0x7007e01c; /* 64KB L1 dcache */ + cpu->ccsidr[1] = 0x2007e01c; /* 64KB L1 icache */ + cpu->ccsidr[2] = 0x70ffe07c; /* 8MB L2 cache */ + cpu->dcz_blocksize = 6; /* 256 bytes */ + cpu->gic_num_lrs = 4; + cpu->gic_vpribits = 5; + cpu->gic_vprebits = 5; + + /* Suppport of A64FX's vector length are 128,256 and 512bit only */ + aarch64_add_sve_properties(obj); + bitmap_zero(cpu->sve_vq_supported, ARM_MAX_VQ); + set_bit(0, cpu->sve_vq_supported); /* 128bit */ + set_bit(1, cpu->sve_vq_supported); /* 256bit */ + set_bit(3, cpu->sve_vq_supported); /* 512bit */ + + /* TODO: Add A64FX specific HPC extension registers */ +} + static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, + { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, { .name = "max", .initfn = aarch64_max_initfn }, }; diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index ed444bf436..33cc75af57 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -654,12 +654,9 @@ static void cortex_m55_initfn(Object *obj) cpu->revidr = 0; cpu->pmsav7_dregion = 16; cpu->sau_sregion = 8; - /* - * These are the MVFR* values for the FPU, no MVE configuration; - * we will update them later when we implement MVE - */ + /* These are the MVFR* values for the FPU + full MVE configuration */ cpu->isar.mvfr0 = 0x10110221; - cpu->isar.mvfr1 = 0x12100011; + cpu->isar.mvfr1 = 0x12100211; cpu->isar.mvfr2 = 0x00000040; cpu->isar.id_pfr0 = 0x20000030; cpu->isar.id_pfr1 = 0x00000230; diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index 3db9b15f12..76bd25006d 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -177,6 +177,16 @@ DEF_HELPER_FLAGS_3(mve_vminab, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vminah, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vminaw, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_ss, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_us, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcvtb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcvtt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcvtb_hs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcvtt_hs, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) @@ -410,6 +420,60 @@ DEF_HELPER_FLAGS_4(mve_vhcadd270b, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vhcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vhcadd270w, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfadds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfsubh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfsubs, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfmulh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmuls, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfabdh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfabds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vmaxnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmaxnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vminnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vminnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vmaxnmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmaxnmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vminnmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vminnmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfcadd90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfcadd90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfcadd270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfmsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vcmul0h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul0s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul180h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul180s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vcmla0h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla0s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla180h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla180s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) @@ -560,6 +624,18 @@ DEF_HELPER_FLAGS_3(mve_vminavb, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vminavh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxnmvh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxnmvs, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminnmvh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminnmvs, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vmaxnmavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxnmavs, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminnmavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminnmavs, TCG_CALL_NO_WG, i32, env, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) @@ -746,3 +822,69 @@ DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpeqh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpeqs, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpneh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpnes, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpgeh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpges, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmplth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmplts, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpgth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpgts, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmples, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpeq_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpeq_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpne_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpne_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpge_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpge_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmplt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmplt_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpgt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpgt_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmple_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfadd_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfsub_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfsub_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfmul_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfmul_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfma_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfma_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfmas_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfmas_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vcvt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_hs, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_hu, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_sf, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_uf, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_fs, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_fu, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vrint_rm_h, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrint_rm_s, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vrintx_h, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vrintx_s, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index 8744681629..14a4f39802 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -26,6 +26,14 @@ # VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit %size_28 28:1 !function=plus_1 +# 2 operand fp insns have size in bit 20: 1 for 16 bit, 0 for 32 bit, +# like Neon FP insns. +%2op_fp_size 20:1 !function=neon_3same_fp_size +# VCADD is an exception, where bit 20 is 0 for 16 bit and 1 for 32 bit +%2op_fp_size_rev 20:1 !function=plus_1 +# FP scalars have size in bit 28, 1 for 16 bit, 0 for 32 bit +%2op_fp_scalar_size 28:1 !function=neon_3same_fp_size + # 1imm format immediate %imm_28_16_0 28:1 16:3 0:4 @@ -116,8 +124,34 @@ @vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ mask=%mask_22_13 +@vcmp_fp .... .... .... qn:3 . .... .... .... .... &vcmp \ + qm=%qm size=%2op_fp_scalar_size mask=%mask_22_13 + +# Bit 28 is a 2op_fp_scalar_size bit, but we do not decode it in this +# format to avoid complicated overlapping-instruction-groups +@vcmp_fp_scalar .... .... .... qn:3 . .... .... .... rm:4 &vcmp_scalar \ + mask=%mask_22_13 + @vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm +@2op_fp .... .... .... .... .... .... .... .... &2op \ + qd=%qd qn=%qn qm=%qm size=%2op_fp_size + +@2op_fp_size_rev .... .... .... .... .... .... .... .... &2op \ + qd=%qd qn=%qn qm=%qm size=%2op_fp_size_rev + +# 2-operand, but Qd and Qn share a field. Size is in bit 28, but we +# don't decode it in this format +@vmaxnma .... .... .... .... .... .... .... .... &2op \ + qd=%qd qn=%qd qm=%qm + +# Here also we don't decode the bit 28 size in the format to avoid +# awkward nested overlap groups +@vmaxnmv .... .... .... .... rda:4 .... .... .... &vmaxv qm=%qm + +@2op_fp_scalar .... .... .... .... .... .... .... rm:4 &2scalar \ + qd=%qd qn=%qn size=%2op_fp_scalar_size + # Vector loads and stores # Widening loads and narrowing stores: @@ -187,6 +221,10 @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op # The VSHLL T2 encoding is not a @2op pattern, but is here because it # overlaps what would be size=0b11 VMULH/VRMULH { + VCVTB_SH 111 0 1110 0 . 11 1111 ... 0 1110 0 0 . 0 ... 1 @1op_nosz + + VMAXNMA 111 0 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=2 + VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -199,6 +237,10 @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VCVTB_HS 111 1 1110 0 . 11 1111 ... 0 1110 0 0 . 0 ... 1 @1op_nosz + + VMAXNMA 111 1 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=1 + VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -209,6 +251,9 @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VCVTT_SH 111 0 1110 0 . 11 1111 ... 1 1110 0 0 . 0 ... 1 @1op_nosz + + VMINNMA 111 0 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=2 VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -221,6 +266,9 @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VCVTT_HS 111 1 1110 0 . 11 1111 ... 1 1110 0 0 . 0 ... 1 @1op_nosz + + VMINNMA 111 1 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=1 VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -274,15 +322,29 @@ VQSHL_U 111 1 1111 0 . .. ... 0 ... 0 0100 . 1 . 1 ... 0 @2op_rev VQRSHL_S 111 0 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev VQRSHL_U 111 1 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev -VQDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op -VQDMLADHX 1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op -VQRDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op -VQRDMLADHX 1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op +{ + VCMUL0 111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 0 @2op_sz28 + VQDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op + VQDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op +} + +{ + VCMUL180 111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 0 @2op_sz28 + VQDMLADHX 111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op + VQDMLSDHX 111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op +} + +{ + VCMUL90 111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 1 @2op_sz28 + VQRDMLADH 111 0 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op + VQRDMLSDH 111 1 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op +} -VQDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op -VQDMLSDHX 1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op -VQRDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op -VQRDMLSDHX 1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op +{ + VCMUL270 111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 1 @2op_sz28 + VQRDMLADHX 111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op + VQRDMLSDHX 111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op +} VQDMULLB 111 . 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 1 @2op_sz28 VQDMULLT 111 . 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 1 @2op_sz28 @@ -351,8 +413,10 @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 VIWDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 ... . @viwdup } { - VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup - VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup + VCMPGT_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 0110 .... @vcmp_fp_scalar size=2 + VCMPLE_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 1110 .... @vcmp_fp_scalar size=2 + VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup + VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup } # multiply-add long dual accumulate @@ -398,25 +462,50 @@ VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz { - VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv - VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv - VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv - VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + [ + VMAXNMAV 1110 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2 + VMINNMAV 1110 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2 + VMAXNMV 1110 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2 + VMINNMV 1110 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2 + ] + [ + VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + ] VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } { - VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv - VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + [ + VMAXNMAV 1111 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1 + VMINNMAV 1111 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1 + VMAXNMV 1111 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1 + VMINNMV 1111 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1 + ] + [ + VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + ] VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } # Scalar operations -VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar -VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar +{ + VCMPEQ_fp_scalar 1110 1110 0 . 11 ... 1 ... 0 1111 0100 .... @vcmp_fp_scalar size=2 + VCMPNE_fp_scalar 1110 1110 0 . 11 ... 1 ... 0 1111 1100 .... @vcmp_fp_scalar size=2 + VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar +} + +{ + VCMPLT_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 1100 .... @vcmp_fp_scalar size=2 + VCMPGE_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 0100 .... @vcmp_fp_scalar size=2 + VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar +} { VSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar @@ -434,10 +523,17 @@ VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar } -VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar -VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar -VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar -VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar +{ + VADD_fp_scalar 111 . 1110 0 . 11 ... 0 ... 0 1111 . 100 .... @2op_fp_scalar + VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar + VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar +} + +{ + VSUB_fp_scalar 111 . 1110 0 . 11 ... 0 ... 1 1111 . 100 .... @2op_fp_scalar + VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar + VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar +} { VQADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 110 .... @2scalar @@ -453,12 +549,23 @@ VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar size=%size_28 } -VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar -VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +{ + VMUL_fp_scalar 111 . 1110 0 . 11 ... 1 ... 0 1110 . 110 .... @2op_fp_scalar + VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar + VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +} -# The U bit (28) is don't-care because it does not affect the result -VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar -VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +{ + VFMA_scalar 111 . 1110 0 . 11 ... 1 ... 0 1110 . 100 .... @2op_fp_scalar + # The U bit (28) is don't-care because it does not affect the result + VMLA 111 - 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar +} + +{ + VFMAS_scalar 111 . 1110 0 . 11 ... 1 ... 1 1110 . 100 .... @2op_fp_scalar + # The U bit (28) is don't-care because it does not affect the result + VMLAS 111 - 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +} VQRDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 100 .... @2scalar VQRDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 100 .... @2scalar @@ -591,27 +698,135 @@ VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd # Comparisons. We expand out the conditions which are split across # encodings T1, T2, T3 and the fc bits. These include VPT, which is # effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. -VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp -VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +{ + VCMPEQ_fp 111 . 1110 0 . 11 ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp_fp + VCMPEQ 111 1 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp +} + +{ + VCMPNE_fp 111 . 1110 0 . 11 ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp_fp + VCMPNE 111 1 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +} + +{ + VCMPGE_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp_fp + VCMPGE 111 1 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp +} + +{ + VCMPLT_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp_fp + VCMPLT 111 1 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp +} + +{ + VCMPGT_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp_fp + VCMPGT 111 1 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp +} + +{ + VCMPLE_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp_fp + VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp +} + { VPSEL 1111 1110 0 . 11 ... 1 ... 0 1111 . 0 . 0 ... 1 @2op_nosz VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp } -VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp -VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp -VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp -VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp { - VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 - VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 - VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar + VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 + VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 + VCMPEQ_fp_scalar 1111 1110 0 . 11 ... 1 ... 0 1111 0100 .... @vcmp_fp_scalar size=1 + VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0100 .... @vcmp_scalar +} + +{ + VCMPNE_fp_scalar 1111 1110 0 . 11 ... 1 ... 0 1111 1100 .... @vcmp_fp_scalar size=1 + VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1100 .... @vcmp_scalar +} + +{ + VCMPGT_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 0110 .... @vcmp_fp_scalar size=1 + VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0110 .... @vcmp_scalar +} + +{ + VCMPLE_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 1110 .... @vcmp_fp_scalar size=1 + VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1110 .... @vcmp_scalar +} + +{ + VCMPGE_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 0100 .... @vcmp_fp_scalar size=1 + VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0100 .... @vcmp_scalar } -VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 0 0 .... @vcmp_scalar +{ + VCMPLT_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 1100 .... @vcmp_fp_scalar size=1 + VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1100 .... @vcmp_scalar +} + VCMPCS_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 1 0 .... @vcmp_scalar VCMPHI_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 1 0 .... @vcmp_scalar -VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar -VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar -VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar -VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar + +# 2-operand FP +VADD_fp 1110 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp +VSUB_fp 1110 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp +VMUL_fp 1111 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 1 ... 