The following changes since commit 3b2fe44bb7f605f179e5e7feb2c13c2eb3abbb80: Merge tag 'pull-request-2024-05-29' of https://gitlab.com/thuth/qemu into staging (2024-05-29 08:38:20 -0700) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20240531 for you to fetch changes up to 3c3c233677d4f2fe5f35c5d6d6e9b53df48054f4: hw/usb/hcd-ohci: Fix #1510, #303: pid not IN or OUT (2024-05-31 11:26:00 +0100) ---------------------------------------------------------------- target-arm: * hw/intc/arm_gic: Fix set pending of PPIs * hw/intc/arm_gic: Fix writes to GICD_ITARGETSRn * xilinx_zynq: Add cache controller * xilinx_zynq: Support up to two CPU cores * tests/avocado: update sbsa-ref firmware * sbsa-ref: move to Neoverse-N2 as default * More decodetree conversion of A64 ASIMD insns * docs/system/target-arm: Re-alphabetize board list * Implement FEAT WFxT and enable for '-cpu max' * hw/usb/hcd-ohci: Fix #1510, #303: pid not IN or OUT ---------------------------------------------------------------- David Hubbard (1): hw/usb/hcd-ohci: Fix #1510, #303: pid not IN or OUT Marcin Juszkiewicz (3): tests/avocado: update sbsa-ref firmware arm/sbsa-ref: move to Neoverse-N2 as default target/arm: Disable SVE extensions when SVE is disabled Peter Maydell (3): docs/system/target-arm: Re-alphabetize board list accel/tcg: Make TCGCPUOps::cpu_exec_halt return bool for whether to halt target/arm: Implement FEAT WFxT and enable for '-cpu max' Richard Henderson (32): target/arm: Improve vector UQADD, UQSUB, SQADD, SQSUB target/arm: Assert oprsz in range when using vfp.qc target/arm: Convert SUQADD and USQADD to gvec target/arm: Inline scalar SUQADD and USQADD target/arm: Inline scalar SQADD, UQADD, SQSUB, UQSUB target/arm: Convert SQADD, SQSUB, UQADD, UQSUB to decodetree target/arm: Convert SUQADD, USQADD to decodetree target/arm: Convert SSHL, USHL to decodetree target/arm: Convert SRSHL and URSHL (register) to gvec target/arm: Convert SRSHL, URSHL to decodetree target/arm: Convert SQSHL and UQSHL (register) to gvec target/arm: Convert SQSHL, UQSHL to decodetree target/arm: Convert SQRSHL and UQRSHL (register) to gvec target/arm: Convert SQRSHL, UQRSHL to decodetree target/arm: Convert ADD, SUB (vector) to decodetree target/arm: Convert CMGT, CMHI, CMGE, CMHS, CMTST, CMEQ to decodetree target/arm: Use TCG_COND_TSTNE in gen_cmtst_{i32, i64} target/arm: Use TCG_COND_TSTNE in gen_cmtst_vec target/arm: Convert SHADD, UHADD to gvec target/arm: Convert SHADD, UHADD to decodetree target/arm: Convert SHSUB, UHSUB to gvec target/arm: Convert SHSUB, UHSUB to decodetree target/arm: Convert SRHADD, URHADD to gvec target/arm: Convert SRHADD, URHADD to decodetree target/arm: Convert SMAX, SMIN, UMAX, UMIN to decodetree target/arm: Convert SABA, SABD, UABA, UABD to decodetree target/arm: Convert MUL, PMUL to decodetree target/arm: Convert MLA, MLS to decodetree target/arm: Tidy SQDMULH, SQRDMULH (vector) target/arm: Convert SQDMULH, SQRDMULH to decodetree target/arm: Convert FMADD, FMSUB, FNMADD, FNMSUB to decodetree target/arm: Convert FCSEL to decodetree Sebastian Huber (4): hw/intc/arm_gic: Fix set pending of PPIs hw/intc/arm_gic: Fix writes to GICD_ITARGETSRn hw/arm/xilinx_zynq: Add cache controller hw/arm/xilinx_zynq: Support up to two CPU cores docs/system/arm/emulation.rst | 1 + docs/system/target-arm.rst | 6 +- include/hw/core/tcg-cpu-ops.h | 15 +- target/arm/cpu-features.h | 5 + target/arm/cpu.h | 3 + target/arm/helper.h | 97 ++- target/arm/internals.h | 8 + target/arm/tcg/translate-a64.h | 14 + target/arm/tcg/translate.h | 44 + target/i386/tcg/helper-tcg.h | 2 +- target/arm/tcg/a64.decode | 119 +++ target/arm/tcg/neon-dp.decode | 37 +- accel/tcg/cpu-exec.c | 7 +- hw/arm/sbsa-ref.c | 2 +- hw/arm/xilinx_zynq.c | 55 +- hw/intc/arm_gic.c | 12 +- hw/usb/hcd-ohci.c | 5 + target/arm/cpu.c | 40 + target/arm/cpu64.c | 6 +- target/arm/helper.c | 4 +- target/arm/machine.c | 20 + target/arm/tcg/cpu64.c | 1 + target/arm/tcg/gengvec.c | 689 ++++++++++++++- target/arm/tcg/gengvec64.c | 181 ++++ target/arm/tcg/neon_helper.c | 506 +++-------- target/arm/tcg/op_helper.c | 54 ++ target/arm/tcg/translate-a64.c | 1362 +++++++++++------------------- target/arm/tcg/translate-neon.c | 118 +-- target/arm/tcg/vec_helper.c | 128 +++ target/i386/tcg/sysemu/seg_helper.c | 3 +- hw/arm/Kconfig | 1 + hw/usb/trace-events | 1 + tests/avocado/machine_aarch64_sbsaref.py | 20 +- 33 files changed, 2034 insertions(+), 1532 deletions(-) From: Sebastian Huber <sebastian.huber@embedded-brains.de> According to the GICv2 specification section 4.3.7, "Interrupt Set-Pending Registers, GICD_ISPENDRn": "In a multiprocessor implementation, GICD_ISPENDR0 is banked for each connected processor. This register holds the Set-pending bits for interrupts 0-31." Signed-off-by: Sebastian Huber <sebastian.huber@embedded-brains.de> Message-id: 20240524113256.8102-2-sebastian.huber@embedded-brains.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gic.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gic.c +++ b/hw/intc/arm_gic.c @@ -XXX,XX +XXX,XX @@ static void gic_dist_writeb(void *opaque, hwaddr offset, for (i = 0; i < 8; i++) { if (value & (1 << i)) { + int mask = (irq < GIC_INTERNAL) ? (1 << cpu) + : GIC_DIST_TARGET(irq + i); + if (s->security_extn && !attrs.secure && !GIC_DIST_TEST_GROUP(irq + i, 1 << cpu)) { continue; /* Ignore Non-secure access of Group0 IRQ */ } - GIC_DIST_SET_PENDING(irq + i, GIC_DIST_TARGET(irq + i)); + GIC_DIST_SET_PENDING(irq + i, mask); } } } else if (offset < 0x300) { -- 2.34.1 From: Sebastian Huber <sebastian.huber@embedded-brains.de> According to the GICv2 specification section 4.3.12, "Interrupt Processor Targets Registers, GICD_ITARGETSRn": "Any change to a CPU targets field value: [...] * Has an effect on any pending interrupts. This means: - adding a CPU interface to the target list of a pending interrupt makes that interrupt pending on that CPU interface - removing a CPU interface from the target list of a pending interrupt removes the pending state of that interrupt on that CPU interface." Signed-off-by: Sebastian Huber <sebastian.huber@embedded-brains.de> Message-id: 20240524113256.8102-3-sebastian.huber@embedded-brains.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gic.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gic.c +++ b/hw/intc/arm_gic.c @@ -XXX,XX +XXX,XX @@ static void gic_dist_writeb(void *opaque, hwaddr offset, value = ALL_CPU_MASK; } s->irq_target[irq] = value & ALL_CPU_MASK; + if (irq >= GIC_INTERNAL && s->irq_state[irq].pending) { + /* + * Changing the target of an interrupt that is currently + * pending updates the set of CPUs it is pending on. + */ + s->irq_state[irq].pending = value & ALL_CPU_MASK; + } } } else if (offset < 0xf00) { /* Interrupt Configuration. */ -- 2.34.1 From: Sebastian Huber <sebastian.huber@embedded-brains.de> The Zynq 7000 SoCs contain a CoreLink L2C-310 cache controller. Add the corresponding Qemu device to the xilinx-zynq-a9 machine. Signed-off-by: Sebastian Huber <sebastian.huber@embedded-brains.de> Message-id: 20240524120837.10057-2-sebastian.huber@embedded-brains.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xilinx_zynq.c | 1 + hw/arm/Kconfig | 1 + 2 files changed, 2 insertions(+) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) busdev = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(busdev, &error_fatal); sysbus_mmio_map(busdev, 0, MPCORE_PERIPHBASE); + sysbus_create_varargs("l2x0", MPCORE_PERIPHBASE + 0x2000, NULL); sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ)); sysbus_connect_irq(busdev, 1, diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ZYNQ select A9MPCORE select CADENCE # UART select PFLASH_CFI02 + select PL310 # cache controller select PL330 select SDHCI select SSI_M25P80 -- 2.34.1 From: Sebastian Huber <sebastian.huber@embedded-brains.de> The Zynq 7000 SoCs contain two Arm Cortex-A9 MPCore (the Zynq 7000S have only one core). Add support for up to two simulated cores. Signed-off-by: Sebastian Huber <sebastian.huber@embedded-brains.de> Message-id: 20240524120837.10057-3-sebastian.huber@embedded-brains.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: removed unnecessary double-cast] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xilinx_zynq.c | 54 +++++++++++++++++++++++++++----------------- 1 file changed, 33 insertions(+), 21 deletions(-) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static const int dma_irqs[8] = { 0xe3401000 + ARMV7_IMM16(extract32((val), 16, 16)), /* movt r1 ... */ \ 0xe5801000 + (addr) +#define ZYNQ_MAX_CPUS 2 + struct ZynqMachineState { MachineState parent; Clock *ps_clk; + ARMCPU *cpu[ZYNQ_MAX_CPUS]; }; static void zynq_write_board_setup(ARMCPU *cpu, @@ -XXX,XX +XXX,XX @@ static inline int zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq, static void zynq_init(MachineState *machine) { ZynqMachineState *zynq_machine = ZYNQ_MACHINE(machine); - ARMCPU *cpu; MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *ocm_ram = g_new(MemoryRegion, 1); DeviceState *dev, *slcr; SysBusDevice *busdev; qemu_irq pic[64]; int n; + unsigned int smp_cpus = machine->smp.cpus; /* max 2GB ram */ if (machine->ram_size > 2 * GiB) { @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) exit(EXIT_FAILURE); } - cpu = ARM_CPU(object_new(machine->cpu_type)); + for (n = 0; n < smp_cpus; n++) { + Object *cpuobj = object_new(machine->cpu_type); - /* By default A9 CPUs have EL3 enabled. This board does not - * currently support EL3 so the CPU EL3 property is disabled before - * realization. - */ - if (object_property_find(OBJECT(cpu), "has_el3")) { - object_property_set_bool(OBJECT(cpu), "has_el3", false, &error_fatal); + /* + * By default A9 CPUs have EL3 enabled. This board does not currently + * support EL3 so the CPU EL3 property is disabled before realization. + */ + if (object_property_find(cpuobj, "has_el3")) { + object_property_set_bool(cpuobj, "has_el3", false, &error_fatal); + } + + object_property_set_int(cpuobj, "midr", ZYNQ_BOARD_MIDR, + &error_fatal); + object_property_set_int(cpuobj, "reset-cbar", MPCORE_PERIPHBASE, + &error_fatal); + + qdev_realize(DEVICE(cpuobj), NULL, &error_fatal); + + zynq_machine->cpu[n] = ARM_CPU(cpuobj); } - object_property_set_int(OBJECT(cpu), "midr", ZYNQ_BOARD_MIDR, - &error_fatal); - object_property_set_int(OBJECT(cpu), "reset-cbar", MPCORE_PERIPHBASE, - &error_fatal); - qdev_realize(DEVICE(cpu), NULL, &error_fatal); - /* DDR remapped to address zero. */ memory_region_add_subregion(address_space_mem, 0, machine->ram); @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) sysbus_mmio_map(SYS_BUS_DEVICE(slcr), 0, 0xF8000000); dev = qdev_new(TYPE_A9MPCORE_PRIV); - qdev_prop_set_uint32(dev, "num-cpu", 1); + qdev_prop_set_uint32(dev, "num-cpu", smp_cpus); busdev = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(busdev, &error_fatal); sysbus_mmio_map(busdev, 0, MPCORE_PERIPHBASE); + zynq_binfo.gic_cpu_if_addr = MPCORE_PERIPHBASE + 0x100; sysbus_create_varargs("l2x0", MPCORE_PERIPHBASE + 0x2000, NULL); - sysbus_connect_irq(busdev, 0, - qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ)); - sysbus_connect_irq(busdev, 1, - qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_FIQ)); + for (n = 0; n < smp_cpus; n++) { + DeviceState *cpudev = DEVICE(zynq_machine->cpu[n]); + sysbus_connect_irq(busdev, (2 * n) + 0, + qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); + sysbus_connect_irq(busdev, (2 * n) + 1, + qdev_get_gpio_in(cpudev, ARM_CPU_FIQ)); + } for (n = 0; n < 64; n++) { pic[n] = qdev_get_gpio_in(dev, n); @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) zynq_binfo.board_setup_addr = BOARD_SETUP_ADDR; zynq_binfo.write_board_setup = zynq_write_board_setup; - arm_load_kernel(cpu, machine, &zynq_binfo); + arm_load_kernel(zynq_machine->cpu[0], machine, &zynq_binfo); } static void zynq_machine_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void zynq_machine_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); mc->desc = "Xilinx Zynq Platform Baseboard for Cortex-A9"; mc->init = zynq_init; - mc->max_cpus = 1; + mc->max_cpus = ZYNQ_MAX_CPUS; mc->no_sdcard = 1; mc->ignore_memory_transaction_failures = true; mc->valid_cpu_types = valid_cpu_types; -- 2.34.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Partial support for NUMA setup: - cpu nodes - memory nodes Used versions: - Trusted Firmware v2.11.0 - Tianocore EDK2 stable202405 - Tianocore EDK2 Platforms code commit 4bbd0ed Firmware is built using Debian 'bookworm' cross toolchain (gcc 12.2.0). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/avocado/machine_aarch64_sbsaref.py | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/tests/avocado/machine_aarch64_sbsaref.py b/tests/avocado/machine_aarch64_sbsaref.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/machine_aarch64_sbsaref.py +++ b/tests/avocado/machine_aarch64_sbsaref.py @@ -XXX,XX +XXX,XX @@ def fetch_firmware(self): Used components: - - Trusted Firmware 2.10.2 - - Tianocore EDK2 stable202402 - - Tianocore EDK2-platforms commit 085c2fb + - Trusted Firmware 2.11.0 + - Tianocore EDK2 stable202405 + - Tianocore EDK2-platforms commit 4bbd0ed """ # Secure BootRom (TF-A code) fs0_xz_url = ( "https://artifacts.codelinaro.org/artifactory/linaro-419-sbsa-ref/" - "20240313-116475/edk2/SBSA_FLASH0.fd.xz" + "20240528-140808/edk2/SBSA_FLASH0.fd.xz" ) - fs0_xz_hash = "637593749cc307dea7dc13265c32e5d020267552f22b18a31850b8429fc5e159" + fs0_xz_hash = "fa6004900b67172914c908b78557fec4d36a5f784f4c3dd08f49adb75e1892a9" tar_xz_path = self.fetch_asset(fs0_xz_url, asset_hash=fs0_xz_hash, algorithm='sha256') archive.extract(tar_xz_path, self.workdir) @@ -XXX,XX +XXX,XX @@ def fetch_firmware(self): # Non-secure rom (UEFI and EFI variables) fs1_xz_url = ( "https://artifacts.codelinaro.org/artifactory/linaro-419-sbsa-ref/" - "20240313-116475/edk2/SBSA_FLASH1.fd.xz" + "20240528-140808/edk2/SBSA_FLASH1.fd.xz" ) - fs1_xz_hash = "cb0a5e8cf5e303c5d3dc106cfd5943ffe9714b86afddee7164c69ee1dd41991c" + fs1_xz_hash = "5f3747d4000bc416d9641e33ff4ac60c3cc8cb74ca51b6e932e58531c62eb6f7" tar_xz_path = self.fetch_asset(fs1_xz_url, asset_hash=fs1_xz_hash, algorithm='sha256') archive.extract(tar_xz_path, self.workdir) @@ -XXX,XX +XXX,XX @@ def test_sbsaref_edk2_firmware(self): # AP Trusted ROM wait_for_console_pattern(self, "Booting Trusted Firmware") - wait_for_console_pattern(self, "BL1: v2.10.2(release):") + wait_for_console_pattern(self, "BL1: v2.11.0(release):") wait_for_console_pattern(self, "BL1: Booting BL2") # Trusted Boot Firmware - wait_for_console_pattern(self, "BL2: v2.10.2(release)") + wait_for_console_pattern(self, "BL2: v2.11.0(release)") wait_for_console_pattern(self, "Booting BL31") # EL3 Runtime Software - wait_for_console_pattern(self, "BL31: v2.10.2(release)") + wait_for_console_pattern(self, "BL31: v2.11.0(release)") # Non-trusted Firmware wait_for_console_pattern(self, "UEFI firmware (version 1.0") -- 2.34.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Moving to Neoverse-N2 gives us several cpu features to use for expanding our platform: - branch target identification - pointer authentication - RME for confidential computing - RNG for EFI_PROTOCOL_RNG - SVE being enabled by default We do not go for "max" as default to have stable set of features enabled by default. It is still supported and can be selected with "--cpu" argument. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Leif Lindholm <quic_llindhol@quicinc.com> Message-id: 20240523165353.6547-1-marcin.juszkiewicz@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_class_init(ObjectClass *oc, void *data) mc->init = sbsa_ref_init; mc->desc = "QEMU 'SBSA Reference' ARM Virtual Machine"; - mc->default_cpu_type = ARM_CPU_TYPE_NAME("neoverse-n1"); + mc->default_cpu_type = ARM_CPU_TYPE_NAME("neoverse-n2"); mc->valid_cpu_types = valid_cpu_types; mc->max_cpus = 512; mc->pci_allow_0_address = true; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> No need for a full comparison; xor produces non-zero bits for QC just fine. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/gengvec.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } -static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, +static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { TCGv_vec x = tcg_temp_new_vec_matching(t); tcg_gen_add_vec(vece, x, a, b); tcg_gen_usadd_vec(vece, t, a, b); - tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); - tcg_gen_or_vec(vece, sat, sat, x); + tcg_gen_xor_vec(vece, x, x, t); + tcg_gen_or_vec(vece, qc, qc, x); } void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) { static const TCGOpcode vecop_list[] = { - INDEX_op_usadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 + INDEX_op_usadd_vec, INDEX_op_add_vec, 0 }; static const GVecGen4 ops[4] = { { .fniv = gen_uqadd_vec, @@ -XXX,XX +XXX,XX @@ void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } -static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, +static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { TCGv_vec x = tcg_temp_new_vec_matching(t); tcg_gen_add_vec(vece, x, a, b); tcg_gen_ssadd_vec(vece, t, a, b); - tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); - tcg_gen_or_vec(vece, sat, sat, x); + tcg_gen_xor_vec(vece, x, x, t); + tcg_gen_or_vec(vece, qc, qc, x); } void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) { static const TCGOpcode vecop_list[] = { - INDEX_op_ssadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 + INDEX_op_ssadd_vec, INDEX_op_add_vec, 0 }; static const GVecGen4 ops[4] = { { .fniv = gen_sqadd_vec, @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } -static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, +static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { TCGv_vec x = tcg_temp_new_vec_matching(t); tcg_gen_sub_vec(vece, x, a, b); tcg_gen_ussub_vec(vece, t, a, b); - tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); - tcg_gen_or_vec(vece, sat, sat, x); + tcg_gen_xor_vec(vece, x, x, t); + tcg_gen_or_vec(vece, qc, qc, x); } void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) { static const TCGOpcode vecop_list[] = { - INDEX_op_ussub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 + INDEX_op_ussub_vec, INDEX_op_sub_vec, 0 }; static const GVecGen4 ops[4] = { { .fniv = gen_uqsub_vec, @@ -XXX,XX +XXX,XX @@ void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } -static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, +static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { TCGv_vec x = tcg_temp_new_vec_matching(t); tcg_gen_sub_vec(vece, x, a, b); tcg_gen_sssub_vec(vece, t, a, b); - tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); - tcg_gen_or_vec(vece, sat, sat, x); + tcg_gen_xor_vec(vece, x, x, t); + tcg_gen_or_vec(vece, qc, qc, x); } void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) { static const TCGOpcode vecop_list[] = { - INDEX_op_sssub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 + INDEX_op_sssub_vec, INDEX_op_sub_vec, 0 }; static const GVecGen4 ops[4] = { { .fniv = gen_sqsub_vec, -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240528203044.612851-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/gengvec.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, { TCGv_ptr qc_ptr = tcg_temp_new_ptr(); + tcg_debug_assert(opr_sz <= sizeof_field(CPUARMState, vfp.qc)); tcg_gen_addi_ptr(qc_ptr, tcg_env, offsetof(CPUARMState, vfp.qc)); tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, qc_ptr, opr_sz, max_sz, 0, fn); @@ -XXX,XX +XXX,XX @@ void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, .opt_opc = vecop_list, .vece = MO_64 }, }; + + tcg_debug_assert(opr_sz <= sizeof_field(CPUARMState, vfp.qc)); tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, .write_aofs = true, .vece = MO_64 }, }; + + tcg_debug_assert(opr_sz <= sizeof_field(CPUARMState, vfp.qc)); tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } @@ -XXX,XX +XXX,XX @@ void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, .write_aofs = true, .vece = MO_64 }, }; + + tcg_debug_assert(opr_sz <= sizeof_field(CPUARMState, vfp.qc)); tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, .write_aofs = true, .vece = MO_64 }, }; + + tcg_debug_assert(opr_sz <= sizeof_field(CPUARMState, vfp.qc)); tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 16 +++++ target/arm/tcg/translate-a64.h | 6 ++ target/arm/tcg/gengvec64.c | 110 ++++++++++++++++++++++++++++++++ target/arm/tcg/translate-a64.c | 113 ++++++++++++++------------------- target/arm/tcg/vec_helper.c | 64 +++++++++++++++++++ 5 files changed, 245 insertions(+), 64 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_sqsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_sqsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usqadd_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usqadd_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usqadd_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usqadd_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_suqadd_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_suqadd_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_suqadd_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_suqadd_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmlal_a32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.h +++ b/target/arm/tcg/translate-a64.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_eor3(unsigned vece, uint32_t d, uint32_t n, uint32_t m, uint32_t a, uint32_t oprsz, uint32_t maxsz); void gen_gvec_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, uint32_t a, uint32_t oprsz, uint32_t maxsz); +void gen_gvec_suqadd_qc(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz); void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); diff --git a/target/arm/tcg/gengvec64.c b/target/arm/tcg/gengvec64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec64.c +++ b/target/arm/tcg/gengvec64.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); } +static void gen_suqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec max = + tcg_constant_vec_matching(t, vece, (1ull << ((8 << vece) - 1)) - 1); + TCGv_vec u = tcg_temp_new_vec_matching(t); + + /* Maximum value that can be added to @a without overflow. */ + tcg_gen_sub_vec(vece, u, max, a); + + /* Constrain addend so that the next addition never overflows. */ + tcg_gen_umin_vec(vece, u, u, b); + tcg_gen_add_vec(vece, t, u, a); + + /* Compute QC by comparing the adjusted @b. */ + tcg_gen_xor_vec(vece, u, u, b); + tcg_gen_or_vec(vece, qc, qc, u); +} + +void gen_gvec_suqadd_qc(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_add_vec, INDEX_op_sub_vec, INDEX_op_umin_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_suqadd_vec, + .fno = gen_helper_gvec_suqadd_b, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_suqadd_vec, + .fno = gen_helper_gvec_suqadd_h, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_suqadd_vec, + .fno = gen_helper_gvec_suqadd_s, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_suqadd_vec, + .fno = gen_helper_gvec_suqadd_d, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_64 }, + }; + + tcg_debug_assert(opr_sz <= sizeof_field(CPUARMState, vfp.qc)); + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_usqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec u = tcg_temp_new_vec_matching(t); + TCGv_vec z = tcg_constant_vec_matching(t, vece, 0); + + /* Compute unsigned saturation of add for +b and sub for -b. */ + tcg_gen_neg_vec(vece, t, b); + tcg_gen_usadd_vec(vece, u, a, b); + tcg_gen_ussub_vec(vece, t, a, t); + + /* Select the correct result depending on the sign of b. */ + tcg_gen_cmpsel_vec(TCG_COND_LT, vece, t, b, z, t, u); + + /* Compute QC by comparing against the non-saturated result. */ + tcg_gen_add_vec(vece, u, a, b); + tcg_gen_xor_vec(vece, u, u, t); + tcg_gen_or_vec(vece, qc, qc, u); +} + +void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_neg_vec, INDEX_op_add_vec, + INDEX_op_usadd_vec, INDEX_op_ussub_vec, + INDEX_op_cmpsel_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_usqadd_vec, + .fno = gen_helper_gvec_usqadd_b, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_usqadd_vec, + .fno = gen_helper_gvec_usqadd_h, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_usqadd_vec, + .fno = gen_helper_gvec_usqadd_s, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_usqadd_vec, + .fno = gen_helper_gvec_usqadd_d, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_64 }, + }; + + tcg_debug_assert(opr_sz <= sizeof_field(CPUARMState, vfp.qc)); + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, /* Remaining saturating accumulating ops */ static void handle_2misc_satacc(DisasContext *s, bool is_scalar, bool is_u, - bool is_q, int size, int rn, int rd) + bool is_q, unsigned size, int rn, int rd) { - bool is_double = (size == 3); + if (!is_scalar) { + gen_gvec_fn3(s, is_q, rd, rd, rn, + is_u ? gen_gvec_usqadd_qc : gen_gvec_suqadd_qc, size); + return; + } - if (is_double) { + if (size == 3) { TCGv_i64 tcg_rn = tcg_temp_new_i64(); TCGv_i64 tcg_rd = tcg_temp_new_i64(); - int pass; - for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) { - read_vec_element(s, tcg_rn, rn, pass, MO_64); - read_vec_element(s, tcg_rd, rd, pass, MO_64); + read_vec_element(s, tcg_rn, rn, 0, MO_64); + read_vec_element(s, tcg_rd, rd, 0, MO_64); - if (is_u) { /* USQADD */ - gen_helper_neon_uqadd_s64(tcg_rd, tcg_env, tcg_rn, tcg_rd); - } else { /* SUQADD */ - gen_helper_neon_sqadd_u64(tcg_rd, tcg_env, tcg_rn, tcg_rd); - } - write_vec_element(s, tcg_rd, rd, pass, MO_64); + if (is_u) { /* USQADD */ + gen_helper_neon_uqadd_s64(tcg_rd, tcg_env, tcg_rn, tcg_rd); + } else { /* SUQADD */ + gen_helper_neon_sqadd_u64(tcg_rd, tcg_env, tcg_rn, tcg_rd); } - clear_vec_high(s, !is_scalar, rd); + write_vec_element(s, tcg_rd, rd, 0, MO_64); + clear_vec_high(s, false, rd); } else { TCGv_i32 tcg_rn = tcg_temp_new_i32(); TCGv_i32 tcg_rd = tcg_temp_new_i32(); - int pass, maxpasses; - if (is_scalar) { - maxpasses = 1; - } else { - maxpasses = is_q ? 4 : 2; + read_vec_element_i32(s, tcg_rn, rn, 0, size); + read_vec_element_i32(s, tcg_rd, rd, 0, size); + + if (is_u) { /* USQADD */ + switch (size) { + case 0: + gen_helper_neon_uqadd_s8(tcg_rd, tcg_env, tcg_rn, tcg_rd); + break; + case 1: + gen_helper_neon_uqadd_s16(tcg_rd, tcg_env, tcg_rn, tcg_rd); + break; + case 2: + gen_helper_neon_uqadd_s32(tcg_rd, tcg_env, tcg_rn, tcg_rd); + break; + default: + g_assert_not_reached(); + } + } else { /* SUQADD */ + switch (size) { + case 0: + gen_helper_neon_sqadd_u8(tcg_rd, tcg_env, tcg_rn, tcg_rd); + break; + case 1: + gen_helper_neon_sqadd_u16(tcg_rd, tcg_env, tcg_rn, tcg_rd); + break; + case 2: + gen_helper_neon_sqadd_u32(tcg_rd, tcg_env, tcg_rn, tcg_rd); + break; + default: + g_assert_not_reached(); + } } - for (pass = 0; pass < maxpasses; pass++) { - if (is_scalar) { - read_vec_element_i32(s, tcg_rn, rn, pass, size); - read_vec_element_i32(s, tcg_rd, rd, pass, size); - } else { - read_vec_element_i32(s, tcg_rn, rn, pass, MO_32); - read_vec_element_i32(s, tcg_rd, rd, pass, MO_32); - } - - if (is_u) { /* USQADD */ - switch (size) { - case 0: - gen_helper_neon_uqadd_s8(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - case 1: - gen_helper_neon_uqadd_s16(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - case 2: - gen_helper_neon_uqadd_s32(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - default: - g_assert_not_reached(); - } - } else { /* SUQADD */ - switch (size) { - case 0: - gen_helper_neon_sqadd_u8(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - case 1: - gen_helper_neon_sqadd_u16(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - case 2: - gen_helper_neon_sqadd_u32(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - default: - g_assert_not_reached(); - } - } - - if (is_scalar) { - write_vec_element(s, tcg_constant_i64(0), rd, 0, MO_64); - } - write_vec_element_i32(s, tcg_rd, rd, pass, MO_32); - } - clear_vec_high(s, is_q, rd); + write_vec_element(s, tcg_constant_i64(0), rd, 0, MO_64); + write_vec_element_i32(s, tcg_rd, rd, 0, MO_32); + clear_vec_high(s, false, rd); } } diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_SAT(gvec_sqsub_b, int, int8_t, int8_t, -, INT8_MIN, INT8_MAX) DO_SAT(gvec_sqsub_h, int, int16_t, int16_t, -, INT16_MIN, INT16_MAX) DO_SAT(gvec_sqsub_s, int64_t, int32_t, int32_t, -, INT32_MIN, INT32_MAX) +DO_SAT(gvec_usqadd_b, int, uint8_t, int8_t, +, 0, UINT8_MAX) +DO_SAT(gvec_usqadd_h, int, uint16_t, int16_t, +, 0, UINT16_MAX) +DO_SAT(gvec_usqadd_s, int64_t, uint32_t, int32_t, +, 0, UINT32_MAX) + +DO_SAT(gvec_suqadd_b, int, int8_t, uint8_t, +, INT8_MIN, INT8_MAX) +DO_SAT(gvec_suqadd_h, int, int16_t, uint16_t, +, INT16_MIN, INT16_MAX) +DO_SAT(gvec_suqadd_s, int64_t, int32_t, uint32_t, +, INT32_MIN, INT32_MAX) + #undef DO_SAT void HELPER(gvec_uqadd_d)(void *vd, void *vq, void *vn, @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sqsub_d)(void *vd, void *vq, void *vn, clear_tail(d, oprsz, simd_maxsz(desc)); } +void HELPER(gvec_usqadd_d)(void *vd, void *vq, void *vn, + void *vm, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + bool q = false; + + for (i = 0; i < oprsz / 8; i++) { + uint64_t nn = n[i]; + int64_t mm = m[i]; + uint64_t dd = nn + mm; + + if (mm < 0) { + if (nn < (uint64_t)-mm) { + dd = 0; + q = true; + } + } else { + if (dd < nn) { + dd = UINT64_MAX; + q = true; + } + } + d[i] = dd; + } + if (q) { + uint32_t *qc = vq; + qc[0] = 1; + } + clear_tail(d, oprsz, simd_maxsz(desc)); +} + +void HELPER(gvec_suqadd_d)(void *vd, void *vq, void *vn, + void *vm, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + bool q = false; + + for (i = 0; i < oprsz / 8; i++) { + int64_t nn = n[i]; + uint64_t mm = m[i]; + int64_t dd = nn + mm; + + if (mm > (uint64_t)(INT64_MAX - nn)) { + dd = INT64_MAX; + q = true; + } + d[i] = dd; + } + if (q) { + uint32_t *qc = vq; + qc[0] = 1; + } + clear_tail(d, oprsz, simd_maxsz(desc)); +} #define DO_SRA(NAME, TYPE) \ void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This eliminates the last uses of these neon helpers. Incorporate the MO_64 expanders as an option to the vector expander. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 8 -- target/arm/tcg/translate-a64.h | 8 ++ target/arm/tcg/gengvec64.c | 71 ++++++++++++++ target/arm/tcg/neon_helper.c | 165 --------------------------------- target/arm/tcg/translate-a64.c | 73 +++++---------- 5 files changed, 103 insertions(+), 222 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(neon_qadd_u16, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(neon_qadd_s16, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(neon_qadd_u32, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(neon_qadd_s32, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_uqadd_s8, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_uqadd_s16, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_uqadd_s32, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_uqadd_s64, TCG_CALL_NO_RWG, i64, env, i64, i64) -DEF_HELPER_FLAGS_3(neon_sqadd_u8, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_sqadd_u16, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_sqadd_u32, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_sqadd_u64, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_3(neon_qsub_u8, i32, env, i32, i32) DEF_HELPER_3(neon_qsub_s8, i32, env, i32, i32) DEF_HELPER_3(neon_qsub_u16, i32, env, i32, i32) diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.h +++ b/target/arm/tcg/translate-a64.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_eor3(unsigned vece, uint32_t d, uint32_t n, uint32_t m, uint32_t a, uint32_t oprsz, uint32_t maxsz); void gen_gvec_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, uint32_t a, uint32_t oprsz, uint32_t maxsz); + +void gen_suqadd_bhs(TCGv_i64 res, TCGv_i64 qc, + TCGv_i64 a, TCGv_i64 b, MemOp esz); +void gen_suqadd_d(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b); void gen_gvec_suqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + +void gen_usqadd_bhs(TCGv_i64 res, TCGv_i64 qc, + TCGv_i64 a, TCGv_i64 b, MemOp esz); +void gen_usqadd_d(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b); void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); diff --git a/target/arm/tcg/gengvec64.c b/target/arm/tcg/gengvec64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec64.c +++ b/target/arm/tcg/gengvec64.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); } +/* + * Set @res to the correctly saturated result. + * Set @qc non-zero if saturation occured. + */ +void gen_suqadd_bhs(TCGv_i64 res, TCGv_i64 qc, + TCGv_i64 a, TCGv_i64 b, MemOp esz) +{ + TCGv_i64 max = tcg_constant_i64((1ull << ((8 << esz) - 1)) - 1); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_add_i64(t, a, b); + tcg_gen_smin_i64(res, t, max); + tcg_gen_xor_i64(t, t, res); + tcg_gen_or_i64(qc, qc, t); +} + +void gen_suqadd_d(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 max = tcg_constant_i64(INT64_MAX); + TCGv_i64 t = tcg_temp_new_i64(); + + /* Maximum value that can be added to @a without overflow. */ + tcg_gen_sub_i64(t, max, a); + + /* Constrain addend so that the next addition never overflows. */ + tcg_gen_umin_i64(t, t, b); + tcg_gen_add_i64(res, a, t); + + tcg_gen_xor_i64(t, t, b); + tcg_gen_or_i64(qc, qc, t); +} + static void gen_suqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { @@ -XXX,XX +XXX,XX @@ void gen_gvec_suqadd_qc(unsigned vece, uint32_t rd_ofs, .write_aofs = true, .vece = MO_32 }, { .fniv = gen_suqadd_vec, + .fni8 = gen_suqadd_d, .fno = gen_helper_gvec_suqadd_d, .opt_opc = vecop_list, .write_aofs = true, @@ -XXX,XX +XXX,XX @@ void gen_gvec_suqadd_qc(unsigned vece, uint32_t rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +void gen_usqadd_bhs(TCGv_i64 res, TCGv_i64 qc, + TCGv_i64 a, TCGv_i64 b, MemOp esz) +{ + TCGv_i64 max = tcg_constant_i64(MAKE_64BIT_MASK(0, 8 << esz)); + TCGv_i64 zero = tcg_constant_i64(0); + TCGv_i64 tmp = tcg_temp_new_i64(); + + tcg_gen_add_i64(tmp, a, b); + tcg_gen_smin_i64(res, tmp, max); + tcg_gen_smax_i64(res, res, zero); + tcg_gen_xor_i64(tmp, tmp, res); + tcg_gen_or_i64(qc, qc, tmp); +} + +void gen_usqadd_d(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 tmp = tcg_temp_new_i64(); + TCGv_i64 tneg = tcg_temp_new_i64(); + TCGv_i64 tpos = tcg_temp_new_i64(); + TCGv_i64 max = tcg_constant_i64(UINT64_MAX); + TCGv_i64 zero = tcg_constant_i64(0); + + tcg_gen_add_i64(tmp, a, b); + + /* If @b is positive, saturate if (a + b) < a, aka unsigned overflow. */ + tcg_gen_movcond_i64(TCG_COND_LTU, tpos, tmp, a, max, tmp); + + /* If @b is negative, saturate if a < -b, ie subtraction is negative. */ + tcg_gen_neg_i64(tneg, b); + tcg_gen_movcond_i64(TCG_COND_LTU, tneg, a, tneg, zero, tmp); + + /* Select correct result from sign of @b. */ + tcg_gen_movcond_i64(TCG_COND_LT, res, b, zero, tneg, tpos); + tcg_gen_xor_i64(tmp, tmp, res); + tcg_gen_or_i64(qc, qc, tmp); +} + static void gen_usqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { @@ -XXX,XX +XXX,XX @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs, .write_aofs = true, .vece = MO_32 }, { .fniv = gen_usqadd_vec, + .fni8 = gen_usqadd_d, .fno = gen_helper_gvec_usqadd_d, .opt_opc = vecop_list, .write_aofs = true, diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_qadd_s64)(CPUARMState *env, uint64_t src1, uint64_t src2) return res; } -/* Unsigned saturating accumulate of signed value - * - * Op1/Rn is treated as signed - * Op2/Rd is treated as unsigned - * - * Explicit casting is used to ensure the correct sign extension of - * inputs. The result is treated as a unsigned value and saturated as such. - * - * We use a macro for the 8/16 bit cases which expects signed integers of va, - * vb, and vr for interim calculation and an unsigned 32 bit result value r. - */ - -#define USATACC(bits, shift) \ - do { \ - va = sextract32(a, shift, bits); \ - vb = extract32(b, shift, bits); \ - vr = va + vb; \ - if (vr > UINT##bits##_MAX) { \ - SET_QC(); \ - vr = UINT##bits##_MAX; \ - } else if (vr < 0) { \ - SET_QC(); \ - vr = 0; \ - } \ - r = deposit32(r, shift, bits, vr); \ - } while (0) - -uint32_t HELPER(neon_uqadd_s8)(CPUARMState *env, uint32_t a, uint32_t b) -{ - int16_t va, vb, vr; - uint32_t r = 0; - - USATACC(8, 0); - USATACC(8, 8); - USATACC(8, 16); - USATACC(8, 24); - return r; -} - -uint32_t HELPER(neon_uqadd_s16)(CPUARMState *env, uint32_t a, uint32_t b) -{ - int32_t va, vb, vr; - uint64_t r = 0; - - USATACC(16, 0); - USATACC(16, 16); - return r; -} - -#undef USATACC - -uint32_t HELPER(neon_uqadd_s32)(CPUARMState *env, uint32_t a, uint32_t b) -{ - int64_t va = (int32_t)a; - int64_t vb = (uint32_t)b; - int64_t vr = va + vb; - if (vr > UINT32_MAX) { - SET_QC(); - vr = UINT32_MAX; - } else if (vr < 0) { - SET_QC(); - vr = 0; - } - return vr; -} - -uint64_t HELPER(neon_uqadd_s64)(CPUARMState *env, uint64_t a, uint64_t b) -{ - uint64_t res; - res = a + b; - /* We only need to look at the pattern of SIGN bits to detect - * +ve/-ve saturation - */ - if (~a & b & ~res & SIGNBIT64) { - SET_QC(); - res = UINT64_MAX; - } else if (a & ~b & res & SIGNBIT64) { - SET_QC(); - res = 0; - } - return res; -} - -/* Signed saturating accumulate of unsigned value - * - * Op1/Rn is treated as unsigned - * Op2/Rd is treated as signed - * - * The result is treated as a signed value and saturated as such - * - * We use a macro for the 8/16 bit cases which expects signed integers of va, - * vb, and vr for interim calculation and an unsigned 32 bit result value r. - */ - -#define SSATACC(bits, shift) \ - do { \ - va = extract32(a, shift, bits); \ - vb = sextract32(b, shift, bits); \ - vr = va + vb; \ - if (vr > INT##bits##_MAX) { \ - SET_QC(); \ - vr = INT##bits##_MAX; \ - } else if (vr < INT##bits##_MIN) { \ - SET_QC(); \ - vr = INT##bits##_MIN; \ - } \ - r = deposit32(r, shift, bits, vr); \ - } while (0) - -uint32_t HELPER(neon_sqadd_u8)(CPUARMState *env, uint32_t a, uint32_t b) -{ - int16_t va, vb, vr; - uint32_t r = 0; - - SSATACC(8, 0); - SSATACC(8, 8); - SSATACC(8, 16); - SSATACC(8, 24); - return r; -} - -uint32_t HELPER(neon_sqadd_u16)(CPUARMState *env, uint32_t a, uint32_t b) -{ - int32_t va, vb, vr; - uint32_t r = 0; - - SSATACC(16, 0); - SSATACC(16, 16); - - return r; -} - -#undef SSATACC - -uint32_t HELPER(neon_sqadd_u32)(CPUARMState *env, uint32_t a, uint32_t b) -{ - int64_t res; - int64_t op1 = (uint32_t)a; - int64_t op2 = (int32_t)b; - res = op1 + op2; - if (res > INT32_MAX) { - SET_QC(); - res = INT32_MAX; - } else if (res < INT32_MIN) { - SET_QC(); - res = INT32_MIN; - } - return res; -} - -uint64_t HELPER(neon_sqadd_u64)(CPUARMState *env, uint64_t a, uint64_t b) -{ - uint64_t res; - res = a + b; - /* We only need to look at the pattern of SIGN bits to detect an overflow */ - if (((a & res) - | (~b & res) - | (a & ~b)) & SIGNBIT64) { - SET_QC(); - res = INT64_MAX; - } - return res; -} - - #define NEON_USAT(dest, src1, src2, type) do { \ uint32_t tmp = (uint32_t)src1 - (uint32_t)src2; \ if (tmp != (type)tmp) { \ diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, static void handle_2misc_satacc(DisasContext *s, bool is_scalar, bool is_u, bool is_q, unsigned size, int rn, int rd) { + TCGv_i64 res, qc, a, b; + if (!is_scalar) { gen_gvec_fn3(s, is_q, rd, rd, rn, is_u ? gen_gvec_usqadd_qc : gen_gvec_suqadd_qc, size); return; } - if (size == 3) { - TCGv_i64 tcg_rn = tcg_temp_new_i64(); - TCGv_i64 tcg_rd = tcg_temp_new_i64(); + res = tcg_temp_new_i64(); + qc = tcg_temp_new_i64(); + a = tcg_temp_new_i64(); + b = tcg_temp_new_i64(); - read_vec_element(s, tcg_rn, rn, 0, MO_64); - read_vec_element(s, tcg_rd, rd, 0, MO_64); + /* Read and extend scalar inputs to 64-bits. */ + read_vec_element(s, a, rd, 0, size | (is_u ? 0 : MO_SIGN)); + read_vec_element(s, b, rn, 0, size | (is_u ? MO_SIGN : 0)); + tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); - if (is_u) { /* USQADD */ - gen_helper_neon_uqadd_s64(tcg_rd, tcg_env, tcg_rn, tcg_rd); - } else { /* SUQADD */ - gen_helper_neon_sqadd_u64(tcg_rd, tcg_env, tcg_rn, tcg_rd); + if (size == MO_64) { + if (is_u) { + gen_usqadd_d(res, qc, a, b); + } else { + gen_suqadd_d(res, qc, a, b); } - write_vec_element(s, tcg_rd, rd, 0, MO_64); - clear_vec_high(s, false, rd); } else { - TCGv_i32 tcg_rn = tcg_temp_new_i32(); - TCGv_i32 tcg_rd = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_rn, rn, 0, size); - read_vec_element_i32(s, tcg_rd, rd, 0, size); - - if (is_u) { /* USQADD */ - switch (size) { - case 0: - gen_helper_neon_uqadd_s8(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - case 1: - gen_helper_neon_uqadd_s16(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - case 2: - gen_helper_neon_uqadd_s32(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - default: - g_assert_not_reached(); - } - } else { /* SUQADD */ - switch (size) { - case 0: - gen_helper_neon_sqadd_u8(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - case 1: - gen_helper_neon_sqadd_u16(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - case 2: - gen_helper_neon_sqadd_u32(tcg_rd, tcg_env, tcg_rn, tcg_rd); - break; - default: - g_assert_not_reached(); - } + if (is_u) { + gen_usqadd_bhs(res, qc, a, b, size); + } else { + gen_suqadd_bhs(res, qc, a, b, size); + /* Truncate signed 64-bit result for writeback. */ + tcg_gen_ext_i64(res, res, size); } - - write_vec_element(s, tcg_constant_i64(0), rd, 0, MO_64); - write_vec_element_i32(s, tcg_rd, rd, 0, MO_32); - clear_vec_high(s, false, rd); } + + write_fp_dreg(s, rd, res); + tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); } /* AdvSIMD scalar two reg misc -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This eliminates the last uses of these neon helpers. Incorporate the MO_64 expanders as an option to the vector expander. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 17 ---- target/arm/tcg/translate.h | 15 +++ target/arm/tcg/gengvec.c | 116 +++++++++++++++++++++++ target/arm/tcg/neon_helper.c | 162 --------------------------------- target/arm/tcg/translate-a64.c | 67 ++++++++------ 5 files changed, 169 insertions(+), 208 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(fjcvtzs, TCG_CALL_NO_RWG, i64, f64, ptr) DEF_HELPER_FLAGS_3(check_hcr_el2_trap, TCG_CALL_NO_WG, void, env, i32, i32) /* neon_helper.c */ -DEF_HELPER_FLAGS_3(neon_qadd_u8, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_qadd_s8, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_qadd_u16, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_qadd_s16, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_qadd_u32, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_FLAGS_3(neon_qadd_s32, TCG_CALL_NO_RWG, i32, env, i32, i32) -DEF_HELPER_3(neon_qsub_u8, i32, env, i32, i32) -DEF_HELPER_3(neon_qsub_s8, i32, env, i32, i32) -DEF_HELPER_3(neon_qsub_u16, i32, env, i32, i32) -DEF_HELPER_3(neon_qsub_s16, i32, env, i32, i32) -DEF_HELPER_3(neon_qsub_u32, i32, env, i32, i32) -DEF_HELPER_3(neon_qsub_s32, i32, env, i32, i32) -DEF_HELPER_3(neon_qadd_u64, i64, env, i64, i64) -DEF_HELPER_3(neon_qadd_s64, i64, env, i64, i64) -DEF_HELPER_3(neon_qsub_u64, i64, env, i64, i64) -DEF_HELPER_3(neon_qsub_s64, i64, env, i64, i64) - DEF_HELPER_2(neon_hadd_s8, i32, i32, i32) DEF_HELPER_2(neon_hadd_u8, i32, i32, i32) DEF_HELPER_2(neon_hadd_s16, i32, i32, i32) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ void gen_sshl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); void gen_ushl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_sshl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); +void gen_uqadd_bhs(TCGv_i64 res, TCGv_i64 qc, + TCGv_i64 a, TCGv_i64 b, MemOp esz); +void gen_uqadd_d(TCGv_i64 d, TCGv_i64 q, TCGv_i64 a, TCGv_i64 b); void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + +void gen_sqadd_bhs(TCGv_i64 res, TCGv_i64 qc, + TCGv_i64 a, TCGv_i64 b, MemOp esz); +void gen_sqadd_d(TCGv_i64 d, TCGv_i64 q, TCGv_i64 a, TCGv_i64 b); void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + +void gen_uqsub_bhs(TCGv_i64 res, TCGv_i64 qc, + TCGv_i64 a, TCGv_i64 b, MemOp esz); +void gen_uqsub_d(TCGv_i64 d, TCGv_i64 q, TCGv_i64 a, TCGv_i64 b); void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + +void gen_sqsub_bhs(TCGv_i64 res, TCGv_i64 qc, + TCGv_i64 a, TCGv_i64 b, MemOp esz); +void gen_sqsub_d(TCGv_i64 d, TCGv_i64 q, TCGv_i64 a, TCGv_i64 b); void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +void gen_uqadd_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz) +{ + uint64_t max = MAKE_64BIT_MASK(0, 8 << esz); + TCGv_i64 tmp = tcg_temp_new_i64(); + + tcg_gen_add_i64(tmp, a, b); + tcg_gen_umin_i64(res, tmp, tcg_constant_i64(max)); + tcg_gen_xor_i64(tmp, tmp, res); + tcg_gen_or_i64(qc, qc, tmp); +} + +void gen_uqadd_d(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_add_i64(t, a, b); + tcg_gen_movcond_i64(TCG_COND_LTU, res, t, a, + tcg_constant_i64(UINT64_MAX), t); + tcg_gen_xor_i64(t, t, res); + tcg_gen_or_i64(qc, qc, t); +} + static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { @@ -XXX,XX +XXX,XX @@ void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, .opt_opc = vecop_list, .vece = MO_32 }, { .fniv = gen_uqadd_vec, + .fni8 = gen_uqadd_d, .fno = gen_helper_gvec_uqadd_d, .write_aofs = true, .opt_opc = vecop_list, @@ -XXX,XX +XXX,XX @@ void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +void gen_sqadd_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz) +{ + int64_t max = MAKE_64BIT_MASK(0, (8 << esz) - 1); + int64_t min = -1ll - max; + TCGv_i64 tmp = tcg_temp_new_i64(); + + tcg_gen_add_i64(tmp, a, b); + tcg_gen_smin_i64(res, tmp, tcg_constant_i64(max)); + tcg_gen_smax_i64(res, res, tcg_constant_i64(min)); + tcg_gen_xor_i64(tmp, tmp, res); + tcg_gen_or_i64(qc, qc, tmp); +} + +void gen_sqadd_d(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t0 = tcg_temp_new_i64(); + TCGv_i64 t1 = tcg_temp_new_i64(); + TCGv_i64 t2 = tcg_temp_new_i64(); + + tcg_gen_add_i64(t0, a, b); + + /* Compute signed overflow indication into T1 */ + tcg_gen_xor_i64(t1, a, b); + tcg_gen_xor_i64(t2, t0, a); + tcg_gen_andc_i64(t1, t2, t1); + + /* Compute saturated value into T2 */ + tcg_gen_sari_i64(t2, a, 63); + tcg_gen_xori_i64(t2, t2, INT64_MAX); + + tcg_gen_movcond_i64(TCG_COND_LT, res, t1, tcg_constant_i64(0), t2, t0); + tcg_gen_xor_i64(t0, t0, res); + tcg_gen_or_i64(qc, qc, t0); +} + static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, .write_aofs = true, .vece = MO_32 }, { .fniv = gen_sqadd_vec, + .fni8 = gen_sqadd_d, .fno = gen_helper_gvec_sqadd_d, .opt_opc = vecop_list, .write_aofs = true, @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +void gen_uqsub_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz) +{ + TCGv_i64 tmp = tcg_temp_new_i64(); + + tcg_gen_sub_i64(tmp, a, b); + tcg_gen_smax_i64(res, tmp, tcg_constant_i64(0)); + tcg_gen_xor_i64(tmp, tmp, res); + tcg_gen_or_i64(qc, qc, tmp); +} + +void gen_uqsub_d(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_sub_i64(t, a, b); + tcg_gen_movcond_i64(TCG_COND_LTU, res, a, b, tcg_constant_i64(0), t); + tcg_gen_xor_i64(t, t, res); + tcg_gen_or_i64(qc, qc, t); +} + static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { @@ -XXX,XX +XXX,XX @@ void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, .write_aofs = true, .vece = MO_32 }, { .fniv = gen_uqsub_vec, + .fni8 = gen_uqsub_d, .fno = gen_helper_gvec_uqsub_d, .opt_opc = vecop_list, .write_aofs = true, @@ -XXX,XX +XXX,XX @@ void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +void gen_sqsub_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz) +{ + int64_t max = MAKE_64BIT_MASK(0, (8 << esz) - 1); + int64_t min = -1ll - max; + TCGv_i64 tmp = tcg_temp_new_i64(); + + tcg_gen_sub_i64(tmp, a, b); + tcg_gen_smin_i64(res, tmp, tcg_constant_i64(max)); + tcg_gen_smax_i64(res, res, tcg_constant_i64(min)); + tcg_gen_xor_i64(tmp, tmp, res); + tcg_gen_or_i64(qc, qc, tmp); +} + +void gen_sqsub_d(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t0 = tcg_temp_new_i64(); + TCGv_i64 t1 = tcg_temp_new_i64(); + TCGv_i64 t2 = tcg_temp_new_i64(); + + tcg_gen_sub_i64(t0, a, b); + + /* Compute signed overflow indication into T1 */ + tcg_gen_xor_i64(t1, a, b); + tcg_gen_xor_i64(t2, t0, a); + tcg_gen_and_i64(t1, t1, t2); + + /* Compute saturated value into T2 */ + tcg_gen_sari_i64(t2, a, 63); + tcg_gen_xori_i64(t2, t2, INT64_MAX); + + tcg_gen_movcond_i64(TCG_COND_LT, res, t1, tcg_constant_i64(0), t2, t0); + tcg_gen_xor_i64(t0, t0, res); + tcg_gen_or_i64(qc, qc, t0); +} + static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec qc, TCGv_vec a, TCGv_vec b) { @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, .write_aofs = true, .vece = MO_32 }, { .fniv = gen_sqsub_vec, + .fni8 = gen_sqsub_d, .fno = gen_helper_gvec_sqsub_d, .opt_opc = vecop_list, .write_aofs = true, diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(glue(neon_,name))(uint32_t arg) \ return arg; \ } - -#define NEON_USAT(dest, src1, src2, type) do { \ - uint32_t tmp = (uint32_t)src1 + (uint32_t)src2; \ - if (tmp != (type)tmp) { \ - SET_QC(); \ - dest = ~0; \ - } else { \ - dest = tmp; \ - }} while(0) -#define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint8_t) -NEON_VOP_ENV(qadd_u8, neon_u8, 4) -#undef NEON_FN -#define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint16_t) -NEON_VOP_ENV(qadd_u16, neon_u16, 2) -#undef NEON_FN -#undef NEON_USAT - -uint32_t HELPER(neon_qadd_u32)(CPUARMState *env, uint32_t a, uint32_t b) -{ - uint32_t res = a + b; - if (res < a) { - SET_QC(); - res = ~0; - } - return res; -} - -uint64_t HELPER(neon_qadd_u64)(CPUARMState *env, uint64_t src1, uint64_t src2) -{ - uint64_t res; - - res = src1 + src2; - if (res < src1) { - SET_QC(); - res = ~(uint64_t)0; - } - return res; -} - -#define NEON_SSAT(dest, src1, src2, type) do { \ - int32_t tmp = (uint32_t)src1 + (uint32_t)src2; \ - if (tmp != (type)tmp) { \ - SET_QC(); \ - if (src2 > 0) { \ - tmp = (1 << (sizeof(type) * 8 - 1)) - 1; \ - } else { \ - tmp = 1 << (sizeof(type) * 8 - 1); \ - } \ - } \ - dest = tmp; \ - } while(0) -#define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int8_t) -NEON_VOP_ENV(qadd_s8, neon_s8, 4) -#undef NEON_FN -#define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int16_t) -NEON_VOP_ENV(qadd_s16, neon_s16, 2) -#undef NEON_FN -#undef NEON_SSAT - -uint32_t HELPER(neon_qadd_s32)(CPUARMState *env, uint32_t a, uint32_t b) -{ - uint32_t res = a + b; - if (((res ^ a) & SIGNBIT) && !((a ^ b) & SIGNBIT)) { - SET_QC(); - res = ~(((int32_t)a >> 31) ^ SIGNBIT); - } - return res; -} - -uint64_t HELPER(neon_qadd_s64)(CPUARMState *env, uint64_t src1, uint64_t src2) -{ - uint64_t res; - - res = src1 + src2; - if (((res ^ src1) & SIGNBIT64) && !((src1 ^ src2) & SIGNBIT64)) { - SET_QC(); - res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64; - } - return res; -} - -#define NEON_USAT(dest, src1, src2, type) do { \ - uint32_t tmp = (uint32_t)src1 - (uint32_t)src2; \ - if (tmp != (type)tmp) { \ - SET_QC(); \ - dest = 0; \ - } else { \ - dest = tmp; \ - }} while(0) -#define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint8_t) -NEON_VOP_ENV(qsub_u8, neon_u8, 4) -#undef NEON_FN -#define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint16_t) -NEON_VOP_ENV(qsub_u16, neon_u16, 2) -#undef NEON_FN -#undef NEON_USAT - -uint32_t HELPER(neon_qsub_u32)(CPUARMState *env, uint32_t a, uint32_t b) -{ - uint32_t res = a - b; - if (res > a) { - SET_QC(); - res = 0; - } - return res; -} - -uint64_t HELPER(neon_qsub_u64)(CPUARMState *env, uint64_t src1, uint64_t src2) -{ - uint64_t res; - - if (src1 < src2) { - SET_QC(); - res = 0; - } else { - res = src1 - src2; - } - return res; -} - -#define NEON_SSAT(dest, src1, src2, type) do { \ - int32_t tmp = (uint32_t)src1 - (uint32_t)src2; \ - if (tmp != (type)tmp) { \ - SET_QC(); \ - if (src2 < 0) { \ - tmp = (1 << (sizeof(type) * 8 - 1)) - 1; \ - } else { \ - tmp = 1 << (sizeof(type) * 8 - 1); \ - } \ - } \ - dest = tmp; \ - } while(0) -#define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int8_t) -NEON_VOP_ENV(qsub_s8, neon_s8, 4) -#undef NEON_FN -#define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int16_t) -NEON_VOP_ENV(qsub_s16, neon_s16, 2) -#undef NEON_FN -#undef NEON_SSAT - -uint32_t HELPER(neon_qsub_s32)(CPUARMState *env, uint32_t a, uint32_t b) -{ - uint32_t res = a - b; - if (((res ^ a) & SIGNBIT) && ((a ^ b) & SIGNBIT)) { - SET_QC(); - res = ~(((int32_t)a >> 31) ^ SIGNBIT); - } - return res; -} - -uint64_t HELPER(neon_qsub_s64)(CPUARMState *env, uint64_t src1, uint64_t src2) -{ - uint64_t res; - - res = src1 - src2; - if (((res ^ src1) & SIGNBIT64) && ((src1 ^ src2) & SIGNBIT64)) { - SET_QC(); - res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64; - } - return res; -} - #define NEON_FN(dest, src1, src2) dest = (src1 + src2) >> 1 NEON_VOP(hadd_s8, neon_s8, 4) NEON_VOP(hadd_u8, neon_u8, 4) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, * or scalar-three-reg-same groups. */ TCGCond cond; + TCGv_i64 qc; switch (opcode) { case 0x1: /* SQADD */ + qc = tcg_temp_new_i64(); + tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); if (u) { - gen_helper_neon_qadd_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm); + gen_uqadd_d(tcg_rd, qc, tcg_rn, tcg_rm); } else { - gen_helper_neon_qadd_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm); + gen_sqadd_d(tcg_rd, qc, tcg_rn, tcg_rm); } + tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); break; case 0x5: /* SQSUB */ + qc = tcg_temp_new_i64(); + tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); if (u) { - gen_helper_neon_qsub_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm); + gen_uqsub_d(tcg_rd, qc, tcg_rn, tcg_rm); } else { - gen_helper_neon_qsub_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm); + gen_sqsub_d(tcg_rd, qc, tcg_rn, tcg_rm); } + tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); break; case 0x6: /* CMGT, CMHI */ cond = u ? TCG_COND_GTU : TCG_COND_GT; @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) * OPTME: special-purpose helpers would avoid doing some * unnecessary work in the helper for the 8 and 16 bit cases. */ - NeonGenTwoOpEnvFn *genenvfn; - TCGv_i32 tcg_rn = tcg_temp_new_i32(); - TCGv_i32 tcg_rm = tcg_temp_new_i32(); - TCGv_i32 tcg_rd32 = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_rn, rn, 0, size); - read_vec_element_i32(s, tcg_rm, rm, 0, size); + NeonGenTwoOpEnvFn *genenvfn = NULL; + void (*genfn)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp) = NULL; switch (opcode) { case 0x1: /* SQADD, UQADD */ - { - static NeonGenTwoOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qadd_s8, gen_helper_neon_qadd_u8 }, - { gen_helper_neon_qadd_s16, gen_helper_neon_qadd_u16 }, - { gen_helper_neon_qadd_s32, gen_helper_neon_qadd_u32 }, - }; - genenvfn = fns[size][u]; + genfn = u ? gen_uqadd_bhs : gen_sqadd_bhs; break; - } case 0x5: /* SQSUB, UQSUB */ - { - static NeonGenTwoOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qsub_s8, gen_helper_neon_qsub_u8 }, - { gen_helper_neon_qsub_s16, gen_helper_neon_qsub_u16 }, - { gen_helper_neon_qsub_s32, gen_helper_neon_qsub_u32 }, - }; - genenvfn = fns[size][u]; + genfn = u ? gen_uqsub_bhs : gen_sqsub_bhs; break; - } case 0x9: /* SQSHL, UQSHL */ { static NeonGenTwoOpEnvFn * const fns[3][2] = { @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) g_assert_not_reached(); } - genenvfn(tcg_rd32, tcg_env, tcg_rn, tcg_rm); - tcg_gen_extu_i32_i64(tcg_rd, tcg_rd32); + if (genenvfn) { + TCGv_i32 tcg_rn = tcg_temp_new_i32(); + TCGv_i32 tcg_rm = tcg_temp_new_i32(); + + read_vec_element_i32(s, tcg_rn, rn, 0, size); + read_vec_element_i32(s, tcg_rm, rm, 0, size); + genenvfn(tcg_rn, tcg_env, tcg_rn, tcg_rm); + tcg_gen_extu_i32_i64(tcg_rd, tcg_rn); + } else { + TCGv_i64 tcg_rn = tcg_temp_new_i64(); + TCGv_i64 tcg_rm = tcg_temp_new_i64(); + TCGv_i64 qc = tcg_temp_new_i64(); + + read_vec_element(s, tcg_rn, rn, 0, size | (u ? 