0 @2op_fp +VABD_fp 1111 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp + +VMAXNM 1111 1111 0 . 0 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp +VMINNM 1111 1111 0 . 1 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp + +VCADD90_fp 1111 1100 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCADD270_fp 1111 1101 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev + +VFMA 1110 1111 0 . 0 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp +VFMS 1110 1111 0 . 1 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp + +VCMLA0 1111 110 00 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCMLA90 1111 110 01 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCMLA180 1111 110 10 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCMLA270 1111 110 11 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev + +# floating-point <-> fixed-point conversions. Naming convention: +# VCVT_<from><to>, S = signed int, U = unsigned int, H = halfprec, F = singleprec +@vcvt .... .... .. 1 ..... .... .. 1 . .... .... &2shift \ + qd=%qd qm=%qm shift=%rshift_i5 size=2 +@vcvt_f16 .... .... .. 11 .... .... .. 0 . .... .... &2shift \ + qd=%qd qm=%qm shift=%rshift_i4 size=1 + +VCVT_SH_fixed 1110 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt_f16 +VCVT_UH_fixed 1111 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt_f16 + +VCVT_HS_fixed 1110 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt_f16 +VCVT_HU_fixed 1111 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt_f16 + +VCVT_SF_fixed 1110 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt +VCVT_UF_fixed 1111 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt + +VCVT_FS_fixed 1110 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt +VCVT_FU_fixed 1111 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt + +# VCVT between floating point and integer (halfprec and single); +# VCVT_<from><to>, S = signed int, U = unsigned int, F = float +VCVT_SF 1111 1111 1 . 11 .. 11 ... 0 011 00 1 . 0 ... 0 @1op +VCVT_UF 1111 1111 1 . 11 .. 11 ... 0 011 01 1 . 0 ... 0 @1op +VCVT_FS 1111 1111 1 . 11 .. 11 ... 0 011 10 1 . 0 ... 0 @1op +VCVT_FU 1111 1111 1 . 11 .. 11 ... 0 011 11 1 . 0 ... 0 @1op + +# VCVT from floating point to integer with specified rounding mode +VCVTAS 1111 1111 1 . 11 .. 11 ... 000 00 0 1 . 0 ... 0 @1op +VCVTAU 1111 1111 1 . 11 .. 11 ... 000 00 1 1 . 0 ... 0 @1op +VCVTNS 1111 1111 1 . 11 .. 11 ... 000 01 0 1 . 0 ... 0 @1op +VCVTNU 1111 1111 1 . 11 .. 11 ... 000 01 1 1 . 0 ... 0 @1op +VCVTPS 1111 1111 1 . 11 .. 11 ... 000 10 0 1 . 0 ... 0 @1op +VCVTPU 1111 1111 1 . 11 .. 11 ... 000 10 1 1 . 0 ... 0 @1op +VCVTMS 1111 1111 1 . 11 .. 11 ... 000 11 0 1 . 0 ... 0 @1op +VCVTMU 1111 1111 1 . 11 .. 11 ... 000 11 1 1 . 0 ... 0 @1op + +VRINTN 1111 1111 1 . 11 .. 10 ... 001 000 1 . 0 ... 0 @1op +VRINTX 1111 1111 1 . 11 .. 10 ... 001 001 1 . 0 ... 0 @1op +VRINTA 1111 1111 1 . 11 .. 10 ... 001 010 1 . 0 ... 0 @1op +VRINTZ 1111 1111 1 . 11 .. 10 ... 001 011 1 . 0 ... 0 @1op +VRINTM 1111 1111 1 . 11 .. 10 ... 001 101 1 . 0 ... 0 @1op +VRINTP 1111 1111 1 . 11 .. 10 ... 001 111 1 . 0 ... 0 @1op diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index c2826eb5f9..846962bf4c 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -25,6 +25,7 @@ #include "exec/cpu_ldst.h" #include "exec/exec-all.h" #include "tcg/tcg.h" +#include "fpu/softfloat.h" static uint16_t mve_eci_mask(CPUARMState *env) { @@ -2798,3 +2799,652 @@ DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX) DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN) DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN) DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN) + +/* + * 2-operand floating point. Note that if an element is partially + * predicated we must do the FP operation to update the non-predicated + * bytes, but we must be careful to avoid updating the FP exception + * state unless byte 0 of the element was unpredicated. + */ +#define DO_2OP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)], fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2OP_FP_ALL(OP, FN) \ + DO_2OP_FP(OP##h, 2, float16, float16_##FN) \ + DO_2OP_FP(OP##s, 4, float32, float32_##FN) + +DO_2OP_FP_ALL(vfadd, add) +DO_2OP_FP_ALL(vfsub, sub) +DO_2OP_FP_ALL(vfmul, mul) + +static inline float16 float16_abd(float16 a, float16 b, float_status *s) +{ + return float16_abs(float16_sub(a, b, s)); +} + +static inline float32 float32_abd(float32 a, float32 b, float_status *s) +{ + return float32_abs(float32_sub(a, b, s)); +} + +DO_2OP_FP_ALL(vfabd, abd) +DO_2OP_FP_ALL(vmaxnm, maxnum) +DO_2OP_FP_ALL(vminnm, minnum) + +static inline float16 float16_maxnuma(float16 a, float16 b, float_status *s) +{ + return float16_maxnum(float16_abs(a), float16_abs(b), s); +} + +static inline float32 float32_maxnuma(float32 a, float32 b, float_status *s) +{ + return float32_maxnum(float32_abs(a), float32_abs(b), s); +} + +static inline float16 float16_minnuma(float16 a, float16 b, float_status *s) +{ + return float16_minnum(float16_abs(a), float16_abs(b), s); +} + +static inline float32 float32_minnuma(float32 a, float32 b, float_status *s) +{ + return float32_minnum(float32_abs(a), float32_abs(b), s); +} + +DO_2OP_FP_ALL(vmaxnma, maxnuma) +DO_2OP_FP_ALL(vminnma, minnuma) + +#define DO_VCADD_FP(OP, ESIZE, TYPE, FN0, FN1) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r[16 / ESIZE]; \ + uint16_t tm, mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + /* Calculate all results first to avoid overwriting inputs */ \ + for (e = 0, tm = mask; e < 16 / ESIZE; e++, tm >>= ESIZE) { \ + if ((tm & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + r[e] = 0; \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(tm & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + if (!(e & 1)) { \ + r[e] = FN0(n[H##ESIZE(e)], m[H##ESIZE(e + 1)], fpst); \ + } else { \ + r[e] = FN1(n[H##ESIZE(e)], m[H##ESIZE(e - 1)], fpst); \ + } \ + } \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], r[e], mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VCADD_FP(vfcadd90h, 2, float16, float16_sub, float16_add) +DO_VCADD_FP(vfcadd90s, 4, float32, float32_sub, float32_add) +DO_VCADD_FP(vfcadd270h, 2, float16, float16_add, float16_sub) +DO_VCADD_FP(vfcadd270s, 4, float32, float32_add, float32_sub) + +#define DO_VFMA(OP, ESIZE, TYPE, CHS) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = n[H##ESIZE(e)]; \ + if (CHS) { \ + r = TYPE##_chs(r); \ + } \ + r = TYPE##_muladd(r, m[H##ESIZE(e)], d[H##ESIZE(e)], \ + 0, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VFMA(vfmah, 2, float16, false) +DO_VFMA(vfmas, 4, float32, false) +DO_VFMA(vfmsh, 2, float16, true) +DO_VFMA(vfmss, 4, float32, true) + +#define DO_VCMLA(OP, ESIZE, TYPE, ROT, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r0, r1, e1, e2, e3, e4; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst0, *fpst1; \ + float_status scratch_fpst; \ + /* We loop through pairs of elements at a time */ \ + for (e = 0; e < 16 / ESIZE; e += 2, mask >>= ESIZE * 2) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE * 2)) == 0) { \ + continue; \ + } \ + fpst0 = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + fpst1 = fpst0; \ + if (!(mask & 1)) { \ + scratch_fpst = *fpst0; \ + fpst0 = &scratch_fpst; \ + } \ + if (!(mask & (1 << ESIZE))) { \ + scratch_fpst = *fpst1; \ + fpst1 = &scratch_fpst; \ + } \ + switch (ROT) { \ + case 0: \ + e1 = m[H##ESIZE(e)]; \ + e2 = n[H##ESIZE(e)]; \ + e3 = m[H##ESIZE(e + 1)]; \ + e4 = n[H##ESIZE(e)]; \ + break; \ + case 1: \ + e1 = TYPE##_chs(m[H##ESIZE(e + 1)]); \ + e2 = n[H##ESIZE(e + 1)]; \ + e3 = m[H##ESIZE(e)]; \ + e4 = n[H##ESIZE(e + 1)]; \ + break; \ + case 2: \ + e1 = TYPE##_chs(m[H##ESIZE(e)]); \ + e2 = n[H##ESIZE(e)]; \ + e3 = TYPE##_chs(m[H##ESIZE(e + 1)]); \ + e4 = n[H##ESIZE(e)]; \ + break; \ + case 3: \ + e1 = m[H##ESIZE(e + 1)]; \ + e2 = n[H##ESIZE(e + 1)]; \ + e3 = TYPE##_chs(m[H##ESIZE(e)]); \ + e4 = n[H##ESIZE(e + 1)]; \ + break; \ + default: \ + g_assert_not_reached(); \ + } \ + r0 = FN(e2, e1, d[H##ESIZE(e)], fpst0); \ + r1 = FN(e4, e3, d[H##ESIZE(e + 1)], fpst1); \ + mergemask(&d[H##ESIZE(e)], r0, mask); \ + mergemask(&d[H##ESIZE(e + 1)], r1, mask >> ESIZE); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VCMULH(N, M, D, S) float16_mul(N, M, S) +#define DO_VCMULS(N, M, D, S) float32_mul(N, M, S) + +#define DO_VCMLAH(N, M, D, S) float16_muladd(N, M, D, 0, S) +#define DO_VCMLAS(N, M, D, S) float32_muladd(N, M, D, 0, S) + +DO_VCMLA(vcmul0h, 2, float16, 0, DO_VCMULH) +DO_VCMLA(vcmul0s, 4, float32, 0, DO_VCMULS) +DO_VCMLA(vcmul90h, 2, float16, 1, DO_VCMULH) +DO_VCMLA(vcmul90s, 4, float32, 1, DO_VCMULS) +DO_VCMLA(vcmul180h, 2, float16, 2, DO_VCMULH) +DO_VCMLA(vcmul180s, 4, float32, 2, DO_VCMULS) +DO_VCMLA(vcmul270h, 2, float16, 3, DO_VCMULH) +DO_VCMLA(vcmul270s, 4, float32, 3, DO_VCMULS) + +DO_VCMLA(vcmla0h, 2, float16, 0, DO_VCMLAH) +DO_VCMLA(vcmla0s, 4, float32, 0, DO_VCMLAS) +DO_VCMLA(vcmla90h, 2, float16, 1, DO_VCMLAH) +DO_VCMLA(vcmla90s, 4, float32, 1, DO_VCMLAS) +DO_VCMLA(vcmla180h, 2, float16, 2, DO_VCMLAH) +DO_VCMLA(vcmla180s, 4, float32, 2, DO_VCMLAS) +DO_VCMLA(vcmla270h, 2, float16, 3, DO_VCMLAH) +DO_VCMLA(vcmla270s, 4, float32, 3, DO_VCMLAS) + +#define DO_2OP_FP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE r, m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2OP_FP_SCALAR_ALL(OP, FN) \ + DO_2OP_FP_SCALAR(OP##h, 2, float16, float16_##FN) \ + DO_2OP_FP_SCALAR(OP##s, 4, float32, float32_##FN) + +DO_2OP_FP_SCALAR_ALL(vfadd_scalar, add) +DO_2OP_FP_SCALAR_ALL(vfsub_scalar, sub) +DO_2OP_FP_SCALAR_ALL(vfmul_scalar, mul) + +#define DO_2OP_FP_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE r, m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m, d[H##ESIZE(e)], 0, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +/* VFMAS is vector * vector + scalar, so swap op2 and op3 */ +#define DO_VFMAS_SCALARH(N, M, D, F, S) float16_muladd(N, D, M, F, S) +#define DO_VFMAS_SCALARS(N, M, D, F, S) float32_muladd(N, D, M, F, S) + +/* VFMA is vector * scalar + vector */ +DO_2OP_FP_ACC_SCALAR(vfma_scalarh, 2, float16, float16_muladd) +DO_2OP_FP_ACC_SCALAR(vfma_scalars, 4, float32, float32_muladd) +DO_2OP_FP_ACC_SCALAR(vfmas_scalarh, 2, float16, DO_VFMAS_SCALARH) +DO_2OP_FP_ACC_SCALAR(vfmas_scalars, 4, float32, DO_VFMAS_SCALARS) + +/* Floating point max/min across vector. */ +#define DO_FP_VMAXMINV(OP, ESIZE, TYPE, ABS, FN) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ + uint32_t ra_in) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm; \ + TYPE ra = (TYPE)ra_in; \ + float_status *fpst = (ESIZE == 2) ? \ + &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + TYPE v = m[H##ESIZE(e)]; \ + if (TYPE##_is_signaling_nan(ra, fpst)) { \ + ra = TYPE##_silence_nan(ra, fpst); \ + float_raise(float_flag_invalid, fpst); \ + } \ + if (TYPE##_is_signaling_nan(v, fpst)) { \ + v = TYPE##_silence_nan(v, fpst); \ + float_raise(float_flag_invalid, fpst); \ + } \ + if (ABS) { \ + v = TYPE##_abs(v); \ + } \ + ra = FN(ra, v, fpst); \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } \ + +#define NOP(X) (X) + +DO_FP_VMAXMINV(vmaxnmvh, 2, float16, false, float16_maxnum) +DO_FP_VMAXMINV(vmaxnmvs, 4, float32, false, float32_maxnum) +DO_FP_VMAXMINV(vminnmvh, 2, float16, false, float16_minnum) +DO_FP_VMAXMINV(vminnmvs, 4, float32, false, float32_minnum) +DO_FP_VMAXMINV(vmaxnmavh, 2, float16, true, float16_maxnum) +DO_FP_VMAXMINV(vmaxnmavs, 4, float32, true, float32_maxnum) +DO_FP_VMAXMINV(vminnmavh, 2, float16, true, float16_minnum) +DO_FP_VMAXMINV(vminnmavs, 4, float32, true, float32_minnum) + +/* FP compares; note that all comparisons signal InvalidOp for QNaNs */ +#define DO_VCMP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, void *vm) \ + { \ + TYPE *n = vn, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + bool r; \ + for (e = 0; e < 16 / ESIZE; e++, emask <<= ESIZE) { \ + if ((mask & emask) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & (1 << (e * ESIZE)))) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)], fpst); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +#define DO_VCMP_FP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + uint32_t rm) \ + { \ + TYPE *n = vn; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + bool r; \ + for (e = 0; e < 16 / ESIZE; e++, emask <<= ESIZE) { \ + if ((mask & emask) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & (1 << (e * ESIZE)))) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], (TYPE)rm, fpst); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +#define DO_VCMP_FP_BOTH(VOP, SOP, ESIZE, TYPE, FN) \ + DO_VCMP_FP(VOP, ESIZE, TYPE, FN) \ + DO_VCMP_FP_SCALAR(SOP, ESIZE, TYPE, FN) + +/* + * Some care is needed here to get the correct result for the unordered case. + * Architecturally EQ, GE and GT are defined to be false for unordered, but + * the NE, LT and LE comparisons are defined as simple logical inverses of + * EQ, GE and GT and so they must return true for unordered. The softfloat + * comparison functions float*_{eq,le,lt} all return false for unordered. + */ +#define DO_GE16(X, Y, S) float16_le(Y, X, S) +#define DO_GE32(X, Y, S) float32_le(Y, X, S) +#define DO_GT16(X, Y, S) float16_lt(Y, X, S) +#define DO_GT32(X, Y, S) float32_lt(Y, X, S) + +DO_VCMP_FP_BOTH(vfcmpeqh, vfcmpeq_scalarh, 2, float16, float16_eq) +DO_VCMP_FP_BOTH(vfcmpeqs, vfcmpeq_scalars, 4, float32, float32_eq) + +DO_VCMP_FP_BOTH(vfcmpneh, vfcmpne_scalarh, 2, float16, !float16_eq) +DO_VCMP_FP_BOTH(vfcmpnes, vfcmpne_scalars, 4, float32, !float32_eq) + +DO_VCMP_FP_BOTH(vfcmpgeh, vfcmpge_scalarh, 2, float16, DO_GE16) +DO_VCMP_FP_BOTH(vfcmpges, vfcmpge_scalars, 4, float32, DO_GE32) + +DO_VCMP_FP_BOTH(vfcmplth, vfcmplt_scalarh, 2, float16, !DO_GE16) +DO_VCMP_FP_BOTH(vfcmplts, vfcmplt_scalars, 4, float32, !DO_GE32) + +DO_VCMP_FP_BOTH(vfcmpgth, vfcmpgt_scalarh, 2, float16, DO_GT16) +DO_VCMP_FP_BOTH(vfcmpgts, vfcmpgt_scalars, 4, float32, DO_GT32) + +DO_VCMP_FP_BOTH(vfcmpleh, vfcmple_scalarh, 2, float16, !DO_GT16) +DO_VCMP_FP_BOTH(vfcmples, vfcmple_scalars, 4, float32, !DO_GT32) + +#define DO_VCVT_FIXED(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vm, \ + uint32_t shift) \ + { \ + TYPE *d = vd, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(m[H##ESIZE(e)], shift, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VCVT_FIXED(vcvt_sh, 2, int16_t, helper_vfp_shtoh) +DO_VCVT_FIXED(vcvt_uh, 2, uint16_t, helper_vfp_uhtoh) +DO_VCVT_FIXED(vcvt_hs, 2, int16_t, helper_vfp_toshh_round_to_zero) +DO_VCVT_FIXED(vcvt_hu, 2, uint16_t, helper_vfp_touhh_round_to_zero) +DO_VCVT_FIXED(vcvt_sf, 4, int32_t, helper_vfp_sltos) +DO_VCVT_FIXED(vcvt_uf, 4, uint32_t, helper_vfp_ultos) +DO_VCVT_FIXED(vcvt_fs, 4, int32_t, helper_vfp_tosls_round_to_zero) +DO_VCVT_FIXED(vcvt_fu, 4, uint32_t, helper_vfp_touls_round_to_zero) + +/* VCVT with specified rmode */ +#define DO_VCVT_RMODE(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vm, uint32_t rmode) \ + { \ + TYPE *d = vd, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + float_status *base_fpst = (ESIZE == 2) ? \ + &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + uint32_t prev_rmode = get_float_rounding_mode(base_fpst); \ + set_float_rounding_mode(rmode, base_fpst); \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = base_fpst; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(m[H##ESIZE(e)], 0, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + set_float_rounding_mode(prev_rmode, base_fpst); \ + mve_advance_vpt(env); \ + } + +DO_VCVT_RMODE(vcvt_rm_sh, 2, uint16_t, helper_vfp_toshh) +DO_VCVT_RMODE(vcvt_rm_uh, 2, uint16_t, helper_vfp_touhh) +DO_VCVT_RMODE(vcvt_rm_ss, 4, uint32_t, helper_vfp_tosls) +DO_VCVT_RMODE(vcvt_rm_us, 4, uint32_t, helper_vfp_touls) + +#define DO_VRINT_RM_H(M, F, S) helper_rinth(M, S) +#define DO_VRINT_RM_S(M, F, S) helper_rints(M, S) + +DO_VCVT_RMODE(vrint_rm_h, 2, uint16_t, DO_VRINT_RM_H) +DO_VCVT_RMODE(vrint_rm_s, 4, uint32_t, DO_VRINT_RM_S) + +/* + * VCVT between halfprec and singleprec. As usual for halfprec + * conversions, FZ16 is ignored and AHP is observed. + */ +static void do_vcvt_sh(CPUARMState *env, void *vd, void *vm, int top) +{ + uint16_t *d = vd; + uint32_t *m = vm; + uint16_t r; + uint16_t mask = mve_element_mask(env); + bool ieee = !(env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_AHP); + unsigned e; + float_status *fpst; + float_status scratch_fpst; + float_status *base_fpst = &env->vfp.standard_fp_status; + bool old_fz = get_flush_to_zero(base_fpst); + set_flush_to_zero(false, base_fpst); + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + if ((mask & MAKE_64BIT_MASK(0, 4)) == 0) { + continue; + } + fpst = base_fpst; + if (!(mask & 1)) { + /* We need the result but without updating flags */ + scratch_fpst = *fpst; + fpst = &scratch_fpst; + } + r = float32_to_float16(m[H4(e)], ieee, fpst); + mergemask(&d[H2(e * 2 + top)], r, mask >> (top * 2)); + } + set_flush_to_zero(old_fz, base_fpst); + mve_advance_vpt(env); +} + +static void do_vcvt_hs(CPUARMState *env, void *vd, void *vm, int top) +{ + uint32_t *d = vd; + uint16_t *m = vm; + uint32_t r; + uint16_t mask = mve_element_mask(env); + bool ieee = !(env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_AHP); + unsigned e; + float_status *fpst; + float_status scratch_fpst; + float_status *base_fpst = &env->vfp.standard_fp_status; + bool old_fiz = get_flush_inputs_to_zero(base_fpst); + set_flush_inputs_to_zero(false, base_fpst); + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + if ((mask & MAKE_64BIT_MASK(0, 4)) == 0) { + continue; + } + fpst = base_fpst; + if (!