0 : MO_SIGN)); + read_vec_element(s, tcg_rm, rm, 0, size | (u ? 0 : MO_SIGN)); + tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); + genfn(tcg_rd, qc, tcg_rn, tcg_rm, size); + tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); + if (!u) { + /* Truncate signed 64-bit result for writeback. */ + tcg_gen_ext_i64(tcg_rd, tcg_rd, size); + } + } } write_fp_dreg(s, rd, tcg_rd); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 11 ++++ target/arm/tcg/translate-a64.c | 96 +++++++++++++++++++--------------- 2 files changed, 64 insertions(+), 43 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ @rrr_h ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=1 @rrr_sd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_sd @rrr_hsd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_hsd +@rrr_e ........ esz:2 . rm:5 ...... rn:5 rd:5 &rrr_e @rrx_h ........ .. .. rm:4 .... . . rn:5 rd:5 &rrx_e esz=1 idx=%hlm @rrx_s ........ .. . rm:5 .... . . rn:5 rd:5 &rrx_e esz=2 idx=%hl @@ -XXX,XX +XXX,XX @@ FRECPS_s 0101 1110 0.1 ..... 11111 1 ..... ..... @rrr_sd FRSQRTS_s 0101 1110 110 ..... 00111 1 ..... ..... @rrr_h FRSQRTS_s 0101 1110 1.1 ..... 11111 1 ..... ..... @rrr_sd +SQADD_s 0101 1110 ..1 ..... 00001 1 ..... ..... @rrr_e +UQADD_s 0111 1110 ..1 ..... 00001 1 ..... ..... @rrr_e +SQSUB_s 0101 1110 ..1 ..... 00101 1 ..... ..... @rrr_e +UQSUB_s 0111 1110 ..1 ..... 00101 1 ..... ..... @rrr_e + ### Advanced SIMD scalar pairwise FADDP_s 0101 1110 0011 0000 1101 10 ..... ..... @rr_h @@ -XXX,XX +XXX,XX @@ BSL_v 0.10 1110 011 ..... 00011 1 ..... ..... @qrrr_b BIT_v 0.10 1110 101 ..... 00011 1 ..... ..... @qrrr_b BIF_v 0.10 1110 111 ..... 00011 1 ..... ..... @qrrr_b +SQADD_v 0.00 1110 ..1 ..... 00001 1 ..... ..... @qrrr_e +UQADD_v 0.10 1110 ..1 ..... 00001 1 ..... ..... @qrrr_e +SQSUB_v 0.00 1110 ..1 ..... 00101 1 ..... ..... @qrrr_e +UQSUB_v 0.10 1110 ..1 ..... 00101 1 ..... ..... @qrrr_e + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static const FPScalar f_scalar_frsqrts = { }; TRANS(FRSQRTS_s, do_fp3_scalar, a, &f_scalar_frsqrts) +static bool do_satacc_s(DisasContext *s, arg_rrr_e *a, + MemOp sgn_n, MemOp sgn_m, + void (*gen_bhs)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp), + void (*gen_d)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64)) +{ + TCGv_i64 t0, t1, t2, qc; + MemOp esz = a->esz; + + if (!fp_access_check(s)) { + return true; + } + + t0 = tcg_temp_new_i64(); + t1 = tcg_temp_new_i64(); + t2 = tcg_temp_new_i64(); + qc = tcg_temp_new_i64(); + read_vec_element(s, t1, a->rn, 0, esz | sgn_n); + read_vec_element(s, t2, a->rm, 0, esz | sgn_m); + tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); + + if (esz == MO_64) { + gen_d(t0, qc, t1, t2); + } else { + gen_bhs(t0, qc, t1, t2, esz); + tcg_gen_ext_i64(t0, t0, esz); + } + + write_fp_dreg(s, a->rd, t0); + tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); + return true; +} + +TRANS(SQADD_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqadd_bhs, gen_sqadd_d) +TRANS(SQSUB_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqsub_bhs, gen_sqsub_d) +TRANS(UQADD_s, do_satacc_s, a, 0, 0, gen_uqadd_bhs, gen_uqadd_d) +TRANS(UQSUB_s, do_satacc_s, a, 0, 0, gen_uqsub_bhs, gen_uqsub_d) + static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -XXX,XX +XXX,XX @@ TRANS(BSL_v, do_bitsel, a->q, a->rd, a->rd, a->rn, a->rm) TRANS(BIT_v, do_bitsel, a->q, a->rd, a->rm, a->rn, a->rd) TRANS(BIF_v, do_bitsel, a->q, a->rd, a->rm, a->rd, a->rn) +TRANS(SQADD_v, do_gvec_fn3, a, gen_gvec_sqadd_qc) +TRANS(UQADD_v, do_gvec_fn3, a, gen_gvec_uqadd_qc) +TRANS(SQSUB_v, do_gvec_fn3, a, gen_gvec_sqsub_qc) +TRANS(UQSUB_v, do_gvec_fn3, a, gen_gvec_uqsub_qc) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, * or scalar-three-reg-same groups. */ TCGCond cond; - TCGv_i64 qc; switch (opcode) { - case 0x1: /* SQADD */ - qc = tcg_temp_new_i64(); - tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); - if (u) { - gen_uqadd_d(tcg_rd, qc, tcg_rn, tcg_rm); - } else { - gen_sqadd_d(tcg_rd, qc, tcg_rn, tcg_rm); - } - tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); - break; - case 0x5: /* SQSUB */ - qc = tcg_temp_new_i64(); - tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); - if (u) { - gen_uqsub_d(tcg_rd, qc, tcg_rn, tcg_rm); - } else { - gen_sqsub_d(tcg_rd, qc, tcg_rn, tcg_rm); - } - tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); - break; case 0x6: /* CMGT, CMHI */ cond = u ? TCG_COND_GTU : TCG_COND_GT; do_cmop: @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, } break; default: + case 0x1: /* SQADD / UQADD */ + case 0x5: /* SQSUB / UQSUB */ g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) TCGv_i64 tcg_rd; switch (opcode) { - case 0x1: /* SQADD, UQADD */ - case 0x5: /* SQSUB, UQSUB */ case 0x9: /* SQSHL, UQSHL */ case 0xb: /* SQRSHL, UQRSHL */ break; @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) } break; default: + case 0x1: /* SQADD, UQADD */ + case 0x5: /* SQSUB, UQSUB */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) void (*genfn)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp) = NULL; switch (opcode) { - case 0x1: /* SQADD, UQADD */ - genfn = u ? gen_uqadd_bhs : gen_sqadd_bhs; - break; - case 0x5: /* SQSUB, UQSUB */ - genfn = u ? gen_uqsub_bhs : gen_sqsub_bhs; - break; case 0x9: /* SQSHL, UQSHL */ { static NeonGenTwoOpEnvFn * const fns[3][2] = { @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) break; } default: + case 0x1: /* SQADD, UQADD */ + case 0x5: /* SQSUB, UQSUB */ g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) return; } break; + + case 0x01: /* SQADD, UQADD */ + case 0x05: /* SQSUB, UQSUB */ + unallocated_encoding(s); + return; } if (!fp_access_check(s)) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x01: /* SQADD, UQADD */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqadd_qc, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqadd_qc, size); - } - return; - case 0x05: /* SQSUB, UQSUB */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqsub_qc, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqsub_qc, size); - } - return; case 0x08: /* SSHL, USHL */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_ushl, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> These are faux 2-operand instructions, reading from rd. Sort them next to the other three-operand same insns for clarity. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 8 +++++ target/arm/tcg/translate-a64.c | 64 ++++------------------------------ 2 files changed, 14 insertions(+), 58 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ @rrr_sd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_sd @rrr_hsd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_hsd @rrr_e ........ esz:2 . rm:5 ...... rn:5 rd:5 &rrr_e +@r2r_e ........ esz:2 . ..... ...... rm:5 rd:5 &rrr_e rn=%rd @rrx_h ........ .. .. rm:4 .... . . rn:5 rd:5 &rrx_e esz=1 idx=%hlm @rrx_s ........ .. . rm:5 .... . . rn:5 rd:5 &rrx_e esz=2 idx=%hl @@ -XXX,XX +XXX,XX @@ @qrrr_h . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=1 @qrrr_sd . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=%esz_sd @qrrr_e . q:1 ...... esz:2 . rm:5 ...... rn:5 rd:5 &qrrr_e +@qr2r_e . q:1 ...... esz:2 . ..... ...... rm:5 rd:5 &qrrr_e rn=%rd @qrrx_h . q:1 .. .... .. .. rm:4 .... . . rn:5 rd:5 \ &qrrx_e esz=1 idx=%hlm @@ -XXX,XX +XXX,XX @@ UQADD_s 0111 1110 ..1 ..... 00001 1 ..... ..... @rrr_e SQSUB_s 0101 1110 ..1 ..... 00101 1 ..... ..... @rrr_e UQSUB_s 0111 1110 ..1 ..... 00101 1 ..... ..... @rrr_e +SUQADD_s 0101 1110 ..1 00000 00111 0 ..... ..... @r2r_e +USQADD_s 0111 1110 ..1 00000 00111 0 ..... ..... @r2r_e + ### Advanced SIMD scalar pairwise FADDP_s 0101 1110 0011 0000 1101 10 ..... ..... @rr_h @@ -XXX,XX +XXX,XX @@ UQADD_v 0.10 1110 ..1 ..... 00001 1 ..... ..... @qrrr_e SQSUB_v 0.00 1110 ..1 ..... 00101 1 ..... ..... @qrrr_e UQSUB_v 0.10 1110 ..1 ..... 00101 1 ..... ..... @qrrr_e +SUQADD_v 0.00 1110 ..1 00000 00111 0 ..... ..... @qr2r_e +USQADD_v 0.10 1110 ..1 00000 00111 0 ..... ..... @qr2r_e + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(SQADD_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqadd_bhs, gen_sqadd_d) TRANS(SQSUB_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqsub_bhs, gen_sqsub_d) TRANS(UQADD_s, do_satacc_s, a, 0, 0, gen_uqadd_bhs, gen_uqadd_d) TRANS(UQSUB_s, do_satacc_s, a, 0, 0, gen_uqsub_bhs, gen_uqsub_d) +TRANS(SUQADD_s, do_satacc_s, a, MO_SIGN, 0, gen_suqadd_bhs, gen_suqadd_d) +TRANS(USQADD_s, do_satacc_s, a, 0, MO_SIGN, gen_usqadd_bhs, gen_usqadd_d) static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) @@ -XXX,XX +XXX,XX @@ TRANS(SQADD_v, do_gvec_fn3, a, gen_gvec_sqadd_qc) TRANS(UQADD_v, do_gvec_fn3, a, gen_gvec_uqadd_qc) TRANS(SQSUB_v, do_gvec_fn3, a, gen_gvec_sqsub_qc) TRANS(UQSUB_v, do_gvec_fn3, a, gen_gvec_uqsub_qc) +TRANS(SUQADD_v, do_gvec_fn3, a, gen_gvec_suqadd_qc) +TRANS(USQADD_v, do_gvec_fn3, a, gen_gvec_usqadd_qc) /* * Advanced SIMD scalar/vector x indexed element @@ -XXX,XX +XXX,XX @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, clear_vec_high(s, is_q, rd); } -/* Remaining saturating accumulating ops */ -static void handle_2misc_satacc(DisasContext *s, bool is_scalar, bool is_u, - bool is_q, unsigned size, int rn, int rd) -{ - TCGv_i64 res, qc, a, b; - - if (!is_scalar) { - gen_gvec_fn3(s, is_q, rd, rd, rn, - is_u ? gen_gvec_usqadd_qc : gen_gvec_suqadd_qc, size); - return; - } - - res = tcg_temp_new_i64(); - qc = tcg_temp_new_i64(); - a = tcg_temp_new_i64(); - b = tcg_temp_new_i64(); - - /* Read and extend scalar inputs to 64-bits. */ - read_vec_element(s, a, rd, 0, size | (is_u ? 0 : MO_SIGN)); - read_vec_element(s, b, rn, 0, size | (is_u ? MO_SIGN : 0)); - tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); - - if (size == MO_64) { - if (is_u) { - gen_usqadd_d(res, qc, a, b); - } else { - gen_suqadd_d(res, qc, a, b); - } - } else { - if (is_u) { - gen_usqadd_bhs(res, qc, a, b, size); - } else { - gen_suqadd_bhs(res, qc, a, b, size); - /* Truncate signed 64-bit result for writeback. */ - tcg_gen_ext_i64(res, res, size); - } - } - - write_fp_dreg(s, rd, res); - tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); -} - /* AdvSIMD scalar two reg misc * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----+---+-----------+------+-----------+--------+-----+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) TCGv_ptr tcg_fpstatus; switch (opcode) { - case 0x3: /* USQADD / SUQADD*/ - if (!fp_access_check(s)) { - return; - } - handle_2misc_satacc(s, true, u, false, size, rn, rd); - return; case 0x7: /* SQABS / SQNEG */ break; case 0xa: /* CMLT */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) } break; default: + case 0x3: /* USQADD / SUQADD */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) return; } break; - case 0x3: /* SUQADD, USQADD */ - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_2misc_satacc(s, false, u, is_q, size, rn, rd); - return; case 0x7: /* SQABS, SQNEG */ if (size == 3 && !is_q) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) break; } default: + case 0x3: /* SUQADD, USQADD */ unallocated_encoding(s); return; } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 7 ++++++ target/arm/tcg/translate-a64.c | 40 +++++++++++++++++++++------------- 2 files changed, 32 insertions(+), 15 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ @rr_sd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_sd @rrr_h ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=1 +@rrr_d ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=3 @rrr_sd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_sd @rrr_hsd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_hsd @rrr_e ........ esz:2 . rm:5 ...... rn:5 rd:5 &rrr_e @@ -XXX,XX +XXX,XX @@ UQSUB_s 0111 1110 ..1 ..... 00101 1 ..... ..... @rrr_e SUQADD_s 0101 1110 ..1 00000 00111 0 ..... ..... @r2r_e USQADD_s 0111 1110 ..1 00000 00111 0 ..... ..... @r2r_e +SSHL_s 0101 1110 111 ..... 01000 1 ..... ..... @rrr_d +USHL_s 0111 1110 111 ..... 01000 1 ..... ..... @rrr_d + ### Advanced SIMD scalar pairwise FADDP_s 0101 1110 0011 0000 1101 10 ..... ..... @rr_h @@ -XXX,XX +XXX,XX @@ UQSUB_v 0.10 1110 ..1 ..... 00101 1 ..... ..... @qrrr_e SUQADD_v 0.00 1110 ..1 00000 00111 0 ..... ..... @qr2r_e USQADD_v 0.10 1110 ..1 00000 00111 0 ..... ..... @qr2r_e +SSHL_v 0.00 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e +USHL_v 0.10 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(UQSUB_s, do_satacc_s, a, 0, 0, gen_uqsub_bhs, gen_uqsub_d) TRANS(SUQADD_s, do_satacc_s, a, MO_SIGN, 0, gen_suqadd_bhs, gen_suqadd_d) TRANS(USQADD_s, do_satacc_s, a, 0, MO_SIGN, gen_usqadd_bhs, gen_usqadd_d) +static bool do_int3_scalar_d(DisasContext *s, arg_rrr_e *a, + void (*fn)(TCGv_i64, TCGv_i64, TCGv_i64)) +{ + if (fp_access_check(s)) { + TCGv_i64 t0 = tcg_temp_new_i64(); + TCGv_i64 t1 = tcg_temp_new_i64(); + + read_vec_element(s, t0, a->rn, 0, MO_64); + read_vec_element(s, t1, a->rm, 0, MO_64); + fn(t0, t0, t1); + write_fp_dreg(s, a->rd, t0); + } + return true; +} + +TRANS(SSHL_s, do_int3_scalar_d, a, gen_sshl_i64) +TRANS(USHL_s, do_int3_scalar_d, a, gen_ushl_i64) + static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -XXX,XX +XXX,XX @@ TRANS(UQSUB_v, do_gvec_fn3, a, gen_gvec_uqsub_qc) TRANS(SUQADD_v, do_gvec_fn3, a, gen_gvec_suqadd_qc) TRANS(USQADD_v, do_gvec_fn3, a, gen_gvec_usqadd_qc) +TRANS(SSHL_v, do_gvec_fn3, a, gen_gvec_sshl) +TRANS(USHL_v, do_gvec_fn3, a, gen_gvec_ushl) + + /* * Advanced SIMD scalar/vector x indexed element */ @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, } gen_cmtst_i64(tcg_rd, tcg_rn, tcg_rm); break; - case 0x8: /* SSHL, USHL */ - if (u) { - gen_ushl_i64(tcg_rd, tcg_rn, tcg_rm); - } else { - gen_sshl_i64(tcg_rd, tcg_rn, tcg_rm); - } - break; case 0x9: /* SQSHL, UQSHL */ if (u) { gen_helper_neon_qshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm); @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, default: case 0x1: /* SQADD / UQADD */ case 0x5: /* SQSUB / UQSUB */ + case 0x8: /* SSHL, USHL */ g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x9: /* SQSHL, UQSHL */ case 0xb: /* SQRSHL, UQRSHL */ break; - case 0x8: /* SSHL, USHL */ case 0xa: /* SRSHL, URSHL */ case 0x6: /* CMGT, CMHI */ case 0x7: /* CMGE, CMHS */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) default: case 0x1: /* SQADD, UQADD */ case 0x5: /* SQSUB, UQSUB */ + case 0x8: /* SSHL, USHL */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x01: /* SQADD, UQADD */ case 0x05: /* SQSUB, UQSUB */ + case 0x08: /* SSHL, USHL */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x08: /* SSHL, USHL */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_ushl, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sshl, size); - } - return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240528203044.612851-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 10 +++++++++ target/arm/tcg/translate.h | 4 ++++ target/arm/tcg/neon-dp.decode | 10 ++------- target/arm/tcg/gengvec.c | 22 +++++++++++++++++++ target/arm/tcg/neon_helper.c | 38 ++++++++++++++++++++++++++++++++- target/arm/tcg/translate-a64.c | 17 ++++++--------- target/arm/tcg/translate-neon.c | 6 ++---- 7 files changed, 84 insertions(+), 23 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(neon_qrshl_s32, i32, env, i32, i32) DEF_HELPER_3(neon_qrshl_u64, i64, env, i64, i64) DEF_HELPER_3(neon_qrshl_s64, i64, env, i64, i64) +DEF_HELPER_FLAGS_4(gvec_srshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_srshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_srshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_urshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_urshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_urshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_urshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_2(neon_add_u8, i32, i32, i32) DEF_HELPER_2(neon_add_u16, i32, i32, i32) DEF_HELPER_2(neon_sub_u8, i32, i32, i32) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_srshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); diff --git a/target/arm/tcg/neon-dp.decode b/target/arm/tcg/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon-dp.decode +++ b/target/arm/tcg/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev } -{ - VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev - VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev -} -{ - VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev - VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev -} +VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev +VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev { VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +void gen_gvec_srshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[] = { + gen_helper_gvec_srshl_b, gen_helper_gvec_srshl_h, + gen_helper_gvec_srshl_s, gen_helper_gvec_srshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} + +void gen_gvec_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[] = { + gen_helper_gvec_urshl_b, gen_helper_gvec_urshl_h, + gen_helper_gvec_urshl_s, gen_helper_gvec_urshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} + void gen_uqadd_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz) { uint64_t max = MAKE_64BIT_MASK(0, 8 << esz); diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ * * This code is licensed under the GNU GPL v2. */ -#include "qemu/osdep.h" +#include "qemu/osdep.h" #include "cpu.h" #include "exec/helper-proto.h" +#include "tcg/tcg-gvec-desc.h" #include "fpu/softfloat.h" #include "vec_internal.h" @@ -XXX,XX +XXX,XX @@ NEON_VOP_BODY(vtype, n) uint32_t HELPER(glue(neon_,name))(CPUARMState *env, uint32_t arg1, uint32_t arg2) \ NEON_VOP_BODY(vtype, n) +#define NEON_GVEC_VOP2(name, vtype) \ +void HELPER(name)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + vtype *d = vd, *n = vn, *m = vm; \ + for (i = 0; i < opr_sz / sizeof(vtype); i++) { \ + NEON_FN(d[i], n[i], m[i]); \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + /* Pairwise operations. */ /* For 32-bit elements each segment only contains a single element, so the elementwise and pairwise operations are the same. */ @@ -XXX,XX +XXX,XX @@ NEON_VOP(shl_s16, neon_s16, 2) #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, NULL)) NEON_VOP(rshl_s8, neon_s8, 4) +NEON_GVEC_VOP2(gvec_srshl_b, int8_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, NULL)) NEON_VOP(rshl_s16, neon_s16, 2) +NEON_GVEC_VOP2(gvec_srshl_h, int16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, true, NULL)) +NEON_GVEC_VOP2(gvec_srshl_s, int32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_d(src1, (int8_t)src2, true, NULL)) +NEON_GVEC_VOP2(gvec_srshl_d, int64_t) #undef NEON_FN uint32_t HELPER(neon_rshl_s32)(uint32_t val, uint32_t shift) @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_rshl_s64)(uint64_t val, uint64_t shift) #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, NULL)) NEON_VOP(rshl_u8, neon_u8, 4) +NEON_GVEC_VOP2(gvec_urshl_b, uint8_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, NULL)) NEON_VOP(rshl_u16, neon_u16, 2) +NEON_GVEC_VOP2(gvec_urshl_h, uint16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, true, NULL)) +NEON_GVEC_VOP2(gvec_urshl_s, int32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_d(src1, (int8_t)src2, true, NULL)) +NEON_GVEC_VOP2(gvec_urshl_d, int64_t) #undef NEON_FN uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shift) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x0a: /* SRSHL, URSHL */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_urshl, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_srshl, size); + } + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genenvfn = fns[size][u]; break; } - case 0xa: /* SRSHL, URSHL */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_rshl_s8, gen_helper_neon_rshl_u8 }, - { gen_helper_neon_rshl_s16, gen_helper_neon_rshl_u16 }, - { gen_helper_neon_rshl_s32, gen_helper_neon_rshl_u32 }, - }; - genfn = fns[size][u]; - break; - } case 0xb: /* SQRSHL, UQRSHL */ { static NeonGenTwoOpEnvFn * const fns[3][2] = { diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_3SAME(VQADD_S, gen_gvec_sqadd_qc) DO_3SAME(VQADD_U, gen_gvec_uqadd_qc) DO_3SAME(VQSUB_S, gen_gvec_sqsub_qc) DO_3SAME(VQSUB_U, gen_gvec_uqsub_qc) +DO_3SAME(VRSHL_S, gen_gvec_srshl) +DO_3SAME(VRSHL_U, gen_gvec_urshl) /* These insns are all gvec_bitsel but with the inputs in various orders. */ #define DO_3SAME_BITSEL(INSN, O1, O2, O3) \ @@ -XXX,XX +XXX,XX @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) } \ DO_3SAME_64(INSN, gen_##INSN##_elt) -DO_3SAME_64(VRSHL_S64, gen_helper_neon_rshl_s64) -DO_3SAME_64(VRSHL_U64, gen_helper_neon_rshl_u64) DO_3SAME_64_ENV(VQSHL_S64, gen_helper_neon_qshl_s64) DO_3SAME_64_ENV(VQSHL_U64, gen_helper_neon_qshl_u64) DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64) @@ -XXX,XX +XXX,XX @@ DO_3SAME_32(VHSUB_S, hsub_s) DO_3SAME_32(VHSUB_U, hsub_u) DO_3SAME_32(VRHADD_S, rhadd_s) DO_3SAME_32(VRHADD_U, rhadd_u) -DO_3SAME_32(VRSHL_S, rshl_s) -DO_3SAME_32(VRSHL_U, rshl_u) DO_3SAME_32_ENV(VQSHL_S, qshl_s) DO_3SAME_32_ENV(VQSHL_U, qshl_u) -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 4 ++++ target/arm/tcg/translate-a64.c | 22 +++++++--------------- 2 files changed, 11 insertions(+), 15 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ USQADD_s 0111 1110 ..1 00000 00111 0 ..... ..... @r2r_e SSHL_s 0101 1110 111 ..... 01000 1 ..... ..... @rrr_d USHL_s 0111 1110 111 ..... 01000 1 ..... ..... @rrr_d +SRSHL_s 0101 1110 111 ..... 01010 1 ..... ..... @rrr_d +URSHL_s 0111 1110 111 ..... 01010 1 ..... ..... @rrr_d ### Advanced SIMD scalar pairwise @@ -XXX,XX +XXX,XX @@ USQADD_v 0.10 1110 ..1 00000 00111 0 ..... ..... @qr2r_e SSHL_v 0.00 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e USHL_v 0.10 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e +SRSHL_v 0.00 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e +URSHL_v 0.10 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool do_int3_scalar_d(DisasContext *s, arg_rrr_e *a, TRANS(SSHL_s, do_int3_scalar_d, a, gen_sshl_i64) TRANS(USHL_s, do_int3_scalar_d, a, gen_ushl_i64) +TRANS(SRSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_s64) +TRANS(URSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_u64) static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) @@ -XXX,XX +XXX,XX @@ TRANS(USQADD_v, do_gvec_fn3, a, gen_gvec_usqadd_qc) TRANS(SSHL_v, do_gvec_fn3, a, gen_gvec_sshl) TRANS(USHL_v, do_gvec_fn3, a, gen_gvec_ushl) +TRANS(SRSHL_v, do_gvec_fn3, a, gen_gvec_srshl) +TRANS(URSHL_v, do_gvec_fn3, a, gen_gvec_urshl) /* @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, gen_helper_neon_qshl_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm); } break; - case 0xa: /* SRSHL, URSHL */ - if (u) { - gen_helper_neon_rshl_u64(tcg_rd, tcg_rn, tcg_rm); - } else { - gen_helper_neon_rshl_s64(tcg_rd, tcg_rn, tcg_rm); - } - break; case 0xb: /* SQRSHL, UQRSHL */ if (u) { gen_helper_neon_qrshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm); @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, case 0x1: /* SQADD / UQADD */ case 0x5: /* SQSUB / UQSUB */ case 0x8: /* SSHL, USHL */ + case 0xa: /* SRSHL, URSHL */ g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x9: /* SQSHL, UQSHL */ case 0xb: /* SQRSHL, UQRSHL */ break; - case 0xa: /* SRSHL, URSHL */ case 0x6: /* CMGT, CMHI */ case 0x7: /* CMGE, CMHS */ case 0x11: /* CMTST, CMEQ */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x1: /* SQADD, UQADD */ case 0x5: /* SQSUB, UQSUB */ case 0x8: /* SSHL, USHL */ + case 0xa: /* SRSHL, URSHL */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x01: /* SQADD, UQADD */ case 0x05: /* SQSUB, UQSUB */ case 0x08: /* SSHL, USHL */ + case 0x0a: /* SRSHL, URSHL */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x0a: /* SRSHL, URSHL */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_urshl, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_srshl, size); - } - return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240528203044.612851-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 8 ++++++++ target/arm/tcg/translate.h | 4 ++++ target/arm/tcg/neon-dp.decode | 10 ++------- target/arm/tcg/gengvec.c | 24 ++++++++++++++++++++++ target/arm/tcg/neon_helper.c | 36 +++++++++++++++++++++++++++++++++ target/arm/tcg/translate-a64.c | 17 +++++++--------- target/arm/tcg/translate-neon.c | 6 ++---- 7 files changed, 83 insertions(+), 22 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(neon_qrshl_u32, i32, env, i32, i32) DEF_HELPER_3(neon_qrshl_s32, i32, env, i32, i32) DEF_HELPER_3(neon_qrshl_u64, i64, env, i64, i64) DEF_HELPER_3(neon_qrshl_s64, i64, env, i64, i64) +DEF_HELPER_FLAGS_5(neon_sqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_srshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_srshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_neon_sqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_neon_uqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); diff --git a/target/arm/tcg/neon-dp.decode b/target/arm/tcg/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon-dp.decode +++ b/target/arm/tcg/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev @3same_64_rev .... ... . . . 11 .... .... .... . q:1 . . .... \ &3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3 -{ - VQSHL_S64_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev - VQSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev -} -{ - VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev - VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev -} +VQSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev +VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev { diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); } +void gen_neon_sqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[] = { + gen_helper_neon_sqshl_b, gen_helper_neon_sqshl_h, + gen_helper_neon_sqshl_s, gen_helper_neon_sqshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, tcg_env, + opr_sz, max_sz, 0, fns[vece]); +} + +void gen_neon_uqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[] = { + gen_helper_neon_uqshl_b, gen_helper_neon_uqshl_h, + gen_helper_neon_uqshl_s, gen_helper_neon_uqshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, tcg_env, + opr_sz, max_sz, 0, fns[vece]); +} + void gen_uqadd_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz) { uint64_t max = MAKE_64BIT_MASK(0, 8 << esz); diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(name)(void *vd, void *vn, void *vm, uint32_t desc) \ clear_tail(d, opr_sz, simd_maxsz(desc)); \ } +#define NEON_GVEC_VOP2_ENV(name, vtype) \ +void HELPER(name)(void *vd, void *vn, void *vm, void *venv, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + vtype *d = vd, *n = vn, *m = vm; \ + CPUARMState *env = venv; \ + for (i = 0; i < opr_sz / sizeof(vtype); i++) { \ + NEON_FN(d[i], n[i], m[i]); \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + /* Pairwise operations. */ /* For 32-bit elements each segment only contains a single element, so the elementwise and pairwise operations are the same. */ @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shift) #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc)) NEON_VOP_ENV(qshl_u8, neon_u8, 4) +NEON_GVEC_VOP2_ENV(neon_uqshl_b, uint8_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc)) NEON_VOP_ENV(qshl_u16, neon_u16, 2) +NEON_GVEC_VOP2_ENV(neon_uqshl_h, uint16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, false, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_uqshl_s, uint32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_d(src1, (int8_t)src2, false, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_uqshl_d, uint64_t) #undef NEON_FN uint32_t HELPER(neon_qshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift) @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift) #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc)) NEON_VOP_ENV(qshl_s8, neon_s8, 4) +NEON_GVEC_VOP2_ENV(neon_sqshl_b, int8_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc)) NEON_VOP_ENV(qshl_s16, neon_s16, 2) +NEON_GVEC_VOP2_ENV(neon_sqshl_h, int16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, false, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_sqshl_s, int32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_d(src1, (int8_t)src2, false, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_sqshl_d, int64_t) #undef NEON_FN uint32_t HELPER(neon_qshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x09: /* SQSHL, UQSHL */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_uqshl, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_sqshl, size); + } + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } - case 0x9: /* SQSHL, UQSHL */ - { - static NeonGenTwoOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 }, - { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 }, - { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 }, - }; - genenvfn = fns[size][u]; - break; - } case 0xb: /* SQRSHL, UQRSHL */ { static NeonGenTwoOpEnvFn * const fns[3][2] = { diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_3SAME(VQSUB_S, gen_gvec_sqsub_qc) DO_3SAME(VQSUB_U, gen_gvec_uqsub_qc) DO_3SAME(VRSHL_S, gen_gvec_srshl) DO_3SAME(VRSHL_U, gen_gvec_urshl) +DO_3SAME(VQSHL_S, gen_neon_sqshl) +DO_3SAME(VQSHL_U, gen_neon_uqshl) /* These insns are all gvec_bitsel but with the inputs in various orders. */ #define DO_3SAME_BITSEL(INSN, O1, O2, O3) \ @@ -XXX,XX +XXX,XX @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) } \ DO_3SAME_64(INSN, gen_##INSN##_elt) -DO_3SAME_64_ENV(VQSHL_S64, gen_helper_neon_qshl_s64) -DO_3SAME_64_ENV(VQSHL_U64, gen_helper_neon_qshl_u64) DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64) DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64) @@ -XXX,XX +XXX,XX @@ DO_3SAME_32(VHSUB_U, hsub_u) DO_3SAME_32(VRHADD_S, rhadd_s) DO_3SAME_32(VRHADD_U, rhadd_u) -DO_3SAME_32_ENV(VQSHL_S, qshl_s) -DO_3SAME_32_ENV(VQSHL_U, qshl_u) DO_3SAME_32_ENV(VQRSHL_S, qrshl_s) DO_3SAME_32_ENV(VQRSHL_U, qrshl_u) -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 4 ++ target/arm/tcg/translate-a64.c | 74 ++++++++++++++++++++++------------ 2 files changed, 53 insertions(+), 25 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SSHL_s 0101 1110 111 ..... 01000 1 ..... ..... @rrr_d USHL_s 0111 1110 111 ..... 01000 1 ..... ..... @rrr_d SRSHL_s 0101 1110 111 ..... 01010 1 ..... ..... @rrr_d URSHL_s 0111 1110 111 ..... 01010 1 ..... ..... @rrr_d +SQSHL_s 0101 1110 ..1 ..... 01001 1 ..... ..... @rrr_e +UQSHL_s 0111 1110 ..1 ..... 01001 1 ..... ..... @rrr_e ### Advanced SIMD scalar pairwise @@ -XXX,XX +XXX,XX @@ SSHL_v 0.00 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e USHL_v 0.10 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e SRSHL_v 0.00 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e URSHL_v 0.10 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e +SQSHL_v 0.00 1110 ..1 ..... 01001 1 ..... ..... @qrrr_e +UQSHL_v 0.10 1110 ..1 ..... 01001 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(USHL_s, do_int3_scalar_d, a, gen_ushl_i64) TRANS(SRSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_s64) TRANS(URSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_u64) +typedef struct ENVScalar2 { + NeonGenTwoOpEnvFn *gen_bhs[3]; + NeonGenTwo64OpEnvFn *gen_d; +} ENVScalar2; + +static bool do_env_scalar2(DisasContext *s, arg_rrr_e *a, const ENVScalar2 *f) +{ + if (!fp_access_check(s)) { + return true; + } + if (a->esz == MO_64) { + TCGv_i64 t0 = read_fp_dreg(s, a->rn); + TCGv_i64 t1 = read_fp_dreg(s, a->rm); + f->gen_d(t0, tcg_env, t0, t1); + write_fp_dreg(s, a->rd, t0); + } else { + TCGv_i32 t0 = tcg_temp_new_i32(); + TCGv_i32 t1 = tcg_temp_new_i32(); + + read_vec_element_i32(s, t0, a->rn, 0, a->esz); + read_vec_element_i32(s, t1, a->rm, 0, a->esz); + f->gen_bhs[a->esz](t0, tcg_env, t0, t1); + write_fp_sreg(s, a->rd, t0); + } + return true; +} + +static const ENVScalar2 f_scalar_sqshl = { + { gen_helper_neon_qshl_s8, + gen_helper_neon_qshl_s16, + gen_helper_neon_qshl_s32 }, + gen_helper_neon_qshl_s64, +}; +TRANS(SQSHL_s, do_env_scalar2, a, &f_scalar_sqshl) + +static const ENVScalar2 f_scalar_uqshl = { + { gen_helper_neon_qshl_u8, + gen_helper_neon_qshl_u16, + gen_helper_neon_qshl_u32 }, + gen_helper_neon_qshl_u64, +}; +TRANS(UQSHL_s, do_env_scalar2, a, &f_scalar_uqshl) + static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -XXX,XX +XXX,XX @@ TRANS(SSHL_v, do_gvec_fn3, a, gen_gvec_sshl) TRANS(USHL_v, do_gvec_fn3, a, gen_gvec_ushl) TRANS(SRSHL_v, do_gvec_fn3, a, gen_gvec_srshl) TRANS(URSHL_v, do_gvec_fn3, a, gen_gvec_urshl) +TRANS(SQSHL_v, do_gvec_fn3, a, gen_neon_sqshl) +TRANS(UQSHL_v, do_gvec_fn3, a, gen_neon_uqshl) /* @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, } gen_cmtst_i64(tcg_rd, tcg_rn, tcg_rm); break; - case 0x9: /* SQSHL, UQSHL */ - if (u) { - gen_helper_neon_qshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm); - } else { - gen_helper_neon_qshl_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm); - } - break; case 0xb: /* SQRSHL, UQRSHL */ if (u) { gen_helper_neon_qrshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm); @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, case 0x1: /* SQADD / UQADD */ case 0x5: /* SQSUB / UQSUB */ case 0x8: /* SSHL, USHL */ + case 0x9: /* SQSHL, UQSHL */ case 0xa: /* SRSHL, URSHL */ g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) TCGv_i64 tcg_rd; switch (opcode) { - case 0x9: /* SQSHL, UQSHL */ case 0xb: /* SQRSHL, UQRSHL */ break; case 0x6: /* CMGT, CMHI */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x1: /* SQADD, UQADD */ case 0x5: /* SQSUB, UQSUB */ case 0x8: /* SSHL, USHL */ + case 0x9: /* SQSHL, UQSHL */ case 0xa: /* SRSHL, URSHL */ unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) void (*genfn)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp) = NULL; switch (opcode) { - case 0x9: /* SQSHL, UQSHL */ - { - static NeonGenTwoOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 }, - { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 }, - { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 }, - }; - genenvfn = fns[size][u]; - break; - } case 0xb: /* SQRSHL, UQRSHL */ { static NeonGenTwoOpEnvFn * const fns[3][2] = { @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) default: case 0x1: /* SQADD, UQADD */ case 0x5: /* SQSUB, UQSUB */ + case 0x9: /* SQSHL, UQSHL */ g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x01: /* SQADD, UQADD */ case 0x05: /* SQSUB, UQSUB */ case 0x08: /* SSHL, USHL */ + case 0x09: /* SQSHL, UQSHL */ case 0x0a: /* SRSHL, URSHL */ unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x09: /* SQSHL, UQSHL */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_uqshl, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_sqshl, size); - } - return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 8 ++++++ target/arm/tcg/translate.h | 4 +++ target/arm/tcg/neon-dp.decode | 17 ++---------- target/arm/tcg/gengvec.c | 24 ++++++++++++++++ target/arm/tcg/neon_helper.c | 24 ++++++++++++++++ target/arm/tcg/translate-a64.c | 17 +++++------- target/arm/tcg/translate-neon.c | 49 ++------------------------------- 7 files changed, 71 insertions(+), 72 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(neon_uqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_uqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_uqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_uqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_srshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ void gen_neon_sqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_neon_uqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_neon_sqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_neon_uqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); diff --git a/target/arm/tcg/neon-dp.decode b/target/arm/tcg/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon-dp.decode +++ b/target/arm/tcg/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same_rev VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev - -# Insns operating on 64-bit elements (size!=0b11 handled elsewhere) -# The _rev suffix indicates that Vn and Vm are reversed (as explained -# by the comment for the @3same_rev format). -@3same_64_rev .... ... . . . 11 .... .... .... . q:1 . . .... \ - &3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3 - VQSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev -{ - VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev - VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev -} -{ - VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev - VQRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_rev -} +VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev +VQRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_rev VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_neon_uqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, opr_sz, max_sz, 0, fns[vece]); } +void gen_neon_sqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[] = { + gen_helper_neon_sqrshl_b, gen_helper_neon_sqrshl_h, + gen_helper_neon_sqrshl_s, gen_helper_neon_sqrshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, tcg_env, + opr_sz, max_sz, 0, fns[vece]); +} + +void gen_neon_uqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[] = { + gen_helper_neon_uqrshl_b, gen_helper_neon_uqrshl_h, + gen_helper_neon_uqrshl_s, gen_helper_neon_uqrshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, tcg_env, + opr_sz, max_sz, 0, fns[vece]); +} + void gen_uqadd_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz) { uint64_t max = MAKE_64BIT_MASK(0, 8 << esz); diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t val, uint64_t shift) #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_u8, neon_u8, 4) +NEON_GVEC_VOP2_ENV(neon_uqrshl_b, uint8_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_u16, neon_u16, 2) +NEON_GVEC_VOP2_ENV(neon_uqrshl_h, uint16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, true, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_uqrshl_s, uint32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_d(src1, (int8_t)src2, true, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_uqrshl_d, uint64_t) #undef NEON_FN uint32_t HELPER(neon_qrshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift) @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_qrshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift) #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_s8, neon_s8, 4) +NEON_GVEC_VOP2_ENV(neon_sqrshl_b, int8_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_s16, neon_s16, 2) +NEON_GVEC_VOP2_ENV(neon_sqrshl_h, int16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, true, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_sqrshl_s, int32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_d(src1, (int8_t)src2, true, env->vfp.qc)) +NEON_GVEC_VOP2_ENV(neon_sqrshl_d, int64_t) #undef NEON_FN uint32_t HELPER(neon_qrshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x0b: /* SQRSHL, UQRSHL */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_uqrshl, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_sqrshl, size); + } + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } - case 0xb: /* SQRSHL, UQRSHL */ - { - static NeonGenTwoOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qrshl_s8, gen_helper_neon_qrshl_u8 }, - { gen_helper_neon_qrshl_s16, gen_helper_neon_qrshl_u16 }, - { gen_helper_neon_qrshl_s32, gen_helper_neon_qrshl_u32 }, - }; - genenvfn = fns[size][u]; - break; - } default: g_assert_not_reached(); } diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_3SAME(VRSHL_S, gen_gvec_srshl) DO_3SAME(VRSHL_U, gen_gvec_urshl) DO_3SAME(VQSHL_S, gen_neon_sqshl) DO_3SAME(VQSHL_U, gen_neon_uqshl) +DO_3SAME(VQRSHL_S, gen_neon_sqrshl) +DO_3SAME(VQRSHL_U, gen_neon_uqrshl) /* These insns are all gvec_bitsel but with the inputs in various orders. */ #define DO_3SAME_BITSEL(INSN, O1, O2, O3) \ @@ -XXX,XX +XXX,XX @@ DO_SHA2(SHA256H, gen_helper_crypto_sha256h) DO_SHA2(SHA256H2, gen_helper_crypto_sha256h2) DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) -#define DO_3SAME_64(INSN, FUNC) \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - static const GVecGen3 op = { .fni8 = FUNC }; \ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &op); \ - } \ - DO_3SAME(INSN, gen_##INSN##_3s) - -#define DO_3SAME_64_ENV(INSN, FUNC) \ - static void gen_##INSN##_elt(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m) \ - { \ - FUNC(d, tcg_env, n, m); \ - } \ - DO_3SAME_64(INSN, gen_##INSN##_elt) - -DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64) -DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64) - #define DO_3SAME_32(INSN, FUNC) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ uint32_t rn_ofs, uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64) FUNC(d, tcg_env, n, m); \ } -#define DO_3SAME_32_ENV(INSN, FUNC) \ - WRAP_ENV_FN(gen_##INSN##_tramp8, gen_helper_neon_##FUNC##8); \ - WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##16); \ - WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##32); \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - static const GVecGen3 ops[4] = { \ - { .fni4 = gen_##INSN##_tramp8 }, \ - { .fni4 = gen_##INSN##_tramp16 }, \ - { .fni4 = gen_##INSN##_tramp32 }, \ - { 0 }, \ - }; \ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece]); \ - } \ - static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ - { \ - if (a->size > 2) { \ - return false; \ - } \ - return do_3same(s, a, gen_##INSN##_3s); \ - } - DO_3SAME_32(VHADD_S, hadd_s) DO_3SAME_32(VHADD_U, hadd_u) DO_3SAME_32(VHSUB_S, hsub_s) @@ -XXX,XX +XXX,XX @@ DO_3SAME_32(VHSUB_U, hsub_u) DO_3SAME_32(VRHADD_S, rhadd_s) DO_3SAME_32(VRHADD_U, rhadd_u) -DO_3SAME_32_ENV(VQRSHL_S, qrshl_s) -DO_3SAME_32_ENV(VQRSHL_U, qrshl_u) - #define DO_3SAME_VQDMULH(INSN, FUNC) \ WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##_s16); \ WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##_s32); \ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 4 +++ target/arm/tcg/translate-a64.c | 48 ++++++++++++++++------------------ 2 files changed, 26 insertions(+), 26 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SRSHL_s 0101 1110 111 ..... 01010 1 ..... ..... @rrr_d URSHL_s 0111 1110 111 ..... 01010 1 ..... ..... @rrr_d SQSHL_s 0101 1110 ..1 ..... 01001 1 ..... ..... @rrr_e UQSHL_s 0111 1110 ..1 ..... 01001 1 ..... ..... @rrr_e +SQRSHL_s 0101 1110 ..1 ..... 01011 1 ..... ..... @rrr_e +UQRSHL_s 0111 1110 ..1 ..... 01011 1 ..... ..... @rrr_e ### Advanced SIMD scalar pairwise @@ -XXX,XX +XXX,XX @@ SRSHL_v 0.00 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e URSHL_v 0.10 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e SQSHL_v 0.00 1110 ..1 ..... 01001 1 ..... ..... @qrrr_e UQSHL_v 0.10 1110 ..1 ..... 01001 1 ..... ..... @qrrr_e +SQRSHL_v 0.00 1110 ..1 ..... 01011 1 ..... ..... @qrrr_e +UQRSHL_v 0.10 1110 ..1 ..... 01011 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static const ENVScalar2 f_scalar_uqshl = { }; TRANS(UQSHL_s, do_env_scalar2, a, &f_scalar_uqshl) +static const ENVScalar2 f_scalar_sqrshl = { + { gen_helper_neon_qrshl_s8, + gen_helper_neon_qrshl_s16, + gen_helper_neon_qrshl_s32 }, + gen_helper_neon_qrshl_s64, +}; +TRANS(SQRSHL_s, do_env_scalar2, a, &f_scalar_sqrshl) + +static const ENVScalar2 f_scalar_uqrshl = { + { gen_helper_neon_qrshl_u8, + gen_helper_neon_qrshl_u16, + gen_helper_neon_qrshl_u32 }, + gen_helper_neon_qrshl_u64, +}; +TRANS(UQRSHL_s, do_env_scalar2, a, &f_scalar_uqrshl) + static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -XXX,XX +XXX,XX @@ TRANS(SRSHL_v, do_gvec_fn3, a, gen_gvec_srshl) TRANS(URSHL_v, do_gvec_fn3, a, gen_gvec_urshl) TRANS(SQSHL_v, do_gvec_fn3, a, gen_neon_sqshl) TRANS(UQSHL_v, do_gvec_fn3, a, gen_neon_uqshl) +TRANS(SQRSHL_v, do_gvec_fn3, a, gen_neon_sqrshl) +TRANS(UQRSHL_v, do_gvec_fn3, a, gen_neon_uqrshl) /* @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, } gen_cmtst_i64(tcg_rd, tcg_rn, tcg_rm); break; - case 0xb: /* SQRSHL, UQRSHL */ - if (u) { - gen_helper_neon_qrshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm); - } else { - gen_helper_neon_qrshl_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm); - } - break; case 0x10: /* ADD, SUB */ if (u) { tcg_gen_sub_i64(tcg_rd, tcg_rn, tcg_rm); @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, case 0x8: /* SSHL, USHL */ case 0x9: /* SQSHL, UQSHL */ case 0xa: /* SRSHL, URSHL */ + case 0xb: /* SQRSHL, UQRSHL */ g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) TCGv_i64 tcg_rd; switch (opcode) { - case 0xb: /* SQRSHL, UQRSHL */ - break; case 0x6: /* CMGT, CMHI */ case 0x7: /* CMGE, CMHS */ case 0x11: /* CMTST, CMEQ */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x8: /* SSHL, USHL */ case 0x9: /* SQSHL, UQSHL */ case 0xa: /* SRSHL, URSHL */ + case 0xb: /* SQRSHL, UQRSHL */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) void (*genfn)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp) = NULL; switch (opcode) { - case 0xb: /* SQRSHL, UQRSHL */ - { - static NeonGenTwoOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qrshl_s8, gen_helper_neon_qrshl_u8 }, - { gen_helper_neon_qrshl_s16, gen_helper_neon_qrshl_u16 }, - { gen_helper_neon_qrshl_s32, gen_helper_neon_qrshl_u32 }, - }; - genenvfn = fns[size][u]; - break; - } case 0x16: /* SQDMULH, SQRDMULH */ { static NeonGenTwoOpEnvFn * const fns[2][2] = { @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x1: /* SQADD, UQADD */ case 0x5: /* SQSUB, UQSUB */ case 0x9: /* SQSHL, UQSHL */ + case 0xb: /* SQRSHL, UQRSHL */ g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x08: /* SSHL, USHL */ case 0x09: /* SQSHL, UQSHL */ case 0x0a: /* SRSHL, URSHL */ + case 0x0b: /* SQRSHL, UQRSHL */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x0b: /* SQRSHL, UQRSHL */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_uqrshl, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_sqrshl, size); - } - return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 6 ++++++ target/arm/tcg/translate-a64.c | 22 +++++++--------------- 2 files changed, 13 insertions(+), 15 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ UQSHL_s 0111 1110 ..1 ..... 01001 1 ..... ..... @rrr_e SQRSHL_s 0101 1110 ..1 ..... 01011 1 ..... ..... @rrr_e UQRSHL_s 0111 1110 ..1 ..... 01011 1 ..... ..... @rrr_e +ADD_s 0101 1110 111 ..... 10000 1 ..... ..... @rrr_d +SUB_s 0111 1110 111 ..... 10000 1 ..... ..... @rrr_d + ### Advanced SIMD scalar pairwise FADDP_s 0101 1110 0011 0000 1101 10 ..... ..... @rr_h @@ -XXX,XX +XXX,XX @@ UQSHL_v 0.10 1110 ..1 ..... 01001 1 ..... ..... @qrrr_e SQRSHL_v 0.00 1110 ..1 ..... 01011 1 ..... ..... @qrrr_e UQRSHL_v 0.10 1110 ..1 ..... 01011 1 ..... ..... @qrrr_e +ADD_v 0.00 1110 ..1 ..... 10000 1 ..... ..... @qrrr_e +SUB_v 0.10 1110 ..1 ..... 10000 1 ..... ..... @qrrr_e + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(SSHL_s, do_int3_scalar_d, a, gen_sshl_i64) TRANS(USHL_s, do_int3_scalar_d, a, gen_ushl_i64) TRANS(SRSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_s64) TRANS(URSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_u64) +TRANS(ADD_s, do_int3_scalar_d, a, tcg_gen_add_i64) +TRANS(SUB_s, do_int3_scalar_d, a, tcg_gen_sub_i64) typedef struct ENVScalar2 { NeonGenTwoOpEnvFn *gen_bhs[3]; @@ -XXX,XX +XXX,XX @@ TRANS(UQSHL_v, do_gvec_fn3, a, gen_neon_uqshl) TRANS(SQRSHL_v, do_gvec_fn3, a, gen_neon_sqrshl) TRANS(UQRSHL_v, do_gvec_fn3, a, gen_neon_uqrshl) +TRANS(ADD_v, do_gvec_fn3, a, tcg_gen_gvec_add) +TRANS(SUB_v, do_gvec_fn3, a, tcg_gen_gvec_sub) /* * Advanced SIMD scalar/vector x indexed element @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, } gen_cmtst_i64(tcg_rd, tcg_rn, tcg_rm); break; - case 0x10: /* ADD, SUB */ - if (u) { - tcg_gen_sub_i64(tcg_rd, tcg_rn, tcg_rm); - } else { - tcg_gen_add_i64(tcg_rd, tcg_rn, tcg_rm); - } - break; default: case 0x1: /* SQADD / UQADD */ case 0x5: /* SQSUB / UQSUB */ @@ -XXX,XX +XXX,XX @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, case 0x9: /* SQSHL, UQSHL */ case 0xa: /* SRSHL, URSHL */ case 0xb: /* SQRSHL, UQRSHL */ + case 0x10: /* ADD, SUB */ g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x6: /* CMGT, CMHI */ case 0x7: /* CMGE, CMHS */ case 0x11: /* CMTST, CMEQ */ - case 0x10: /* ADD, SUB (vector) */ if (size != 3) { unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x9: /* SQSHL, UQSHL */ case 0xa: /* SRSHL, URSHL */ case 0xb: /* SQRSHL, UQRSHL */ + case 0x10: /* ADD, SUB (vector) */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x09: /* SQSHL, UQSHL */ case 0x0a: /* SRSHL, URSHL */ case 0x0b: /* SQRSHL, UQRSHL */ + case 0x10: /* ADD, SUB */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_saba, size); } return; - case 0x10: /* ADD, SUB */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_sub, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_add, size); - } - return; case 0x13: /* MUL, PMUL */ if (!u) { /* MUL */ gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_mul, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 12 +++ target/arm/tcg/translate-a64.c | 132 ++++++++++++--------------------- 2 files changed, 60 insertions(+), 84 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ UQRSHL_s 0111 1110 ..1 ..... 01011 1 ..... ..... @rrr_e ADD_s 0101 1110 111 ..... 10000 1 ..... ..... @rrr_d SUB_s 0111 1110 111 ..... 10000 1 ..... ..... @rrr_d +CMGT_s 0101 1110 111 ..... 00110 1 ..... ..... @rrr_d +CMHI_s 0111 1110 111 ..... 00110 1 ..... ..... @rrr_d +CMGE_s 0101 1110 111 ..... 00111 1 ..... ..... @rrr_d +CMHS_s 0111 1110 111 ..... 00111 1 ..... ..... @rrr_d +CMTST_s 0101 1110 111 ..... 10001 1 ..... ..... @rrr_d +CMEQ_s 0111 1110 111 ..... 10001 1 ..... ..... @rrr_d ### Advanced SIMD scalar pairwise @@ -XXX,XX +XXX,XX @@ UQRSHL_v 0.10 1110 ..1 ..... 01011 1 ..... ..... @qrrr_e ADD_v 0.00 1110 ..1 ..... 10000 1 ..... ..... @qrrr_e SUB_v 0.10 1110 ..1 ..... 10000 1 ..... ..... @qrrr_e +CMGT_v 0.00 1110 ..1 ..... 00110 1 ..... ..... @qrrr_e +CMHI_v 0.10 1110 ..1 ..... 00110 1 ..... ..... @qrrr_e +CMGE_v 0.00 1110 ..1 ..... 00111 1 ..... ..... @qrrr_e +CMHS_v 0.10 1110 ..1 ..... 00111 1 ..... ..... @qrrr_e +CMTST_v 0.00 1110 ..1 ..... 10001 1 ..... ..... @qrrr_e +CMEQ_v 0.10 1110 ..1 ..... 10001 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static const ENVScalar2 f_scalar_uqrshl = { }; TRANS(UQRSHL_s, do_env_scalar2, a, &f_scalar_uqrshl) +static bool do_cmop_d(DisasContext *s, arg_rrr_e *a, TCGCond cond) +{ + if (fp_access_check(s)) { + TCGv_i64 t0 = read_fp_dreg(s, a->rn); + TCGv_i64 t1 = read_fp_dreg(s, a->rm); + tcg_gen_negsetcond_i64(cond, t0, t0, t1); + write_fp_dreg(s, a->rd, t0); + } + return true; +} + +TRANS(CMGT_s, do_cmop_d, a, TCG_COND_GT) +TRANS(CMHI_s, do_cmop_d, a, TCG_COND_GTU) +TRANS(CMGE_s, do_cmop_d, a, TCG_COND_GE) +TRANS(CMHS_s, do_cmop_d, a, TCG_COND_GEU) +TRANS(CMEQ_s, do_cmop_d, a, TCG_COND_EQ) +TRANS(CMTST_s, do_cmop_d, a, TCG_COND_TSTNE) + static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -XXX,XX +XXX,XX @@ TRANS(UQRSHL_v, do_gvec_fn3, a, gen_neon_uqrshl) TRANS(ADD_v, do_gvec_fn3, a, tcg_gen_gvec_add) TRANS(SUB_v, do_gvec_fn3, a, tcg_gen_gvec_sub) +static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond) +{ + if (a->esz == MO_64 && !a->q) { + return false; + } + if (fp_access_check(s)) { + tcg_gen_gvec_cmp(cond, a->esz, + vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + a->q ? 16 : 8, vec_full_reg_size(s)); + } + return true; +} + +TRANS(CMGT_v, do_cmop_v, a, TCG_COND_GT) +TRANS(CMHI_v, do_cmop_v, a, TCG_COND_GTU) +TRANS(CMGE_v, do_cmop_v, a, TCG_COND_GE) +TRANS(CMHS_v, do_cmop_v, a, TCG_COND_GEU) +TRANS(CMEQ_v, do_cmop_v, a, TCG_COND_EQ) +TRANS(CMTST_v, do_gvec_fn3, a, gen_gvec_cmtst) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn) } } -static void handle_3same_64(DisasContext *s, int opcode, bool u, - TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i64 tcg_rm) -{ - /* Handle 64x64->64 opcodes which are shared between the scalar - * and vector 3-same groups. We cover every opcode where size == 3 - * is valid in either the three-reg-same (integer, not pairwise) - * or scalar-three-reg-same groups. - */ - TCGCond cond; - - switch (opcode) { - case 0x6: /* CMGT, CMHI */ - cond = u ? TCG_COND_GTU : TCG_COND_GT; - do_cmop: - /* 64 bit integer comparison, result = test ? -1 : 0. */ - tcg_gen_negsetcond_i64(cond, tcg_rd, tcg_rn, tcg_rm); - break; - case 0x7: /* CMGE, CMHS */ - cond = u ? TCG_COND_GEU : TCG_COND_GE; - goto do_cmop; - case 0x11: /* CMTST, CMEQ */ - if (u) { - cond = TCG_COND_EQ; - goto do_cmop; - } - gen_cmtst_i64(tcg_rd, tcg_rn, tcg_rm); - break; - default: - case 0x1: /* SQADD / UQADD */ - case 0x5: /* SQSUB / UQSUB */ - case 0x8: /* SSHL, USHL */ - case 0x9: /* SQSHL, UQSHL */ - case 0xa: /* SRSHL, URSHL */ - case 0xb: /* SQRSHL, UQRSHL */ - case 0x10: /* ADD, SUB */ - g_assert_not_reached(); - } -} - /* AdvSIMD scalar three same * 31 30 29 28 24 23 22 21 20 16 15 11 10 9 5 4 0 * +-----+---+-----------+------+---+------+--------+---+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) TCGv_i64 tcg_rd; switch (opcode) { - case 0x6: /* CMGT, CMHI */ - case 0x7: /* CMGE, CMHS */ - case 0x11: /* CMTST, CMEQ */ - if (size != 3) { - unallocated_encoding(s); - return; - } - break; case 0x16: /* SQDMULH, SQRDMULH (vector) */ if (size != 1 && size != 2) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) default: case 0x1: /* SQADD, UQADD */ case 0x5: /* SQSUB, UQSUB */ + case 0x6: /* CMGT, CMHI */ + case 0x7: /* CMGE, CMHS */ case 0x8: /* SSHL, USHL */ case 0x9: /* SQSHL, UQSHL */ case 0xa: /* SRSHL, URSHL */ case 0xb: /* SQRSHL, UQRSHL */ case 0x10: /* ADD, SUB (vector) */ + case 0x11: /* CMTST, CMEQ */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) tcg_rd = tcg_temp_new_i64(); if (size == 3) { - TCGv_i64 tcg_rn = read_fp_dreg(s, rn); - TCGv_i64 tcg_rm = read_fp_dreg(s, rm); - - handle_3same_64(s, opcode, u, tcg_rd, tcg_rn, tcg_rm); + g_assert_not_reached(); } else { /* Do a single operation on the lowest element in the vector. * We use the standard Neon helpers and rely on 0 OP 0 == 0 with @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); int pass; - TCGCond cond; switch (opcode) { case 0x13: /* MUL, PMUL */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x01: /* SQADD, UQADD */ case 0x05: /* SQSUB, UQSUB */ + case 0x06: /* CMGT, CMHI */ + case 0x07: /* CMGE, CMHS */ case 0x08: /* SSHL, USHL */ case 0x09: /* SQSHL, UQSHL */ case 0x0a: /* SRSHL, URSHL */ case 0x0b: /* SQRSHL, UQRSHL */ case 0x10: /* ADD, SUB */ + case 0x11: /* CMTST, CMEQ */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) gen_gvec_op3_qc(s, is_q, rd, rn, rm, fns[size - 1][u]); } return; - case 0x11: - if (!u) { /* CMTST */ - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_cmtst, size); - return; - } - /* else CMEQ */ - cond = TCG_COND_EQ; - goto do_gvec_cmp; - case 0x06: /* CMGT, CMHI */ - cond = u ? TCG_COND_GTU : TCG_COND_GT; - goto do_gvec_cmp; - case 0x07: /* CMGE, CMHS */ - cond = u ? TCG_COND_GEU : TCG_COND_GE; - do_gvec_cmp: - tcg_gen_gvec_cmp(cond, size, vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - is_q ? 