(mask & (1 << (top * 2)))) { + /* We need the result but without updating flags */ + scratch_fpst = *fpst; + fpst = &scratch_fpst; + } + r = float16_to_float32(m[H2(e * 2 + top)], ieee, fpst); + mergemask(&d[H4(e)], r, mask); + } + set_flush_inputs_to_zero(old_fiz, base_fpst); + mve_advance_vpt(env); +} + +void HELPER(mve_vcvtb_sh)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_sh(env, vd, vm, 0); +} +void HELPER(mve_vcvtt_sh)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_sh(env, vd, vm, 1); +} +void HELPER(mve_vcvtb_hs)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_hs(env, vd, vm, 0); +} +void HELPER(mve_vcvtt_hs)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_hs(env, vd, vm, 1); +} + +#define DO_1OP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vm) \ + { \ + TYPE *d = vd, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(m[H##ESIZE(e)], fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_1OP_FP(vrintx_h, 2, float16, float16_round_to_int) +DO_1OP_FP(vrintx_s, 4, float32, float32_round_to_int) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index 78229c44c6..2ed91577ec 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -49,6 +49,7 @@ typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenVCVTRmodeFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -543,6 +544,148 @@ DO_1OP(VQNEG, vqneg) DO_1OP(VMAXA, vmaxa) DO_1OP(VMINA, vmina) +/* + * For simple float/int conversions we use the fixed-point + * conversion helpers with a zero shift count + */ +#define DO_VCVT(INSN, HFN, SFN) \ + static void gen_##INSN##h(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_##HFN(env, qd, qm, tcg_constant_i32(0)); \ + } \ + static void gen_##INSN##s(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_##SFN(env, qd, qm, tcg_constant_i32(0)); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + NULL, \ + gen_##INSN##h, \ + gen_##INSN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_1op(s, a, fns[a->size]); \ + } + +DO_VCVT(VCVT_SF, vcvt_sh, vcvt_sf) +DO_VCVT(VCVT_UF, vcvt_uh, vcvt_uf) +DO_VCVT(VCVT_FS, vcvt_hs, vcvt_fs) +DO_VCVT(VCVT_FU, vcvt_hu, vcvt_fu) + +static bool do_vcvt_rmode(DisasContext *s, arg_1op *a, + enum arm_fprounding rmode, bool u) +{ + /* + * Handle VCVT fp to int with specified rounding mode. + * This is a 1op fn but we must pass the rounding mode as + * an immediate to the helper. + */ + TCGv_ptr qd, qm; + static MVEGenVCVTRmodeFn * const fns[4][2] = { + { NULL, NULL }, + { gen_helper_mve_vcvt_rm_sh, gen_helper_mve_vcvt_rm_uh }, + { gen_helper_mve_vcvt_rm_ss, gen_helper_mve_vcvt_rm_us }, + { NULL, NULL }, + }; + MVEGenVCVTRmodeFn *fn = fns[a->size][u]; + + if (!dc_isar_feature(aa32_mve_fp, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, tcg_constant_i32(arm_rmode_to_sf(rmode))); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +#define DO_VCVT_RMODE(INSN, RMODE, U) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + return do_vcvt_rmode(s, a, RMODE, U); \ + } \ + +DO_VCVT_RMODE(VCVTAS, FPROUNDING_TIEAWAY, false) +DO_VCVT_RMODE(VCVTAU, FPROUNDING_TIEAWAY, true) +DO_VCVT_RMODE(VCVTNS, FPROUNDING_TIEEVEN, false) +DO_VCVT_RMODE(VCVTNU, FPROUNDING_TIEEVEN, true) +DO_VCVT_RMODE(VCVTPS, FPROUNDING_POSINF, false) +DO_VCVT_RMODE(VCVTPU, FPROUNDING_POSINF, true) +DO_VCVT_RMODE(VCVTMS, FPROUNDING_NEGINF, false) +DO_VCVT_RMODE(VCVTMU, FPROUNDING_NEGINF, true) + +#define DO_VCVT_SH(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_1op(s, a, gen_helper_mve_##FN); \ + } \ + +DO_VCVT_SH(VCVTB_SH, vcvtb_sh) +DO_VCVT_SH(VCVTT_SH, vcvtt_sh) +DO_VCVT_SH(VCVTB_HS, vcvtb_hs) +DO_VCVT_SH(VCVTT_HS, vcvtt_hs) + +#define DO_VRINT(INSN, RMODE) \ + static void gen_##INSN##h(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_vrint_rm_h(env, qd, qm, \ + tcg_constant_i32(arm_rmode_to_sf(RMODE))); \ + } \ + static void gen_##INSN##s(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_vrint_rm_s(env, qd, qm, \ + tcg_constant_i32(arm_rmode_to_sf(RMODE))); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + NULL, \ + gen_##INSN##h, \ + gen_##INSN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_1op(s, a, fns[a->size]); \ + } + +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 trans_VRINTX(DisasContext *s, arg_1op *a) +{ + static MVEGenOneOpFn * const fns[] = { + NULL, + gen_helper_mve_vrintx_h, + gen_helper_mve_vrintx_s, + NULL, + }; + if (!dc_isar_feature(aa32_mve_fp, s)) { + return false; + } + return do_1op(s, a, fns[a->size]); +} + /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_1op *a) \ @@ -831,6 +974,42 @@ static bool trans_VSBCI(DisasContext *s, arg_2op *a) return do_2op(s, a, gen_helper_mve_vsbci); } +#define DO_2OP_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2op *a) \ + { \ + static MVEGenTwoOpFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_2op(s, a, fns[a->size]); \ + } + +DO_2OP_FP(VADD_fp, vfadd) +DO_2OP_FP(VSUB_fp, vfsub) +DO_2OP_FP(VMUL_fp, vfmul) +DO_2OP_FP(VABD_fp, vfabd) +DO_2OP_FP(VMAXNM, vmaxnm) +DO_2OP_FP(VMINNM, vminnm) +DO_2OP_FP(VCADD90_fp, vfcadd90) +DO_2OP_FP(VCADD270_fp, vfcadd270) +DO_2OP_FP(VFMA, vfma) +DO_2OP_FP(VFMS, vfms) +DO_2OP_FP(VCMUL0, vcmul0) +DO_2OP_FP(VCMUL90, vcmul90) +DO_2OP_FP(VCMUL180, vcmul180) +DO_2OP_FP(VCMUL270, vcmul270) +DO_2OP_FP(VCMLA0, vcmla0) +DO_2OP_FP(VCMLA90, vcmla90) +DO_2OP_FP(VCMLA180, vcmla180) +DO_2OP_FP(VCMLA270, vcmla270) +DO_2OP_FP(VMAXNMA, vmaxnma) +DO_2OP_FP(VMINNMA, vminnma) + static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, MVEGenTwoOpScalarFn fn) { @@ -861,7 +1040,7 @@ static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, return true; } -#define DO_2OP_SCALAR(INSN, FN) \ +#define DO_2OP_SCALAR(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2scalar *a) \ { \ static MVEGenTwoOpScalarFn * const fns[] = { \ @@ -924,6 +1103,28 @@ static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a) return do_2op_scalar(s, a, fns[a->size]); } + +#define DO_2OP_FP_SCALAR(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2scalar *a) \ + { \ + static MVEGenTwoOpScalarFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_2op_scalar(s, a, fns[a->size]); \ + } + +DO_2OP_FP_SCALAR(VADD_fp_scalar, vfadd_scalar) +DO_2OP_FP_SCALAR(VSUB_fp_scalar, vfsub_scalar) +DO_2OP_FP_SCALAR(VMUL_fp_scalar, vfmul_scalar) +DO_2OP_FP_SCALAR(VFMA_scalar, vfma_scalar) +DO_2OP_FP_SCALAR(VFMAS_scalar, vfmas_scalar) + static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, MVEGenLongDualAccOpFn *fn) { @@ -1381,6 +1582,24 @@ DO_2SHIFT(VRSHRI_U, vrshli_u, true) DO_2SHIFT(VSRI, vsri, false) DO_2SHIFT(VSLI, vsli, false) +#define DO_2SHIFT_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ + { \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_2shift(s, a, gen_helper_mve_##FN, false); \ + } + +DO_2SHIFT_FP(VCVT_SH_fixed, vcvt_sh) +DO_2SHIFT_FP(VCVT_UH_fixed, vcvt_uh) +DO_2SHIFT_FP(VCVT_HS_fixed, vcvt_hs) +DO_2SHIFT_FP(VCVT_HU_fixed, vcvt_hu) +DO_2SHIFT_FP(VCVT_SF_fixed, vcvt_sf) +DO_2SHIFT_FP(VCVT_UF_fixed, vcvt_uf) +DO_2SHIFT_FP(VCVT_FS_fixed, vcvt_fs) +DO_2SHIFT_FP(VCVT_FU_fixed, vcvt_fu) + static bool do_2shift_scalar(DisasContext *s, arg_shl_scalar *a, MVEGenTwoOpShiftFn *fn) { @@ -1700,6 +1919,42 @@ DO_VCMP(VCMPLT, vcmplt) DO_VCMP(VCMPGT, vcmpgt) DO_VCMP(VCMPLE, vcmple) +#define DO_VCMP_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ + { \ + static MVEGenCmpFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_vcmp(s, a, fns[a->size]); \ + } \ + static bool trans_##INSN##_scalar(DisasContext *s, \ + arg_vcmp_scalar *a) \ + { \ + static MVEGenScalarCmpFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##_scalarh, \ + gen_helper_mve_##FN##_scalars, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_vcmp_scalar(s, a, fns[a->size]); \ + } + +DO_VCMP_FP(VCMPEQ_fp, vfcmpeq) +DO_VCMP_FP(VCMPNE_fp, vfcmpne) +DO_VCMP_FP(VCMPGE_fp, vfcmpge) +DO_VCMP_FP(VCMPLT_fp, vfcmplt) +DO_VCMP_FP(VCMPGT_fp, vfcmpgt) +DO_VCMP_FP(VCMPLE_fp, vfcmple) + static bool do_vmaxv(DisasContext *s, arg_vmaxv *a, MVEGenVADDVFn fn) { /* @@ -1748,6 +2003,26 @@ DO_VMAXV(VMINV_S, vminvs) DO_VMAXV(VMINV_U, vminvu) DO_VMAXV(VMINAV, vminav) +#define DO_VMAXV_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmaxv *a) \ + { \ + static MVEGenVADDVFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_vmaxv(s, a, fns[a->size]); \ + } + +DO_VMAXV_FP(VMAXNMV, vmaxnmv) +DO_VMAXV_FP(VMINNMV, vminnmv) +DO_VMAXV_FP(VMAXNMAV, vmaxnmav) +DO_VMAXV_FP(VMINNMAV, vminnmav) + static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) { /* Absolute difference accumulated across vector */ diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index c53ab20fa4..dd43de558e 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -28,12 +28,6 @@ #include "translate.h" #include "translate-a32.h" -static inline int neon_3same_fp_size(DisasContext *s, int x) -{ - /* Convert 0==fp32, 1==fp16 into a MO_* value */ - return MO_32 - x; -} - /* Include the generated Neon decoder */ #include "decode-neon-dp.c.inc" #include "decode-neon-ls.c.inc" diff --git a/target/arm/translate.h b/target/arm/translate.h index 241596c5bd..8636c20c3b 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -181,6 +181,12 @@ static inline int rsub_8(DisasContext *s, int x) return 8 - x; } +static inline int neon_3same_fp_size(DisasContext *s, int x) +{ + /* Convert 0==fp32, 1==fp16 into a MO_* value */ + return MO_32 - x; +} + static inline int arm_dc_feature(DisasContext *dc, int feature) { return (dc->features & (1ULL << feature)) != 0; diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index 991a6bb760..1a2b03d579 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -392,9 +392,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) RISCVCPU *cpu = RISCV_CPU(dev); CPURISCVState *env = &cpu->env; RISCVCPUClass *mcc = RISCV_CPU_GET_CLASS(dev); - int priv_version = PRIV_VERSION_1_11_0; - int bext_version = BEXT_VERSION_0_93_0; - int vext_version = VEXT_VERSION_0_07_1; + int priv_version = 0; target_ulong target_misa = env->misa; Error *local_err = NULL; @@ -417,9 +415,11 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) } } - set_priv_version(env, priv_version); - set_bext_version(env, bext_version); - set_vext_version(env, vext_version); + if (priv_version) { + set_priv_version(env, priv_version); + } else if (!env->priv_ver) { + set_priv_version(env, PRIV_VERSION_1_11_0); + } if (cpu->cfg.mmu) { set_feature(env, RISCV_FEATURE_MMU); @@ -497,6 +497,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) target_misa |= RVH; } if (cpu->cfg.ext_b) { + int bext_version = BEXT_VERSION_0_93_0; target_misa |= RVB; if (cpu->cfg.bext_spec) { @@ -515,6 +516,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp) set_bext_version(env, bext_version); } if (cpu->cfg.ext_v) { + int vext_version = VEXT_VERSION_0_07_1; target_misa |= RVV; if (!is_power_of_2(cpu->cfg.vlen)) { error_setg(errp, diff --git a/target/riscv/csr.c b/target/riscv/csr.c index 9a4ed18ac5..50a2c3a3b4 100644 --- a/target/riscv/csr.c +++ b/target/riscv/csr.c @@ -937,9 +937,12 @@ static RISCVException rmw_vsip(CPURISCVState *env, int csrno, /* Shift the S bits to their VS bit location in mip */ int ret = rmw_mip(env, 0, ret_value, new_value << 1, (write_mask << 1) & vsip_writable_mask & env->hideleg); - *ret_value &= VS_MODE_INTERRUPTS; - /* Shift the VS bits to their S bit location in vsip */ - *ret_value >>= 1; + + if (ret_value) { + *ret_value &= VS_MODE_INTERRUPTS; + /* Shift the VS bits to their S bit location in vsip */ + *ret_value >>= 1; + } return ret; } @@ -956,7 +959,9 @@ static RISCVException rmw_sip(CPURISCVState *env, int csrno, write_mask & env->mideleg & sip_writable_mask); } - *ret_value &= env->mideleg; + if (ret_value) { + *ret_value &= env->mideleg; + } return ret; } @@ -1072,8 +1077,9 @@ static RISCVException rmw_hvip(CPURISCVState *env, int csrno, int ret = rmw_mip(env, 0, ret_value, new_value, write_mask & hvip_writable_mask); - *ret_value &= hvip_writable_mask; - + if (ret_value) { + *ret_value &= hvip_writable_mask; + } return ret; } @@ -1084,8 +1090,9 @@ static RISCVException rmw_hip(CPURISCVState *env, int csrno, int ret = rmw_mip(env, 0, ret_value, new_value, write_mask & hip_writable_mask); - *ret_value &= hip_writable_mask; - + if (ret_value) { + *ret_value &= hip_writable_mask; + } return ret; } @@ -1117,17 +1124,12 @@ static RISCVException write_hcounteren(CPURISCVState *env, int csrno, return RISCV_EXCP_NONE; } -static RISCVException read_hgeie(CPURISCVState *env, int csrno, - target_ulong *val) -{ - qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); - return RISCV_EXCP_NONE; -} - static RISCVException write_hgeie(CPURISCVState *env, int csrno, target_ulong val) { - qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + if (val) { + qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + } return RISCV_EXCP_NONE; } @@ -1158,17 +1160,12 @@ static RISCVException write_htinst(CPURISCVState *env, int csrno, return RISCV_EXCP_NONE; } -static RISCVException read_hgeip(CPURISCVState *env, int csrno, - target_ulong *val) -{ - qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); - return RISCV_EXCP_NONE; -} - static RISCVException write_hgeip(CPURISCVState *env, int csrno, target_ulong val) { - qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + if (val) { + qemu_log_mask(LOG_UNIMP, "No support for a non-zero GEILEN."); + } return RISCV_EXCP_NONE; } @@ -1422,11 +1419,11 @@ RISCVException riscv_csrrw(CPURISCVState *env, int csrno, RISCVException ret; target_ulong old_value; RISCVCPU *cpu = env_archcpu(env); + int read_only = get_field(csrno, 0xC00) == 3; - /* check privileges and return -1 if check fails */ + /* check privileges and return RISCV_EXCP_ILLEGAL_INST if check fails */ #if !defined(CONFIG_USER_ONLY) int effective_priv = env->priv; - int read_only = get_field(csrno, 0xC00) == 3; if (riscv_has_ext(env, RVH) && env->priv == PRV_S && @@ -1439,11 +1436,13 @@ RISCVException riscv_csrrw(CPURISCVState *env, int csrno, effective_priv++; } - if ((write_mask && read_only) || - (!env->debugger && (effective_priv < get_field(csrno, 0x300)))) { + if (!env->debugger && (effective_priv < get_field(csrno, 0x300))) { return RISCV_EXCP_ILLEGAL_INST; } #endif + if (write_mask && read_only) { + return RISCV_EXCP_ILLEGAL_INST; + } /* ensure the CSR extension is enabled. */ if (!cpu->cfg.ext_icsr) { @@ -1592,10 +1591,10 @@ riscv_csr_operations csr_ops[CSR_TABLE_SIZE] = { [CSR_HIP] = { "hip", hmode, NULL, NULL, rmw_hip }, [CSR_HIE] = { "hie", hmode, read_hie, write_hie }, [CSR_HCOUNTEREN] = { "hcounteren", hmode, read_hcounteren, write_hcounteren }, - [CSR_HGEIE] = { "hgeie", hmode, read_hgeie, write_hgeie }, + [CSR_HGEIE] = { "hgeie", hmode, read_zero, write_hgeie }, [CSR_HTVAL] = { "htval", hmode, read_htval, write_htval }, [CSR_HTINST] = { "htinst", hmode, read_htinst, write_htinst }, - [CSR_HGEIP] = { "hgeip", hmode, read_hgeip, write_hgeip }, + [CSR_HGEIP] = { "hgeip", hmode, read_zero, write_hgeip }, [CSR_HGATP] = { "hgatp", hmode, read_hgatp, write_hgatp }, [CSR_HTIMEDELTA] = { "htimedelta", hmode, read_htimedelta, write_htimedelta }, [CSR_HTIMEDELTAH] = { "htimedeltah", hmode32, read_htimedeltah, write_htimedeltah }, diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 415e37bc37..460eee9988 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -65,9 +65,9 @@ DEF_HELPER_FLAGS_2(gorc, TCG_CALL_NO_RWG_SE, tl, tl, tl) DEF_HELPER_FLAGS_2(gorcw, TCG_CALL_NO_RWG_SE, tl, tl, tl) /* Special functions */ -DEF_HELPER_3(csrrw, tl, env, tl, tl) -DEF_HELPER_4(csrrs, tl, env, tl, tl, tl) -DEF_HELPER_4(csrrc, tl, env, tl, tl, tl) +DEF_HELPER_2(csrr, tl, env, int) +DEF_HELPER_3(csrw, void, env, int, tl) +DEF_HELPER_4(csrrw, tl, env, int, tl, tl) #ifndef CONFIG_USER_ONLY DEF_HELPER_2(sret, tl, env, tl) DEF_HELPER_2(mret, tl, env, tl) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index f09f8d5faf..2cd921d51c 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -42,6 +42,7 @@ &j imm rd &r rd rs1 rs2 &r2 rd rs1 +&r2_s rs1 rs2 &s imm rs1 rs2 &u imm rd &shift shamt rs1 rd diff --git a/target/riscv/insn_trans/trans_rva.c.inc b/target/riscv/insn_trans/trans_rva.c.inc index ab2ec4f0a5..6ea07d89b0 100644 --- a/target/riscv/insn_trans/trans_rva.c.inc +++ b/target/riscv/insn_trans/trans_rva.c.inc @@ -18,11 +18,10 @@ * this program. If not, see <http://www.gnu.org/licenses/>. */ -static inline bool gen_lr(DisasContext *ctx, arg_atomic *a, MemOp mop) +static bool gen_lr(DisasContext *ctx, arg_atomic *a, MemOp mop) { - TCGv src1 = tcg_temp_new(); - /* Put addr in load_res, data in load_val. */ - gen_get_gpr(src1, a->rs1); + TCGv src1 = get_gpr(ctx, a->rs1, EXT_ZERO); + if (a->rl) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); } @@ -30,33 +29,33 @@ static inline bool gen_lr(DisasContext *ctx, arg_atomic *a, MemOp mop) if (a->aq) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } + + /* Put addr in load_res, data in load_val. */ tcg_gen_mov_tl(load_res, src1); - gen_set_gpr(a->rd, load_val); + gen_set_gpr(ctx, a->rd, load_val); - tcg_temp_free(src1); return true; } -static inline bool gen_sc(DisasContext *ctx, arg_atomic *a, MemOp mop) +static bool gen_sc(DisasContext *ctx, arg_atomic *a, MemOp mop) { - TCGv src1 = tcg_temp_new(); - TCGv src2 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); + TCGv dest, src1, src2; TCGLabel *l1 = gen_new_label(); TCGLabel *l2 = gen_new_label(); - gen_get_gpr(src1, a->rs1); + src1 = get_gpr(ctx, a->rs1, EXT_ZERO); tcg_gen_brcond_tl(TCG_COND_NE, load_res, src1, l1); - gen_get_gpr(src2, a->rs2); /* * Note that the TCG atomic primitives are SC, * so we can ignore AQ/RL along this path. */ - tcg_gen_atomic_cmpxchg_tl(src1, load_res, load_val, src2, + dest = dest_gpr(ctx, a->rd); + src2 = get_gpr(ctx, a->rs2, EXT_NONE); + tcg_gen_atomic_cmpxchg_tl(dest, load_res, load_val, src2, ctx->mem_idx, mop); - tcg_gen_setcond_tl(TCG_COND_NE, dat, src1, load_val); - gen_set_gpr(a->rd, dat); + tcg_gen_setcond_tl(TCG_COND_NE, dest, dest, load_val); + gen_set_gpr(ctx, a->rd, dest); tcg_gen_br(l2); gen_set_label(l1); @@ -65,8 +64,7 @@ static inline bool gen_sc(DisasContext *ctx, arg_atomic *a, MemOp mop) * provide the memory barrier implied by AQ/RL. */ tcg_gen_mb(TCG_MO_ALL + a->aq * TCG_BAR_LDAQ + a->rl * TCG_BAR_STRL); - tcg_gen_movi_tl(dat, 1); - gen_set_gpr(a->rd, dat); + gen_set_gpr(ctx, a->rd, tcg_constant_tl(1)); gen_set_label(l2); /* @@ -75,9 +73,6 @@ static inline bool gen_sc(DisasContext *ctx, arg_atomic *a, MemOp mop) */ tcg_gen_movi_tl(load_res, -1); - tcg_temp_free(dat); - tcg_temp_free(src1); - tcg_temp_free(src2); return true; } @@ -85,17 +80,13 @@ static bool gen_amo(DisasContext *ctx, arg_atomic *a, void(*func)(TCGv, TCGv, TCGv, TCGArg, MemOp), MemOp mop) { - TCGv src1 = tcg_temp_new(); - TCGv src2 = tcg_temp_new(); - - gen_get_gpr(src1, a->rs1); - gen_get_gpr(src2, a->rs2); + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, EXT_NONE); + TCGv src2 = get_gpr(ctx, a->rs2, EXT_NONE); - (*func)(src2, src1, src2, ctx->mem_idx, mop); + func(dest, src1, src2, ctx->mem_idx, mop); - gen_set_gpr(a->rd, src2); - tcg_temp_free(src1); - tcg_temp_free(src2); + gen_set_gpr(ctx, a->rd, dest); return true; } diff --git a/target/riscv/insn_trans/trans_rvb.c.inc b/target/riscv/insn_trans/trans_rvb.c.inc index 9e81f6e3de..b72e76255c 100644 --- a/target/riscv/insn_trans/trans_rvb.c.inc +++ b/target/riscv/insn_trans/trans_rvb.c.inc @@ -17,422 +17,632 @@ * this program. If not, see <http://www.gnu.org/licenses/>. */ + +static void gen_clz(TCGv ret, TCGv arg1) +{ + tcg_gen_clzi_tl(ret, arg1, TARGET_LONG_BITS); +} + static bool trans_clz(DisasContext *ctx, arg_clz *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_clz); + return gen_unary(ctx, a, EXT_ZERO, gen_clz); +} + +static void gen_ctz(TCGv ret, TCGv arg1) +{ + tcg_gen_ctzi_tl(ret, arg1, TARGET_LONG_BITS); } static bool trans_ctz(DisasContext *ctx, arg_ctz *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_ctz); + return gen_unary(ctx, a, EXT_ZERO, gen_ctz); } static bool trans_cpop(DisasContext *ctx, arg_cpop *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, tcg_gen_ctpop_tl); + return gen_unary(ctx, a, EXT_ZERO, tcg_gen_ctpop_tl); } static bool trans_andn(DisasContext *ctx, arg_andn *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_andc_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_andc_tl); } static bool trans_orn(DisasContext *ctx, arg_orn *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_orc_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_orc_tl); } static bool trans_xnor(DisasContext *ctx, arg_xnor *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_eqv_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_eqv_tl); +} + +static void gen_pack(TCGv ret, TCGv arg1, TCGv arg2) +{ + tcg_gen_deposit_tl(ret, arg1, arg2, + TARGET_LONG_BITS / 2, + TARGET_LONG_BITS / 2); } static bool trans_pack(DisasContext *ctx, arg_pack *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_pack); + return gen_arith(ctx, a, EXT_NONE, gen_pack); +} + +static void gen_packu(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t = tcg_temp_new(); + tcg_gen_shri_tl(t, arg1, TARGET_LONG_BITS / 