16 : 8, vec_full_reg_size(s)); - return; } if (size == 3) { - assert(is_q); - for (pass = 0; pass < 2; pass++) { - TCGv_i64 tcg_op1 = tcg_temp_new_i64(); - TCGv_i64 tcg_op2 = tcg_temp_new_i64(); - TCGv_i64 tcg_res = tcg_temp_new_i64(); - - read_vec_element(s, tcg_op1, rn, pass, MO_64); - read_vec_element(s, tcg_op2, rm, pass, MO_64); - - handle_3same_64(s, opcode, u, tcg_res, tcg_op1, tcg_op2); - - write_vec_element(s, tcg_res, rd, pass, MO_64); - } + g_assert_not_reached(); } else { for (pass = 0; pass < (is_q ? 4 : 2); pass++) { TCGv_i32 tcg_op1 = tcg_temp_new_i32(); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/gengvec.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, /* CMTST : test is "if (X & Y != 0)". */ static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) { - tcg_gen_and_i32(d, a, b); - tcg_gen_negsetcond_i32(TCG_COND_NE, d, d, tcg_constant_i32(0)); + tcg_gen_negsetcond_i32(TCG_COND_TSTNE, d, a, b); } void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) { - tcg_gen_and_i64(d, a, b); - tcg_gen_negsetcond_i64(TCG_COND_NE, d, d, tcg_constant_i64(0)); + tcg_gen_negsetcond_i64(TCG_COND_TSTNE, d, a, b); } static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/gengvec.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) { - tcg_gen_and_vec(vece, d, a, b); - tcg_gen_dupi_vec(vece, a, 0); - tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a); + tcg_gen_cmp_vec(TCG_COND_TSTNE, vece, d, a, b); } void gen_gvec_cmtst(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 6 -- target/arm/tcg/translate.h | 5 ++ target/arm/tcg/gengvec.c | 144 ++++++++++++++++++++++++++++++++ target/arm/tcg/neon_helper.c | 27 ------ target/arm/tcg/translate-a64.c | 17 ++-- target/arm/tcg/translate-neon.c | 4 +- 6 files changed, 158 insertions(+), 45 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(fjcvtzs, TCG_CALL_NO_RWG, i64, f64, ptr) DEF_HELPER_FLAGS_3(check_hcr_el2_trap, TCG_CALL_NO_WG, void, env, i32, i32) /* neon_helper.c */ -DEF_HELPER_2(neon_hadd_s8, i32, i32, i32) -DEF_HELPER_2(neon_hadd_u8, i32, i32, i32) -DEF_HELPER_2(neon_hadd_s16, i32, i32, i32) -DEF_HELPER_2(neon_hadd_u16, i32, i32, i32) -DEF_HELPER_2(neon_hadd_s32, s32, s32, s32) -DEF_HELPER_2(neon_hadd_u32, i32, i32, i32) DEF_HELPER_2(neon_rhadd_s8, i32, i32, i32) DEF_HELPER_2(neon_rhadd_u8, i32, i32, i32) DEF_HELPER_2(neon_rhadd_s16, i32, i32, i32) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ void gen_neon_sqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_neon_uqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_shadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_uhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); void gen_sshl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_uminp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_debug_assert(vece <= MO_32); tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); } + +static void gen_shadd8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_and_i64(t, a, b); + tcg_gen_vec_sar8i_i64(a, a, 1); + tcg_gen_vec_sar8i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_add8_i64(d, a, b); + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_shadd16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_and_i64(t, a, b); + tcg_gen_vec_sar16i_i64(a, a, 1); + tcg_gen_vec_sar16i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_add16_i64(d, a, b); + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_shadd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_and_i32(t, a, b); + tcg_gen_sari_i32(a, a, 1); + tcg_gen_sari_i32(b, b, 1); + tcg_gen_andi_i32(t, t, 1); + tcg_gen_add_i32(d, a, b); + tcg_gen_add_i32(d, d, t); +} + +static void gen_shadd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_and_vec(vece, t, a, b); + tcg_gen_sari_vec(vece, a, a, 1); + tcg_gen_sari_vec(vece, b, b, 1); + tcg_gen_and_vec(vece, t, t, tcg_constant_vec_matching(d, vece, 1)); + tcg_gen_add_vec(vece, d, a, b); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_shadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sari_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen3 g[] = { + { .fni8 = gen_shadd8_i64, + .fniv = gen_shadd_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_shadd16_i64, + .fniv = gen_shadd_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_shadd_i32, + .fniv = gen_shadd_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + }; + tcg_debug_assert(vece <= MO_32); + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); +} + +static void gen_uhadd8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_and_i64(t, a, b); + tcg_gen_vec_shr8i_i64(a, a, 1); + tcg_gen_vec_shr8i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_add8_i64(d, a, b); + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_uhadd16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_and_i64(t, a, b); + tcg_gen_vec_shr16i_i64(a, a, 1); + tcg_gen_vec_shr16i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_add16_i64(d, a, b); + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_uhadd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_and_i32(t, a, b); + tcg_gen_shri_i32(a, a, 1); + tcg_gen_shri_i32(b, b, 1); + tcg_gen_andi_i32(t, t, 1); + tcg_gen_add_i32(d, a, b); + tcg_gen_add_i32(d, d, t); +} + +static void gen_uhadd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_and_vec(vece, t, a, b); + tcg_gen_shri_vec(vece, a, a, 1); + tcg_gen_shri_vec(vece, b, b, 1); + tcg_gen_and_vec(vece, t, t, tcg_constant_vec_matching(d, vece, 1)); + tcg_gen_add_vec(vece, d, a, b); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_uhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen3 g[] = { + { .fni8 = gen_uhadd8_i64, + .fniv = gen_uhadd_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_uhadd16_i64, + .fniv = gen_uhadd_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_uhadd_i32, + .fniv = gen_uhadd_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + }; + tcg_debug_assert(vece <= MO_32); + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); +} diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(glue(neon_,name))(uint32_t arg) \ return arg; \ } -#define NEON_FN(dest, src1, src2) dest = (src1 + src2) >> 1 -NEON_VOP(hadd_s8, neon_s8, 4) -NEON_VOP(hadd_u8, neon_u8, 4) -NEON_VOP(hadd_s16, neon_s16, 2) -NEON_VOP(hadd_u16, neon_u16, 2) -#undef NEON_FN - -int32_t HELPER(neon_hadd_s32)(int32_t src1, int32_t src2) -{ - int32_t dest; - - dest = (src1 >> 1) + (src2 >> 1); - if (src1 & src2 & 1) - dest++; - return dest; -} - -uint32_t HELPER(neon_hadd_u32)(uint32_t src1, uint32_t src2) -{ - uint32_t dest; - - dest = (src1 >> 1) + (src2 >> 1); - if (src1 & src2 & 1) - dest++; - return dest; -} - #define NEON_FN(dest, src1, src2) dest = (src1 + src2 + 1) >> 1 NEON_VOP(rhadd_s8, neon_s8, 4) NEON_VOP(rhadd_u8, neon_u8, 4) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x00: /* SHADD, UHADD */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uhadd, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_shadd, size); + } + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_op2, rm, pass, MO_32); switch (opcode) { - case 0x0: /* SHADD, UHADD */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_hadd_s8, gen_helper_neon_hadd_u8 }, - { gen_helper_neon_hadd_s16, gen_helper_neon_hadd_u16 }, - { gen_helper_neon_hadd_s32, gen_helper_neon_hadd_u32 }, - }; - genfn = fns[size][u]; - break; - } case 0x2: /* SRHADD, URHADD */ { static NeonGenTwoOpFn * const fns[3][2] = { diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VPMAX_S, gen_gvec_smaxp) DO_3SAME_NO_SZ_3(VPMIN_S, gen_gvec_sminp) DO_3SAME_NO_SZ_3(VPMAX_U, gen_gvec_umaxp) DO_3SAME_NO_SZ_3(VPMIN_U, gen_gvec_uminp) +DO_3SAME_NO_SZ_3(VHADD_S, gen_gvec_shadd) +DO_3SAME_NO_SZ_3(VHADD_U, gen_gvec_uhadd) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) FUNC(d, tcg_env, n, m); \ } -DO_3SAME_32(VHADD_S, hadd_s) -DO_3SAME_32(VHADD_U, hadd_u) DO_3SAME_32(VHSUB_S, hsub_s) DO_3SAME_32(VHSUB_U, hsub_u) DO_3SAME_32(VRHADD_S, rhadd_s) -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 2 ++ target/arm/tcg/translate-a64.c | 11 +++-------- 2 files changed, 5 insertions(+), 8 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ CMGE_v 0.00 1110 ..1 ..... 00111 1 ..... ..... @qrrr_e CMHS_v 0.10 1110 ..1 ..... 00111 1 ..... ..... @qrrr_e CMTST_v 0.00 1110 ..1 ..... 10001 1 ..... ..... @qrrr_e CMEQ_v 0.10 1110 ..1 ..... 10001 1 ..... ..... @qrrr_e +SHADD_v 0.00 1110 ..1 ..... 00000 1 ..... ..... @qrrr_e +UHADD_v 0.10 1110 ..1 ..... 00000 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(UQRSHL_v, do_gvec_fn3, a, gen_neon_uqrshl) TRANS(ADD_v, do_gvec_fn3, a, tcg_gen_gvec_add) TRANS(SUB_v, do_gvec_fn3, a, tcg_gen_gvec_sub) +TRANS(SHADD_v, do_gvec_fn3_no64, a, gen_gvec_shadd) +TRANS(UHADD_v, do_gvec_fn3_no64, a, gen_gvec_uhadd) static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) return; } /* fall through */ - case 0x0: /* SHADD, UHADD */ case 0x2: /* SRHADD, URHADD */ case 0x4: /* SHSUB, UHSUB */ case 0xc: /* SMAX, UMAX */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } break; + case 0x0: /* SHADD, UHADD */ case 0x01: /* SQADD, UQADD */ case 0x05: /* SQSUB, UQSUB */ case 0x06: /* CMGT, CMHI */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x00: /* SHADD, UHADD */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uhadd, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_shadd, size); - } - return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 6 -- target/arm/tcg/translate.h | 4 + target/arm/tcg/gengvec.c | 144 ++++++++++++++++++++++++++++++++ target/arm/tcg/neon_helper.c | 27 ------ target/arm/tcg/translate-a64.c | 17 ++-- target/arm/tcg/translate-neon.c | 4 +- 6 files changed, 157 insertions(+), 45 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(neon_rhadd_s16, i32, i32, i32) DEF_HELPER_2(neon_rhadd_u16, i32, i32, i32) DEF_HELPER_2(neon_rhadd_s32, s32, s32, s32) DEF_HELPER_2(neon_rhadd_u32, i32, i32, i32) -DEF_HELPER_2(neon_hsub_s8, i32, i32, i32) -DEF_HELPER_2(neon_hsub_u8, i32, i32, i32) -DEF_HELPER_2(neon_hsub_s16, i32, i32, i32) -DEF_HELPER_2(neon_hsub_u16, i32, i32, i32) -DEF_HELPER_2(neon_hsub_s32, s32, s32, s32) -DEF_HELPER_2(neon_hsub_u32, i32, i32, i32) DEF_HELPER_2(neon_pmin_u8, i32, i32, i32) DEF_HELPER_2(neon_pmin_s8, i32, i32, i32) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_shadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_uhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_shsub(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_uhsub(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_uhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_debug_assert(vece <= MO_32); tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); } + +static void gen_shsub8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_andc_i64(t, b, a); + tcg_gen_vec_sar8i_i64(a, a, 1); + tcg_gen_vec_sar8i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_sub8_i64(d, a, b); + tcg_gen_vec_sub8_i64(d, d, t); +} + +static void gen_shsub16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_andc_i64(t, b, a); + tcg_gen_vec_sar16i_i64(a, a, 1); + tcg_gen_vec_sar16i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_sub16_i64(d, a, b); + tcg_gen_vec_sub16_i64(d, d, t); +} + +static void gen_shsub_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_andc_i32(t, b, a); + tcg_gen_sari_i32(a, a, 1); + tcg_gen_sari_i32(b, b, 1); + tcg_gen_andi_i32(t, t, 1); + tcg_gen_sub_i32(d, a, b); + tcg_gen_sub_i32(d, d, t); +} + +static void gen_shsub_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_andc_vec(vece, t, b, a); + tcg_gen_sari_vec(vece, a, a, 1); + tcg_gen_sari_vec(vece, b, b, 1); + tcg_gen_and_vec(vece, t, t, tcg_constant_vec_matching(d, vece, 1)); + tcg_gen_sub_vec(vece, d, a, b); + tcg_gen_sub_vec(vece, d, d, t); +} + +void gen_gvec_shsub(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sari_vec, INDEX_op_sub_vec, 0 + }; + static const GVecGen3 g[4] = { + { .fni8 = gen_shsub8_i64, + .fniv = gen_shsub_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_shsub16_i64, + .fniv = gen_shsub_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_shsub_i32, + .fniv = gen_shsub_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); +} + +static void gen_uhsub8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_andc_i64(t, b, a); + tcg_gen_vec_shr8i_i64(a, a, 1); + tcg_gen_vec_shr8i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_sub8_i64(d, a, b); + tcg_gen_vec_sub8_i64(d, d, t); +} + +static void gen_uhsub16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_andc_i64(t, b, a); + tcg_gen_vec_shr16i_i64(a, a, 1); + tcg_gen_vec_shr16i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_sub16_i64(d, a, b); + tcg_gen_vec_sub16_i64(d, d, t); +} + +static void gen_uhsub_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_andc_i32(t, b, a); + tcg_gen_shri_i32(a, a, 1); + tcg_gen_shri_i32(b, b, 1); + tcg_gen_andi_i32(t, t, 1); + tcg_gen_sub_i32(d, a, b); + tcg_gen_sub_i32(d, d, t); +} + +static void gen_uhsub_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_andc_vec(vece, t, b, a); + tcg_gen_shri_vec(vece, a, a, 1); + tcg_gen_shri_vec(vece, b, b, 1); + tcg_gen_and_vec(vece, t, t, tcg_constant_vec_matching(d, vece, 1)); + tcg_gen_sub_vec(vece, d, a, b); + tcg_gen_sub_vec(vece, d, d, t); +} + +void gen_gvec_uhsub(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_sub_vec, 0 + }; + static const GVecGen3 g[4] = { + { .fni8 = gen_uhsub8_i64, + .fniv = gen_uhsub_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_uhsub16_i64, + .fniv = gen_uhsub_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_uhsub_i32, + .fniv = gen_uhsub_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); +} diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_rhadd_u32)(uint32_t src1, uint32_t src2) return dest; } -#define NEON_FN(dest, src1, src2) dest = (src1 - src2) >> 1 -NEON_VOP(hsub_s8, neon_s8, 4) -NEON_VOP(hsub_u8, neon_u8, 4) -NEON_VOP(hsub_s16, neon_s16, 2) -NEON_VOP(hsub_u16, neon_u16, 2) -#undef NEON_FN - -int32_t HELPER(neon_hsub_s32)(int32_t src1, int32_t src2) -{ - int32_t dest; - - dest = (src1 >> 1) - (src2 >> 1); - if ((~src1) & src2 & 1) - dest--; - return dest; -} - -uint32_t HELPER(neon_hsub_u32)(uint32_t src1, uint32_t src2) -{ - uint32_t dest; - - dest = (src1 >> 1) - (src2 >> 1); - if ((~src1) & src2 & 1) - dest--; - return dest; -} - #define NEON_FN(dest, src1, src2) dest = (src1 < src2) ? src1 : src2 NEON_POP(pmin_s8, neon_s8, 4) NEON_POP(pmin_u8, neon_u8, 4) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x04: /* SHSUB, UHSUB */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uhsub, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_shsub, size); + } + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } - case 0x4: /* SHSUB, UHSUB */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_hsub_s8, gen_helper_neon_hsub_u8 }, - { gen_helper_neon_hsub_s16, gen_helper_neon_hsub_u16 }, - { gen_helper_neon_hsub_s32, gen_helper_neon_hsub_u32 }, - }; - genfn = fns[size][u]; - break; - } default: g_assert_not_reached(); } diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VPMAX_U, gen_gvec_umaxp) DO_3SAME_NO_SZ_3(VPMIN_U, gen_gvec_uminp) DO_3SAME_NO_SZ_3(VHADD_S, gen_gvec_shadd) DO_3SAME_NO_SZ_3(VHADD_U, gen_gvec_uhadd) +DO_3SAME_NO_SZ_3(VHSUB_S, gen_gvec_shsub) +DO_3SAME_NO_SZ_3(VHSUB_U, gen_gvec_uhsub) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) FUNC(d, tcg_env, n, m); \ } -DO_3SAME_32(VHSUB_S, hsub_s) -DO_3SAME_32(VHSUB_U, hsub_u) DO_3SAME_32(VRHADD_S, rhadd_s) DO_3SAME_32(VRHADD_U, rhadd_u) -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 2 ++ target/arm/tcg/translate-a64.c | 11 +++-------- 2 files changed, 5 insertions(+), 8 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ CMTST_v 0.00 1110 ..1 ..... 10001 1 ..... ..... @qrrr_e CMEQ_v 0.10 1110 ..1 ..... 10001 1 ..... ..... @qrrr_e SHADD_v 0.00 1110 ..1 ..... 00000 1 ..... ..... @qrrr_e UHADD_v 0.10 1110 ..1 ..... 00000 1 ..... ..... @qrrr_e +SHSUB_v 0.00 1110 ..1 ..... 00100 1 ..... ..... @qrrr_e +UHSUB_v 0.10 1110 ..1 ..... 00100 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(ADD_v, do_gvec_fn3, a, tcg_gen_gvec_add) TRANS(SUB_v, do_gvec_fn3, a, tcg_gen_gvec_sub) TRANS(SHADD_v, do_gvec_fn3_no64, a, gen_gvec_shadd) TRANS(UHADD_v, do_gvec_fn3_no64, a, gen_gvec_uhadd) +TRANS(SHSUB_v, do_gvec_fn3_no64, a, gen_gvec_shsub) +TRANS(UHSUB_v, do_gvec_fn3_no64, a, gen_gvec_uhsub) static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } /* fall through */ case 0x2: /* SRHADD, URHADD */ - case 0x4: /* SHSUB, UHSUB */ case 0xc: /* SMAX, UMAX */ case 0xd: /* SMIN, UMIN */ case 0xe: /* SABD, UABD */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x0: /* SHADD, UHADD */ case 0x01: /* SQADD, UQADD */ + case 0x04: /* SHSUB, UHSUB */ case 0x05: /* SQSUB, UQSUB */ case 0x06: /* CMGT, CMHI */ case 0x07: /* CMGE, CMHS */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x04: /* SHSUB, UHSUB */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uhsub, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_shsub, size); - } - return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 7 -- target/arm/tcg/translate.h | 4 + target/arm/tcg/gengvec.c | 144 ++++++++++++++++++++++++++++++++ target/arm/tcg/neon_helper.c | 27 ------ target/arm/tcg/translate-a64.c | 48 ++--------- target/arm/tcg/translate-neon.c | 26 +----- 6 files changed, 158 insertions(+), 98 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(fjcvtzs, TCG_CALL_NO_RWG, i64, f64, ptr) DEF_HELPER_FLAGS_3(check_hcr_el2_trap, TCG_CALL_NO_WG, void, env, i32, i32) /* neon_helper.c */ -DEF_HELPER_2(neon_rhadd_s8, i32, i32, i32) -DEF_HELPER_2(neon_rhadd_u8, i32, i32, i32) -DEF_HELPER_2(neon_rhadd_s16, i32, i32, i32) -DEF_HELPER_2(neon_rhadd_u16, i32, i32, i32) -DEF_HELPER_2(neon_rhadd_s32, s32, s32, s32) -DEF_HELPER_2(neon_rhadd_u32, i32, i32, i32) - DEF_HELPER_2(neon_pmin_u8, i32, i32, i32) DEF_HELPER_2(neon_pmin_s8, i32, i32, i32) DEF_HELPER_2(neon_pmin_u16, i32, i32, i32) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_shsub(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_uhsub(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_srhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_urhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_uhsub(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, assert(vece <= MO_32); tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); } + +static void gen_srhadd8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_or_i64(t, a, b); + tcg_gen_vec_sar8i_i64(a, a, 1); + tcg_gen_vec_sar8i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_add8_i64(d, a, b); + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_srhadd16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_or_i64(t, a, b); + tcg_gen_vec_sar16i_i64(a, a, 1); + tcg_gen_vec_sar16i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_add16_i64(d, a, b); + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_srhadd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_or_i32(t, a, b); + tcg_gen_sari_i32(a, a, 1); + tcg_gen_sari_i32(b, b, 1); + tcg_gen_andi_i32(t, t, 1); + tcg_gen_add_i32(d, a, b); + tcg_gen_add_i32(d, d, t); +} + +static void gen_srhadd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_or_vec(vece, t, a, b); + tcg_gen_sari_vec(vece, a, a, 1); + tcg_gen_sari_vec(vece, b, b, 1); + tcg_gen_and_vec(vece, t, t, tcg_constant_vec_matching(d, vece, 1)); + tcg_gen_add_vec(vece, d, a, b); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_srhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sari_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen3 g[] = { + { .fni8 = gen_srhadd8_i64, + .fniv = gen_srhadd_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_srhadd16_i64, + .fniv = gen_srhadd_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_srhadd_i32, + .fniv = gen_srhadd_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); +} + +static void gen_urhadd8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_or_i64(t, a, b); + tcg_gen_vec_shr8i_i64(a, a, 1); + tcg_gen_vec_shr8i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_add8_i64(d, a, b); + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_urhadd16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_or_i64(t, a, b); + tcg_gen_vec_shr16i_i64(a, a, 1); + tcg_gen_vec_shr16i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_add16_i64(d, a, b); + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_urhadd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_or_i32(t, a, b); + tcg_gen_shri_i32(a, a, 1); + tcg_gen_shri_i32(b, b, 1); + tcg_gen_andi_i32(t, t, 1); + tcg_gen_add_i32(d, a, b); + tcg_gen_add_i32(d, d, t); +} + +static void gen_urhadd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_or_vec(vece, t, a, b); + tcg_gen_shri_vec(vece, a, a, 1); + tcg_gen_shri_vec(vece, b, b, 1); + tcg_gen_and_vec(vece, t, t, tcg_constant_vec_matching(d, vece, 1)); + tcg_gen_add_vec(vece, d, a, b); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_urhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen3 g[] = { + { .fni8 = gen_urhadd8_i64, + .fniv = gen_urhadd_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_urhadd16_i64, + .fniv = gen_urhadd_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_urhadd_i32, + .fniv = gen_urhadd_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); +} diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(glue(neon_,name))(uint32_t arg) \ return arg; \ } -#define NEON_FN(dest, src1, src2) dest = (src1 + src2 + 1) >> 1 -NEON_VOP(rhadd_s8, neon_s8, 4) -NEON_VOP(rhadd_u8, neon_u8, 4) -NEON_VOP(rhadd_s16, neon_s16, 2) -NEON_VOP(rhadd_u16, neon_u16, 2) -#undef NEON_FN - -int32_t HELPER(neon_rhadd_s32)(int32_t src1, int32_t src2) -{ - int32_t dest; - - dest = (src1 >> 1) + (src2 >> 1); - if ((src1 | src2) & 1) - dest++; - return dest; -} - -uint32_t HELPER(neon_rhadd_u32)(uint32_t src1, uint32_t src2) -{ - uint32_t dest; - - dest = (src1 >> 1) + (src2 >> 1); - if ((src1 | src2) & 1) - dest++; - return dest; -} - #define NEON_FN(dest, src1, src2) dest = (src1 < src2) ? src1 : src2 NEON_POP(pmin_s8, neon_s8, 4) NEON_POP(pmin_u8, neon_u8, 4) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int pass; switch (opcode) { case 0x13: /* MUL, PMUL */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x02: /* SRHADD, URHADD */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_urhadd, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_srhadd, size); + } + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } return; } - - if (size == 3) { - g_assert_not_reached(); - } else { - for (pass = 0; pass < (is_q ? 4 : 2); pass++) { - TCGv_i32 tcg_op1 = tcg_temp_new_i32(); - TCGv_i32 tcg_op2 = tcg_temp_new_i32(); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - NeonGenTwoOpFn *genfn = NULL; - NeonGenTwoOpEnvFn *genenvfn = NULL; - - read_vec_element_i32(s, tcg_op1, rn, pass, MO_32); - read_vec_element_i32(s, tcg_op2, rm, pass, MO_32); - - switch (opcode) { - case 0x2: /* SRHADD, URHADD */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_rhadd_s8, gen_helper_neon_rhadd_u8 }, - { gen_helper_neon_rhadd_s16, gen_helper_neon_rhadd_u16 }, - { gen_helper_neon_rhadd_s32, gen_helper_neon_rhadd_u32 }, - }; - genfn = fns[size][u]; - break; - } - default: - g_assert_not_reached(); - } - - if (genenvfn) { - genenvfn(tcg_res, tcg_env, tcg_op1, tcg_op2); - } else { - genfn(tcg_res, tcg_op1, tcg_op2); - } - - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); - } - } - clear_vec_high(s, is_q, rd); + g_assert_not_reached(); } /* AdvSIMD three same diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VHADD_S, gen_gvec_shadd) DO_3SAME_NO_SZ_3(VHADD_U, gen_gvec_uhadd) DO_3SAME_NO_SZ_3(VHSUB_S, gen_gvec_shsub) DO_3SAME_NO_SZ_3(VHSUB_U, gen_gvec_uhsub) +DO_3SAME_NO_SZ_3(VRHADD_S, gen_gvec_srhadd) +DO_3SAME_NO_SZ_3(VRHADD_U, gen_gvec_urhadd) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_SHA2(SHA256H, gen_helper_crypto_sha256h) DO_SHA2(SHA256H2, gen_helper_crypto_sha256h2) DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) -#define DO_3SAME_32(INSN, FUNC) \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - static const GVecGen3 ops[4] = { \ - { .fni4 = gen_helper_neon_##FUNC##8 }, \ - { .fni4 = gen_helper_neon_##FUNC##16 }, \ - { .fni4 = gen_helper_neon_##FUNC##32 }, \ - { 0 }, \ - }; \ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece]); \ - } \ - static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ - { \ - if (a->size > 2) { \ - return false; \ - } \ - return do_3same(s, a, gen_##INSN##_3s); \ - } - /* * Some helper functions need to be passed the tcg_env. In order * to use those with the gvec APIs like tcg_gen_gvec_3() we need @@ -XXX,XX +XXX,XX @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) FUNC(d, tcg_env, n, m); \ } -DO_3SAME_32(VRHADD_S, rhadd_s) -DO_3SAME_32(VRHADD_U, rhadd_u) - #define DO_3SAME_VQDMULH(INSN, FUNC) \ WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##_s16); \ WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##_s32); \ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 2 ++ target/arm/tcg/translate-a64.c | 11 +++-------- 2 files changed, 5 insertions(+), 8 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SHADD_v 0.00 1110 ..1 ..... 00000 1 ..... ..... @qrrr_e UHADD_v 0.10 1110 ..1 ..... 00000 1 ..... ..... @qrrr_e SHSUB_v 0.00 1110 ..1 ..... 00100 1 ..... ..... @qrrr_e UHSUB_v 0.10 1110 ..1 ..... 00100 1 ..... ..... @qrrr_e +SRHADD_v 0.00 1110 ..1 ..... 00010 1 ..... ..... @qrrr_e +URHADD_v 0.10 1110 ..1 ..... 