2); + tcg_gen_deposit_tl(ret, arg2, t, 0, TARGET_LONG_BITS / 2); + tcg_temp_free(t); } static bool trans_packu(DisasContext *ctx, arg_packu *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_packu); + return gen_arith(ctx, a, EXT_NONE, gen_packu); +} + +static void gen_packh(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t = tcg_temp_new(); + tcg_gen_ext8u_tl(t, arg2); + tcg_gen_deposit_tl(ret, arg1, t, 8, TARGET_LONG_BITS - 8); + tcg_temp_free(t); } static bool trans_packh(DisasContext *ctx, arg_packh *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_packh); + return gen_arith(ctx, a, EXT_NONE, gen_packh); } static bool trans_min(DisasContext *ctx, arg_min *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_smin_tl); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_smin_tl); } static bool trans_max(DisasContext *ctx, arg_max *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_smax_tl); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_smax_tl); } static bool trans_minu(DisasContext *ctx, arg_minu *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_umin_tl); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_umin_tl); } static bool trans_maxu(DisasContext *ctx, arg_maxu *a) { REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, tcg_gen_umax_tl); + return gen_arith(ctx, a, EXT_SIGN, tcg_gen_umax_tl); } static bool trans_sext_b(DisasContext *ctx, arg_sext_b *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, tcg_gen_ext8s_tl); + return gen_unary(ctx, a, EXT_NONE, tcg_gen_ext8s_tl); } static bool trans_sext_h(DisasContext *ctx, arg_sext_h *a) { REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, tcg_gen_ext16s_tl); + return gen_unary(ctx, a, EXT_NONE, tcg_gen_ext16s_tl); +} + +static void gen_sbop_mask(TCGv ret, TCGv shamt) +{ + tcg_gen_movi_tl(ret, 1); + tcg_gen_shl_tl(ret, ret, shamt); +} + +static void gen_bset(TCGv ret, TCGv arg1, TCGv shamt) +{ + TCGv t = tcg_temp_new(); + + gen_sbop_mask(t, shamt); + tcg_gen_or_tl(ret, arg1, t); + + tcg_temp_free(t); } static bool trans_bset(DisasContext *ctx, arg_bset *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_bset); + return gen_shift(ctx, a, EXT_NONE, gen_bset); } static bool trans_bseti(DisasContext *ctx, arg_bseti *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_bset); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bset); +} + +static void gen_bclr(TCGv ret, TCGv arg1, TCGv shamt) +{ + TCGv t = tcg_temp_new(); + + gen_sbop_mask(t, shamt); + tcg_gen_andc_tl(ret, arg1, t); + + tcg_temp_free(t); } static bool trans_bclr(DisasContext *ctx, arg_bclr *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_bclr); + return gen_shift(ctx, a, EXT_NONE, gen_bclr); } static bool trans_bclri(DisasContext *ctx, arg_bclri *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_bclr); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bclr); +} + +static void gen_binv(TCGv ret, TCGv arg1, TCGv shamt) +{ + TCGv t = tcg_temp_new(); + + gen_sbop_mask(t, shamt); + tcg_gen_xor_tl(ret, arg1, t); + + tcg_temp_free(t); } static bool trans_binv(DisasContext *ctx, arg_binv *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_binv); + return gen_shift(ctx, a, EXT_NONE, gen_binv); } static bool trans_binvi(DisasContext *ctx, arg_binvi *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_binv); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_binv); +} + +static void gen_bext(TCGv ret, TCGv arg1, TCGv shamt) +{ + tcg_gen_shr_tl(ret, arg1, shamt); + tcg_gen_andi_tl(ret, ret, 1); } static bool trans_bext(DisasContext *ctx, arg_bext *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_bext); + return gen_shift(ctx, a, EXT_NONE, gen_bext); } static bool trans_bexti(DisasContext *ctx, arg_bexti *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_bext); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bext); +} + +static void gen_slo(TCGv ret, TCGv arg1, TCGv arg2) +{ + tcg_gen_not_tl(ret, arg1); + tcg_gen_shl_tl(ret, ret, arg2); + tcg_gen_not_tl(ret, ret); } static bool trans_slo(DisasContext *ctx, arg_slo *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_slo); + return gen_shift(ctx, a, EXT_NONE, gen_slo); } static bool trans_sloi(DisasContext *ctx, arg_sloi *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_slo); + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_slo); +} + +static void gen_sro(TCGv ret, TCGv arg1, TCGv arg2) +{ + tcg_gen_not_tl(ret, arg1); + tcg_gen_shr_tl(ret, ret, arg2); + tcg_gen_not_tl(ret, ret); } static bool trans_sro(DisasContext *ctx, arg_sro *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_sro); + return gen_shift(ctx, a, EXT_ZERO, gen_sro); } static bool trans_sroi(DisasContext *ctx, arg_sroi *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_sro); + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_sro); } static bool trans_ror(DisasContext *ctx, arg_ror *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, tcg_gen_rotr_tl); + return gen_shift(ctx, a, EXT_NONE, tcg_gen_rotr_tl); } static bool trans_rori(DisasContext *ctx, arg_rori *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, tcg_gen_rotr_tl); + return gen_shift_imm_fn(ctx, a, EXT_NONE, tcg_gen_rotri_tl); } static bool trans_rol(DisasContext *ctx, arg_rol *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, tcg_gen_rotl_tl); + return gen_shift(ctx, a, EXT_NONE, tcg_gen_rotl_tl); } static bool trans_grev(DisasContext *ctx, arg_grev *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_helper_grev); + return gen_shift(ctx, a, EXT_NONE, gen_helper_grev); } -static bool trans_grevi(DisasContext *ctx, arg_grevi *a) +static void gen_grevi(TCGv dest, TCGv src, target_long shamt) { - REQUIRE_EXT(ctx, RVB); - - if (a->shamt >= TARGET_LONG_BITS) { - return false; + if (shamt == TARGET_LONG_BITS - 8) { + /* rev8, byte swaps */ + tcg_gen_bswap_tl(dest, src); + } else { + gen_helper_grev(dest, src, tcg_constant_tl(shamt)); } +} - return gen_grevi(ctx, a); +static bool trans_grevi(DisasContext *ctx, arg_grevi *a) +{ + REQUIRE_EXT(ctx, RVB); + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_grevi); } static bool trans_gorc(DisasContext *ctx, arg_gorc *a) { REQUIRE_EXT(ctx, RVB); - return gen_shift(ctx, a, gen_helper_gorc); + return gen_shift(ctx, a, EXT_ZERO, gen_helper_gorc); } static bool trans_gorci(DisasContext *ctx, arg_gorci *a) { REQUIRE_EXT(ctx, RVB); - return gen_shifti(ctx, a, gen_helper_gorc); + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_helper_gorc); +} + +#define GEN_SHADD(SHAMT) \ +static void gen_sh##SHAMT##add(TCGv ret, TCGv arg1, TCGv arg2) \ +{ \ + TCGv t = tcg_temp_new(); \ + \ + tcg_gen_shli_tl(t, arg1, SHAMT); \ + tcg_gen_add_tl(ret, t, arg2); \ + \ + tcg_temp_free(t); \ } +GEN_SHADD(1) +GEN_SHADD(2) +GEN_SHADD(3) + #define GEN_TRANS_SHADD(SHAMT) \ static bool trans_sh##SHAMT##add(DisasContext *ctx, arg_sh##SHAMT##add *a) \ { \ REQUIRE_EXT(ctx, RVB); \ - return gen_arith(ctx, a, gen_sh##SHAMT##add); \ + return gen_arith(ctx, a, EXT_NONE, gen_sh##SHAMT##add); \ } GEN_TRANS_SHADD(1) GEN_TRANS_SHADD(2) GEN_TRANS_SHADD(3) +static void gen_clzw(TCGv ret, TCGv arg1) +{ + tcg_gen_clzi_tl(ret, ret, 64); + tcg_gen_subi_tl(ret, ret, 32); +} + static bool trans_clzw(DisasContext *ctx, arg_clzw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_clzw); + return gen_unary(ctx, a, EXT_ZERO, gen_clzw); +} + +static void gen_ctzw(TCGv ret, TCGv arg1) +{ + tcg_gen_ori_tl(ret, arg1, (target_ulong)MAKE_64BIT_MASK(32, 32)); + tcg_gen_ctzi_tl(ret, ret, 64); } static bool trans_ctzw(DisasContext *ctx, arg_ctzw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_ctzw); + return gen_unary(ctx, a, EXT_NONE, gen_ctzw); } static bool trans_cpopw(DisasContext *ctx, arg_cpopw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_unary(ctx, a, gen_cpopw); + ctx->w = true; + return gen_unary(ctx, a, EXT_ZERO, tcg_gen_ctpop_tl); +} + +static void gen_packw(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t = tcg_temp_new(); + tcg_gen_ext16s_tl(t, arg2); + tcg_gen_deposit_tl(ret, arg1, t, 16, 48); + tcg_temp_free(t); } static bool trans_packw(DisasContext *ctx, arg_packw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_packw); + return gen_arith(ctx, a, EXT_NONE, gen_packw); +} + +static void gen_packuw(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv t = tcg_temp_new(); + tcg_gen_shri_tl(t, arg1, 16); + tcg_gen_deposit_tl(ret, arg2, t, 0, 16); + tcg_gen_ext32s_tl(ret, ret); + tcg_temp_free(t); } static bool trans_packuw(DisasContext *ctx, arg_packuw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_packuw); + return gen_arith(ctx, a, EXT_NONE, gen_packuw); } static bool trans_bsetw(DisasContext *ctx, arg_bsetw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_bset); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_bset); } static bool trans_bsetiw(DisasContext *ctx, arg_bsetiw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_bset); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bset); } static bool trans_bclrw(DisasContext *ctx, arg_bclrw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_bclr); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_bclr); } static bool trans_bclriw(DisasContext *ctx, arg_bclriw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_bclr); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_bclr); } static bool trans_binvw(DisasContext *ctx, arg_binvw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_binv); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_binv); } static bool trans_binviw(DisasContext *ctx, arg_binviw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_binv); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_binv); } static bool trans_bextw(DisasContext *ctx, arg_bextw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_bext); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_bext); } static bool trans_slow(DisasContext *ctx, arg_slow *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_slo); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_slo); } static bool trans_sloiw(DisasContext *ctx, arg_sloiw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_slo); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_slo); } static bool trans_srow(DisasContext *ctx, arg_srow *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_sro); + ctx->w = true; + return gen_shift(ctx, a, EXT_ZERO, gen_sro); } static bool trans_sroiw(DisasContext *ctx, arg_sroiw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_sro); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_sro); +} + +static void gen_rorw(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv_i32 t1 = tcg_temp_new_i32(); + TCGv_i32 t2 = tcg_temp_new_i32(); + + /* truncate to 32-bits */ + tcg_gen_trunc_tl_i32(t1, arg1); + tcg_gen_trunc_tl_i32(t2, arg2); + + tcg_gen_rotr_i32(t1, t1, t2); + + /* sign-extend 64-bits */ + tcg_gen_ext_i32_tl(ret, t1); + + tcg_temp_free_i32(t1); + tcg_temp_free_i32(t2); } static bool trans_rorw(DisasContext *ctx, arg_rorw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_rorw); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_rorw); } static bool trans_roriw(DisasContext *ctx, arg_roriw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_rorw); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_NONE, gen_rorw); +} + +static void gen_rolw(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv_i32 t1 = tcg_temp_new_i32(); + TCGv_i32 t2 = tcg_temp_new_i32(); + + /* truncate to 32-bits */ + tcg_gen_trunc_tl_i32(t1, arg1); + tcg_gen_trunc_tl_i32(t2, arg2); + + tcg_gen_rotl_i32(t1, t1, t2); + + /* sign-extend 64-bits */ + tcg_gen_ext_i32_tl(ret, t1); + + tcg_temp_free_i32(t1); + tcg_temp_free_i32(t2); } static bool trans_rolw(DisasContext *ctx, arg_rolw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_rolw); + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, gen_rolw); } static bool trans_grevw(DisasContext *ctx, arg_grevw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_grevw); + ctx->w = true; + return gen_shift(ctx, a, EXT_ZERO, gen_helper_grev); } static bool trans_greviw(DisasContext *ctx, arg_greviw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_grevw); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_helper_grev); } static bool trans_gorcw(DisasContext *ctx, arg_gorcw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftw(ctx, a, gen_gorcw); + ctx->w = true; + return gen_shift(ctx, a, EXT_ZERO, gen_helper_gorc); } static bool trans_gorciw(DisasContext *ctx, arg_gorciw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_shiftiw(ctx, a, gen_gorcw); + ctx->w = true; + return gen_shift_imm_tl(ctx, a, EXT_ZERO, gen_helper_gorc); } +#define GEN_SHADD_UW(SHAMT) \ +static void gen_sh##SHAMT##add_uw(TCGv ret, TCGv arg1, TCGv arg2) \ +{ \ + TCGv t = tcg_temp_new(); \ + \ + tcg_gen_ext32u_tl(t, arg1); \ + \ + tcg_gen_shli_tl(t, t, SHAMT); \ + tcg_gen_add_tl(ret, t, arg2); \ + \ + tcg_temp_free(t); \ +} + +GEN_SHADD_UW(1) +GEN_SHADD_UW(2) +GEN_SHADD_UW(3) + #define GEN_TRANS_SHADD_UW(SHAMT) \ static bool trans_sh##SHAMT##add_uw(DisasContext *ctx, \ arg_sh##SHAMT##add_uw *a) \ { \ REQUIRE_64BIT(ctx); \ REQUIRE_EXT(ctx, RVB); \ - return gen_arith(ctx, a, gen_sh##SHAMT##add_uw); \ + return gen_arith(ctx, a, EXT_NONE, gen_sh##SHAMT##add_uw); \ } GEN_TRANS_SHADD_UW(1) GEN_TRANS_SHADD_UW(2) GEN_TRANS_SHADD_UW(3) +static void gen_add_uw(TCGv ret, TCGv arg1, TCGv arg2) +{ + tcg_gen_ext32u_tl(arg1, arg1); + tcg_gen_add_tl(ret, arg1, arg2); +} + static bool trans_add_uw(DisasContext *ctx, arg_add_uw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - return gen_arith(ctx, a, gen_add_uw); + return gen_arith(ctx, a, EXT_NONE, gen_add_uw); +} + +static void gen_slli_uw(TCGv dest, TCGv src, target_long shamt) +{ + tcg_gen_deposit_z_tl(dest, src, shamt, MIN(32, TARGET_LONG_BITS - shamt)); } static bool trans_slli_uw(DisasContext *ctx, arg_slli_uw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVB); - - TCGv source1 = tcg_temp_new(); - gen_get_gpr(source1, a->rs1); - - if (a->shamt < 32) { - tcg_gen_deposit_z_tl(source1, source1, a->shamt, 32); - } else { - tcg_gen_shli_tl(source1, source1, a->shamt); - } - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - return true; + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_slli_uw); } diff --git a/target/riscv/insn_trans/trans_rvd.c.inc b/target/riscv/insn_trans/trans_rvd.c.inc index 7e45538ae0..db9ae15755 100644 --- a/target/riscv/insn_trans/trans_rvd.c.inc +++ b/target/riscv/insn_trans/trans_rvd.c.inc @@ -20,30 +20,40 @@ static bool trans_fld(DisasContext *ctx, arg_fld *a) { + TCGv addr; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); - tcg_gen_qemu_ld_i64(cpu_fpr[a->rd], t0, ctx->mem_idx, MO_TEQ); + addr = get_gpr(ctx, a->rs1, EXT_NONE); + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + + tcg_gen_qemu_ld_i64(cpu_fpr[a->rd], addr, ctx->mem_idx, MO_TEQ); mark_fs_dirty(ctx); - tcg_temp_free(t0); return true; } static bool trans_fsd(DisasContext *ctx, arg_fsd *a) { + TCGv addr; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); - tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], t0, ctx->mem_idx, MO_TEQ); + addr = get_gpr(ctx, a->rs1, EXT_NONE); + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + + tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], addr, ctx->mem_idx, MO_TEQ); - tcg_temp_free(t0); return true; } @@ -252,11 +262,10 @@ static bool trans_feq_d(DisasContext *ctx, arg_feq_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_helper_feq_d(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + TCGv dest = dest_gpr(ctx, a->rd); + gen_helper_feq_d(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -265,11 +274,10 @@ static bool trans_flt_d(DisasContext *ctx, arg_flt_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_helper_flt_d(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + TCGv dest = dest_gpr(ctx, a->rd); + gen_helper_flt_d(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -278,11 +286,10 @@ static bool trans_fle_d(DisasContext *ctx, arg_fle_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_helper_fle_d(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + TCGv dest = dest_gpr(ctx, a->rd); + gen_helper_fle_d(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -291,10 +298,10 @@ static bool trans_fclass_d(DisasContext *ctx, arg_fclass_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_helper_fclass_d(t0, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_fclass_d(dest, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -303,12 +310,11 @@ static bool trans_fcvt_w_d(DisasContext *ctx, arg_fcvt_w_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_set_rm(ctx, a->rm); - gen_helper_fcvt_w_d(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_w_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -317,12 +323,11 @@ static bool trans_fcvt_wu_d(DisasContext *ctx, arg_fcvt_wu_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_set_rm(ctx, a->rm); - gen_helper_fcvt_wu_d(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_wu_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -331,12 +336,10 @@ static bool trans_fcvt_d_w(DisasContext *ctx, arg_fcvt_d_w *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN); gen_set_rm(ctx, a->rm); - gen_helper_fcvt_d_w(cpu_fpr[a->rd], cpu_env, t0); - tcg_temp_free(t0); + gen_helper_fcvt_d_w(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); return true; @@ -347,12 +350,10 @@ static bool trans_fcvt_d_wu(DisasContext *ctx, arg_fcvt_d_wu *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); gen_set_rm(ctx, a->rm); - gen_helper_fcvt_d_wu(cpu_fpr[a->rd], cpu_env, t0); - tcg_temp_free(t0); + gen_helper_fcvt_d_wu(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); return true; @@ -364,11 +365,11 @@ static bool trans_fcvt_l_d(DisasContext *ctx, arg_fcvt_l_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); - gen_helper_fcvt_l_d(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + gen_helper_fcvt_l_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -378,11 +379,11 @@ static bool trans_fcvt_lu_d(DisasContext *ctx, arg_fcvt_lu_d *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); - gen_helper_fcvt_lu_d(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + gen_helper_fcvt_lu_d(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -393,7 +394,7 @@ static bool trans_fmv_x_d(DisasContext *ctx, arg_fmv_x_d *a) REQUIRE_EXT(ctx, RVD); #ifdef TARGET_RISCV64 - gen_set_gpr(a->rd, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, cpu_fpr[a->rs1]); return true; #else qemu_build_not_reached(); @@ -406,12 +407,11 @@ static bool trans_fcvt_d_l(DisasContext *ctx, arg_fcvt_d_l *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN); gen_set_rm(ctx, a->rm); - gen_helper_fcvt_d_l(cpu_fpr[a->rd], cpu_env, t0); - tcg_temp_free(t0); + gen_helper_fcvt_d_l(cpu_fpr[a->rd], cpu_env, src); + mark_fs_dirty(ctx); return true; } @@ -422,12 +422,11 @@ static bool trans_fcvt_d_lu(DisasContext *ctx, arg_fcvt_d_lu *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVD); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); gen_set_rm(ctx, a->rm); - gen_helper_fcvt_d_lu(cpu_fpr[a->rd], cpu_env, t0); - tcg_temp_free(t0); + gen_helper_fcvt_d_lu(cpu_fpr[a->rd], cpu_env, src); + mark_fs_dirty(ctx); return true; } @@ -439,11 +438,7 @@ static bool trans_fmv_d_x(DisasContext *ctx, arg_fmv_d_x *a) REQUIRE_EXT(ctx, RVD); #ifdef TARGET_RISCV64 - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - - tcg_gen_mov_tl(cpu_fpr[a->rd], t0); - tcg_temp_free(t0); + tcg_gen_mov_tl(cpu_fpr[a->rd], get_gpr(ctx, a->rs1, EXT_NONE)); mark_fs_dirty(ctx); return