00010 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(SHADD_v, do_gvec_fn3_no64, a, gen_gvec_shadd) TRANS(UHADD_v, do_gvec_fn3_no64, a, gen_gvec_uhadd) TRANS(SHSUB_v, do_gvec_fn3_no64, a, gen_gvec_shsub) TRANS(UHSUB_v, do_gvec_fn3_no64, a, gen_gvec_uhsub) +TRANS(SRHADD_v, do_gvec_fn3_no64, a, gen_gvec_srhadd) +TRANS(URHADD_v, do_gvec_fn3_no64, a, gen_gvec_urhadd) static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) return; } /* fall through */ - case 0x2: /* SRHADD, URHADD */ case 0xc: /* SMAX, UMAX */ case 0xd: /* SMIN, UMIN */ case 0xe: /* SABD, UABD */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x0: /* SHADD, UHADD */ case 0x01: /* SQADD, UQADD */ + case 0x02: /* SRHADD, URHADD */ case 0x04: /* SHSUB, UHSUB */ case 0x05: /* SQSUB, UQSUB */ case 0x06: /* CMGT, CMHI */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x02: /* SRHADD, URHADD */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_urhadd, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_srhadd, size); - } - return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 4 ++++ target/arm/tcg/translate-a64.c | 22 ++++++---------------- 2 files changed, 10 insertions(+), 16 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SHSUB_v 0.00 1110 ..1 ..... 00100 1 ..... ..... @qrrr_e UHSUB_v 0.10 1110 ..1 ..... 00100 1 ..... ..... @qrrr_e SRHADD_v 0.00 1110 ..1 ..... 00010 1 ..... ..... @qrrr_e URHADD_v 0.10 1110 ..1 ..... 00010 1 ..... ..... @qrrr_e +SMAX_v 0.00 1110 ..1 ..... 01100 1 ..... ..... @qrrr_e +UMAX_v 0.10 1110 ..1 ..... 01100 1 ..... ..... @qrrr_e +SMIN_v 0.00 1110 ..1 ..... 01101 1 ..... ..... @qrrr_e +UMIN_v 0.10 1110 ..1 ..... 01101 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(SHSUB_v, do_gvec_fn3_no64, a, gen_gvec_shsub) TRANS(UHSUB_v, do_gvec_fn3_no64, a, gen_gvec_uhsub) TRANS(SRHADD_v, do_gvec_fn3_no64, a, gen_gvec_srhadd) TRANS(URHADD_v, do_gvec_fn3_no64, a, gen_gvec_urhadd) +TRANS(SMAX_v, do_gvec_fn3_no64, a, tcg_gen_gvec_smax) +TRANS(UMAX_v, do_gvec_fn3_no64, a, tcg_gen_gvec_umax) +TRANS(SMIN_v, do_gvec_fn3_no64, a, tcg_gen_gvec_smin) +TRANS(UMIN_v, do_gvec_fn3_no64, a, tcg_gen_gvec_umin) static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) return; } /* fall through */ - case 0xc: /* SMAX, UMAX */ - case 0xd: /* SMIN, UMIN */ case 0xe: /* SABD, UABD */ case 0xf: /* SABA, UABA */ case 0x12: /* MLA, MLS */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x09: /* SQSHL, UQSHL */ case 0x0a: /* SRSHL, URSHL */ case 0x0b: /* SQRSHL, UQRSHL */ + case 0x0c: /* SMAX, UMAX */ + case 0x0d: /* SMIN, UMIN */ case 0x10: /* ADD, SUB */ case 0x11: /* CMTST, CMEQ */ unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x0c: /* SMAX, UMAX */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_smax, size); - } - return; - case 0x0d: /* SMIN, UMIN */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umin, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_smin, size); - } - return; case 0xe: /* SABD, UABD */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uabd, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 4 ++++ target/arm/tcg/translate-a64.c | 22 ++++++---------------- 2 files changed, 10 insertions(+), 16 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SMAX_v 0.00 1110 ..1 ..... 01100 1 ..... ..... @qrrr_e UMAX_v 0.10 1110 ..1 ..... 01100 1 ..... ..... @qrrr_e SMIN_v 0.00 1110 ..1 ..... 01101 1 ..... ..... @qrrr_e UMIN_v 0.10 1110 ..1 ..... 01101 1 ..... ..... @qrrr_e +SABD_v 0.00 1110 ..1 ..... 01110 1 ..... ..... @qrrr_e +UABD_v 0.10 1110 ..1 ..... 01110 1 ..... ..... @qrrr_e +SABA_v 0.00 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e +UABA_v 0.10 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(SMAX_v, do_gvec_fn3_no64, a, tcg_gen_gvec_smax) TRANS(UMAX_v, do_gvec_fn3_no64, a, tcg_gen_gvec_umax) TRANS(SMIN_v, do_gvec_fn3_no64, a, tcg_gen_gvec_smin) TRANS(UMIN_v, do_gvec_fn3_no64, a, tcg_gen_gvec_umin) +TRANS(SABA_v, do_gvec_fn3_no64, a, gen_gvec_saba) +TRANS(UABA_v, do_gvec_fn3_no64, a, gen_gvec_uaba) +TRANS(SABD_v, do_gvec_fn3_no64, a, gen_gvec_sabd) +TRANS(UABD_v, do_gvec_fn3_no64, a, gen_gvec_uabd) static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) return; } /* fall through */ - case 0xe: /* SABD, UABD */ - case 0xf: /* SABA, UABA */ case 0x12: /* MLA, MLS */ if (size == 3) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x0b: /* SQRSHL, UQRSHL */ case 0x0c: /* SMAX, UMAX */ case 0x0d: /* SMIN, UMIN */ + case 0x0e: /* SABD, UABD */ + case 0x0f: /* SABA, UABA */ case 0x10: /* ADD, SUB */ case 0x11: /* CMTST, CMEQ */ unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0xe: /* SABD, UABD */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uabd, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sabd, size); - } - return; - case 0xf: /* SABA, UABA */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uaba, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_saba, size); - } - return; case 0x13: /* MUL, PMUL */ if (!u) { /* MUL */ gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_mul, size); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 5 ++++ target/arm/tcg/translate-a64.c | 51 +++++++++++++--------------------- 2 files changed, 25 insertions(+), 31 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SABD_v 0.00 1110 ..1 ..... 01110 1 ..... ..... @qrrr_e UABD_v 0.10 1110 ..1 ..... 01110 1 ..... ..... @qrrr_e SABA_v 0.00 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e UABA_v 0.10 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e +MUL_v 0.00 1110 ..1 ..... 10011 1 ..... ..... @qrrr_e +PMUL_v 0.10 1110 001 ..... 10011 1 ..... ..... @qrrr_b ### Advanced SIMD scalar x indexed element @@ -XXX,XX +XXX,XX @@ FMLAL_vi 0.00 1111 10 .. .... 0000 . 0 ..... ..... @qrrx_h FMLSL_vi 0.00 1111 10 .. .... 0100 . 0 ..... ..... @qrrx_h FMLAL2_vi 0.10 1111 10 .. .... 1000 . 0 ..... ..... @qrrx_h FMLSL2_vi 0.10 1111 10 .. .... 1100 . 0 ..... ..... @qrrx_h + +MUL_vi 0.00 1111 01 .. .... 1000 . 0 ..... ..... @qrrx_h +MUL_vi 0.00 1111 10 . ..... 1000 . 0 ..... ..... @qrrx_s diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(SABA_v, do_gvec_fn3_no64, a, gen_gvec_saba) TRANS(UABA_v, do_gvec_fn3_no64, a, gen_gvec_uaba) TRANS(SABD_v, do_gvec_fn3_no64, a, gen_gvec_sabd) TRANS(UABD_v, do_gvec_fn3_no64, a, gen_gvec_uabd) +TRANS(MUL_v, do_gvec_fn3_no64, a, tcg_gen_gvec_mul) +TRANS(PMUL_v, do_gvec_op3_ool, a, 0, gen_helper_gvec_pmul_b) static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond) { @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMLSL_vi, aa64_fhm, do_fmlal_idx, a, true, false) TRANS_FEAT(FMLAL2_vi, aa64_fhm, do_fmlal_idx, a, false, true) TRANS_FEAT(FMLSL2_vi, aa64_fhm, do_fmlal_idx, a, true, true) +static bool do_int3_vector_idx(DisasContext *s, arg_qrrx_e *a, + gen_helper_gvec_3 * const fns[2]) +{ + assert(a->esz == MO_16 || a->esz == MO_32); + if (fp_access_check(s)) { + gen_gvec_op3_ool(s, a->q, a->rd, a->rn, a->rm, a->idx, fns[a->esz - 1]); + } + return true; +} + +static gen_helper_gvec_3 * const f_vector_idx_mul[2] = { + gen_helper_gvec_mul_idx_h, + gen_helper_gvec_mul_idx_s, +}; +TRANS(MUL_vi, do_int3_vector_idx, a, f_vector_idx_mul) + /* * Advanced SIMD scalar pairwise */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) int rd = extract32(insn, 0, 5); switch (opcode) { - case 0x13: /* MUL, PMUL */ - if (u && size != 0) { - unallocated_encoding(s); - return; - } - /* fall through */ case 0x12: /* MLA, MLS */ if (size == 3) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x0f: /* SABA, UABA */ case 0x10: /* ADD, SUB */ case 0x11: /* CMTST, CMEQ */ + case 0x13: /* MUL, PMUL */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x13: /* MUL, PMUL */ - if (!u) { /* MUL */ - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_mul, size); - } else { /* PMUL */ - gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0, gen_helper_gvec_pmul_b); - } - return; case 0x12: /* MLA, MLS */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mls, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) TCGv_ptr fpst; switch (16 * u + opcode) { - case 0x08: /* MUL */ case 0x10: /* MLA */ case 0x14: /* MLS */ if (is_scalar) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x01: /* FMLA */ case 0x04: /* FMLSL */ case 0x05: /* FMLS */ + case 0x08: /* MUL */ case 0x09: /* FMUL */ case 0x18: /* FMLAL2 */ case 0x19: /* FMULX */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } return; - case 0x08: /* MUL */ - if (!is_long && !is_scalar) { - static gen_helper_gvec_3 * const fns[3] = { - gen_helper_gvec_mul_idx_h, - gen_helper_gvec_mul_idx_s, - gen_helper_gvec_mul_idx_d, - }; - tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - is_q ? 16 : 8, vec_full_reg_size(s), - index, fns[size - 1]); - return; - } - break; - case 0x10: /* MLA */ if (!is_long && !is_scalar) { static gen_helper_gvec_4 * const fns[3] = { @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_op, rn, pass, is_scalar ? size : MO_32); switch (16 * u + opcode) { - case 0x08: /* MUL */ case 0x10: /* MLA */ case 0x14: /* MLS */ { -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 8 ++++ target/arm/tcg/translate-a64.c | 77 ++++++++++------------------------ 2 files changed, 31 insertions(+), 54 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SABA_v 0.00 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e UABA_v 0.10 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e MUL_v 0.00 1110 ..1 ..... 10011 1 ..... ..... @qrrr_e PMUL_v 0.10 1110 001 ..... 10011 1 ..... ..... @qrrr_b +MLA_v 0.00 1110 ..1 ..... 10010 1 ..... ..... @qrrr_e +MLS_v 0.10 1110 ..1 ..... 10010 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element @@ -XXX,XX +XXX,XX @@ FMLSL2_vi 0.10 1111 10 .. .... 1100 . 0 ..... ..... @qrrx_h MUL_vi 0.00 1111 01 .. .... 1000 . 0 ..... ..... @qrrx_h MUL_vi 0.00 1111 10 . ..... 1000 . 0 ..... ..... @qrrx_s + +MLA_vi 0.10 1111 01 .. .... 0000 . 0 ..... ..... @qrrx_h +MLA_vi 0.10 1111 10 . ..... 0000 . 0 ..... ..... @qrrx_s + +MLS_vi 0.10 1111 01 .. .... 0100 . 0 ..... ..... @qrrx_h +MLS_vi 0.10 1111 10 . ..... 0100 . 0 ..... ..... @qrrx_s diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(SABD_v, do_gvec_fn3_no64, a, gen_gvec_sabd) TRANS(UABD_v, do_gvec_fn3_no64, a, gen_gvec_uabd) TRANS(MUL_v, do_gvec_fn3_no64, a, tcg_gen_gvec_mul) TRANS(PMUL_v, do_gvec_op3_ool, a, 0, gen_helper_gvec_pmul_b) +TRANS(MLA_v, do_gvec_fn3_no64, a, gen_gvec_mla) +TRANS(MLS_v, do_gvec_fn3_no64, a, gen_gvec_mls) static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond) { @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const f_vector_idx_mul[2] = { }; TRANS(MUL_vi, do_int3_vector_idx, a, f_vector_idx_mul) +static bool do_mla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool sub) +{ + static gen_helper_gvec_4 * const fns[2][2] = { + { gen_helper_gvec_mla_idx_h, gen_helper_gvec_mls_idx_h }, + { gen_helper_gvec_mla_idx_s, gen_helper_gvec_mls_idx_s }, + }; + + assert(a->esz == MO_16 || a->esz == MO_32); + if (fp_access_check(s)) { + gen_gvec_op4_ool(s, a->q, a->rd, a->rn, a->rm, a->rd, + a->idx, fns[a->esz - 1][sub]); + } + return true; +} + +TRANS(MLA_vi, do_mla_vector_idx, a, false) +TRANS(MLS_vi, do_mla_vector_idx, a, true) + /* * Advanced SIMD scalar pairwise */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) int rd = extract32(insn, 0, 5); switch (opcode) { - case 0x12: /* MLA, MLS */ - if (size == 3) { - unallocated_encoding(s); - return; - } - break; case 0x16: /* SQDMULH, SQRDMULH */ if (size == 0 || size == 3) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x0f: /* SABA, UABA */ case 0x10: /* ADD, SUB */ case 0x11: /* CMTST, CMEQ */ + case 0x12: /* MLA, MLS */ case 0x13: /* MUL, PMUL */ unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x12: /* MLA, MLS */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mls, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mla, size); - } - return; case 0x16: /* SQDMULH, SQRDMULH */ { static gen_helper_gvec_3_ptr * const fns[2][2] = { @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) TCGv_ptr fpst; switch (16 * u + opcode) { - case 0x10: /* MLA */ - case 0x14: /* MLS */ - if (is_scalar) { - unallocated_encoding(s); - return; - } - break; case 0x02: /* SMLAL, SMLAL2 */ case 0x12: /* UMLAL, UMLAL2 */ case 0x06: /* SMLSL, SMLSL2 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x05: /* FMLS */ case 0x08: /* MUL */ case 0x09: /* FMUL */ + case 0x10: /* MLA */ + case 0x14: /* MLS */ case 0x18: /* FMLAL2 */ case 0x19: /* FMULX */ case 0x1c: /* FMLSL2 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) : gen_helper_gvec_fcmlah_idx); } return; - - case 0x10: /* MLA */ - if (!is_long && !is_scalar) { - static gen_helper_gvec_4 * const fns[3] = { - gen_helper_gvec_mla_idx_h, - gen_helper_gvec_mla_idx_s, - gen_helper_gvec_mla_idx_d, - }; - tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - vec_full_reg_offset(s, rd), - is_q ? 16 : 8, vec_full_reg_size(s), - index, fns[size - 1]); - return; - } - break; - - case 0x14: /* MLS */ - if (!is_long && !is_scalar) { - static gen_helper_gvec_4 * const fns[3] = { - gen_helper_gvec_mls_idx_h, - gen_helper_gvec_mls_idx_s, - gen_helper_gvec_mls_idx_d, - }; - tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - vec_full_reg_offset(s, rd), - is_q ? 16 : 8, vec_full_reg_size(s), - index, fns[size - 1]); - return; - } - break; } if (size == 3) { -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> We already have a gvec helper for the operations, but we aren't using it on the aa32 neon side. Create a unified expander for use by both aa32 and aa64 translators. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate.h | 4 ++++ target/arm/tcg/gengvec.c | 20 ++++++++++++++++++++ target/arm/tcg/translate-a64.c | 23 ++++------------------- target/arm/tcg/translate-neon.c | 23 +++-------------------- 4 files changed, 31 insertions(+), 39 deletions(-) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sqdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sqrdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, opr_sz, max_sz, 0, fn); } +void gen_gvec_sqdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[2] = { + gen_helper_neon_sqdmulh_h, gen_helper_neon_sqdmulh_s + }; + tcg_debug_assert(vece >= 1 && vece <= 2); + gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]); +} + +void gen_gvec_sqrdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[2] = { + gen_helper_neon_sqrdmulh_h, gen_helper_neon_sqrdmulh_s + }; + tcg_debug_assert(vece >= 1 && vece <= 2); + gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]); +} + void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) { diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_op3_fpst(DisasContext *s, bool is_q, int rd, int rn, is_q ? 16 : 8, vec_full_reg_size(s), data, fn); } -/* Expand a 3-operand + qc + operation using an out-of-line helper. */ -static void gen_gvec_op3_qc(DisasContext *s, bool is_q, int rd, int rn, - int rm, gen_helper_gvec_3_ptr *fn) -{ - TCGv_ptr qc_ptr = tcg_temp_new_ptr(); - - tcg_gen_addi_ptr(qc_ptr, tcg_env, offsetof(CPUARMState, vfp.qc)); - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), qc_ptr, - is_q ? 16 : 8, vec_full_reg_size(s), 0, fn); -} - /* Expand a 4-operand operation using an out-of-line helper. */ static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn, int rm, int ra, int data, gen_helper_gvec_4 *fn) @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) switch (opcode) { case 0x16: /* SQDMULH, SQRDMULH */ - { - static gen_helper_gvec_3_ptr * const fns[2][2] = { - { gen_helper_neon_sqdmulh_h, gen_helper_neon_sqrdmulh_h }, - { gen_helper_neon_sqdmulh_s, gen_helper_neon_sqrdmulh_s }, - }; - gen_gvec_op3_qc(s, is_q, rd, rn, rm, fns[size - 1][u]); + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqrdmulh_qc, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqdmulh_qc, size); } return; } diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -XXX,XX +XXX,XX @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) } #define DO_3SAME_VQDMULH(INSN, FUNC) \ - WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##_s16); \ - WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##_s32); \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - static const GVecGen3 ops[2] = { \ - { .fni4 = gen_##INSN##_tramp16 }, \ - { .fni4 = gen_##INSN##_tramp32 }, \ - }; \ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece - 1]); \ - } \ static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ - { \ - if (a->size != 1 && a->size != 2) { \ - return false; \ - } \ - return do_3same(s, a, gen_##INSN##_3s); \ - } + { return a->size >= 1 && a->size <= 2 && do_3same(s, a, FUNC); } -DO_3SAME_VQDMULH(VQDMULH, qdmulh) -DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) +DO_3SAME_VQDMULH(VQDMULH, gen_gvec_sqdmulh_qc) +DO_3SAME_VQDMULH(VQRDMULH, gen_gvec_sqrdmulh_qc) #define WRAP_FP_GVEC(WRAPNAME, FPST, FUNC) \ static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> These are the last instructions within disas_simd_three_reg_same and disas_simd_scalar_three_reg_same, so remove them. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240528203044.612851-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 10 ++ target/arm/tcg/a64.decode | 18 +++ target/arm/tcg/translate-a64.c | 276 ++++++++++----------------------- target/arm/tcg/vec_helper.c | 64 ++++++++ 4 files changed, 172 insertions(+), 196 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(neon_sqrdmulh_h, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(neon_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqdmulh_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqdmulh_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(neon_sqrdmulh_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrdmulh_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve2_sqdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ CMHS_s 0111 1110 111 ..... 00111 1 ..... ..... @rrr_d CMTST_s 0101 1110 111 ..... 10001 1 ..... ..... @rrr_d CMEQ_s 0111 1110 111 ..... 10001 1 ..... ..... @rrr_d +SQDMULH_s 0101 1110 ..1 ..... 10110 1 ..... ..... @rrr_e +SQRDMULH_s 0111 1110 ..1 ..... 10110 1 ..... ..... @rrr_e + ### Advanced SIMD scalar pairwise FADDP_s 0101 1110 0011 0000 1101 10 ..... ..... @rr_h @@ -XXX,XX +XXX,XX @@ PMUL_v 0.10 1110 001 ..... 10011 1 ..... ..... @qrrr_b MLA_v 0.00 1110 ..1 ..... 10010 1 ..... ..... @qrrr_e MLS_v 0.10 1110 ..1 ..... 10010 1 ..... ..... @qrrr_e +SQDMULH_v 0.00 1110 ..1 ..... 10110 1 ..... ..... @qrrr_e +SQRDMULH_v 0.10 1110 ..1 ..... 10110 1 ..... ..... @qrrr_e + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h @@ -XXX,XX +XXX,XX @@ FMULX_si 0111 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h FMULX_si 0111 1111 10 . ..... 1001 . 0 ..... ..... @rrx_s FMULX_si 0111 1111 11 0 ..... 1001 . 0 ..... ..... @rrx_d +SQDMULH_si 0101 1111 01 .. .... 1100 . 0 ..... ..... @rrx_h +SQDMULH_si 0101 1111 10 .. .... 1100 . 0 ..... ..... @rrx_s + +SQRDMULH_si 0101 1111 01 .. .... 1101 . 0 ..... ..... @rrx_h +SQRDMULH_si 0101 1111 10 . ..... 1101 . 0 ..... ..... @rrx_s + ### Advanced SIMD vector x indexed element FMUL_vi 0.00 1111 00 .. .... 1001 . 0 ..... ..... @qrrx_h @@ -XXX,XX +XXX,XX @@ MLA_vi 0.10 1111 10 . ..... 0000 . 0 ..... ..... @qrrx_s MLS_vi 0.10 1111 01 .. .... 0100 . 0 ..... ..... @qrrx_h MLS_vi 0.10 1111 10 . ..... 0100 . 0 ..... ..... @qrrx_s + +SQDMULH_vi 0.00 1111 01 .. .... 1100 . 0 ..... ..... @qrrx_h +SQDMULH_vi 0.00 1111 10 . ..... 1100 . 0 ..... ..... @qrrx_s + +SQRDMULH_vi 0.00 1111 01 .. .... 1101 . 0 ..... ..... @qrrx_h +SQRDMULH_vi 0.00 1111 10 . ..... 1101 . 0 ..... ..... @qrrx_s diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool do_gvec_fn3_no64(DisasContext *s, arg_qrrr_e *a, GVecGen3Fn *fn) return true; } +static bool do_gvec_fn3_no8_no64(DisasContext *s, arg_qrrr_e *a, GVecGen3Fn *fn) +{ + if (a->esz == MO_8) { + return false; + } + return do_gvec_fn3_no64(s, a, fn); +} + static bool do_gvec_fn4(DisasContext *s, arg_qrrrr_e *a, GVecGen4Fn *fn) { if (!a->q && a->esz == MO_64) { @@ -XXX,XX +XXX,XX @@ static const ENVScalar2 f_scalar_uqrshl = { }; TRANS(UQRSHL_s, do_env_scalar2, a, &f_scalar_uqrshl) +static bool do_env_scalar2_hs(DisasContext *s, arg_rrr_e *a, + const ENVScalar2 *f) +{ + if (a->esz == MO_16 || a->esz == MO_32) { + return do_env_scalar2(s, a, f); + } + return false; +} + +static const ENVScalar2 f_scalar_sqdmulh = { + { NULL, gen_helper_neon_qdmulh_s16, gen_helper_neon_qdmulh_s32 } +}; +TRANS(SQDMULH_s, do_env_scalar2_hs, a, &f_scalar_sqdmulh) + +static const ENVScalar2 f_scalar_sqrdmulh = { + { NULL, gen_helper_neon_qrdmulh_s16, gen_helper_neon_qrdmulh_s32 } +}; +TRANS(SQRDMULH_s, do_env_scalar2_hs, a, &f_scalar_sqrdmulh) + static bool do_cmop_d(DisasContext *s, arg_rrr_e *a, TCGCond cond) { if (fp_access_check(s)) { @@ -XXX,XX +XXX,XX @@ TRANS(CMHS_v, do_cmop_v, a, TCG_COND_GEU) TRANS(CMEQ_v, do_cmop_v, a, TCG_COND_EQ) TRANS(CMTST_v, do_gvec_fn3, a, gen_gvec_cmtst) +TRANS(SQDMULH_v, do_gvec_fn3_no8_no64, a, gen_gvec_sqdmulh_qc) +TRANS(SQRDMULH_v, do_gvec_fn3_no8_no64, a, gen_gvec_sqrdmulh_qc) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -XXX,XX +XXX,XX @@ static bool do_fmla_scalar_idx(DisasContext *s, arg_rrx_e *a, bool neg) TRANS(FMLA_si, do_fmla_scalar_idx, a, false) TRANS(FMLS_si, do_fmla_scalar_idx, a, true) +static bool do_env_scalar2_idx_hs(DisasContext *s, arg_rrx_e *a, + const ENVScalar2 *f) +{ + if (a->esz < MO_16 || a->esz > MO_32) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 t0 = tcg_temp_new_i32(); + TCGv_i32 t1 = tcg_temp_new_i32(); + + read_vec_element_i32(s, t0, a->rn, 0, a->esz); + read_vec_element_i32(s, t1, a->rm, a->idx, a->esz); + f->gen_bhs[a->esz](t0, tcg_env, t0, t1); + write_fp_sreg(s, a->rd, t0); + } + return true; +} + +TRANS(SQDMULH_si, do_env_scalar2_idx_hs, a, &f_scalar_sqdmulh) +TRANS(SQRDMULH_si, do_env_scalar2_idx_hs, a, &f_scalar_sqrdmulh) + static bool do_fp3_vector_idx(DisasContext *s, arg_qrrx_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -XXX,XX +XXX,XX @@ static bool do_mla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool sub) TRANS(MLA_vi, do_mla_vector_idx, a, false) TRANS(MLS_vi, do_mla_vector_idx, a, true) +static bool do_int3_qc_vector_idx(DisasContext *s, arg_qrrx_e *a, + gen_helper_gvec_4 * const fns[2]) +{ + assert(a->esz == MO_16 || a->esz == MO_32); + if (fp_access_check(s)) { + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + offsetof(CPUARMState, vfp.qc), + a->q ? 16 : 8, vec_full_reg_size(s), + a->idx, fns[a->esz - 1]); + } + return true; +} + +static gen_helper_gvec_4 * const f_vector_idx_sqdmulh[2] = { + gen_helper_neon_sqdmulh_idx_h, + gen_helper_neon_sqdmulh_idx_s, +}; +TRANS(SQDMULH_vi, do_int3_qc_vector_idx, a, f_vector_idx_sqdmulh) + +static gen_helper_gvec_4 * const f_vector_idx_sqrdmulh[2] = { + gen_helper_neon_sqrdmulh_idx_h, + gen_helper_neon_sqrdmulh_idx_s, +}; +TRANS(SQRDMULH_vi, do_int3_qc_vector_idx, a, f_vector_idx_sqrdmulh) + /* * Advanced SIMD scalar pairwise */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn) } } -/* AdvSIMD scalar three same - * 31 30 29 28 24 23 22 21 20 16 15 11 10 9 5 4 0 - * +-----+---+-----------+------+---+------+--------+---+------+------+ - * | 0 1 | U | 1 1 1 1 0 | size | 1 | Rm | opcode | 1 | Rn | Rd | - * +-----+---+-----------+------+---+------+--------+---+------+------+ - */ -static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int opcode = extract32(insn, 11, 5); - int rm = extract32(insn, 16, 5); - int size = extract32(insn, 22, 2); - bool u = extract32(insn, 29, 1); - TCGv_i64 tcg_rd; - - switch (opcode) { - case 0x16: /* SQDMULH, SQRDMULH (vector) */ - if (size != 1 && size != 2) { - unallocated_encoding(s); - return; - } - break; - default: - case 0x1: /* SQADD, UQADD */ - case 0x5: /* SQSUB, UQSUB */ - case 0x6: /* CMGT, CMHI */ - case 0x7: /* CMGE, CMHS */ - case 0x8: /* SSHL, USHL */ - case 0x9: /* SQSHL, UQSHL */ - case 0xa: /* SRSHL, URSHL */ - case 0xb: /* SQRSHL, UQRSHL */ - case 0x10: /* ADD, SUB (vector) */ - case 0x11: /* CMTST, CMEQ */ - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - tcg_rd = tcg_temp_new_i64(); - - if (size == 3) { - g_assert_not_reached(); - } else { - /* Do a single operation on the lowest element in the vector. - * We use the standard Neon helpers and rely on 0 OP 0 == 0 with - * no side effects for all these operations. - * OPTME: special-purpose helpers would avoid doing some - * unnecessary work in the helper for the 8 and 16 bit cases. - */ - NeonGenTwoOpEnvFn *genenvfn = NULL; - void (*genfn)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp) = NULL; - - switch (opcode) { - case 0x16: /* SQDMULH, SQRDMULH */ - { - static NeonGenTwoOpEnvFn * const fns[2][2] = { - { gen_helper_neon_qdmulh_s16, gen_helper_neon_qrdmulh_s16 }, - { gen_helper_neon_qdmulh_s32, gen_helper_neon_qrdmulh_s32 }, - }; - assert(size == 1 || size == 2); - genenvfn = fns[size - 1][u]; - break; - } - default: - case 0x1: /* SQADD, UQADD */ - case 0x5: /* SQSUB, UQSUB */ - case 0x9: /* SQSHL, UQSHL */ - case 0xb: /* SQRSHL, UQRSHL */ - g_assert_not_reached(); - } - - if (genenvfn) { - TCGv_i32 tcg_rn = tcg_temp_new_i32(); - TCGv_i32 tcg_rm = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_rn, rn, 0, size); - read_vec_element_i32(s, tcg_rm, rm, 0, size); - genenvfn(tcg_rn, tcg_env, tcg_rn, tcg_rm); - tcg_gen_extu_i32_i64(tcg_rd, tcg_rn); - } else { - TCGv_i64 tcg_rn = tcg_temp_new_i64(); - TCGv_i64 tcg_rm = tcg_temp_new_i64(); - TCGv_i64 qc = tcg_temp_new_i64(); - - read_vec_element(s, tcg_rn, rn, 0, size | (u ? 0 : MO_SIGN)); - read_vec_element(s, tcg_rm, rm, 0, size | (u ? 0 : MO_SIGN)); - tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); - genfn(tcg_rd, qc, tcg_rn, tcg_rm, size); - tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); - if (!u) { - /* Truncate signed 64-bit result for writeback. */ - tcg_gen_ext_i64(tcg_rd, tcg_rd, size); - } - } - } - - write_fp_dreg(s, rd, tcg_rd); -} - /* AdvSIMD scalar three same extra * 31 30 29 28 24 23 22 21 20 16 15 14 11 10 9 5 4 0 * +-----+---+-----------+------+---+------+---+--------+---+----+----+ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) } } -/* Integer op subgroup of C3.6.16. */ -static void disas_simd_3same_int(DisasContext *s, uint32_t insn) -{ - int is_q = extract32(insn, 30, 1); - int u = extract32(insn, 29, 1); - int size = extract32(insn, 22, 2); - int opcode = extract32(insn, 11, 5); - int rm = extract32(insn, 16, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - - switch (opcode) { - case 0x16: /* SQDMULH, SQRDMULH */ - if (size == 0 || size == 3) { - unallocated_encoding(s); - return; - } - break; - default: - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - break; - - case 0x0: /* SHADD, UHADD */ - case 0x01: /* SQADD, UQADD */ - case 0x02: /* SRHADD, URHADD */ - case 0x04: /* SHSUB, UHSUB */ - case 0x05: /* SQSUB, UQSUB */ - case 0x06: /* CMGT, CMHI */ - case 0x07: /* CMGE, CMHS */ - case 0x08: /* SSHL, USHL */ - case 0x09: /* SQSHL, UQSHL */ - case 0x0a: /* SRSHL, URSHL */ - case 0x0b: /* SQRSHL, UQRSHL */ - case 0x0c: /* SMAX, UMAX */ - case 0x0d: /* SMIN, UMIN */ - case 0x0e: /* SABD, UABD */ - case 0x0f: /* SABA, UABA */ - case 0x10: /* ADD, SUB */ - case 0x11: /* CMTST, CMEQ */ - case 0x12: /* MLA, MLS */ - case 0x13: /* MUL, PMUL */ - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - switch (opcode) { - case 0x16: /* SQDMULH, SQRDMULH */ - if (u) { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqrdmulh_qc, size); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqdmulh_qc, size); - } - return; - } - g_assert_not_reached(); -} - -/* AdvSIMD three same - * 31 30 29 28 24 23 22 21 20 16 15 11 10 9 5 4 0 - * +---+---+---+-----------+------+---+------+--------+---+------+------+ - * | 0 | Q | U | 0 1 1 1 0 | size | 1 | Rm | opcode | 1 | Rn | Rd | - * +---+---+---+-----------+------+---+------+--------+---+------+------+ - */ -static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn) -{ - int opcode = extract32(insn, 11, 5); - - switch (opcode) { - default: - disas_simd_3same_int(s, insn); - break; - case 0x3: /* logic ops */ - case 0x14: /* SMAXP, UMAXP */ - case 0x15: /* SMINP, UMINP */ - case 0x17: /* ADDP */ - case 0x18 ... 