true; #else diff --git a/target/riscv/insn_trans/trans_rvf.c.inc b/target/riscv/insn_trans/trans_rvf.c.inc index db1c0c9974..bddbd418d9 100644 --- a/target/riscv/insn_trans/trans_rvf.c.inc +++ b/target/riscv/insn_trans/trans_rvf.c.inc @@ -25,32 +25,43 @@ static bool trans_flw(DisasContext *ctx, arg_flw *a) { + TCGv_i64 dest; + TCGv addr; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); - tcg_gen_qemu_ld_i64(cpu_fpr[a->rd], t0, ctx->mem_idx, MO_TEUL); - gen_nanbox_s(cpu_fpr[a->rd], cpu_fpr[a->rd]); + addr = get_gpr(ctx, a->rs1, EXT_NONE); + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } + + dest = cpu_fpr[a->rd]; + tcg_gen_qemu_ld_i64(dest, addr, ctx->mem_idx, MO_TEUL); + gen_nanbox_s(dest, dest); - tcg_temp_free(t0); mark_fs_dirty(ctx); return true; } static bool trans_fsw(DisasContext *ctx, arg_fsw *a) { + TCGv addr; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); + addr = get_gpr(ctx, a->rs1, EXT_NONE); + if (a->imm) { + TCGv temp = tcg_temp_new(); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } - tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], t0, ctx->mem_idx, MO_TEUL); + tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], addr, ctx->mem_idx, MO_TEUL); - tcg_temp_free(t0); return true; } @@ -200,12 +211,11 @@ static bool trans_fsgnjn_s(DisasContext *ctx, arg_fsgnjn_s *a) * Replace bit 31 in rs1 with inverse in rs2. * This formulation retains the nanboxing of rs1. */ - mask = tcg_const_i64(~MAKE_64BIT_MASK(31, 1)); + mask = tcg_constant_i64(~MAKE_64BIT_MASK(31, 1)); tcg_gen_nor_i64(rs2, rs2, mask); tcg_gen_and_i64(rs1, mask, rs1); tcg_gen_or_i64(cpu_fpr[a->rd], rs1, rs2); - tcg_temp_free_i64(mask); tcg_temp_free_i64(rs2); } tcg_temp_free_i64(rs1); @@ -272,12 +282,11 @@ static bool trans_fcvt_w_s(DisasContext *ctx, arg_fcvt_w_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_set_rm(ctx, a->rm); - gen_helper_fcvt_w_s(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_w_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -286,12 +295,11 @@ static bool trans_fcvt_wu_s(DisasContext *ctx, arg_fcvt_wu_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_set_rm(ctx, a->rm); - gen_helper_fcvt_wu_s(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); + gen_helper_fcvt_wu_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -301,17 +309,15 @@ static bool trans_fmv_x_w(DisasContext *ctx, arg_fmv_x_w *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); #if defined(TARGET_RISCV64) - tcg_gen_ext32s_tl(t0, cpu_fpr[a->rs1]); + tcg_gen_ext32s_tl(dest, cpu_fpr[a->rs1]); #else - tcg_gen_extrl_i64_i32(t0, cpu_fpr[a->rs1]); + tcg_gen_extrl_i64_i32(dest, cpu_fpr[a->rs1]); #endif - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); - + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -319,10 +325,11 @@ static bool trans_feq_s(DisasContext *ctx, arg_feq_s *a) { REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_helper_feq_s(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_feq_s(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -330,10 +337,11 @@ static bool trans_flt_s(DisasContext *ctx, arg_flt_s *a) { REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_helper_flt_s(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_flt_s(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -341,10 +349,11 @@ static bool trans_fle_s(DisasContext *ctx, arg_fle_s *a) { REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_helper_fle_s(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + + TCGv dest = dest_gpr(ctx, a->rd); + + gen_helper_fle_s(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -353,13 +362,10 @@ static bool trans_fclass_s(DisasContext *ctx, arg_fclass_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - - gen_helper_fclass_s(t0, cpu_fpr[a->rs1]); - - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + TCGv dest = dest_gpr(ctx, a->rd); + gen_helper_fclass_s(dest, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -368,15 +374,12 @@ static bool trans_fcvt_s_w(DisasContext *ctx, arg_fcvt_s_w *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN); gen_set_rm(ctx, a->rm); - gen_helper_fcvt_s_w(cpu_fpr[a->rd], cpu_env, t0); + gen_helper_fcvt_s_w(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); - tcg_temp_free(t0); - return true; } @@ -385,15 +388,12 @@ static bool trans_fcvt_s_wu(DisasContext *ctx, arg_fcvt_s_wu *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); gen_set_rm(ctx, a->rm); - gen_helper_fcvt_s_wu(cpu_fpr[a->rd], cpu_env, t0); + gen_helper_fcvt_s_wu(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); - tcg_temp_free(t0); - return true; } @@ -403,15 +403,12 @@ static bool trans_fmv_w_x(DisasContext *ctx, arg_fmv_w_x *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); - tcg_gen_extu_tl_i64(cpu_fpr[a->rd], t0); + tcg_gen_extu_tl_i64(cpu_fpr[a->rd], src); gen_nanbox_s(cpu_fpr[a->rd], cpu_fpr[a->rd]); mark_fs_dirty(ctx); - tcg_temp_free(t0); - return true; } @@ -421,11 +418,11 @@ static bool trans_fcvt_l_s(DisasContext *ctx, arg_fcvt_l_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); - gen_helper_fcvt_l_s(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + gen_helper_fcvt_l_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -435,11 +432,11 @@ static bool trans_fcvt_lu_s(DisasContext *ctx, arg_fcvt_lu_s *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + gen_set_rm(ctx, a->rm); - gen_helper_fcvt_lu_s(t0, cpu_env, cpu_fpr[a->rs1]); - gen_set_gpr(a->rd, t0); - tcg_temp_free(t0); + gen_helper_fcvt_lu_s(dest, cpu_env, cpu_fpr[a->rs1]); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -449,14 +446,12 @@ static bool trans_fcvt_s_l(DisasContext *ctx, arg_fcvt_s_l *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN); gen_set_rm(ctx, a->rm); - gen_helper_fcvt_s_l(cpu_fpr[a->rd], cpu_env, t0); + gen_helper_fcvt_s_l(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); - tcg_temp_free(t0); return true; } @@ -466,13 +461,11 @@ static bool trans_fcvt_s_lu(DisasContext *ctx, arg_fcvt_s_lu *a) REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); - TCGv t0 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); + TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO); gen_set_rm(ctx, a->rm); - gen_helper_fcvt_s_lu(cpu_fpr[a->rd], cpu_env, t0); + gen_helper_fcvt_s_lu(cpu_fpr[a->rd], cpu_env, src); mark_fs_dirty(ctx); - tcg_temp_free(t0); return true; } diff --git a/target/riscv/insn_trans/trans_rvh.c.inc b/target/riscv/insn_trans/trans_rvh.c.inc index 6b5edf82b7..ecbf77ff9c 100644 --- a/target/riscv/insn_trans/trans_rvh.c.inc +++ b/target/riscv/insn_trans/trans_rvh.c.inc @@ -17,281 +17,139 @@ */ #ifndef CONFIG_USER_ONLY -static void check_access(DisasContext *ctx) { +static bool check_access(DisasContext *ctx) +{ if (!ctx->hlsx) { if (ctx->virt_enabled) { generate_exception(ctx, RISCV_EXCP_VIRT_INSTRUCTION_FAULT); } else { generate_exception(ctx, RISCV_EXCP_ILLEGAL_INST); } + return false; } + return true; } #endif -static bool trans_hlv_b(DisasContext *ctx, arg_hlv_b *a) +static bool do_hlv(DisasContext *ctx, arg_r2 *a, MemOp mop) { - REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_SB); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else +#ifdef CONFIG_USER_ONLY return false; +#else + if (check_access(ctx)) { + TCGv dest = dest_gpr(ctx, a->rd); + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + int mem_idx = ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK; + tcg_gen_qemu_ld_tl(dest, addr, mem_idx, mop); + gen_set_gpr(ctx, a->rd, dest); + } + return true; #endif } -static bool trans_hlv_h(DisasContext *ctx, arg_hlv_h *a) +static bool trans_hlv_b(DisasContext *ctx, arg_hlv_b *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TESW); - gen_set_gpr(a->rd, t1); + return do_hlv(ctx, a, MO_SB); +} - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif +static bool trans_hlv_h(DisasContext *ctx, arg_hlv_h *a) +{ + REQUIRE_EXT(ctx, RVH); + return do_hlv(ctx, a, MO_TESW); } static bool trans_hlv_w(DisasContext *ctx, arg_hlv_w *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TESL); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + return do_hlv(ctx, a, MO_TESL); } static bool trans_hlv_bu(DisasContext *ctx, arg_hlv_bu *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_UB); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + return do_hlv(ctx, a, MO_UB); } static bool trans_hlv_hu(DisasContext *ctx, arg_hlv_hu *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TEUW); - gen_set_gpr(a->rd, t1); + return do_hlv(ctx, a, MO_TEUW); +} - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else +static bool do_hsv(DisasContext *ctx, arg_r2_s *a, MemOp mop) +{ +#ifdef CONFIG_USER_ONLY return false; +#else + if (check_access(ctx)) { + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + TCGv data = get_gpr(ctx, a->rs2, EXT_NONE); + int mem_idx = ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK; + tcg_gen_qemu_st_tl(data, addr, mem_idx, mop); + } + return true; #endif } static bool trans_hsv_b(DisasContext *ctx, arg_hsv_b *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - gen_get_gpr(dat, a->rs2); - - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_SB); - - tcg_temp_free(t0); - tcg_temp_free(dat); - return true; -#else - return false; -#endif + return do_hsv(ctx, a, MO_SB); } static bool trans_hsv_h(DisasContext *ctx, arg_hsv_h *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - gen_get_gpr(dat, a->rs2); - - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TESW); - - tcg_temp_free(t0); - tcg_temp_free(dat); - return true; -#else - return false; -#endif + return do_hsv(ctx, a, MO_TESW); } static bool trans_hsv_w(DisasContext *ctx, arg_hsv_w *a) { REQUIRE_EXT(ctx, RVH); -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - gen_get_gpr(dat, a->rs2); - - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TESL); - - tcg_temp_free(t0); - tcg_temp_free(dat); - return true; -#else - return false; -#endif + return do_hsv(ctx, a, MO_TESL); } static bool trans_hlv_wu(DisasContext *ctx, arg_hlv_wu *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVH); - -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TEUL); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + return do_hlv(ctx, a, MO_TEUL); } static bool trans_hlv_d(DisasContext *ctx, arg_hlv_d *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVH); - -#ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TEQ); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; -#else - return false; -#endif + return do_hlv(ctx, a, MO_TEQ); } static bool trans_hsv_d(DisasContext *ctx, arg_hsv_d *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVH); + return do_hsv(ctx, a, MO_TEQ); +} #ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - gen_get_gpr(dat, a->rs2); - - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx | TB_FLAGS_PRIV_HYP_ACCESS_MASK, MO_TEQ); - - tcg_temp_free(t0); - tcg_temp_free(dat); +static bool do_hlvx(DisasContext *ctx, arg_r2 *a, + void (*func)(TCGv, TCGv_env, TCGv)) +{ + if (check_access(ctx)) { + TCGv dest = dest_gpr(ctx, a->rd); + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + func(dest, cpu_env, addr); + gen_set_gpr(ctx, a->rd, dest); + } return true; -#else - return false; -#endif } +#endif static bool trans_hlvx_hu(DisasContext *ctx, arg_hlvx_hu *a) { REQUIRE_EXT(ctx, RVH); #ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - gen_helper_hyp_hlvx_hu(t1, cpu_env, t0); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; + return do_hlvx(ctx, a, gen_helper_hyp_hlvx_hu); #else return false; #endif @@ -301,19 +159,7 @@ static bool trans_hlvx_wu(DisasContext *ctx, arg_hlvx_wu *a) { REQUIRE_EXT(ctx, RVH); #ifndef CONFIG_USER_ONLY - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - - check_access(ctx); - - gen_get_gpr(t0, a->rs1); - - gen_helper_hyp_hlvx_wu(t1, cpu_env, t0); - gen_set_gpr(a->rd, t1); - - tcg_temp_free(t0); - tcg_temp_free(t1); - return true; + return do_hlvx(ctx, a, gen_helper_hyp_hlvx_wu); #else return false; #endif diff --git a/target/riscv/insn_trans/trans_rvi.c.inc b/target/riscv/insn_trans/trans_rvi.c.inc index 6e736c9d0d..920ae0edb3 100644 --- a/target/riscv/insn_trans/trans_rvi.c.inc +++ b/target/riscv/insn_trans/trans_rvi.c.inc @@ -54,24 +54,25 @@ static bool trans_jal(DisasContext *ctx, arg_jal *a) static bool trans_jalr(DisasContext *ctx, arg_jalr *a) { - /* no chaining with JALR */ TCGLabel *misaligned = NULL; - TCGv t0 = tcg_temp_new(); - - gen_get_gpr(cpu_pc, a->rs1); - tcg_gen_addi_tl(cpu_pc, cpu_pc, a->imm); + tcg_gen_addi_tl(cpu_pc, get_gpr(ctx, a->rs1, EXT_NONE), a->imm); tcg_gen_andi_tl(cpu_pc, cpu_pc, (target_ulong)-2); if (!has_ext(ctx, RVC)) { + TCGv t0 = tcg_temp_new(); + misaligned = gen_new_label(); tcg_gen_andi_tl(t0, cpu_pc, 0x2); tcg_gen_brcondi_tl(TCG_COND_NE, t0, 0x0, misaligned); + tcg_temp_free(t0); } if (a->rd != 0) { tcg_gen_movi_tl(cpu_gpr[a->rd], ctx->pc_succ_insn); } + + /* No chaining with JALR. */ lookup_and_goto_ptr(ctx); if (misaligned) { @@ -80,21 +81,18 @@ static bool trans_jalr(DisasContext *ctx, arg_jalr *a) } ctx->base.is_jmp = DISAS_NORETURN; - tcg_temp_free(t0); return true; } static bool gen_branch(DisasContext *ctx, arg_b *a, TCGCond cond) { TCGLabel *l = gen_new_label(); - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); + TCGv src1 = get_gpr(ctx, a->rs1, EXT_SIGN); + TCGv src2 = get_gpr(ctx, a->rs2, EXT_SIGN); - tcg_gen_brcond_tl(cond, source1, source2, l); + tcg_gen_brcond_tl(cond, src1, src2, l); gen_goto_tb(ctx, 1, ctx->pc_succ_insn); + gen_set_label(l); /* branch taken */ if (!has_ext(ctx, RVC) && ((ctx->base.pc_next + a->imm) & 0x3)) { @@ -105,9 +103,6 @@ static bool gen_branch(DisasContext *ctx, arg_b *a, TCGCond cond) } ctx->base.is_jmp = DISAS_NORETURN; - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; } @@ -143,15 +138,17 @@ static bool trans_bgeu(DisasContext *ctx, arg_bgeu *a) static bool gen_load(DisasContext *ctx, arg_lb *a, MemOp memop) { - TCGv t0 = tcg_temp_new(); - TCGv t1 = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); + TCGv dest = dest_gpr(ctx, a->rd); + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } - tcg_gen_qemu_ld_tl(t1, t0, ctx->mem_idx, memop); - gen_set_gpr(a->rd, t1); - tcg_temp_free(t0); - tcg_temp_free(t1); + tcg_gen_qemu_ld_tl(dest, addr, ctx->mem_idx, memop); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -182,19 +179,19 @@ static bool trans_lhu(DisasContext *ctx, arg_lhu *a) static bool gen_store(DisasContext *ctx, arg_sb *a, MemOp memop) { - TCGv t0 = tcg_temp_new(); - TCGv dat = tcg_temp_new(); - gen_get_gpr(t0, a->rs1); - tcg_gen_addi_tl(t0, t0, a->imm); - gen_get_gpr(dat, a->rs2); + TCGv addr = get_gpr(ctx, a->rs1, EXT_NONE); + TCGv data = get_gpr(ctx, a->rs2, EXT_NONE); + + if (a->imm) { + TCGv temp = temp_new(ctx); + tcg_gen_addi_tl(temp, addr, a->imm); + addr = temp; + } - tcg_gen_qemu_st_tl(dat, t0, ctx->mem_idx, memop); - tcg_temp_free(t0); - tcg_temp_free(dat); + tcg_gen_qemu_st_tl(data, addr, ctx->mem_idx, memop); return true; } - static bool trans_sb(DisasContext *ctx, arg_sb *a) { return gen_store(ctx, a, MO_SB); @@ -230,7 +227,7 @@ static bool trans_sd(DisasContext *ctx, arg_sd *a) static bool trans_addi(DisasContext *ctx, arg_addi *a) { - return gen_arith_imm_fn(ctx, a, &tcg_gen_addi_tl); + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_addi_tl); } static void gen_slt(TCGv ret, TCGv s1, TCGv s2) @@ -243,204 +240,167 @@ static void gen_sltu(TCGv ret, TCGv s1, TCGv s2) tcg_gen_setcond_tl(TCG_COND_LTU, ret, s1, s2); } - static bool trans_slti(DisasContext *ctx, arg_slti *a) { - return gen_arith_imm_tl(ctx, a, &gen_slt); + return gen_arith_imm_tl(ctx, a, EXT_SIGN, gen_slt); } static bool trans_sltiu(DisasContext *ctx, arg_sltiu *a) { - return gen_arith_imm_tl(ctx, a, &gen_sltu); + return gen_arith_imm_tl(ctx, a, EXT_SIGN, gen_sltu); } static bool trans_xori(DisasContext *ctx, arg_xori *a) { - return gen_arith_imm_fn(ctx, a, &tcg_gen_xori_tl); + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_xori_tl); } + static bool trans_ori(DisasContext *ctx, arg_ori *a) { - return gen_arith_imm_fn(ctx, a, &tcg_gen_ori_tl); + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_ori_tl); } + static bool trans_andi(DisasContext *ctx, arg_andi *a) { - return gen_arith_imm_fn(ctx, a, &tcg_gen_andi_tl); + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_andi_tl); } + static bool trans_slli(DisasContext *ctx, arg_slli *a) { - return gen_shifti(ctx, a, tcg_gen_shl_tl); + return gen_shift_imm_fn(ctx, a, EXT_NONE, tcg_gen_shli_tl); } static bool trans_srli(DisasContext *ctx, arg_srli *a) { - return gen_shifti(ctx, a, tcg_gen_shr_tl); + return gen_shift_imm_fn(ctx, a, EXT_ZERO, tcg_gen_shri_tl); } static bool trans_srai(DisasContext *ctx, arg_srai *a) { - return gen_shifti(ctx, a, tcg_gen_sar_tl); + return gen_shift_imm_fn(ctx, a, EXT_SIGN, tcg_gen_sari_tl); } static bool trans_add(DisasContext *ctx, arg_add *a) { - return gen_arith(ctx, a, &tcg_gen_add_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_add_tl); } static bool trans_sub(DisasContext *ctx, arg_sub *a) { - return gen_arith(ctx, a, &tcg_gen_sub_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_sub_tl); } static bool trans_sll(DisasContext *ctx, arg_sll *a) { - return gen_shift(ctx, a, &tcg_gen_shl_tl); + return gen_shift(ctx, a, EXT_NONE, tcg_gen_shl_tl); } static bool trans_slt(DisasContext *ctx, arg_slt *a) { - return gen_arith(ctx, a, &gen_slt); + return gen_arith(ctx, a, EXT_SIGN, gen_slt); } static bool trans_sltu(DisasContext *ctx, arg_sltu *a) { - return gen_arith(ctx, a, &gen_sltu); + return gen_arith(ctx, a, EXT_SIGN, gen_sltu); } static bool trans_xor(DisasContext *ctx, arg_xor *a) { - return gen_arith(ctx, a, &tcg_gen_xor_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_xor_tl); } static bool trans_srl(DisasContext *ctx, arg_srl *a) { - return gen_shift(ctx, a, &tcg_gen_shr_tl); + return gen_shift(ctx, a, EXT_ZERO, tcg_gen_shr_tl); } static bool trans_sra(DisasContext *ctx, arg_sra *a) { - return gen_shift(ctx, a, &tcg_gen_sar_tl); + return gen_shift(ctx, a, EXT_SIGN, tcg_gen_sar_tl); } static bool trans_or(DisasContext *ctx, arg_or *a) { - return gen_arith(ctx, a, &tcg_gen_or_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_or_tl); } static bool trans_and(DisasContext *ctx, arg_and *a) { - return gen_arith(ctx, a, &tcg_gen_and_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_and_tl); } static bool trans_addiw(DisasContext *ctx, arg_addiw *a) { REQUIRE_64BIT(ctx); - return gen_arith_imm_tl(ctx, a, &gen_addw); + ctx->w = true; + return gen_arith_imm_fn(ctx, a, EXT_NONE, tcg_gen_addi_tl); } static bool trans_slliw(DisasContext *ctx, arg_slliw *a) { REQUIRE_64BIT(ctx); - return gen_shiftiw(ctx, a, tcg_gen_shl_tl); + ctx->w = true; + return gen_shift_imm_fn(ctx, a, EXT_NONE, tcg_gen_shli_tl); +} + +static void gen_srliw(TCGv dst, TCGv src, target_long shamt) +{ + tcg_gen_extract_tl(dst, src, shamt, 32 - shamt); } static bool trans_srliw(DisasContext *ctx, arg_srliw *a) { REQUIRE_64BIT(ctx); - TCGv t = tcg_temp_new(); - gen_get_gpr(t, a->rs1); - tcg_gen_extract_tl(t, t, a->shamt, 32 - a->shamt); - /* sign-extend for W instructions */ - tcg_gen_ext32s_tl(t, t); - gen_set_gpr(a->rd, t); - tcg_temp_free(t); - return true; + ctx->w = true; + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_srliw); +} + +static void gen_sraiw(TCGv dst, TCGv src, target_long shamt) +{ + tcg_gen_sextract_tl(dst, src, shamt, 32 - shamt); } static bool trans_sraiw(DisasContext *ctx, arg_sraiw *a) { REQUIRE_64BIT(ctx); - TCGv t = tcg_temp_new(); - gen_get_gpr(t, a->rs1); - tcg_gen_sextract_tl(t, t, a->shamt, 32 - a->shamt); - gen_set_gpr(a->rd, t); - tcg_temp_free(t); - return true; + ctx->w = true; + return gen_shift_imm_fn(ctx, a, EXT_NONE, gen_sraiw); } static bool trans_addw(DisasContext *ctx, arg_addw *a) { REQUIRE_64BIT(ctx); - return gen_arith(ctx, a, &gen_addw); + ctx->w = true; + return gen_arith(ctx, a, EXT_NONE, tcg_gen_add_tl); } static bool trans_subw(DisasContext *ctx, arg_subw *a) { REQUIRE_64BIT(ctx); - return gen_arith(ctx, a, &gen_subw); + ctx->w = true; + return gen_arith(ctx, a, EXT_NONE, tcg_gen_sub_tl); } static bool trans_sllw(DisasContext *ctx, arg_sllw *a) { REQUIRE_64BIT(ctx); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - tcg_gen_andi_tl(source2, source2, 0x1F); - tcg_gen_shl_tl(source1, source1, source2); - - tcg_gen_ext32s_tl(source1, source1); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; + ctx->w = true; + return gen_shift(ctx, a, EXT_NONE, tcg_gen_shl_tl); } static bool trans_srlw(DisasContext *ctx, arg_srlw *a) { REQUIRE_64BIT(ctx); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - /* clear upper 32 */ - tcg_gen_ext32u_tl(source1, source1); - tcg_gen_andi_tl(source2, source2, 0x1F); - tcg_gen_shr_tl(source1, source1, source2); - - tcg_gen_ext32s_tl(source1, source1); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; + ctx->w = true; + return gen_shift(ctx, a, EXT_ZERO, tcg_gen_shr_tl); } static bool trans_sraw(DisasContext *ctx, arg_sraw *a) { REQUIRE_64BIT(ctx); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - /* - * first, trick to get it to act like working on 32 bits (get rid of - * upper 32, sign extend to fill space) - */ - tcg_gen_ext32s_tl(source1, source1); - tcg_gen_andi_tl(source2, source2, 0x1F); - tcg_gen_sar_tl(source1, source1, source2); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - - return true; + ctx->w = true; + return gen_shift(ctx, a, EXT_SIGN, tcg_gen_sar_tl); } static bool trans_fence(DisasContext *ctx, arg_fence *a) @@ -466,80 +426,150 @@ static bool trans_fence_i(DisasContext *ctx, arg_fence_i *a) return true; } -#define RISCV_OP_CSR_PRE do {\ - source1 = tcg_temp_new(); \ - csr_store = tcg_temp_new(); \ - dest = tcg_temp_new(); \ - rs1_pass = tcg_temp_new(); \ - gen_get_gpr(source1, a->rs1); \ - tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next); \ - tcg_gen_movi_tl(rs1_pass, a->rs1); \ - tcg_gen_movi_tl(csr_store, a->csr); \ - gen_io_start();\ -} while (0) - -#define RISCV_OP_CSR_POST do {\ - gen_set_gpr(a->rd, dest); \ - tcg_gen_movi_tl(cpu_pc, ctx->pc_succ_insn); \ - exit_tb(ctx); \ - ctx->base.is_jmp = DISAS_NORETURN; \ - tcg_temp_free(source1); \ - tcg_temp_free(csr_store); \ - tcg_temp_free(dest); \ - tcg_temp_free(rs1_pass); \ -} while (0) +static bool do_csr_post(DisasContext *ctx) +{ + /* We may have changed important cpu state -- exit to main loop. */ + tcg_gen_movi_tl(cpu_pc, ctx->pc_succ_insn); + exit_tb(ctx); + ctx->base.is_jmp = DISAS_NORETURN; + return true; +} +static bool do_csrr(DisasContext *ctx, int rd, int rc) +{ + TCGv dest = dest_gpr(ctx, rd); + TCGv_i32 csr = tcg_constant_i32(rc); + + if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { + gen_io_start(); + } + gen_helper_csrr(dest, cpu_env, csr); + gen_set_gpr(ctx, rd, dest); + return do_csr_post(ctx); +} + +static bool do_csrw(DisasContext *ctx, int rc, TCGv src) +{ + TCGv_i32 csr = tcg_constant_i32(rc); + + if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { + gen_io_start(); + } + gen_helper_csrw(cpu_env, csr, src); + return do_csr_post(ctx); +} + +static bool do_csrrw(DisasContext *ctx, int rd, int rc, TCGv src, TCGv mask) +{ + TCGv dest = dest_gpr(ctx, rd); + TCGv_i32 csr = tcg_constant_i32(rc); + + if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) { + gen_io_start(); + } + gen_helper_csrrw(dest, cpu_env, csr, src, mask); + gen_set_gpr(ctx, rd, dest); + return do_csr_post(ctx); +} static bool trans_csrrw(DisasContext *ctx, arg_csrrw *a) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrw(dest, cpu_env, source1, csr_store); - RISCV_OP_CSR_POST; - return true; + TCGv src = get_gpr(ctx, a->rs1, EXT_NONE); + + /* + * If rd == 0, the insn shall not read the csr, nor cause any of the + * side effects that might occur on a csr read. + */ + if (a->rd == 0) { + return do_csrw(ctx, a->csr, src); + } + + TCGv mask = tcg_constant_tl(-1); + return do_csrrw(ctx, a->rd, a->csr, src, mask); } static bool trans_csrrs(DisasContext *ctx, arg_csrrs *a) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrs(dest, cpu_env, source1, csr_store, rs1_pass); - RISCV_OP_CSR_POST; - return true; + /* + * If rs1 == 0, the insn shall not write to the csr at all, nor + * cause any of the side effects that might occur on a csr write. + * Note that if rs1 specifies a register other than x0, holding + * a zero value, the instruction will still attempt to write the + * unmodified value back to the csr and will cause side effects. + */ + if (a->rs1 == 0) { + return do_csrr(ctx, a->rd, a->csr); + } + + TCGv ones = tcg_constant_tl(-1); + TCGv mask = get_gpr(ctx, a->rs1, EXT_ZERO); + return do_csrrw(ctx, a->rd, a->csr, ones, mask); } static bool trans_csrrc(DisasContext *ctx, arg_csrrc *a) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrc(dest, cpu_env, source1, csr_store, rs1_pass); - RISCV_OP_CSR_POST; - return true; + /* + * If rs1 == 0, the insn shall not write to the csr at all, nor + * cause any of the side effects that might occur on a csr write. + * Note that if rs1 specifies a register other than x0, holding + * a zero value, the instruction will still attempt to write the + * unmodified value back to the csr and will cause side effects. + */ + if (a->rs1 == 0) { + return do_csrr(ctx, a->rd, a->csr); + } + + TCGv mask = get_gpr(ctx, a->rs1, EXT_ZERO); + return do_csrrw(ctx, a->rd, a->csr, ctx->zero, mask); } static bool trans_csrrwi(DisasContext *ctx, arg_csrrwi *a) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrw(dest, cpu_env, rs1_pass, csr_store); - RISCV_OP_CSR_POST; - return true; + TCGv src = tcg_constant_tl(a->rs1); + + /* + * If rd == 0, the insn shall not read the csr, nor cause any of the + * side effects that might occur on a csr read. + */ + if (a->rd == 0) { + return do_csrw(ctx, a->csr, src); + } + + TCGv mask = tcg_constant_tl(-1); + return do_csrrw(ctx, a->rd, a->csr, src, mask); } static bool trans_csrrsi(DisasContext *ctx, arg_csrrsi *a) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrs(dest, cpu_env, rs1_pass, csr_store, rs1_pass); - RISCV_OP_CSR_POST; - return true; + /* + * If rs1 == 0, the insn shall not write to the csr at all, nor + * cause any of the side effects that might occur on a csr write. + * Note that if rs1 specifies a register other than x0, holding + * a zero value, the instruction will still attempt to write the + * unmodified value back to the csr and will cause side effects. + */ + if (a->rs1 == 0) { + return do_csrr(ctx, a->rd, a->csr); + } + + TCGv ones = tcg_constant_tl(-1); + TCGv mask = tcg_constant_tl(a->rs1); + return do_csrrw(ctx, a->rd, a->csr, ones, mask); } static bool trans_csrrci(DisasContext *ctx, arg_csrrci *a) { - TCGv source1, csr_store, dest, rs1_pass; - RISCV_OP_CSR_PRE; - gen_helper_csrrc(dest, cpu_env, rs1_pass, csr_store, rs1_pass); - RISCV_OP_CSR_POST; - return true; + /* + * If rs1 == 0, the insn shall not write to the csr at all, nor + * cause any of the side effects that might occur on a csr write. + * Note that if rs1 specifies a register other than x0, holding + * a zero value, the instruction will still attempt to write the + * unmodified value back to the csr and will cause side effects. + */ + if (a->rs1 == 0) { + return do_csrr(ctx, a->rd, a->csr); + } + + TCGv mask = tcg_constant_tl(a->rs1); + return do_csrrw(ctx, a->rd, a->csr, ctx->zero, mask); } diff --git a/target/riscv/insn_trans/trans_rvm.c.inc b/target/riscv/insn_trans/trans_rvm.c.inc index 10ecc456fc..b89a85ad3a 100644 --- a/target/riscv/insn_trans/trans_rvm.c.inc +++ b/target/riscv/insn_trans/trans_rvm.c.inc @@ -22,107 +22,230 @@ static bool trans_mul(DisasContext *ctx, arg_mul *a) { REQUIRE_EXT(ctx, RVM); - return gen_arith(ctx, a, &tcg_gen_mul_tl); + return gen_arith(ctx, a, EXT_NONE, tcg_gen_mul_tl); +} + +static void gen_mulh(TCGv ret, TCGv s1, TCGv s2) +{ + TCGv discard = tcg_temp_new(); + + tcg_gen_muls2_tl(discard, ret, s1, s2); + tcg_temp_free(discard); } static bool trans_mulh(DisasContext *ctx, arg_mulh *a) { REQUIRE_EXT(ctx, RVM); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); + return gen_arith(ctx, a, EXT_NONE, gen_mulh); +} - tcg_gen_muls2_tl(source2, source1, source1, source2); +static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2) +{ + TCGv rl = tcg_temp_new(); + TCGv rh = tcg_temp_new(); + + tcg_gen_mulu2_tl(rl, rh, arg1, arg2); + /* fix up for one negative */ + tcg_gen_sari_tl(rl, arg1, TARGET_LONG_BITS - 1); + tcg_gen_and_tl(rl, rl, arg2); + tcg_gen_sub_tl(ret, rh, rl); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; + tcg_temp_free(rl); + tcg_temp_free(rh); } static bool trans_mulhsu(DisasContext *ctx, arg_mulhsu *a) { REQUIRE_EXT(ctx, RVM); - return gen_arith(ctx, a, &gen_mulhsu); + return gen_arith(ctx, a, EXT_NONE, gen_mulhsu); +} + +static void gen_mulhu(TCGv ret, TCGv s1, TCGv s2) +{ + TCGv discard = tcg_temp_new(); + + tcg_gen_mulu2_tl(discard, ret, s1, s2); + tcg_temp_free(discard); } static bool trans_mulhu(DisasContext *ctx, arg_mulhu *a) { REQUIRE_EXT(ctx, RVM); - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - tcg_gen_mulu2_tl(source2, source1, source1, source2); + return gen_arith(ctx, a, EXT_NONE, gen_mulhu); +} - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; +static void gen_div(TCGv ret, TCGv source1, TCGv source2) +{ + TCGv temp1, temp2, zero, one, mone, min; + + temp1 = tcg_temp_new(); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + mone = tcg_constant_tl(-1); + min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1)); + + /* + * If overflow, set temp2 to 1, else source2. + * This produces the required result of min. + */ + tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min); + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone); + tcg_gen_and_tl(temp1, temp1, temp2); + tcg_gen_movcond_tl(TCG_COND_NE, temp2, temp1, zero, one, source2); + + /* + * If div by zero, set temp1 to -1 and temp2 to 1 to + * produce the required result of -1. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, mone, source1); + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, temp2); + + tcg_gen_div_tl(ret, temp1, temp2); + + tcg_temp_free(temp1); + tcg_temp_free(temp2); } static bool trans_div(DisasContext *ctx, arg_div *a) { REQUIRE_EXT(ctx, RVM); - return gen_arith(ctx, a, &gen_div); + return gen_arith(ctx, a, EXT_SIGN, gen_div); +} + +static void gen_divu(TCGv ret, TCGv source1, TCGv source2) +{ + TCGv temp1, temp2, zero, one, max; + + temp1 = tcg_temp_new(); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + max = tcg_constant_tl(~0); + + /* + * If div by zero, set temp1 to max and temp2 to 1 to + * produce the required result of max. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, max, source1); + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2); + tcg_gen_divu_tl(ret, temp1, temp2); + + tcg_temp_free(temp1); + tcg_temp_free(temp2); } static bool trans_divu(DisasContext *ctx, arg_divu *a) { REQUIRE_EXT(ctx, RVM); - return gen_arith(ctx, a, &gen_divu); + return gen_arith(ctx, a, EXT_ZERO, gen_divu); +} + +static void gen_rem(TCGv ret, TCGv source1, TCGv source2) +{ + TCGv temp1, temp2, zero, one, mone, min; + + temp1 = tcg_temp_new(); + temp2 = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + mone = tcg_constant_tl(-1); + min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1)); + + /* + * If overflow, set temp1 to 0, else source1. + * This avoids a possible host trap, and produces the required result of 0. + */ + tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min); + tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone); + tcg_gen_and_tl(temp1, temp1, temp2); + tcg_gen_movcond_tl(TCG_COND_NE, temp1, temp1, zero, zero, source1); + + /* + * If div by zero, set temp2 to 1, else source2. + * This avoids a possible host trap, but produces an incorrect result. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2); + + tcg_gen_rem_tl(temp1, temp1, temp2); + + /* If div by zero, the required result is the original dividend. */ + tcg_gen_movcond_tl(TCG_COND_EQ, ret, source2, zero, source1, temp1); + + tcg_temp_free(temp1); + tcg_temp_free(temp2); } static bool trans_rem(DisasContext *ctx, arg_rem *a) { REQUIRE_EXT(ctx, RVM); - return gen_arith(ctx, a, &gen_rem); + return gen_arith(ctx, a, EXT_SIGN, gen_rem); +} + +static void gen_remu(TCGv ret, TCGv source1, TCGv source2) +{ + TCGv temp, zero, one; + + temp = tcg_temp_new(); + zero = tcg_constant_tl(0); + one = tcg_constant_tl(1); + + /* + * If div by zero, set temp to 1, else source2. + * This avoids a possible host trap, but produces an incorrect result. + */ + tcg_gen_movcond_tl(TCG_COND_EQ, temp, source2, zero, one, source2); + + tcg_gen_remu_tl(temp, source1, temp); + + /* If div by zero, the required result is the original dividend. */ + tcg_gen_movcond_tl(TCG_COND_EQ, ret, source2, zero, source1, temp); + + tcg_temp_free(temp); } static bool trans_remu(DisasContext *ctx, arg_remu *a) { REQUIRE_EXT(ctx, RVM); - return gen_arith(ctx, a, &gen_remu); + return gen_arith(ctx, a, EXT_ZERO, gen_remu); } static bool trans_mulw(DisasContext *ctx, arg_mulw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVM); - - return gen_arith(ctx, a, &gen_mulw); + ctx->w = true; + return gen_arith(ctx, a, EXT_NONE, tcg_gen_mul_tl); } static bool trans_divw(DisasContext *ctx, arg_divw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVM); - - return gen_arith_div_w(ctx, a, &gen_div); + ctx->w = true; + return gen_arith(ctx, a, EXT_SIGN, gen_div); } static bool trans_divuw(DisasContext *ctx, arg_divuw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVM); - - return gen_arith_div_uw(ctx, a, &gen_divu); + ctx->w = true; + return gen_arith(ctx, a, EXT_ZERO, gen_divu); } static bool trans_remw(DisasContext *ctx, arg_remw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVM); - - return gen_arith_div_w(ctx, a, &gen_rem); + ctx->w = true; + return gen_arith(ctx, a, EXT_SIGN, gen_rem); } static bool trans_remuw(DisasContext *ctx, arg_remuw *a) { REQUIRE_64BIT(ctx); REQUIRE_EXT(ctx, RVM); - - return gen_arith_div_uw(ctx, a, &gen_remu); + ctx->w = true; + return gen_arith(ctx, a, EXT_ZERO, gen_remu); } diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index 83d9a285ba..fa451938f1 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -27,27 +27,22 @@ static bool trans_vsetvl(DisasContext *ctx, arg_vsetvl *a) return false; } - s2 = tcg_temp_new(); - dst = tcg_temp_new(); + s2 = get_gpr(ctx, a->rs2, EXT_ZERO); + dst = dest_gpr(ctx, a->rd); /* Using x0 as the rs1 register specifier, encodes an infinite AVL */ if (a->rs1 == 0) { /* As the mask is at least one bit, RV_VLEN_MAX is >= VLMAX */ - s1 = tcg_const_tl(RV_VLEN_MAX); + s1 = tcg_constant_tl(RV_VLEN_MAX); } else { - s1 = tcg_temp_new(); - gen_get_gpr(s1, a->rs1); + s1 = get_gpr(ctx, a->rs1, EXT_ZERO); } - gen_get_gpr(s2, a->rs2); gen_helper_vsetvl(dst, cpu_env, s1, s2); - gen_set_gpr(a->rd, dst); + gen_set_gpr(ctx, a->rd, dst); + tcg_gen_movi_tl(cpu_pc, ctx->pc_succ_insn); lookup_and_goto_ptr(ctx); ctx->base.is_jmp = DISAS_NORETURN; - - tcg_temp_free(s1); - tcg_temp_free(s2); - tcg_temp_free(dst); return true; } @@ -59,25 +54,21 @@ static bool trans_vsetvli(DisasContext *ctx, arg_vsetvli *a) return false; } - s2 = tcg_const_tl(a->zimm); - dst = tcg_temp_new(); + s2 = tcg_constant_tl(a->zimm); + dst = dest_gpr(ctx, a->rd); /* Using x0 as the rs1 register specifier, encodes an infinite AVL */ if (a->rs1 == 0) { /* As the mask is at least one bit, RV_VLEN_MAX is >= VLMAX */ - s1 = tcg_const_tl(RV_VLEN_MAX); + s1 = tcg_constant_tl(RV_VLEN_MAX); } else { - s1 = tcg_temp_new(); - gen_get_gpr(s1, a->rs1); + s1 = get_gpr(ctx, a->rs1, EXT_ZERO); } gen_helper_vsetvl(dst, cpu_env, s1, s2); - gen_set_gpr(a->rd, dst); + gen_set_gpr(ctx, a->rd, dst); + gen_goto_tb(ctx, 0, ctx->pc_succ_insn); ctx->base.is_jmp = DISAS_NORETURN; - - tcg_temp_free(s1); - tcg_temp_free(s2); - tcg_temp_free(dst); return true; } @@ -174,7 +165,7 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); - base = tcg_temp_new(); + base = get_gpr(s, rs1, EXT_NONE); /* * As simd_desc supports at most 256 bytes, and in this implementation, @@ -183,9 +174,8 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data, * The first part is vlen in bytes, encoded in maxsz of simd_desc. * The second part is lmul, encoded in data of simd_desc. */ - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); - gen_get_gpr(base, rs1); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); @@ -193,8 +183,6 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); - tcg_temp_free(base); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -332,12 +320,10 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); - base = tcg_temp_new(); - stride = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + base = get_gpr(s, rs1, EXT_NONE); + stride = get_gpr(s, rs2, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); - gen_get_gpr(base, rs1); - gen_get_gpr(stride, rs2); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); @@ -345,9 +331,6 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); - tcg_temp_free(base); - tcg_temp_free(stride); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -461,10 +444,9 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); index = tcg_temp_new_ptr(); - base = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + base = get_gpr(s, rs1, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); - gen_get_gpr(base, rs1); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(index, cpu_env, vreg_ofs(s, vs2)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); @@ -474,8 +456,6 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(index); - tcg_temp_free(base); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -593,10 +573,9 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); - base = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + base = get_gpr(s, rs1, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); - gen_get_gpr(base, rs1); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); @@ -604,8 +583,6 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); - tcg_temp_free(base); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -670,10 +647,9 @@ static bool amo_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); index = tcg_temp_new_ptr(); - base = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + base = get_gpr(s, rs1, EXT_NONE); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); - gen_get_gpr(base, rs1); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(index, cpu_env, vreg_ofs(s, vs2)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); @@ -683,8 +659,6 @@ static bool amo_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(index); - tcg_temp_free(base); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -868,13 +842,12 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); - src1 = tcg_temp_new(); - gen_get_gpr(src1, rs1); + src1 = get_gpr(s, rs1, EXT_NONE); data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2)); @@ -885,8 +858,6 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free(src1); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -912,15 +883,12 @@ do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn, if (a->vm && s->vl_eq_vlmax) { TCGv_i64 src1 = tcg_temp_new_i64(); - TCGv