0x31: /* floating point ops */ - unallocated_encoding(s); - break; - } -} - /* AdvSIMD three same extra * 31 30 29 28 24 23 22 21 20 16 15 14 11 10 9 5 4 0 * +---+---+---+-----------+------+---+------+---+--------+---+----+----+ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x0b: /* SQDMULL, SQDMULL2 */ is_long = true; break; - case 0x0c: /* SQDMULH */ - case 0x0d: /* SQRDMULH */ - break; case 0x1d: /* SQRDMLAH */ case 0x1f: /* SQRDMLSH */ if (!dc_isar_feature(aa64_rdm, s)) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x05: /* FMLS */ case 0x08: /* MUL */ case 0x09: /* FMUL */ + case 0x0c: /* SQDMULH */ + case 0x0d: /* SQRDMULH */ case 0x10: /* MLA */ case 0x14: /* MLS */ case 0x18: /* FMLAL2 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) */ static const AArch64DecodeTable data_proc_simd[] = { /* pattern , mask , fn */ - { 0x0e200400, 0x9f200400, disas_simd_three_reg_same }, { 0x0e008400, 0x9f208400, disas_simd_three_reg_same_extra }, { 0x0e200000, 0x9f200c00, disas_simd_three_reg_diff }, { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc }, @@ -XXX,XX +XXX,XX @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x0e000000, 0xbf208c00, disas_simd_tb }, { 0x0e000800, 0xbf208c00, disas_simd_zip_trn }, { 0x2e000000, 0xbf208400, disas_simd_ext }, - { 0x5e200400, 0xdf200400, disas_simd_scalar_three_reg_same }, { 0x5e008400, 0xdf208400, disas_simd_scalar_three_reg_same_extra }, { 0x5e200000, 0xdf200c00, disas_simd_scalar_three_reg_diff }, { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc }, diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqrdmulh_h)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(neon_sqdmulh_idx_h)(void *vd, void *vn, void *vm, + void *vq, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + + for (i = 0; i < opr_sz / 2; i += 16 / 2) { + int16_t mm = m[i]; + for (j = 0; j < 16 / 2; ++j) { + d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, false, vq); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(neon_sqrdmulh_idx_h)(void *vd, void *vn, void *vm, + void *vq, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + + for (i = 0; i < opr_sz / 2; i += 16 / 2) { + int16_t mm = m[i]; + for (j = 0; j < 16 / 2; ++j) { + d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, true, vq); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + void HELPER(sve2_sqrdmlah_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqrdmulh_s)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(neon_sqdmulh_idx_s)(void *vd, void *vn, void *vm, + void *vq, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + + for (i = 0; i < opr_sz / 4; i += 16 / 4) { + int32_t mm = m[i]; + for (j = 0; j < 16 / 4; ++j) { + d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, false, vq); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(neon_sqrdmulh_idx_s)(void *vd, void *vn, void *vm, + void *vq, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + + for (i = 0; i < opr_sz / 4; i += 16 / 4) { + int32_t mm = m[i]; + for (j = 0; j < 16 / 4; ++j) { + d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, true, vq); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + void HELPER(sve2_sqrdmlah_s)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> These are the only instructions in the 3 source scalar class. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240528203044.612851-33-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 10 ++ target/arm/tcg/translate-a64.c | 231 ++++++++++++--------------------- 2 files changed, 93 insertions(+), 148 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ &rr_e rd rn esz &rrr_e rd rn rm esz &rrx_e rd rn rm idx esz +&rrrr_e rd rn rm ra esz &qrr_e q rd rn esz &qrrr_e q rd rn rm esz &qrrx_e q rd rn rm idx esz @@ -XXX,XX +XXX,XX @@ SQDMULH_vi 0.00 1111 10 . ..... 1100 . 0 ..... ..... @qrrx_s SQRDMULH_vi 0.00 1111 01 .. .... 1101 . 0 ..... ..... @qrrx_h SQRDMULH_vi 0.00 1111 10 . ..... 1101 . 0 ..... ..... @qrrx_s + +# Floating-point data-processing (3 source) + +@rrrr_hsd .... .... .. . rm:5 . ra:5 rn:5 rd:5 &rrrr_e esz=%esz_hsd + +FMADD 0001 1111 .. 0 ..... 0 ..... ..... ..... @rrrr_hsd +FMSUB 0001 1111 .. 0 ..... 1 ..... ..... ..... @rrrr_hsd +FNMADD 0001 1111 .. 1 ..... 0 ..... ..... ..... @rrrr_hsd +FNMSUB 0001 1111 .. 1 ..... 1 ..... ..... ..... @rrrr_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_ADDP_s(DisasContext *s, arg_rr_e *a) return true; } +/* + * Floating-point data-processing (3 source) + */ + +static bool do_fmadd(DisasContext *s, arg_rrrr_e *a, bool neg_a, bool neg_n) +{ + TCGv_ptr fpst; + + /* + * These are fused multiply-add. Note that doing the negations here + * as separate steps is correct: an input NaN should come out with + * its sign bit flipped if it is a negated-input. + */ + switch (a->esz) { + case MO_64: + if (fp_access_check(s)) { + TCGv_i64 tn = read_fp_dreg(s, a->rn); + TCGv_i64 tm = read_fp_dreg(s, a->rm); + TCGv_i64 ta = read_fp_dreg(s, a->ra); + + if (neg_a) { + gen_vfp_negd(ta, ta); + } + if (neg_n) { + gen_vfp_negd(tn, tn); + } + fpst = fpstatus_ptr(FPST_FPCR); + gen_helper_vfp_muladdd(ta, tn, tm, ta, fpst); + write_fp_dreg(s, a->rd, ta); + } + break; + + case MO_32: + if (fp_access_check(s)) { + TCGv_i32 tn = read_fp_sreg(s, a->rn); + TCGv_i32 tm = read_fp_sreg(s, a->rm); + TCGv_i32 ta = read_fp_sreg(s, a->ra); + + if (neg_a) { + gen_vfp_negs(ta, ta); + } + if (neg_n) { + gen_vfp_negs(tn, tn); + } + fpst = fpstatus_ptr(FPST_FPCR); + gen_helper_vfp_muladds(ta, tn, tm, ta, fpst); + write_fp_sreg(s, a->rd, ta); + } + break; + + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 tn = read_fp_hreg(s, a->rn); + TCGv_i32 tm = read_fp_hreg(s, a->rm); + TCGv_i32 ta = read_fp_hreg(s, a->ra); + + if (neg_a) { + gen_vfp_negh(ta, ta); + } + if (neg_n) { + gen_vfp_negh(tn, tn); + } + fpst = fpstatus_ptr(FPST_FPCR_F16); + gen_helper_advsimd_muladdh(ta, tn, tm, ta, fpst); + write_fp_sreg(s, a->rd, ta); + } + break; + + default: + return false; + } + return true; +} + +TRANS(FMADD, do_fmadd, a, false, false) +TRANS(FNMADD, do_fmadd, a, true, true) +TRANS(FMSUB, do_fmadd, a, false, true) +TRANS(FNMSUB, do_fmadd, a, true, false) + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) } } -/* Floating-point data-processing (3 source) - single precision */ -static void handle_fp_3src_single(DisasContext *s, bool o0, bool o1, - int rd, int rn, int rm, int ra) -{ - TCGv_i32 tcg_op1, tcg_op2, tcg_op3; - TCGv_i32 tcg_res = tcg_temp_new_i32(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); - - tcg_op1 = read_fp_sreg(s, rn); - tcg_op2 = read_fp_sreg(s, rm); - tcg_op3 = read_fp_sreg(s, ra); - - /* These are fused multiply-add, and must be done as one - * floating point operation with no rounding between the - * multiplication and addition steps. - * NB that doing the negations here as separate steps is - * correct : an input NaN should come out with its sign bit - * flipped if it is a negated-input. - */ - if (o1 == true) { - gen_vfp_negs(tcg_op3, tcg_op3); - } - - if (o0 != o1) { - gen_vfp_negs(tcg_op1, tcg_op1); - } - - gen_helper_vfp_muladds(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst); - - write_fp_sreg(s, rd, tcg_res); -} - -/* Floating-point data-processing (3 source) - double precision */ -static void handle_fp_3src_double(DisasContext *s, bool o0, bool o1, - int rd, int rn, int rm, int ra) -{ - TCGv_i64 tcg_op1, tcg_op2, tcg_op3; - TCGv_i64 tcg_res = tcg_temp_new_i64(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); - - tcg_op1 = read_fp_dreg(s, rn); - tcg_op2 = read_fp_dreg(s, rm); - tcg_op3 = read_fp_dreg(s, ra); - - /* These are fused multiply-add, and must be done as one - * floating point operation with no rounding between the - * multiplication and addition steps. - * NB that doing the negations here as separate steps is - * correct : an input NaN should come out with its sign bit - * flipped if it is a negated-input. - */ - if (o1 == true) { - gen_vfp_negd(tcg_op3, tcg_op3); - } - - if (o0 != o1) { - gen_vfp_negd(tcg_op1, tcg_op1); - } - - gen_helper_vfp_muladdd(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst); - - write_fp_dreg(s, rd, tcg_res); -} - -/* Floating-point data-processing (3 source) - half precision */ -static void handle_fp_3src_half(DisasContext *s, bool o0, bool o1, - int rd, int rn, int rm, int ra) -{ - TCGv_i32 tcg_op1, tcg_op2, tcg_op3; - TCGv_i32 tcg_res = tcg_temp_new_i32(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR_F16); - - tcg_op1 = read_fp_hreg(s, rn); - tcg_op2 = read_fp_hreg(s, rm); - tcg_op3 = read_fp_hreg(s, ra); - - /* These are fused multiply-add, and must be done as one - * floating point operation with no rounding between the - * multiplication and addition steps. - * NB that doing the negations here as separate steps is - * correct : an input NaN should come out with its sign bit - * flipped if it is a negated-input. - */ - if (o1 == true) { - tcg_gen_xori_i32(tcg_op3, tcg_op3, 0x8000); - } - - if (o0 != o1) { - tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000); - } - - gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst); - - write_fp_sreg(s, rd, tcg_res); -} - -/* Floating point data-processing (3 source) - * 31 30 29 28 24 23 22 21 20 16 15 14 10 9 5 4 0 - * +---+---+---+-----------+------+----+------+----+------+------+------+ - * | M | 0 | S | 1 1 1 1 1 | type | o1 | Rm | o0 | Ra | Rn | Rd | - * +---+---+---+-----------+------+----+------+----+------+------+------+ - */ -static void disas_fp_3src(DisasContext *s, uint32_t insn) -{ - int mos = extract32(insn, 29, 3); - int type = extract32(insn, 22, 2); - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int ra = extract32(insn, 10, 5); - int rm = extract32(insn, 16, 5); - bool o0 = extract32(insn, 15, 1); - bool o1 = extract32(insn, 21, 1); - - if (mos) { - unallocated_encoding(s); - return; - } - - switch (type) { - case 0: - if (!fp_access_check(s)) { - return; - } - handle_fp_3src_single(s, o0, o1, rd, rn, rm, ra); - break; - case 1: - if (!fp_access_check(s)) { - return; - } - handle_fp_3src_double(s, o0, o1, rd, rn, rm, ra); - break; - case 3: - if (!dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_fp_3src_half(s, o0, o1, rd, rn, rm, ra); - break; - default: - unallocated_encoding(s); - } -} - /* Floating point immediate * 31 30 29 28 24 23 22 21 20 13 12 10 9 5 4 0 * +---+---+---+-----------+------+---+------------+-------+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) static void disas_data_proc_fp(DisasContext *s, uint32_t insn) { if (extract32(insn, 24, 1)) { - /* Floating point data-processing (3 source) */ - disas_fp_3src(s, insn); + unallocated_encoding(s); /* in decodetree */ } else if (extract32(insn, 21, 1) == 0) { /* Floating point to fixed point conversions */ disas_fp_fixed_conv(s, insn); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240528203044.612851-34-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 4 ++ target/arm/tcg/translate-a64.c | 108 ++++++++++++++------------------- 2 files changed, 49 insertions(+), 63 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SQDMULH_vi 0.00 1111 10 . ..... 1100 . 0 ..... ..... @qrrx_s SQRDMULH_vi 0.00 1111 01 .. .... 1101 . 0 ..... ..... @qrrx_h SQRDMULH_vi 0.00 1111 10 . ..... 1101 . 0 ..... ..... @qrrx_s +# Floating-point conditional select + +FCSEL 0001 1110 .. 1 rm:5 cond:4 11 rn:5 rd:5 esz=%esz_hsd + # Floating-point data-processing (3 source) @rrrr_hsd .... .... .. . rm:5 . ra:5 rn:5 rd:5 &rrrr_e esz=%esz_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_ADDP_s(DisasContext *s, arg_rr_e *a) return true; } +/* + * Floating-point conditional select + */ + +static bool trans_FCSEL(DisasContext *s, arg_FCSEL *a) +{ + TCGv_i64 t_true, t_false; + DisasCompare64 c; + + switch (a->esz) { + case MO_32: + case MO_64: + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + break; + default: + return false; + } + + if (!fp_access_check(s)) { + return true; + } + + /* Zero extend sreg & hreg inputs to 64 bits now. */ + t_true = tcg_temp_new_i64(); + t_false = tcg_temp_new_i64(); + read_vec_element(s, t_true, a->rn, 0, a->esz); + read_vec_element(s, t_false, a->rm, 0, a->esz); + + a64_test_cc(&c, a->cond); + tcg_gen_movcond_i64(c.cond, t_true, c.value, tcg_constant_i64(0), + t_true, t_false); + + /* + * Note that sregs & hregs write back zeros to the high bits, + * and we've already done the zero-extension. + */ + write_fp_dreg(s, a->rd, t_true); + return true; +} + /* * Floating-point data-processing (3 source) */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) } } -/* Floating point conditional select - * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 - * +---+---+---+-----------+------+---+------+------+-----+------+------+ - * | M | 0 | S | 1 1 1 1 0 | type | 1 | Rm | cond | 1 1 | Rn | Rd | - * +---+---+---+-----------+------+---+------+------+-----+------+------+ - */ -static void disas_fp_csel(DisasContext *s, uint32_t insn) -{ - unsigned int mos, type, rm, cond, rn, rd; - TCGv_i64 t_true, t_false; - DisasCompare64 c; - MemOp sz; - - mos = extract32(insn, 29, 3); - type = extract32(insn, 22, 2); - rm = extract32(insn, 16, 5); - cond = extract32(insn, 12, 4); - rn = extract32(insn, 5, 5); - rd = extract32(insn, 0, 5); - - if (mos) { - unallocated_encoding(s); - return; - } - - switch (type) { - case 0: - sz = MO_32; - break; - case 1: - sz = MO_64; - break; - case 3: - sz = MO_16; - if (dc_isar_feature(aa64_fp16, s)) { - break; - } - /* fallthru */ - default: - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - /* Zero extend sreg & hreg inputs to 64 bits now. */ - t_true = tcg_temp_new_i64(); - t_false = tcg_temp_new_i64(); - read_vec_element(s, t_true, rn, 0, sz); - read_vec_element(s, t_false, rm, 0, sz); - - a64_test_cc(&c, cond); - tcg_gen_movcond_i64(c.cond, t_true, c.value, tcg_constant_i64(0), - t_true, t_false); - - /* Note that sregs & hregs write back zeros to the high bits, - and we've already done the zero-extension. */ - write_fp_dreg(s, rd, t_true); -} - /* Floating-point data-processing (1 source) - half precision */ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) { @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn) break; case 3: /* Floating point conditional select */ - disas_fp_csel(s, insn); + unallocated_encoding(s); /* in decodetree */ break; case 0: switch (ctz32(extract32(insn, 12, 4))) { -- 2.34.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Cc: qemu-stable@nongnu.org Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2304 Reported-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Message-id: 20240526204551.553282-1-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) * No explicit bits enabled, and no implicit bits from sve-max-vq. */ if (!cpu_isar_feature(aa64_sve, cpu)) { - /* SVE is disabled and so are all vector lengths. Good. */ + /* + * SVE is disabled and so are all vector lengths. Good. + * Disable all SVE extensions as well. + */ + cpu->isar.id_aa64zfr0 = 0; return; } -- 2.34.1 The board list in target-arm.rst is supposed to be in alphabetical order by the title text of each file (which is not the same as alphabetical order by filename). A few items had got out of order; correct them. The entry for "Facebook Yosemite v3.5 Platform and CraterLake Server (fby35)" remains out-of-order, because this is not its own file but is currently part of the aspeed.rst file. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240520141421.1895138-1-peter.maydell@linaro.org --- docs/system/target-arm.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/bananapi_m2u.rst arm/b-l475e-iot01a.rst arm/sabrelite + arm/highbank arm/digic arm/cubieboard arm/emcraft-sf2 - arm/highbank arm/musicpal arm/gumstix arm/mainstone arm/kzm - arm/nrf arm/nseries + arm/nrf arm/nuvoton arm/imx25-pdk arm/orangepi @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/stellaris arm/stm32 arm/virt - arm/xlnx-versal-virt arm/xenpvh + arm/xlnx-versal-virt Emulated CPU architecture support ================================= -- 2.34.1 The TCGCPUOps::cpu_exec_halt method is called from cpu_handle_halt() when the CPU is halted, so that a target CPU emulation can do anything target-specific it needs to do. (At the moment we only use this on i386.) The current specification of the method doesn't allow the target specific code to do something different if the CPU is about to come out of the halt state, because cpu_handle_halt() only determines this after the method has returned. (If the method called cpu_has_work() itself this would introduce a potential race if an interrupt arrived between the target's method implementation checking and cpu_handle_halt() repeating the check.) Change the definition of the method so that it returns a bool to tell cpu_handle_halt() whether to stay in halt or not. We will want this for the Arm target, where FEAT_WFxT wants to do some work only for the case where the CPU is in halt but about to leave it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240430140035.3889879-2-peter.maydell@linaro.org --- include/hw/core/tcg-cpu-ops.h | 15 +++++++++++++-- target/i386/tcg/helper-tcg.h | 2 +- accel/tcg/cpu-exec.c | 7 +++++-- target/i386/tcg/sysemu/seg_helper.c | 3 ++- 4 files changed, 21 insertions(+), 6 deletions(-) diff --git a/include/hw/core/tcg-cpu-ops.h b/include/hw/core/tcg-cpu-ops.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/tcg-cpu-ops.h +++ b/include/hw/core/tcg-cpu-ops.h @@ -XXX,XX +XXX,XX @@ struct TCGCPUOps { void (*do_interrupt)(CPUState *cpu); /** @cpu_exec_interrupt: Callback for processing interrupts in cpu_exec */ bool (*cpu_exec_interrupt)(CPUState *cpu, int interrupt_request); - /** @cpu_exec_halt: Callback for handling halt in cpu_exec */ - void (*cpu_exec_halt)(CPUState *cpu); + /** + * @cpu_exec_halt: Callback for handling halt in cpu_exec. + * + * The target CPU should do any special processing here that it needs + * to do when the CPU is in the halted state. + * + * Return true to indicate that the CPU should now leave halt, false + * if it should remain in the halted state. + * + * If this method is not provided, the default is to do nothing, and + * to leave halt if cpu_has_work() returns true. + */ + bool (*cpu_exec_halt)(CPUState *cpu); /** * @tlb_fill: Handle a softmmu tlb miss * diff --git a/target/i386/tcg/helper-tcg.h b/target/i386/tcg/helper-tcg.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/helper-tcg.h +++ b/target/i386/tcg/helper-tcg.h @@ -XXX,XX +XXX,XX @@ QEMU_BUILD_BUG_ON(TCG_PHYS_ADDR_BITS > TARGET_PHYS_ADDR_SPACE_BITS); */ void x86_cpu_do_interrupt(CPUState *cpu); #ifndef CONFIG_USER_ONLY -void x86_cpu_exec_halt(CPUState *cpu); +bool x86_cpu_exec_halt(CPUState *cpu); bool x86_need_replay_interrupt(int interrupt_request); bool x86_cpu_exec_interrupt(CPUState *cpu, int int_req); #endif diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ static inline bool cpu_handle_halt(CPUState *cpu) #ifndef CONFIG_USER_ONLY if (cpu->halted) { const TCGCPUOps *tcg_ops = cpu->cc->tcg_ops; + bool leave_halt; if (tcg_ops->cpu_exec_halt) { - tcg_ops->cpu_exec_halt(cpu); + leave_halt = tcg_ops->cpu_exec_halt(cpu); + } else { + leave_halt = cpu_has_work(cpu); } - if (!cpu_has_work(cpu)) { + if (!leave_halt) { return true; } diff --git a/target/i386/tcg/sysemu/seg_helper.c b/target/i386/tcg/sysemu/seg_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/sysemu/seg_helper.c +++ b/target/i386/tcg/sysemu/seg_helper.c @@ -XXX,XX +XXX,XX @@ void x86_cpu_do_interrupt(CPUState *cs) } } -void x86_cpu_exec_halt(CPUState *cpu) +bool x86_cpu_exec_halt(CPUState *cpu) { if (cpu->interrupt_request & CPU_INTERRUPT_POLL) { X86CPU *x86_cpu = X86_CPU(cpu); @@ -XXX,XX +XXX,XX @@ void x86_cpu_exec_halt(CPUState *cpu) cpu_reset_interrupt(cpu, CPU_INTERRUPT_POLL); bql_unlock(); } + return cpu_has_work(cpu); } bool x86_need_replay_interrupt(int interrupt_request) -- 2.34.1 FEAT_WFxT introduces new instructions WFIT and WFET, which are like the existing WFI and WFE but allow the guest to pass a timeout value in a register. The instructions will wait for an interrupt/event as usual, but will also stop waiting when the value of CNTVCT_EL0 is greater than or equal to the specified timeout value. We implement WFIT by setting up a timer to expire at the right point; when the timer expires it sets the EXITTB interrupt, which will cause the CPU to leave the halted state. If we come out of halt for some other reason, we unset the pending timer. We implement WFET as a nop, which is architecturally permitted and matches the way we currently make WFE a nop. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240430140035.3889879-3-peter.maydell@linaro.org --- docs/system/arm/emulation.rst | 1 + target/arm/cpu-features.h | 5 ++++ target/arm/cpu.h | 3 ++ target/arm/helper.h | 1 + target/arm/internals.h | 8 +++++ target/arm/tcg/a64.decode | 4 +++ target/arm/cpu.c | 40 +++++++++++++++++++++++++ target/arm/helper.c | 4 +-- target/arm/machine.c | 20 +++++++++++++ target/arm/tcg/cpu64.c | 1 + target/arm/tcg/op_helper.c | 54 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-a64.c | 41 ++++++++++++++++++++++++++ 12 files changed, 180 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_UAO (Unprivileged Access Override control) - FEAT_VHE (Virtualization Host Extensions) - FEAT_VMID16 (16-bit VMID) +- FEAT_WFxT (WFE and WFI instructions with timeout) - FEAT_XNX (Translation table stage 2 Unprivileged Execute-never) For information on the specifics of these extensions, please refer diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; } +static inline bool isar_feature_aa64_wfxt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, WFXT) >= 2; +} + static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ArchCPU { * pmu_op_finish() - it does not need other handling during migration */ QEMUTimer *pmu_timer; + /* Timer used for WFxT timeouts */ + QEMUTimer *wfxt_timer; + /* GPIO outputs for generic timer */ qemu_irq gt_timer_outputs[NUM_GTIMERS]; /* GPIO output for GICv3 maintenance interrupt signal */ diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(exception_pc_alignment, noreturn, env, tl) DEF_HELPER_1(setend, void, env) DEF_HELPER_2(wfi, void, env, i32) DEF_HELPER_1(wfe, void, env) +DEF_HELPER_2(wfit, void, env, i64) DEF_HELPER_1(yield, void, env) DEF_HELPER_1(pre_hvc, void, env) DEF_HELPER_2(pre_smc, void, env, i32) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ bool check_watchpoint_in_range(int i, target_ulong addr); CPUWatchpoint *find_hw_watchpoint(CPUState *cpu, target_ulong addr); int insert_hw_watchpoint(target_ulong addr, target_ulong len, int type); int delete_hw_watchpoint(target_ulong addr, target_ulong len, int type); + +/* Return the current value of the system counter in ticks */ +uint64_t gt_get_countervalue(CPUARMState *env); +/* + * Return the currently applicable offset between the system counter + * and CNTVCT_EL0 (this will be either 0 or the value of CNTVOFF_EL2). + */ +uint64_t gt_virt_cnt_offset(CPUARMState *env); #endif diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ ERETA 1101011 0100 11111 00001 m:1 11111 11111 &reta # ERETAA, ERETAB NOP 1101 0101 0000 0011 0010 ---- --- 11111 } +# System instructions with register argument +WFET 1101 0101 0000 0011 0001 0000 000 rd:5 +WFIT 1101 0101 0000 0011 0001 0000 001 rd:5 + # Barriers CLREX 1101 0101 0000 0011 0011 ---- 010 11111 diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static bool arm_cpu_virtio_is_big_endian(CPUState *cs) return arm_cpu_data_is_big_endian(env); } +#ifdef CONFIG_TCG +static bool arm_cpu_exec_halt(CPUState *cs) +{ + bool leave_halt = cpu_has_work(cs); + + if (leave_halt) { + /* We're about to come out of WFI/WFE: disable the WFxT timer */ + ARMCPU *cpu = ARM_CPU(cs); + if (cpu->wfxt_timer) { + timer_del(cpu->wfxt_timer); + } + } + return leave_halt; +} +#endif + +static void arm_wfxt_timer_cb(void *opaque) +{ + ARMCPU *cpu = opaque; + CPUState *cs = CPU(cpu); + + /* + * We expect the CPU to be halted; this will cause arm_cpu_is_work() + * to return true (so we will come out of halt even with no other + * pending interrupt), and the TCG accelerator's cpu_exec_interrupt() + * function auto-clears the CPU_INTERRUPT_EXITTB flag for us. + */ + cpu_interrupt(cs, CPU_INTERRUPT_EXITTB); +} #endif static void arm_disas_set_info(CPUState *cpu, disassemble_info *info) @@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj) if (cpu->pmu_timer) { timer_free(cpu->pmu_timer); } + if (cpu->wfxt_timer) { + timer_free(cpu->wfxt_timer); + } #endif } @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) #endif } +#ifndef CONFIG_USER_ONLY + if (tcg_enabled() && cpu_isar_feature(aa64_wfxt, cpu)) { + cpu->wfxt_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, + arm_wfxt_timer_cb, cpu); + } +#endif + if (tcg_enabled()) { /* * Don't report some architectural features in the ID registers @@ -XXX,XX +XXX,XX @@ static const TCGCPUOps arm_tcg_ops = { #else .tlb_fill = arm_cpu_tlb_fill, .cpu_exec_interrupt = arm_cpu_exec_interrupt, + .cpu_exec_halt = arm_cpu_exec_halt, .do_interrupt = arm_cpu_do_interrupt, .do_transaction_failed = arm_cpu_do_transaction_failed, .do_unaligned_access = arm_cpu_do_unaligned_access, diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static CPAccessResult gt_stimer_access(CPUARMState *env, } } -static uint64_t gt_get_countervalue(CPUARMState *env) +uint64_t gt_get_countervalue(CPUARMState *env) { ARMCPU *cpu = env_archcpu(env); @@ -XXX,XX +XXX,XX @@ static uint64_t gt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri) return gt_get_countervalue(env) - gt_phys_cnt_offset(env); } -static uint64_t gt_virt_cnt_offset(CPUARMState *env) +uint64_t gt_virt_cnt_offset(CPUARMState *env) { uint64_t hcr; diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_irq_line_state = { } }; +static bool wfxt_timer_needed(void *opaque) +{ + ARMCPU *cpu = opaque; + + /* We'll only have the timer object if FEAT_WFxT is implemented */ + return cpu->wfxt_timer; +} + +static const VMStateDescription vmstate_wfxt_timer = { + .name = "cpu/wfxt-timer", + .version_id = 1, + .minimum_version_id = 1, + .needed = wfxt_timer_needed, + .fields = (const VMStateField[]) { + VMSTATE_TIMER_PTR(wfxt_timer, ARMCPU), + VMSTATE_END_OF_LIST() + } +}; + static bool m_needed(void *opaque) { ARMCPU *cpu = opaque; @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_arm_cpu = { #endif &vmstate_serror, &vmstate_irq_line_state, + &vmstate_wfxt_timer, NULL } }; diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = cpu->isar.id_aa64isar2; t = FIELD_DP64(t, ID_AA64ISAR2, MOPS, 