tmp = tcg_temp_new(); - gen_get_gpr(tmp, a->rs1); - tcg_gen_ext_tl_i64(src1, tmp); + tcg_gen_ext_tl_i64(src1, get_gpr(s, a->rs1, EXT_SIGN)); gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), src1, MAXSZ(s), MAXSZ(s)); tcg_temp_free_i64(src1); - tcg_temp_free(tmp); return true; } return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); @@ -1014,14 +982,14 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm, mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); if (zx) { - src1 = tcg_const_tl(imm); + src1 = tcg_constant_tl(imm); } else { - src1 = tcg_const_tl(sextract64(imm, 0, 5)); + src1 = tcg_constant_tl(sextract64(imm, 0, 5)); } data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2)); @@ -1032,8 +1000,6 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free(src1); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -1080,9 +1046,8 @@ GEN_OPIVI_GVEC_TRANS(vadd_vi, 0, vadd_vx, addi) static void tcg_gen_gvec_rsubi(unsigned vece, uint32_t dofs, uint32_t aofs, int64_t c, uint32_t oprsz, uint32_t maxsz) { - TCGv_i64 tmp = tcg_const_i64(c); + TCGv_i64 tmp = tcg_constant_i64(c); tcg_gen_gvec_rsubs(vece, dofs, aofs, tmp, oprsz, maxsz); - tcg_temp_free_i64(tmp); } GEN_OPIVI_GVEC_TRANS(vrsub_vi, 0, vrsub_vx, rsubi) @@ -1408,16 +1373,13 @@ do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn, if (a->vm && s->vl_eq_vlmax) { TCGv_i32 src1 = tcg_temp_new_i32(); - TCGv tmp = tcg_temp_new(); - gen_get_gpr(tmp, a->rs1); - tcg_gen_trunc_tl_i32(src1, tmp); + tcg_gen_trunc_tl_i32(src1, get_gpr(s, a->rs1, EXT_NONE)); tcg_gen_extract_i32(src1, src1, 0, s->sew + 3); gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), src1, MAXSZ(s), MAXSZ(s)); tcg_temp_free_i32(src1); - tcg_temp_free(tmp); return true; } return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); @@ -1675,14 +1637,13 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - s1 = tcg_temp_new(); - gen_get_gpr(s1, a->rs1); + s1 = get_gpr(s, a->rs1, EXT_SIGN); if (s->vl_eq_vlmax) { tcg_gen_gvec_dup_tl(s->sew, vreg_ofs(s, a->rd), MAXSZ(s), MAXSZ(s), s1); } else { - TCGv_i32 desc ; + TCGv_i32 desc; TCGv_i64 s1_i64 = tcg_temp_new_i64(); TCGv_ptr dest = tcg_temp_new_ptr(); uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul); @@ -1692,16 +1653,14 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a) }; tcg_gen_ext_tl_i64(s1_i64, s1); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd)); fns[s->sew](dest, s1_i64, cpu_env, desc); tcg_temp_free_ptr(dest); - tcg_temp_free_i32(desc); tcg_temp_free_i64(s1_i64); } - tcg_temp_free(s1); gen_set_label(over); return true; } @@ -1729,15 +1688,13 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - s1 = tcg_const_i64(simm); + s1 = tcg_constant_i64(simm); dest = tcg_temp_new_ptr(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd)); fns[s->sew](dest, s1, cpu_env, desc); tcg_temp_free_ptr(dest); - tcg_temp_free_i32(desc); - tcg_temp_free_i64(s1); gen_set_label(over); } return true; @@ -1866,7 +1823,7 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, dest = tcg_temp_new_ptr(); mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2)); @@ -1877,7 +1834,6 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, tcg_temp_free_ptr(dest); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free_i32(desc); gen_set_label(over); return true; } @@ -2231,12 +2187,11 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a) tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); dest = tcg_temp_new_ptr(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd)); fns[s->sew - 1](dest, cpu_fpr[a->rs1], cpu_env, desc); tcg_temp_free_ptr(dest); - tcg_temp_free_i32(desc); gen_set_label(over); } return true; @@ -2427,19 +2382,17 @@ static bool trans_vmpopc_m(DisasContext *s, arg_rmr *a) mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); - dst = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + dst = dest_gpr(s, a->rd); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, a->rs2)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); gen_helper_vmpopc_m(dst, mask, src2, cpu_env, desc); - gen_set_gpr(a->rd, dst); + gen_set_gpr(s, a->rd, dst); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free(dst); - tcg_temp_free_i32(desc); return true; } return false; @@ -2459,19 +2412,17 @@ static bool trans_vmfirst_m(DisasContext *s, arg_rmr *a) mask = tcg_temp_new_ptr(); src2 = tcg_temp_new_ptr(); - dst = tcg_temp_new(); - desc = tcg_const_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); + dst = dest_gpr(s, a->rd); + desc = tcg_constant_i32(simd_desc(s->vlen / 8, s->vlen / 8, data)); tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, a->rs2)); tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); gen_helper_vmfirst_m(dst, mask, src2, cpu_env, desc); - gen_set_gpr(a->rd, dst); + gen_set_gpr(s, a->rd, dst); tcg_temp_free_ptr(mask); tcg_temp_free_ptr(src2); - tcg_temp_free(dst); - tcg_temp_free_i32(desc); return true; } return false; @@ -2636,15 +2587,13 @@ static void vec_element_loadx(DisasContext *s, TCGv_i64 dest, tcg_temp_free_i32(ofs); /* Flush out-of-range indexing to zero. */ - t_vlmax = tcg_const_i64(vlmax); - t_zero = tcg_const_i64(0); + t_vlmax = tcg_constant_i64(vlmax); + t_zero = tcg_constant_i64(0); tcg_gen_extu_tl_i64(t_idx, idx); tcg_gen_movcond_i64(TCG_COND_LTU, dest, t_idx, t_vlmax, dest, t_zero); - tcg_temp_free_i64(t_vlmax); - tcg_temp_free_i64(t_zero); tcg_temp_free_i64(t_idx); } @@ -2657,7 +2606,7 @@ static void vec_element_loadi(DisasContext *s, TCGv_i64 dest, static bool trans_vext_x_v(DisasContext *s, arg_r *a) { TCGv_i64 tmp = tcg_temp_new_i64(); - TCGv dest = tcg_temp_new(); + TCGv dest = dest_gpr(s, a->rd); if (a->rs1 == 0) { /* Special case vmv.x.s rd, vs2. */ @@ -2667,10 +2616,10 @@ static bool trans_vext_x_v(DisasContext *s, arg_r *a) int vlmax = s->vlen >> (3 + s->sew); vec_element_loadx(s, tmp, a->rs2, cpu_gpr[a->rs1], vlmax); } + tcg_gen_trunc_i64_tl(dest, tmp); - gen_set_gpr(a->rd, dest); + gen_set_gpr(s, a->rd, dest); - tcg_temp_free(dest); tcg_temp_free_i64(tmp); return true; } diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c index 3c48e739ac..ee7c24efe7 100644 --- a/target/riscv/op_helper.c +++ b/target/riscv/op_helper.c @@ -37,11 +37,10 @@ void helper_raise_exception(CPURISCVState *env, uint32_t exception) riscv_raise_exception(env, exception, 0); } -target_ulong helper_csrrw(CPURISCVState *env, target_ulong src, - target_ulong csr) +target_ulong helper_csrr(CPURISCVState *env, int csr) { target_ulong val = 0; - RISCVException ret = riscv_csrrw(env, csr, &val, src, -1); + RISCVException ret = riscv_csrrw(env, csr, &val, 0, 0); if (ret != RISCV_EXCP_NONE) { riscv_raise_exception(env, ret, GETPC()); @@ -49,23 +48,20 @@ target_ulong helper_csrrw(CPURISCVState *env, target_ulong src, return val; } -target_ulong helper_csrrs(CPURISCVState *env, target_ulong src, - target_ulong csr, target_ulong rs1_pass) +void helper_csrw(CPURISCVState *env, int csr, target_ulong src) { - target_ulong val = 0; - RISCVException ret = riscv_csrrw(env, csr, &val, -1, rs1_pass ? src : 0); + RISCVException ret = riscv_csrrw(env, csr, NULL, src, -1); if (ret != RISCV_EXCP_NONE) { riscv_raise_exception(env, ret, GETPC()); } - return val; } -target_ulong helper_csrrc(CPURISCVState *env, target_ulong src, - target_ulong csr, target_ulong rs1_pass) +target_ulong helper_csrrw(CPURISCVState *env, int csr, + target_ulong src, target_ulong write_mask) { target_ulong val = 0; - RISCVException ret = riscv_csrrw(env, csr, &val, 0, rs1_pass ? src : 0); + RISCVException ret = riscv_csrrw(env, csr, &val, src, write_mask); if (ret != RISCV_EXCP_NONE) { riscv_raise_exception(env, ret, GETPC()); diff --git a/target/riscv/translate.c b/target/riscv/translate.c index 6983be5723..e356fc6c46 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -39,15 +39,25 @@ static TCGv load_val; #include "exec/gen-icount.h" +/* + * If an operation is being performed on less than TARGET_LONG_BITS, + * it may require the inputs to be sign- or zero-extended; which will + * depend on the exact operation being performed. + */ +typedef enum { + EXT_NONE, + EXT_SIGN, + EXT_ZERO, +} DisasExtend; + typedef struct DisasContext { DisasContextBase base; /* pc_succ_insn points to the instruction following base.pc_next */ target_ulong pc_succ_insn; target_ulong priv_ver; - bool virt_enabled; + target_ulong misa; uint32_t opcode; uint32_t mstatus_fs; - target_ulong misa; uint32_t mem_idx; /* Remember the rounding mode encoded in the previous fp instruction, which we have already installed into env->fp_status. Or -1 for @@ -55,6 +65,8 @@ typedef struct DisasContext { to any system register, which includes CSR_FRM, so we do not have to reset this known value. */ int frm; + bool w; + bool virt_enabled; bool ext_ifencei; bool hlsx; /* vector extension */ @@ -64,7 +76,11 @@ typedef struct DisasContext { uint16_t vlen; uint16_t mlen; bool vl_eq_vlmax; + uint8_t ntemp; CPUState *cs; + TCGv zero; + /* Space for 3 operands plus 1 extra for address computation. */ + TCGv temp[4]; } DisasContext; static inline bool has_ext(DisasContext *ctx, uint32_t ext) @@ -83,6 +99,13 @@ static inline bool is_32bit(DisasContext *ctx) } #endif +/* The word size for this operation. */ +static inline int oper_len(DisasContext *ctx) +{ + return ctx->w ? 32 : TARGET_LONG_BITS; +} + + /* * RISC-V requires NaN-boxing of narrower width floating point values. * This applies when a 32-bit value is assigned to a 64-bit FP register. @@ -104,20 +127,16 @@ static void gen_nanbox_s(TCGv_i64 out, TCGv_i64 in) */ static void gen_check_nanbox_s(TCGv_i64 out, TCGv_i64 in) { - TCGv_i64 t_max = tcg_const_i64(0xffffffff00000000ull); - TCGv_i64 t_nan = tcg_const_i64(0xffffffff7fc00000ull); + TCGv_i64 t_max = tcg_constant_i64(0xffffffff00000000ull); + TCGv_i64 t_nan = tcg_constant_i64(0xffffffff7fc00000ull); tcg_gen_movcond_i64(TCG_COND_GEU, out, in, t_max, in, t_nan); - tcg_temp_free_i64(t_max); - tcg_temp_free_i64(t_nan); } static void generate_exception(DisasContext *ctx, int excp) { tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next); - TCGv_i32 helper_tmp = tcg_const_i32(excp); - gen_helper_raise_exception(cpu_env, helper_tmp); - tcg_temp_free_i32(helper_tmp); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(excp)); ctx->base.is_jmp = DISAS_NORETURN; } @@ -125,17 +144,13 @@ static void generate_exception_mtval(DisasContext *ctx, int excp) { tcg_gen_movi_tl(cpu_pc, ctx->base.pc_next); tcg_gen_st_tl(cpu_pc, cpu_env, offsetof(CPURISCVState, badaddr)); - TCGv_i32 helper_tmp = tcg_const_i32(excp); - gen_helper_raise_exception(cpu_env, helper_tmp); - tcg_temp_free_i32(helper_tmp); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(excp)); ctx->base.is_jmp = DISAS_NORETURN; } static void gen_exception_debug(void) { - TCGv_i32 helper_tmp = tcg_const_i32(EXCP_DEBUG); - gen_helper_raise_exception(cpu_env, helper_tmp); - tcg_temp_free_i32(helper_tmp); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(EXCP_DEBUG)); } /* Wrapper around tcg_gen_exit_tb that handles single stepping */ @@ -180,151 +195,60 @@ static void gen_goto_tb(DisasContext *ctx, int n, target_ulong dest) } } -/* Wrapper for getting reg values - need to check of reg is zero since - * cpu_gpr[0] is not actually allocated - */ -static inline void gen_get_gpr(TCGv t, int reg_num) -{ - if (reg_num == 0) { - tcg_gen_movi_tl(t, 0); - } else { - tcg_gen_mov_tl(t, cpu_gpr[reg_num]); - } -} - -/* Wrapper for setting reg values - need to check of reg is zero since - * cpu_gpr[0] is not actually allocated. this is more for safety purposes, - * since we usually avoid calling the OP_TYPE_gen function if we see a write to - * $zero +/* + * Wrappers for getting reg values. + * + * The $zero register does not have cpu_gpr[0] allocated -- we supply the + * constant zero as a source, and an uninitialized sink as destination. + * + * Further, we may provide an extension for word operations. */ -static inline void gen_set_gpr(int reg_num_dst, TCGv t) +static TCGv temp_new(DisasContext *ctx) { - if (reg_num_dst != 0) { - tcg_gen_mov_tl(cpu_gpr[reg_num_dst], t); - } + assert(ctx->ntemp < ARRAY_SIZE(ctx->temp)); + return ctx->temp[ctx->ntemp++] = tcg_temp_new(); } -static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2) +static TCGv get_gpr(DisasContext *ctx, int reg_num, DisasExtend ext) { - TCGv rl = tcg_temp_new(); - TCGv rh = tcg_temp_new(); - - tcg_gen_mulu2_tl(rl, rh, arg1, arg2); - /* fix up for one negative */ - tcg_gen_sari_tl(rl, arg1, TARGET_LONG_BITS - 1); - tcg_gen_and_tl(rl, rl, arg2); - tcg_gen_sub_tl(ret, rh, rl); + TCGv t; - tcg_temp_free(rl); - tcg_temp_free(rh); -} - -static void gen_div(TCGv ret, TCGv source1, TCGv source2) -{ - TCGv cond1, cond2, zeroreg, resultopt1; - /* - * Handle by altering args to tcg_gen_div to produce req'd results: - * For overflow: want source1 in source1 and 1 in source2 - * For div by zero: want -1 in source1 and 1 in source2 -> -1 result - */ - cond1 = tcg_temp_new(); - cond2 = tcg_temp_new(); - zeroreg = tcg_const_tl(0); - resultopt1 = tcg_temp_new(); - - tcg_gen_movi_tl(resultopt1, (target_ulong)-1); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)(~0L)); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1, - ((target_ulong)1) << (TARGET_LONG_BITS - 1)); - tcg_gen_and_tl(cond1, cond1, cond2); /* cond1 = overflow */ - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, 0); /* cond2 = div 0 */ - /* if div by zero, set source1 to -1, otherwise don't change */ - tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond2, zeroreg, source1, - resultopt1); - /* if overflow or div by zero, set source2 to 1, else don't change */ - tcg_gen_or_tl(cond1, cond1, cond2); - tcg_gen_movi_tl(resultopt1, (target_ulong)1); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, - resultopt1); - tcg_gen_div_tl(ret, source1, source2); - - tcg_temp_free(cond1); - tcg_temp_free(cond2); - tcg_temp_free(zeroreg); - tcg_temp_free(resultopt1); -} + if (reg_num == 0) { + return ctx->zero; + } -static void gen_divu(TCGv ret, TCGv source1, TCGv source2) -{ - TCGv cond1, zeroreg, resultopt1; - cond1 = tcg_temp_new(); - - zeroreg = tcg_const_tl(0); - resultopt1 = tcg_temp_new(); - - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); - tcg_gen_movi_tl(resultopt1, (target_ulong)-1); - tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond1, zeroreg, source1, - resultopt1); - tcg_gen_movi_tl(resultopt1, (target_ulong)1); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, - resultopt1); - tcg_gen_divu_tl(ret, source1, source2); - - tcg_temp_free(cond1); - tcg_temp_free(zeroreg); - tcg_temp_free(resultopt1); + switch (ctx->w ? ext : EXT_NONE) { + case EXT_NONE: + return cpu_gpr[reg_num]; + case EXT_SIGN: + t = temp_new(ctx); + tcg_gen_ext32s_tl(t, cpu_gpr[reg_num]); + return t; + case EXT_ZERO: + t = temp_new(ctx); + tcg_gen_ext32u_tl(t, cpu_gpr[reg_num]); + return t; + } + g_assert_not_reached(); } -static void gen_rem(TCGv ret, TCGv source1, TCGv source2) +static TCGv dest_gpr(DisasContext *ctx, int reg_num) { - TCGv cond1, cond2, zeroreg, resultopt1; - - cond1 = tcg_temp_new(); - cond2 = tcg_temp_new(); - zeroreg = tcg_const_tl(0); - resultopt1 = tcg_temp_new(); - - tcg_gen_movi_tl(resultopt1, 1L); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)-1); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1, - (target_ulong)1 << (TARGET_LONG_BITS - 1)); - tcg_gen_and_tl(cond2, cond1, cond2); /* cond1 = overflow */ - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); /* cond2 = div 0 */ - /* if overflow or div by zero, set source2 to 1, else don't change */ - tcg_gen_or_tl(cond2, cond1, cond2); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond2, zeroreg, source2, - resultopt1); - tcg_gen_rem_tl(resultopt1, source1, source2); - /* if div by zero, just return the original dividend */ - tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1, - source1); - - tcg_temp_free(cond1); - tcg_temp_free(cond2); - tcg_temp_free(zeroreg); - tcg_temp_free(resultopt1); + if (reg_num == 0 || ctx->w) { + return temp_new(ctx); + } + return cpu_gpr[reg_num]; } -static void gen_remu(TCGv ret, TCGv source1, TCGv source2) +static void gen_set_gpr(DisasContext *ctx, int reg_num, TCGv t) { - TCGv cond1, zeroreg, resultopt1; - cond1 = tcg_temp_new(); - zeroreg = tcg_const_tl(0); - resultopt1 = tcg_temp_new(); - - tcg_gen_movi_tl(resultopt1, (target_ulong)1); - tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); - tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2, - resultopt1); - tcg_gen_remu_tl(resultopt1, source1, source2); - /* if div by zero, just return the original dividend */ - tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1, - source1); - - tcg_temp_free(cond1); - tcg_temp_free(zeroreg); - tcg_temp_free(resultopt1); + if (reg_num != 0) { + if (ctx->w) { + tcg_gen_ext32s_tl(cpu_gpr[reg_num], t); + } else { + tcg_gen_mov_tl(cpu_gpr[reg_num], t); + } + } } static void gen_jal(DisasContext *ctx, int rd, target_ulong imm) @@ -384,15 +308,11 @@ static inline void mark_fs_dirty(DisasContext *ctx) { } static void gen_set_rm(DisasContext *ctx, int rm) { - TCGv_i32 t0; - if (ctx->frm == rm) { return; } ctx->frm = rm; - t0 = tcg_const_i32(rm); - gen_helper_set_rounding_mode(cpu_env, t0); - tcg_temp_free_i32(t0); + gen_helper_set_rounding_mode(cpu_env, tcg_constant_i32(rm)); } static int ex_plus_1(DisasContext *ctx, int nf) @@ -437,355 +357,108 @@ static int ex_rvc_shifti(DisasContext *ctx, int imm) /* Include the auto-generated decoder for 32 bit insn */ #include "decode-insn32.c.inc" -static bool gen_arith_imm_fn(DisasContext *ctx, arg_i *a, +static bool gen_arith_imm_fn(DisasContext *ctx, arg_i *a, DisasExtend ext, void (*func)(TCGv, TCGv, target_long)) { - TCGv source1; - source1 = tcg_temp_new(); + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); - gen_get_gpr(source1, a->rs1); + func(dest, src1, a->imm); - (*func)(source1, source1, a->imm); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); + gen_set_gpr(ctx, a->rd, dest); return true; } -static bool gen_arith_imm_tl(DisasContext *ctx, arg_i *a, +static bool gen_arith_imm_tl(DisasContext *ctx, arg_i *a, DisasExtend ext, void (*func)(TCGv, TCGv, TCGv)) { - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - tcg_gen_movi_tl(source2, a->imm); + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + TCGv src2 = tcg_constant_tl(a->imm); - (*func)(source1, source1, source2); + func(dest, src1, src2); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); + gen_set_gpr(ctx, a->rd, dest); return true; } -static void gen_addw(TCGv ret, TCGv arg1, TCGv arg2) +static bool gen_arith(DisasContext *ctx, arg_r *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) { - tcg_gen_add_tl(ret, arg1, arg2); - tcg_gen_ext32s_tl(ret, ret); -} + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + TCGv src2 = get_gpr(ctx, a->rs2, ext); -static void gen_subw(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_sub_tl(ret, arg1, arg2); - tcg_gen_ext32s_tl(ret, ret); -} - -static void gen_mulw(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_mul_tl(ret, arg1, arg2); - tcg_gen_ext32s_tl(ret, ret); -} + func(dest, src1, src2); -static bool gen_arith_div_w(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - tcg_gen_ext32s_tl(source1, source1); - tcg_gen_ext32s_tl(source2, source2); - - (*func)(source1, source1, source2); - - tcg_gen_ext32s_tl(source1, source1); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; -} - -static bool gen_arith_div_uw(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - tcg_gen_ext32u_tl(source1, source1); - tcg_gen_ext32u_tl(source2, source2); - - (*func)(source1, source1, source2); - - tcg_gen_ext32s_tl(source1, source1); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); + gen_set_gpr(ctx, a->rd, dest); return true; } -static void gen_pack(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_deposit_tl(ret, arg1, arg2, - TARGET_LONG_BITS / 2, - TARGET_LONG_BITS / 2); -} - -static void gen_packu(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv t = tcg_temp_new(); - tcg_gen_shri_tl(t, arg1, TARGET_LONG_BITS / 2); - tcg_gen_deposit_tl(ret, arg2, t, 0, TARGET_LONG_BITS / 2); - tcg_temp_free(t); -} - -static void gen_packh(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv t = tcg_temp_new(); - tcg_gen_ext8u_tl(t, arg2); - tcg_gen_deposit_tl(ret, arg1, t, 8, TARGET_LONG_BITS - 8); - tcg_temp_free(t); -} - -static void gen_sbop_mask(TCGv ret, TCGv shamt) -{ - tcg_gen_movi_tl(ret, 1); - tcg_gen_shl_tl(ret, ret, shamt); -} - -static void gen_bset(TCGv ret, TCGv arg1, TCGv shamt) -{ - TCGv t = tcg_temp_new(); - - gen_sbop_mask(t, shamt); - tcg_gen_or_tl(ret, arg1, t); - - tcg_temp_free(t); -} - -static void gen_bclr(TCGv ret, TCGv arg1, TCGv shamt) -{ - TCGv t = tcg_temp_new(); - - gen_sbop_mask(t, shamt); - tcg_gen_andc_tl(ret, arg1, t); - - tcg_temp_free(t); -} - -static void gen_binv(TCGv ret, TCGv arg1, TCGv shamt) -{ - TCGv t = tcg_temp_new(); - - gen_sbop_mask(t, shamt); - tcg_gen_xor_tl(ret, arg1, t); - - tcg_temp_free(t); -} - -static void gen_bext(TCGv ret, TCGv arg1, TCGv shamt) -{ - tcg_gen_shr_tl(ret, arg1, shamt); - tcg_gen_andi_tl(ret, ret, 1); -} - -static void gen_slo(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_not_tl(ret, arg1); - tcg_gen_shl_tl(ret, ret, arg2); - tcg_gen_not_tl(ret, ret); -} - -static void gen_sro(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_not_tl(ret, arg1); - tcg_gen_shr_tl(ret, ret, arg2); - tcg_gen_not_tl(ret, ret); -} - -static bool gen_grevi(DisasContext *ctx, arg_grevi *a) +static bool gen_shift_imm_fn(DisasContext *ctx, arg_shift *a, DisasExtend ext, + void (*func)(TCGv, TCGv, target_long)) { - TCGv source1 = tcg_temp_new(); - TCGv source2; + TCGv dest, src1; + int max_len = oper_len(ctx); - gen_get_gpr(source1, a->rs1); - - if (a->shamt == (TARGET_LONG_BITS - 8)) { - /* rev8, byte swaps */ - tcg_gen_bswap_tl(source1, source1); - } else { - source2 = tcg_temp_new(); - tcg_gen_movi_tl(source2, a->shamt); - gen_helper_grev(source1, source1, source2); - tcg_temp_free(source2); + if (a->shamt >= max_len) { + return false; } - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - return true; -} - -#define GEN_SHADD(SHAMT) \ -static void gen_sh##SHAMT##add(TCGv ret, TCGv arg1, TCGv arg2) \ -{ \ - TCGv t = tcg_temp_new(); \ - \ - tcg_gen_shli_tl(t, arg1, SHAMT); \ - tcg_gen_add_tl(ret, t, arg2); \ - \ - tcg_temp_free(t); \ -} - -GEN_SHADD(1) -GEN_SHADD(2) -GEN_SHADD(3) - -static void gen_ctzw(TCGv ret, TCGv arg1) -{ - tcg_gen_ori_tl(ret, arg1, (target_ulong)MAKE_64BIT_MASK(32, 32)); - tcg_gen_ctzi_tl(ret, ret, 64); -} - -static void gen_clzw(TCGv ret, TCGv arg1) -{ - tcg_gen_ext32u_tl(ret, arg1); - tcg_gen_clzi_tl(ret, ret, 64); - tcg_gen_subi_tl(ret, ret, 32); -} - -static void gen_cpopw(TCGv ret, TCGv arg1) -{ - tcg_gen_ext32u_tl(arg1, arg1); - tcg_gen_ctpop_tl(ret, arg1); -} - -static void gen_packw(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv t = tcg_temp_new(); - tcg_gen_ext16s_tl(t, arg2); - tcg_gen_deposit_tl(ret, arg1, t, 16, 48); - tcg_temp_free(t); -} - -static void gen_packuw(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv t = tcg_temp_new(); - tcg_gen_shri_tl(t, arg1, 16); - tcg_gen_deposit_tl(ret, arg2, t, 0, 16); - tcg_gen_ext32s_tl(ret, ret); - tcg_temp_free(t); -} - -static void gen_rorw(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv_i32 t1 = tcg_temp_new_i32(); - TCGv_i32 t2 = tcg_temp_new_i32(); - - /* truncate to 32-bits */ - tcg_gen_trunc_tl_i32(t1, arg1); - tcg_gen_trunc_tl_i32(t2, arg2); - - tcg_gen_rotr_i32(t1, t1, t2); - - /* sign-extend 64-bits */ - tcg_gen_ext_i32_tl(ret, t1); - - tcg_temp_free_i32(t1); - tcg_temp_free_i32(t2); -} - -static void gen_rolw(TCGv ret, TCGv arg1, TCGv arg2) -{ - TCGv_i32 t1 = tcg_temp_new_i32(); - TCGv_i32 t2 = tcg_temp_new_i32(); + dest = dest_gpr(ctx, a->rd); + src1 = get_gpr(ctx, a->rs1, ext); - /* truncate to 32-bits */ - tcg_gen_trunc_tl_i32(t1, arg1); - tcg_gen_trunc_tl_i32(t2, arg2); + func(dest, src1, a->shamt); - tcg_gen_rotl_i32(t1, t1, t2); - - /* sign-extend 64-bits */ - tcg_gen_ext_i32_tl(ret, t1); - - tcg_temp_free_i32(t1); - tcg_temp_free_i32(t2); + gen_set_gpr(ctx, a->rd, dest); + return true; } -static void gen_grevw(TCGv ret, TCGv arg1, TCGv arg2) +static bool gen_shift_imm_tl(DisasContext *ctx, arg_shift *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) { - tcg_gen_ext32u_tl(arg1, arg1); - gen_helper_grev(ret, arg1, arg2); -} + TCGv dest, src1, src2; + int max_len = oper_len(ctx); -static void gen_gorcw(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_ext32u_tl(arg1, arg1); - gen_helper_gorcw(ret, arg1, arg2); -} + if (a->shamt >= max_len) { + return false; + } -#define GEN_SHADD_UW(SHAMT) \ -static void gen_sh##SHAMT##add_uw(TCGv ret, TCGv arg1, TCGv arg2) \ -{ \ - TCGv t = tcg_temp_new(); \ - \ - tcg_gen_ext32u_tl(t, arg1); \ - \ - tcg_gen_shli_tl(t, t, SHAMT); \ - tcg_gen_add_tl(ret, t, arg2); \ - \ - tcg_temp_free(t); \ -} + dest = dest_gpr(ctx, a->rd); + src1 = get_gpr(ctx, a->rs1, ext); + src2 = tcg_constant_tl(a->shamt); -GEN_SHADD_UW(1) -GEN_SHADD_UW(2) -GEN_SHADD_UW(3) + func(dest, src1, src2); -static void gen_add_uw(TCGv ret, TCGv arg1, TCGv arg2) -{ - tcg_gen_ext32u_tl(arg1, arg1); - tcg_gen_add_tl(ret, arg1, arg2); + gen_set_gpr(ctx, a->rd, dest); + return true; } -static bool gen_arith(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) +static bool gen_shift(DisasContext *ctx, arg_r *a, DisasExtend ext, + void (*func)(TCGv, TCGv, TCGv)) { - TCGv source1, source2; - source1 = tcg_temp_new(); - source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); + TCGv src2 = get_gpr(ctx, a->rs2, EXT_NONE); + TCGv ext2 = tcg_temp_new(); - (*func)(source1, source1, source2); + tcg_gen_andi_tl(ext2, src2, oper_len(ctx) - 1); + func(dest, src1, ext2); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); + gen_set_gpr(ctx, a->rd, dest); + tcg_temp_free(ext2); return true; } -static bool gen_shift(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) +static bool gen_unary(DisasContext *ctx, arg_r2 *a, DisasExtend ext, + void (*func)(TCGv, TCGv)) { - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); + TCGv dest = dest_gpr(ctx, a->rd); + TCGv src1 = get_gpr(ctx, a->rs1, ext); - tcg_gen_andi_tl(source2, source2, TARGET_LONG_BITS - 1); - (*func)(source1, source1, source2); + func(dest, src1); - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); + gen_set_gpr(ctx, a->rd, dest); return true; } @@ -798,88 +471,6 @@ static uint32_t opcode_at(DisasContextBase *dcbase, target_ulong pc) return cpu_ldl_code(env, pc); } -static bool gen_shifti(DisasContext *ctx, arg_shift *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - if (a->shamt >= TARGET_LONG_BITS) { - return false; - } - - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - - tcg_gen_movi_tl(source2, a->shamt); - (*func)(source1, source1, source2); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; -} - -static bool gen_shiftw(DisasContext *ctx, arg_r *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - gen_get_gpr(source2, a->rs2); - - tcg_gen_andi_tl(source2, source2, 31); - (*func)(source1, source1, source2); - tcg_gen_ext32s_tl(source1, source1); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; -} - -static bool gen_shiftiw(DisasContext *ctx, arg_shift *a, - void(*func)(TCGv, TCGv, TCGv)) -{ - TCGv source1 = tcg_temp_new(); - TCGv source2 = tcg_temp_new(); - - gen_get_gpr(source1, a->rs1); - tcg_gen_movi_tl(source2, a->shamt); - - (*func)(source1, source1, source2); - tcg_gen_ext32s_tl(source1, source1); - - gen_set_gpr(a->rd, source1); - tcg_temp_free(source1); - tcg_temp_free(source2); - return true; -} - -static void gen_ctz(TCGv ret, TCGv arg1) -{ - tcg_gen_ctzi_tl(ret, arg1, TARGET_LONG_BITS); -} - -static void gen_clz(TCGv ret, TCGv arg1) -{ - tcg_gen_clzi_tl(ret, arg1, TARGET_LONG_BITS); -} - -static bool gen_unary(DisasContext *ctx, arg_r2 *a, - void(*func)(TCGv, TCGv)) -{ - TCGv source = tcg_temp_new(); - - gen_get_gpr(source, a->rs1); - - (*func)(source, source); - - gen_set_gpr(a->rd, source); - tcg_temp_free(source); - return true; -} - /* Include insn module translation function */ #include "insn_trans/trans_rvi.c.inc" #include "insn_trans/trans_rvm.c.inc" @@ -948,6 +539,11 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) ctx->mlen = 1 << (ctx->sew + 3 - ctx->lmul); ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX); ctx->cs = cs; + ctx->w = false; + ctx->ntemp = 0; + memset(ctx->temp, 0, sizeof(ctx->temp)); + + ctx->zero = tcg_constant_tl(0); } static void riscv_tr_tb_start(DisasContextBase *db, CPUState *cpu) @@ -969,6 +565,13 @@ static void riscv_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) decode_opc(env, ctx, opcode16); ctx->base.pc_next = ctx->pc_succ_insn; + ctx->w = false; + + for (int i = ctx->ntemp - 1; i >= 0; --i) { + tcg_temp_free(ctx->temp[i]); + ctx->temp[i] = NULL; + } + ctx->ntemp = 0; if (ctx->base.is_jmp == DISAS_NEXT) { target_ulong page_start; @@ -1029,9 +632,11 @@ void riscv_translate_init(void) { int i; - /* cpu_gpr[0] is a placeholder for the zero register. Do not use it. */ - /* Use the gen_set_gpr and gen_get_gpr helper functions when accessing */ - /* registers, unless you specifically block reads/writes to reg 0 */ + /* + * cpu_gpr[0] is a placeholder for the zero register. Do not use it. + * Use the gen_set_gpr and get_gpr helper functions when accessing regs, + * unless you specifically block reads/writes to reg 0. + */ cpu_gpr[0] = NULL; for (i = 1; i < 32; i++) { diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index 5248c8097d..0a49c0e276 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -475,7 +475,7 @@ class BootLinuxConsole(LinuxKernelTest): def test_arm_raspi2_uart0(self): """ :avocado: tags=arch:arm - :avocado: tags=machine:raspi2 + :avocado: tags=machine:raspi2b :avocado: tags=device:pl011 :avocado: tags=accel:tcg """ @@ -484,7 +484,7 @@ class BootLinuxConsole(LinuxKernelTest): def test_arm_raspi2_initrd(self): """ :avocado: tags=arch:arm - :avocado: tags=machine:raspi2 + :avocado: tags=machine:raspi2b """ deb_url = ('http://archive.raspberrypi.org/debian/' 'pool/main/r/raspberrypi-firmware/' @@ -971,7 +971,7 @@ class BootLinuxConsole(LinuxKernelTest): def test_aarch64_raspi3_atf(self): """ :avocado: tags=arch:aarch64 - :avocado: tags=machine:raspi3 + :avocado: tags=machine:raspi3b :avocado: tags=cpu:cortex-a53 :avocado: tags=device:pl011 :avocado: tags=atf diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c index 8252b85bb8..90a87f0ea9 100644 --- a/tests/qtest/arm-cpu-features.c +++ b/tests/qtest/arm-cpu-features.c @@ -473,6 +473,19 @@ static void test_query_cpu_model_expansion(const void *data) assert_has_feature_enabled(qts, "cortex-a57", "pmu"); assert_has_feature_enabled(qts, "cortex-a57", "aarch64"); + assert_has_feature_enabled(qts, "a64fx", "pmu"); + assert_has_feature_enabled(qts, "a64fx", "aarch64"); + /* + * A64FX does not support any other vector lengths besides those + * that are enabled by default(128bit, 256bits, 512bit). + */ + assert_has_feature_enabled(qts, "a64fx", "sve"); + assert_sve_vls(qts, "a64fx", 0xb, NULL); + assert_error(qts, "a64fx", "cannot enable sve384", + "{ 'sve384': true }"); + assert_error(qts, "a64fx", "cannot enable sve640", + "{ 'sve640': true }"); + sve_tests_default(qts, "max"); pauth_tests_default(qts, "max"); diff --git a/tests/qtest/boot-serial-test.c b/tests/qtest/boot-serial-test.c index 96849cec91..83828ba270 100644 --- a/tests/qtest/boot-serial-test.c +++ b/tests/qtest/boot-serial-test.c @@ -173,7 +173,7 @@ static testdef_t tests[] = { sizeof(kernel_pls3adsp1800), kernel_pls3adsp1800 }, { "microblazeel", "petalogix-ml605", "", "TT", sizeof(kernel_plml605), kernel_plml605 }, - { "arm", "raspi2", "", "TT", sizeof(bios_raspi2), 0, bios_raspi2 }, + { "arm", "raspi2b", "", "TT", sizeof(bios_raspi2), 0, bios_raspi2 }, /* For hppa, force bios to output to serial by disabling graphics. */ { "hppa", "hppa", "-vga none", "SeaBIOS wants SYSTEM HALT" }, { "aarch64", "virt", "-cpu max", "TT", sizeof(kernel_aarch64), diff --git a/tests/qtest/fuzz-xlnx-dp-test.c b/tests/qtest/fuzz-xlnx-dp-test.c new file mode 100644 index 0000000000..69eb6c0eb1 --- /dev/null +++ b/tests/qtest/fuzz-xlnx-dp-test.c @@ -0,0 +1,33 @@ +/* + * QTest fuzzer-generated testcase for xlnx-dp display device + * + * Copyright (c) 2021 Qiang Liu <cyruscyliu@gmail.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "libqos/libqtest.h" + +/* + * This used to trigger the out-of-bounds read in xlnx_dp_read + */ +static void test_fuzz_xlnx_dp_0x3ac(void) +{ + QTestState *s = qtest_init("-M xlnx-zcu102 -display none "); + qtest_readl(s, 0xfd4a03ac); + qtest_quit(s); +} + +int main(int argc, char **argv) +{ + const char *arch = qtest_get_arch(); + + g_test_init(&argc, &argv, NULL); + + if (strcmp(arch, "aarch64") == 0) { + qtest_add_func("fuzz/test_fuzz_xlnx_dp/3ac", test_fuzz_xlnx_dp_0x3ac); + } + + return g_test_run(); +} diff --git a/tests/qtest/libqos/arm-raspi2-machine.c b/tests/qtest/libqos/arm-raspi2-machine.c index 35bb4709a4..09ca863c10 100644 --- a/tests/qtest/libqos/arm-raspi2-machine.c +++ b/tests/qtest/libqos/arm-raspi2-machine.c @@ -42,7 +42,7 @@ static void *raspi2_get_driver(void *object, const char *interface) return &machine->alloc; } - fprintf(stderr, "%s not present in arm/raspi2\n", interface); + fprintf(stderr, "%s not present in arm/raspi2b\n", interface); g_assert_not_reached(); } @@ -53,7 +53,7 @@ static QOSGraphObject *raspi2_get_device(void *obj, const char *device) return &machine->sdhci.obj; } - fprintf(stderr, "%s not present in arm/raspi2\n", device); + fprintf(stderr, "%s not present in arm/raspi2b\n", device); g_assert_not_reached(); } @@ -85,8 +85,8 @@ static void *qos_create_machine_arm_raspi2(QTestState *qts) static void raspi2_register_nodes(void) { - qos_node_create_machine("arm/raspi2", qos_create_machine_arm_raspi2); - qos_node_contains("arm/raspi2", "generic-sdhci", NULL); + qos_node_create_machine("arm/raspi2b", qos_create_machine_arm_raspi2); + qos_node_contains("arm/raspi2b", "generic-sdhci", NULL); } libqos_init(raspi2_register_nodes); diff --git a/tests/qtest/libqos/qgraph.h b/tests/qtest/libqos/qgraph.h index 54672350c8..871740c0dc 100644 --- a/tests/qtest/libqos/qgraph.h +++ b/tests/qtest/libqos/qgraph.h @@ -252,17 +252,17 @@ void qos_node_create_driver_named(const char *name, const char *qemu_name, * This function can be useful when there are multiple devices * with the same node name contained in a machine/other node * - * For example, if ``arm/raspi2`` contains 2 ``generic-sdhci`` + * For example, if ``arm/raspi2b`` contains 2 ``generic-sdhci`` * devices, the right commands will be: * * .. code:: * - * qos_node_create_machine("arm/raspi2"); + * qos_node_create_machine("arm/raspi2b"); * qos_node_create_driver("generic-sdhci", constructor); * // assume rest of the fields are set NULL * QOSGraphEdgeOptions op1 = { .edge_name = "emmc" }; * QOSGraphEdgeOptions op2 = { .edge_name = "sdcard" }; - * qos_node_contains("arm/raspi2", "generic-sdhci", &op1, &op2, NULL); + * qos_node_contains("arm/raspi2b", "generic-sdhci", &op1, &op2, NULL); * * Of course this also requires that the @container's get_device function * should implement a case for "emmc" and "sdcard". diff --git a/tests/qtest/libqos/qgraph_internal.h b/tests/qtest/libqos/qgraph_internal.h index c0025f5ab9..7d62fd17af 100644 --- a/tests/qtest/libqos/qgraph_internal.h +++ b/tests/qtest/libqos/qgraph_internal.h @@ -230,7 +230,7 @@ void qos_graph_foreach_test_path(QOSTestCallback fn); /** * qos_get_machine_type(): return QEMU machine type for a machine node. * This function requires every machine @name to be in the form - * <arch>/<machine_name>, like "arm/raspi2" or "x86_64/pc". + * <arch>/<machine_name>, like "arm/raspi2b" or "x86_64/pc". * * The function will validate the format and return a pointer to * @machine to <machine_name>. For example, when passed "x86_64/pc" diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index 2bc3efd49f..757bb8499a 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -187,6 +187,7 @@ qtests_aarch64 = \ 'numa-test', 'boot-serial-test', 'xlnx-can-test', + 'fuzz-xlnx-dp-test', 'migration-test'] qtests_s390x = \ diff --git a/tests/tcg/riscv64/Makefile.target b/tests/tcg/riscv64/Makefile.target new file mode 100644 index 0000000000..d41bf6d60d --- /dev/null +++ b/tests/tcg/riscv64/Makefile.target @@ -0,0 +1,5 @@ +# -*- Mode: makefile -*- +# RISC-V specific tweaks + +VPATH += $(SRC_PATH)/tests/tcg/riscv64 +TESTS += test-div diff --git a/tests/tcg/riscv64/test-div.c b/tests/tcg/riscv64/test-div.c new file mode 100644 index 0000000000..a90480be3f --- /dev/null +++ b/tests/tcg/riscv64/test-div.c @@ -0,0 +1,58 @@ +#include <assert.h> +#include <limits.h> + +struct TestS { + long x, y, q, r; +}; + +static struct TestS test_s[] = { + { 4, 2, 2, 0 }, /* normal cases */ + { 9, 7, 1, 2 }, + { 0, 0, -1, 0 }, /* div by zero cases */ + { 9, 0, -1, 9 }, + { LONG_MIN, -1, LONG_MIN, 0 }, /* overflow case */ +}; + +struct TestU { + unsigned long x, y, q, r; +}; + +static struct TestU test_u[] = { + { 4, 2, 2, 0 }, /* normal cases */ + { 9, 7, 1, 2 }, + { 0, 0, ULONG_MAX, 0 }, /* div by zero cases */ + { 9, 0, ULONG_MAX, 9 }, +}; + +#define ARRAY_SIZE(X) (sizeof(X) / sizeof(*(X))) + +int main (void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(test_s); i++) { + long q, r; + + asm("div %0, %2, %3\n\t" + "rem %1, %2, %3" + : "=&r" (q), "=r" (r) + : "r" (test_s[i].x), "r" (test_s[i].y)); + + assert(q == test_s[i].q); + assert(r == test_s[i].r); + } + + for (i = 0; i < ARRAY_SIZE(test_u); i++) { + unsigned long q, r; + + asm("divu %0, %2, %3\n\t" + "remu %1, %2, %3" + : "=&r" (q), "=r" (r) + : "r" (test_u[i].x), "r" (test_u[i].y)); + + assert(q == test_u[i].q); + assert(r == test_u[i].r); + } + + return 0; +} diff --git a/tests/unit/test-qgraph.c b/tests/unit/test-qgraph.c index f819430e2c..334c76c8e7 100644 --- a/tests/unit/test-qgraph.c +++ b/tests/unit/test-qgraph.c @@ -21,7 +21,7 @@ #include "../qtest/libqos/qgraph_internal.h" #define MACHINE_PC "x86_64/pc" -#define MACHINE_RASPI2 "arm/raspi2" +#define MACHINE_RASPI2 "arm/raspi2b" #define I440FX "i440FX-pcihost" #define PCIBUS_PC "pcibus-pc" #define SDHCI "sdhci" diff --git a/ui/meson.build b/ui/meson.build index a3a187d633..7d25c1b95b 100644 --- a/ui/meson.build +++ b/ui/meson.build @@ -12,12 +12,14 @@ softmmu_ss.add(files( 'kbd-state.c', 'keymaps.c', 'qemu-pixman.c', - 'udmabuf.c', )) softmmu_ss.add([spice_headers, files('spice-module.c')]) softmmu_ss.add(when: spice_protocol, if_true: files('vdagent.c')) -softmmu_ss.add(when: 'CONFIG_LINUX', if_true: files('input-linux.c')) +softmmu_ss.add(when: 'CONFIG_LINUX', if_true: files( + 'input-linux.c', + 'udmabuf.c', +)) softmmu_ss.add(when: cocoa, if_true: files('cocoa.m')) vnc_ss = ss.source_set() diff --git a/ui/udmabuf.c b/ui/udmabuf.c index 23abe1e7eb..cebceb2610 100644 --- a/ui/udmabuf.c +++ b/ui/udmabuf.c @@ -8,8 +8,6 @@ #include "qapi/error.h" #include "ui/console.h" -#ifdef CONFIG_LINUX - #include <fcntl.h> #include <sys/ioctl.h> @@ -29,12 +27,3 @@ int udmabuf_fd(void) } return udmabuf; } - -#else - -int udmabuf_fd(void) -{ - return -1; -} - -#endif |