1); /* FEAT_MOPS */ t = FIELD_DP64(t, ID_AA64ISAR2, BC, 1); /* FEAT_HBC */ + t = FIELD_DP64(t, ID_AA64ISAR2, WFXT, 2); /* FEAT_WFxT */ cpu->isar.id_aa64isar2 = t; t = cpu->isar.id_aa64pfr0; diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) #endif } +void HELPER(wfit)(CPUARMState *env, uint64_t timeout) +{ +#ifdef CONFIG_USER_ONLY + /* + * WFI in the user-mode emulator is technically permitted but not + * something any real-world code would do. AArch64 Linux kernels + * trap it via SCTRL_EL1.nTWI and make it an (expensive) NOP; + * AArch32 kernels don't trap it so it will delay a bit. + * For QEMU, make it NOP here, because trying to raise EXCP_HLT + * would trigger an abort. + */ + return; +#else + ARMCPU *cpu = env_archcpu(env); + CPUState *cs = env_cpu(env); + int target_el = check_wfx_trap(env, false); + /* The WFIT should time out when CNTVCT_EL0 >= the specified value. */ + uint64_t cntval = gt_get_countervalue(env); + uint64_t offset = gt_virt_cnt_offset(env); + uint64_t cntvct = cntval - offset; + uint64_t nexttick; + + if (cpu_has_work(cs) || cntvct >= timeout) { + /* + * Don't bother to go into our "low power state" if + * we would just wake up immediately. + */ + return; + } + + if (target_el) { + env->pc -= 4; + raise_exception(env, EXCP_UDEF, syn_wfx(1, 0xe, 0, false), + target_el); + } + + if (uadd64_overflow(timeout, offset, &nexttick)) { + nexttick = UINT64_MAX; + } + if (nexttick > INT64_MAX / gt_cntfrq_period_ns(cpu)) { + /* + * If the timeout is too long for the signed 64-bit range + * of a QEMUTimer, let it expire early. + */ + timer_mod_ns(cpu->wfxt_timer, INT64_MAX); + } else { + timer_mod(cpu->wfxt_timer, nexttick); + } + cs->exception_index = EXCP_HLT; + cs->halted = 1; + cpu_loop_exit(cs); +#endif +} + void HELPER(wfe)(CPUARMState *env) { /* This is a hint instruction that is semantically different diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_WFE(DisasContext *s, arg_WFI *a) return true; } +static bool trans_WFIT(DisasContext *s, arg_WFIT *a) +{ + if (!dc_isar_feature(aa64_wfxt, s)) { + return false; + } + + /* + * Because we need to pass the register value to the helper, + * it's easier to emit the code now, unlike trans_WFI which + * defers it to aarch64_tr_tb_stop(). That means we need to + * check ss_active so that single-stepping a WFIT doesn't halt. + */ + if (s->ss_active) { + /* Act like a NOP under architectural singlestep */ + return true; + } + + gen_a64_update_pc(s, 4); + gen_helper_wfit(tcg_env, cpu_reg(s, a->rd)); + /* Go back to the main loop to check for interrupts */ + s->base.is_jmp = DISAS_EXIT; + return true; +} + +static bool trans_WFET(DisasContext *s, arg_WFET *a) +{ + if (!dc_isar_feature(aa64_wfxt, s)) { + return false; + } + + /* + * We rely here on our WFE implementation being a NOP, so we + * don't need to do anything different to handle the WFET timeout + * from what trans_WFE does. + */ + if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { + s->base.is_jmp = DISAS_WFE; + } + return true; +} + static bool trans_XPACLRI(DisasContext *s, arg_XPACLRI *a) { if (s->pauth_active) { -- 2.34.1 From: David Hubbard <dmamfmgm@gmail.com> This changes the ohci validation to not assert if invalid data is fed to the ohci controller. The poc in https://bugs.launchpad.net/qemu/+bug/1907042 and migrated to bug #303 does the following to feed it a SETUP pid (valid) at an EndPt of 1 (invalid - all SETUP pids must be addressed to EndPt 0): uint32_t MaxPacket = 64; uint32_t TDFormat = 0; uint32_t Skip = 0; uint32_t Speed = 0; uint32_t Direction = 0; /* #define OHCI_TD_DIR_SETUP 0 */ uint32_t EndPt = 1; uint32_t FuncAddress = 0; ed->attr = (MaxPacket << 16) | (TDFormat << 15) | (Skip << 14) | (Speed << 13) | (Direction << 11) | (EndPt << 7) | FuncAddress; ed->tailp = /*TDQTailPntr= */ 0; ed->headp = ((/*TDQHeadPntr= */ &td[0]) & 0xfffffff0) | (/* ToggleCarry= */ 0 << 1); ed->next_ed = (/* NextED= */ 0 & 0xfffffff0) qemu-fuzz also caught the same issue in #1510. They are both fixed by this patch. With a tiny OS[1] that boots and executes the poc the repro shows the issue: * OS that sends USB requests to a USB mass storage device but sends a SETUP with EndPt = 1 * qemu 6.2.0 (Debian 1:6.2+dfsg-2ubuntu6.19) * qemu HEAD (4e66a0854) * Actual OHCI controller (hardware) Command line: qemu-system-x86_64 -m 20 \ -device pci-ohci,id=ohci \ -drive if=none,format=raw,id=d,file=testmbr.raw \ -device usb-storage,bus=ohci.0,drive=d \ --trace "usb_*" --trace "ohci_*" -D qemu.log Results are: qemu 6.2.0 | qemu HEAD | actual HW ------------+-----------+---------------- assertion | assertion | sets stall bit The assertion message is: > qemu-system-x86_64: ../../hw/usb/core.c:744: usb_ep_get: Assertion `pid == USB_TOKEN_IN || pid == USB_TOKEN_OUT' failed. > Aborted (core dumped) Tip: if the flags "-serial pty -serial stdio" are added to the command line the poc outputs its USB requests like this: > Free mem 2M ohci port0 conn FS > setup { 80 6 0 1 0 0 8 0 } > ED info=80000 { mps=8 en=0 d=0 } tail=c20920 > td0 c20880 nxt=c20960 f2000000 setup cbp=c20900 be=c20907 cbp=0 be=c20907 > td1 c20960 nxt=c20980 f3140000 in cbp=c20908 be=c2090f cbp=0 be=c2090f > td2 c20980 nxt=c20920 f3080000 out cbp=0 be=0 cbp=0 be=0 > rx { 12 1 0 2 0 0 0 8 } > setup { 0 5 1 0 0 0 0 0 } tx {} > ED info=80000 { mps=8 en=0 d=0 } tail=c20880 > td0 c20920 nxt=c20960 f2000000 setup cbp=c20900 be=c20907 cbp=0 be=c20907 > td1 c20960 nxt=c20880 f3100000 in cbp=0 be=0 cbp=0 be=0 > setup { 80 6 0 1 0 0 12 0 } > ED info=80081 { mps=8 en=0 d=1 } tail=c20960 > td0 c20880 nxt=c209c0 f2000000 setup cbp=c20920 be=c20927 > td1 c209c0 nxt=c209e0 f3140000 in cbp=c20928 be=c20939 > td2 c209e0 nxt=c20960 f3080000 out cbp=0 be=0qemu-system-x86_64: ../../hw/usb/core.c:744: usb_ep_get: Assertion `pid == USB_TOKEN_IN || pid == USB_TOKEN_OUT' failed. > Aborted (core dumped) [1] The OS disk image has been emailed to philmd@linaro.org, mjt@tls.msk.ru, and kraxel@redhat.com: * testBadSetup.img.xz * sha256: 045b43f4396de02b149518358bf8025d5ba11091e86458875339fc649e6e5ac6 Signed-off-by: David Hubbard <dmamfmgm@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: authorship and signed-off-by tag names fixed up as per on-list agreement] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/hcd-ohci.c | 5 +++++ hw/usb/trace-events | 1 + 2 files changed, 6 insertions(+) diff --git a/hw/usb/hcd-ohci.c b/hw/usb/hcd-ohci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/hcd-ohci.c +++ b/hw/usb/hcd-ohci.c @@ -XXX,XX +XXX,XX @@ static int ohci_service_td(OHCIState *ohci, struct ohci_ed *ed) case OHCI_TD_DIR_SETUP: str = "setup"; pid = USB_TOKEN_SETUP; + if (OHCI_BM(ed->flags, ED_EN) > 0) { /* setup only allowed to ep 0 */ + trace_usb_ohci_td_bad_pid(str, ed->flags, td.flags); + ohci_die(ohci); + return 1; + } break; default: trace_usb_ohci_td_bad_direction(dir); diff --git a/hw/usb/trace-events b/hw/usb/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/trace-events +++ b/hw/usb/trace-events @@ -XXX,XX +XXX,XX @@ usb_ohci_iso_td_data_overrun(int ret, ssize_t len) "DataOverrun %d > %zu" usb_ohci_iso_td_data_underrun(int ret) "DataUnderrun %d" usb_ohci_iso_td_nak(int ret) "got NAK/STALL %d" usb_ohci_iso_td_bad_response(int ret) "Bad device response %d" +usb_ohci_td_bad_pid(const char *s, uint32_t edf, uint32_t tdf) "Bad pid %s: ed.flags 0x%x td.flags 0x%x" usb_ohci_port_attach(int index) "port #%d" usb_ohci_port_detach(int index) "port #%d" usb_ohci_port_wakeup(int index) "port #%d" -- 2.34.1 Hi; here's another arm pullreq; main parts here are the new i.MX 8MM EVK board, and a lot of refactoring. thanks -- PMM The following changes since commit aa15257174da180c6a8a9d58f87319cfe61c5520: Merge tag 'pbouvier/pr/plugins-20260424' of https://gitlab.com/p-b-o/qemu into staging (2026-04-25 10:22:04 -0400) are available in the Git repository at: https://gitlab.com/pm215/qemu.git tags/pull-target-arm-20260427 for you to fetch changes up to 4575da5ecb7a27544aa6da1f78e700e8100ceaea: target/arm: report register in WFIT syndromes (2026-04-27 11:46:34 +0100) ---------------------------------------------------------------- target-arm queue: docs/system: add FEAT_AA32 and FEAT_AA64 to emulation list hw/arm: Add the i.MX 8MM EVK(Evaluation Kit) board target/arm: Build M-profile helper code once only hw/arm: Remove hw_error() for the unimplemented CM_LMBUSCNT register hw: Move ARM_SYSCTL_GPIO definitions to arm sysctl specific header target/arm: Allow 'aarch64=off' to be set for TCG CPUs target/arm: Allow some sysregs to not have to be an exact match for migration hw/arm/raspi4b: NOP all DTB nodes when removing unimplemented devices hw/arm/fsl-imx6ul: Implement LCDIF display device target/arm: Refactor syndrome value code to use registerfields target/arm: Report the register in WFxT syndromes ---------------------------------------------------------------- Alex Bennée (24): docs/system: add FEAT_AA32 and FEAT_AA64 to emulation list target/arm: migrate basic syndrome helpers to registerfields target/arm: migrate system/cp trap syndromes to registerfields target/arm: migrate FP/SIMD trap syndromes to registerfields target/arm: migrate eret trap syndromes to registerfields target/arm: migrate SME trap syndromes to registerfields target/arm: migrate PAC trap syndromes to registerfields target/arm: migrate BTI trap syndromes to registerfields target/arm: migrate BXJ trap syndromes to registerfields target/arm: migrate Granule Protection traps to registerfields target/arm: migrate fault syndromes to registerfields target/arm: migrate debug syndromes to registerfields target/arm: migrate wfx syndromes to registerfields target/arm: migrate gcs syndromes to registerfields target/arm: migrate memory op syndromes to registerfields target/arm: migrate check_hcr_el2_trap to use syndrome helper target/arm: use syndrome helpers in arm_cpu_do_interrupt_aarch32_hyp target/arm: use syndrome helpers to set SAME_EL EC bit target/arm: make whpx use syndrome helpers for decode target/arm: make hvf use syndrome helpers for decode target/arm: use syndrome helpers in merge_syn_data_abort target/arm: use syndrome helpers to query VNCR bit target/arm: remove old syndrome defines target/arm: report register in WFIT syndromes Eric Auger (7): target/arm/cpu: Introduce the infrastructure for cpreg migration tolerances target/arm/machine: Handle ToleranceNotOnBothEnds migration tolerances target/arm/machine: Handle ToleranceOnlySrcTestValue migration tolerance target/arm/cpu64: Mitigate migration failures due to spurious TCR_EL1, PIRE0_EL1 and PIR_EL1 target/arm/cpu64: Define cpreg migration tolerance for KVM_REG_ARM_VENDOR_HYP_BMAP_2 target/arm/helper: Define cpreg migration tolerance for DGBDTR_EL0 Revert "target/arm: Reinstate bogus AArch32 DBGDTRTX register for migration compat" Gaurav Sharma (15): hw/arm: Add the i.MX 8MM EVK(Evaluation Kit) board hw/misc/imx8mp_analog: Add property to analog device hw/arm/fsl-imx8mm: Add Analog device IP to iMX8MM SOC hw/arm/fsl-imx8mm: Add Clock Control Module IP to iMX8MM hw/arm/fsl-imx8mm: Implemented support for SNVS hw/arm/fsl-imx8mm: Adding support for USDHC storage controllers hw/arm/fsl-imx8mm: Add PCIe support hw/arm/fsl-imx8mm: Add GPIO controllers hw/arm/fsl-imx8mm: Adding support for I2C emulation hw/arm/fsl-imx8mm: Adding support for SPI controller hw/arm/fsl-imx8mm: Adding support for Watchdog Timers hw/arm/fsl-imx8mm: Adding support for General Purpose Timers hw/arm/fsl-imx8mm: Adding support for ENET ethernet controller hw/arm/fsl-imx8mm: Adding support for USB controller hw/arm/fsl-imx8mm: Adding functional testing of iMX8MM emulation Osama Abdelkader (1): hw/arm/raspi4b: NOP all DTB nodes when removing unimplemented devices Peter Maydell (4): hw: Move ARM_SYSCTL_GPIO definitions to arm sysctl specific header target/arm: Clear AArch64 ID regs from ARMISARegisters if AArch64 disabled target/arm: Allow 'aarch64=off' to be set for TCG CPUs tests/functional/aarch64: Add basic test of TCG aarch64=off Philippe Mathieu-Daudé (9): target/arm: Ignore endianness when setting MTE tags target/arm: Explode MO_TExx -> MO_TE | MO_xx target/arm: Hoist MO_TE into mve_advance_vpt() target/arm: Hoist MO_TE into MVE DO_VSTR() macro target/arm: Introduce mo_endian() helper target/arm: Replace MO_TE -> mo_endian() for MVE helpers target/arm: Compile mve_helper.c once target/arm: Replace MO_TE -> mo_endian() for Cortex-M helpers target/arm: Compile m_helper.c once Thomas Huth (1): hw/arm: Remove hw_error() for the unimplemented CM_LMBUSCNT register Yucai Liu (2): hw/display: Add i.MX6UL LCDIF device model hw/arm/fsl-imx6ul: Wire in the LCDIF device model MAINTAINERS | 16 +- docs/system/arm/cpu-features.rst | 10 +- docs/system/arm/emulation.rst | 2 + docs/system/arm/{imx8mp-evk.rst => imx8m.rst} | 49 +- docs/system/target-arm.rst | 2 +- hw/arm/Kconfig | 25 + hw/arm/fsl-imx6ul.c | 12 +- hw/arm/fsl-imx8mm.c | 704 ++++++++++++++++++++++ hw/arm/imx8mm-evk.c | 130 ++++ hw/arm/integratorcp.c | 3 - hw/arm/meson.build | 2 + hw/arm/raspi4b.c | 10 +- hw/arm/realview.c | 2 +- hw/arm/vexpress.c | 2 +- hw/arm/virt.c | 1 - hw/display/Kconfig | 4 + hw/display/imx6ul_lcdif.c | 453 ++++++++++++++ hw/display/meson.build | 1 + hw/misc/arm_sysctl.c | 2 +- hw/misc/imx8mp_analog.c | 12 +- hw/timer/imx_gpt.c | 26 + hw/vmapple/vmapple.c | 1 - include/hw/arm/fsl-imx6ul.h | 4 +- include/hw/arm/fsl-imx8mm.h | 242 ++++++++ include/hw/arm/primecell.h | 12 - include/hw/display/imx6ul_lcdif.h | 37 ++ include/hw/misc/arm_sysctl.h | 16 + include/hw/misc/imx8mp_analog.h | 3 + include/hw/timer/imx_gpt.h | 2 + target/arm/cpu-features.h | 5 + target/arm/cpu.c | 153 ++++- target/arm/cpu.h | 4 +- target/arm/cpu64.c | 39 ++ target/arm/debug_helper.c | 29 - target/arm/helper.c | 27 +- target/arm/hvf/hvf.c | 14 +- target/arm/internals.h | 60 ++ target/arm/machine.c | 33 +- target/arm/syndrome.h | 595 ++++++++++++++---- target/arm/tcg/debug.c | 2 +- target/arm/tcg/helper-a64.c | 2 +- target/arm/tcg/helper-defs.h | 2 +- target/arm/tcg/m_helper.c | 8 +- target/arm/tcg/meson.build | 6 +- target/arm/tcg/mve_helper.c | 102 ++-- target/arm/tcg/op_helper.c | 7 +- target/arm/tcg/tlb_helper.c | 6 +- target/arm/tcg/translate-a64.c | 2 +- target/arm/tcg/vfp_helper.c | 5 +- target/arm/trace-events | 2 + target/arm/whpx/whpx-all.c | 13 +- tests/functional/aarch64/meson.build | 3 + tests/functional/aarch64/test_imx8mm_evk.py | 69 +++ tests/functional/aarch64/test_virt_aarch64_off.py | 37 ++ tests/qtest/arm-cpu-features.c | 8 +- 55 files changed, 2743 insertions(+), 275 deletions(-) rename docs/system/arm/{imx8mp-evk.rst => imx8m.rst} (58%) create mode 100644 hw/arm/fsl-imx8mm.c create mode 100644 hw/arm/imx8mm-evk.c create mode 100644 hw/display/imx6ul_lcdif.c create mode 100644 include/hw/arm/fsl-imx8mm.h delete mode 100644 include/hw/arm/primecell.h create mode 100644 include/hw/display/imx6ul_lcdif.h create mode 100644 include/hw/misc/arm_sysctl.h create mode 100755 tests/functional/aarch64/test_imx8mm_evk.py create mode 100755 tests/functional/aarch64/test_virt_aarch64_off.py From: Alex Bennée <alex.bennee@linaro.org> This is just a documentation tweak as we already support both. FEAT_AA32 implies FEAT_AA32EL0. FEAT_AA64 implies FEAT_AA64EL[0123]. This is however useful if you are using emulation.rst as a source of truth of what QEMU emulates and when cross checking with Features.json from Arm. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260421093506.616307-1-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ QEMU's TCG emulation includes support for the Armv5, Armv6, Armv7, Armv8 and Armv9 versions of the A-profile architecture. It also has support for the following architecture extensions: +- FEAT_AA32 (PE Support for AArch32) - FEAT_AA32BF16 (AArch32 BFloat16 instructions) - FEAT_AA32EL0 (Support for AArch32 at EL0) - FEAT_AA32EL1 (Support for AArch32 at EL1) @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_AA32EL3 (Support for AArch32 at EL3) - FEAT_AA32HPD (AArch32 hierarchical permission disables) - FEAT_AA32I8MM (AArch32 Int8 matrix multiplication instructions) +- FEAT_AA64 (PE uses AArch64 after last reboot) - FEAT_AA64EL0 (Support for AArch64 at EL0) - FEAT_AA64EL1 (Support for AArch64 at EL1) - FEAT_AA64EL2 (Support for AArch64 at EL2) -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Implemented CPUs, RAM, UARTs and Interrupt Controller Other peripherals are represented as TYPE_UNIMPLEMENTED_DEVICE Complete memory map of the SoC is provided. Set default RAM size to 2GB and default CPU count to 4 to match the real i.MX8MM EVK hardware configuration. Documentation is shared with imx8mp-evk to avoid duplication. Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> [PMM: fixed over-long lines in doc] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 11 +- docs/system/arm/{imx8mp-evk.rst => imx8m.rst} | 49 ++- docs/system/target-arm.rst | 2 +- hw/arm/Kconfig | 12 + hw/arm/fsl-imx8mm.c | 377 ++++++++++++++++++ hw/arm/imx8mm-evk.c | 112 ++++++ hw/arm/meson.build | 2 + include/hw/arm/fsl-imx8mm.h | 158 ++++++++ 8 files changed, 709 insertions(+), 14 deletions(-) rename docs/system/arm/{imx8mp-evk.rst => imx8m.rst} (58%) create mode 100644 hw/arm/fsl-imx8mm.c create mode 100644 hw/arm/imx8mm-evk.c create mode 100644 include/hw/arm/fsl-imx8mm.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/pci-host/designware.c F: include/hw/pci-host/designware.h F: docs/system/arm/mcimx7d-sabre.rst +MCIMX8MM-EVK / iMX8MM +M: Gaurav Sharma <gaurav.sharma_7@nxp.com> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/fsl-imx8mm.c +F: hw/arm/imx8mm-evk.c +F: include/hw/arm/fsl-imx8mm.h +F: docs/system/arm/imx8m.rst + MCIMX8MP-EVK / i.MX8MP M: Bernhard Beschow <shentey@gmail.com> L: qemu-arm@nongnu.org @@ -XXX,XX +XXX,XX @@ F: hw/rtc/rs5c372.c F: include/hw/arm/fsl-imx8mp.h F: include/hw/misc/imx8mp_*.h F: include/hw/pci-host/fsl_imx8m_phy.h -F: docs/system/arm/imx8mp-evk.rst +F: docs/system/arm/imx8m.rst F: tests/functional/aarch64/test_imx8mp_evk.py F: tests/qtest/rs5c372-test.c diff --git a/docs/system/arm/imx8mp-evk.rst b/docs/system/arm/imx8m.rst similarity index 58% rename from docs/system/arm/imx8mp-evk.rst rename to docs/system/arm/imx8m.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/imx8mp-evk.rst +++ b/docs/system/arm/imx8m.rst @@ -XXX,XX +XXX,XX @@ -NXP i.MX 8M Plus Evaluation Kit (``imx8mp-evk``) -================================================ +NXP i.MX 8M Plus and i.MX 8M Mini Evaluation Kits (``imx8mp-evk``, ``imx8mm-evk``) +================================================================================== -The ``imx8mp-evk`` machine models the i.MX 8M Plus Evaluation Kit, based on an -i.MX 8M Plus SoC. +The ``imx8mp-evk`` and ``imx8mm-evk`` machine models the i.MX 8M Plus +and i.MX 8M Mini Evaluation Kits, based on i.MX 8M Plus and i.MX8M +Mini SoCs. Supported devices ----------------- -The ``imx8mp-evk`` machine implements the following devices: +The ``imx8mp-evk`` and ``imx8mm-evk`` machines implement the +following devices: * Up to 4 Cortex-A53 cores * Generic Interrupt Controller (GICv3) @@ -XXX,XX +XXX,XX @@ The ``imx8mp-evk`` machine implements the following devices: Boot options ------------ -The ``imx8mp-evk`` machine can start a Linux kernel directly using the standard -``-kernel`` functionality. +The ``imx8mp-evk`` and ``imx8mm-evk`` machines can start a Linux +kernel directly using the standard ``-kernel`` functionality. Direct Linux Kernel Boot '''''''''''''''''''''''' @@ -XXX,XX +XXX,XX @@ is to generate an image with Buildroot. Version 2024.11.1 is tested at the time of writing and involves two steps. First run the following commands in the toplevel directory of the Buildroot source tree: +For i.MX 8M Plus EVK: + .. code-block:: bash $ make freescale_imx8mpevk_defconfig $ make +For i.MX 8M Mini EVK: + +.. code-block:: bash + + $ make freescale_imx8mmevk_defconfig + $ make + Once finished successfully there is an ``output/image`` subfolder. Navigate into it and resize the SD card image to a power of two: @@ -XXX,XX +XXX,XX @@ it and resize the SD card image to a power of two: Now that everything is prepared the machine can be started as follows: +For i.MX 8M Plus EVK: + .. code-block:: bash $ qemu-system-aarch64 -M imx8mp-evk \ @@ -XXX,XX +XXX,XX @@ Now that everything is prepared the machine can be started as follows: -append "root=/dev/mmcblk2p2" \ -drive file=sdcard.img,if=sd,bus=2,format=raw,id=mmcblk2 +For i.MX 8M Mini EVK: + +.. code-block:: bash + + $ qemu-system-aarch64 -M imx8mm-evk -smp 4 -m 2G \ + -display none -serial null -serial stdio \ + -kernel Image \ + -dtb imx8mm-evk.dtb \ + -append "root=/dev/mmcblk2p2" \ + -drive file=sdcard.img,if=sd,bus=2,format=raw,id=mmcblk2 KVM Acceleration ---------------- @@ -XXX,XX +XXX,XX @@ To enable hardware-assisted acceleration via KVM, append ``-accel kvm`` to the command line. While this speeds up performance significantly, be aware of the following limitations: -* The ``imx8mp-evk`` machine is not included under the "virtualization use case" - of :doc:`QEMU's security policy </system/security>`. This means that you - should not trust that it can contain malicious guests, whether it is run - using TCG or KVM. If you don't trust your guests and you're relying on QEMU to - be the security boundary, you want to choose another machine such as ``virt``. +* The ``imx8mp-evk`` and ``imx8mm-evk`` machines are not included + under the "virtualization use case" of :doc:`QEMU's security + policy </system/security>`. This means that you should not trust that + it can contain malicious guests, whether it is run using TCG or KVM. + If you don't trust your guests and you're relying on QEMU to be the + security boundary, you want to choose another machine such as + ``virt``. * Rather than Cortex-A53 CPUs, the same CPU type as the host's will be used. This is a limitation of KVM and may not work with guests with a tight dependency on Cortex-A53. diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ Board-specific documentation arm/imx25-pdk arm/mcimx6ul-evk arm/mcimx7d-sabre - arm/imx8mp-evk + arm/imx8m arm/orangepi arm/raspi arm/collie diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK depends on TCG select FSL_IMX8MP +config FSL_IMX8MM + bool + select ARM_GIC + select IMX + +config FSL_IMX8MM_EVK + bool + default y + depends on AARCH64 + depends on TCG + select FSL_IMX8MM + config ARM_SMMUV3_ACCEL bool depends on ARM_SMMUV3 diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ +/* + * i.MX 8MM SoC Implementation + * + * Based on hw/arm/fsl-imx6.c + * + * Copyright (c) 2025, NXP Semiconductors + * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * iMX8MM Reference Manual - https://www.nxp.com/products/i.MX8MMINI -> Documentation + */ + +#include "qemu/osdep.h" +#include "system/address-spaces.h" +#include "hw/arm/bsa.h" +#include "hw/arm/fsl-imx8mm.h" +#include "hw/misc/unimp.h" +#include "hw/core/boards.h" +#include "system/kvm.h" +#include "system/system.h" +#include "target/arm/cpu.h" +#include "target/arm/cpu-qom.h" +#include "target/arm/kvm_arm.h" +#include "qapi/error.h" +#include "qobject/qlist.h" + +static const struct { + hwaddr addr; + size_t size; + const char *name; +} fsl_imx8mm_memmap[] = { + [FSL_IMX8MM_RAM] = { FSL_IMX8MM_RAM_START, FSL_IMX8MM_RAM_SIZE_MAX, "ram" }, + [FSL_IMX8MM_DDR_PHY_BROADCAST] = { 0x3dc00000, 4 * MiB, "ddr_phy_broadcast" }, + [FSL_IMX8MM_DDR_PERF_MON] = { 0x3d800000, 4 * MiB, "ddr_perf_mon" }, + [FSL_IMX8MM_DDR_CTL] = { 0x3d400000, 4 * MiB, "ddr_ctl" }, + [FSL_IMX8MM_DDR_PHY] = { 0x3c000000, 16 * MiB, "ddr_phy" }, + [FSL_IMX8MM_GIC_DIST] = { 0x38800000, 512 * KiB, "gic_dist" }, + [FSL_IMX8MM_GIC_REDIST] = { 0x38880000, 512 * KiB, "gic_redist" }, + [FSL_IMX8MM_VPU] = { 0x38340000, 2 * MiB, "vpu" }, + [FSL_IMX8MM_VPU_BLK_CTRL] = { 0x38330000, 2 * MiB, "vpu_blk_ctrl" }, + [FSL_IMX8MM_VPU_G2_DECODER] = { 0x38310000, 1 * MiB, "vpu_g2_decoder" }, + [FSL_IMX8MM_VPU_G1_DECODER] = { 0x38300000, 1 * MiB, "vpu_g1_decoder" }, + [FSL_IMX8MM_USB2_OTG] = { 0x32e50200, 0x200, "usb2_otg" }, + [FSL_IMX8MM_USB2] = { 0x32e50000, 0x200, "usb2" }, + [FSL_IMX8MM_USB1_OTG] = { 0x32e40200, 0x200, "usb1_otg" }, + [FSL_IMX8MM_USB1] = { 0x32e40000, 0x200, "usb1" }, + [FSL_IMX8MM_GPU2D] = { 0x38000000, 64 * KiB, "gpu2d" }, + [FSL_IMX8MM_QSPI1_RX_BUFFER] = { 0x34000000, 32 * MiB, "qspi1_rx_buffer" }, + [FSL_IMX8MM_PCIE1] = { 0x33800000, 4 * MiB, "pcie1" }, + [FSL_IMX8MM_QSPI1_TX_BUFFER] = { 0x33008000, 32 * KiB, "qspi1_tx_buffer" }, + [FSL_IMX8MM_APBH_DMA] = { 0x33000000, 32 * KiB, "apbh_dma" }, + + /* AIPS-4 Begin */ + [FSL_IMX8MM_TZASC] = { 0x32f80000, 64 * KiB, "tzasc" }, + [FSL_IMX8MM_PCIE_PHY1] = { 0x32f00000, 64 * KiB, "pcie_phy1" }, + [FSL_IMX8MM_MEDIA_BLK_CTL] = { 0x32e28000, 256, "media_blk_ctl" }, + [FSL_IMX8MM_LCDIF] = { 0x32e00000, 64 * KiB, "lcdif" }, + [FSL_IMX8MM_MIPI_DSI] = { 0x32e10000, 64 * KiB, "mipi_dsi" }, + [FSL_IMX8MM_MIPI_CSI] = { 0x32e30000, 64 * KiB, "mipi_csi" }, + [FSL_IMX8MM_AIPS4_CONFIGURATION] = { 0x32df0000, 64 * KiB, "aips4_configuration" }, + /* AIPS-4 End */ + + [FSL_IMX8MM_INTERCONNECT] = { 0x32700000, 1 * MiB, "interconnect" }, + + /* AIPS-3 Begin */ + [FSL_IMX8MM_ENET1] = { 0x30be0000, 64 * KiB, "enet1" }, + [FSL_IMX8MM_SDMA1] = { 0x30bd0000, 64 * KiB, "sdma1" }, + [FSL_IMX8MM_QSPI] = { 0x30bb0000, 64 * KiB, "qspi" }, + [FSL_IMX8MM_USDHC3] = { 0x30b60000, 64 * KiB, "usdhc3" }, + [FSL_IMX8MM_USDHC2] = { 0x30b50000, 64 * KiB, "usdhc2" }, + [FSL_IMX8MM_USDHC1] = { 0x30b40000, 64 * KiB, "usdhc1" }, + [FSL_IMX8MM_SEMAPHORE_HS] = { 0x30ac0000, 64 * KiB, "semaphore_hs" }, + [FSL_IMX8MM_MU_B] = { 0x30ab0000, 64 * KiB, "mu_b" }, + [FSL_IMX8MM_MU_A] = { 0x30aa0000, 64 * KiB, "mu_a" }, + [FSL_IMX8MM_UART4] = { 0x30a60000, 64 * KiB, "uart4" }, + [FSL_IMX8MM_I2C4] = { 0x30a50000, 64 * KiB, "i2c4" }, + [FSL_IMX8MM_I2C3] = { 0x30a40000, 64 * KiB, "i2c3" }, + [FSL_IMX8MM_I2C2] = { 0x30a30000, 64 * KiB, "i2c2" }, + [FSL_IMX8MM_I2C1] = { 0x30a20000, 64 * KiB, "i2c1" }, + [FSL_IMX8MM_AIPS3_CONFIGURATION] = { 0x309f0000, 64 * KiB, "aips3_configuration" }, + [FSL_IMX8MM_CAAM] = { 0x30900000, 256 * KiB, "caam" }, + [FSL_IMX8MM_SPBA1] = { 0x308f0000, 64 * KiB, "spba1" }, + [FSL_IMX8MM_UART2] = { 0x30890000, 64 * KiB, "uart2" }, + [FSL_IMX8MM_UART3] = { 0x30880000, 64 * KiB, "uart3" }, + [FSL_IMX8MM_UART1] = { 0x30860000, 64 * KiB, "uart1" }, + [FSL_IMX8MM_ECSPI3] = { 0x30840000, 64 * KiB, "ecspi3" }, + [FSL_IMX8MM_ECSPI2] = { 0x30830000, 64 * KiB, "ecspi2" }, + [FSL_IMX8MM_ECSPI1] = { 0x30820000, 64 * KiB, "ecspi1" }, + /* AIPS-3 End */ + + /* AIPS-2 Begin */ + [FSL_IMX8MM_QOSC] = { 0x307f0000, 64 * KiB, "qosc" }, + [FSL_IMX8MM_PERFMON2] = { 0x307d0000, 64 * KiB, "perfmon2" }, + [FSL_IMX8MM_PERFMON1] = { 0x307c0000, 64 * KiB, "perfmon1" }, + [FSL_IMX8MM_GPT4] = { 0x30700000, 64 * KiB, "gpt4" }, + [FSL_IMX8MM_GPT5] = { 0x306f0000, 64 * KiB, "gpt5" }, + [FSL_IMX8MM_GPT6] = { 0x306e0000, 64 * KiB, "gpt6" }, + [FSL_IMX8MM_SYSCNT_CTRL] = { 0x306c0000, 64 * KiB, "syscnt_ctrl" }, + [FSL_IMX8MM_SYSCNT_CMP] = { 0x306b0000, 64 * KiB, "syscnt_cmp" }, + [FSL_IMX8MM_SYSCNT_RD] = { 0x306a0000, 64 * KiB, "syscnt_rd" }, + [FSL_IMX8MM_PWM4] = { 0x30690000, 64 * KiB, "pwm4" }, + [FSL_IMX8MM_PWM3] = { 0x30680000, 64 * KiB, "pwm3" }, + [FSL_IMX8MM_PWM2] = { 0x30670000, 64 * KiB, "pwm2" }, + [FSL_IMX8MM_PWM1] = { 0x30660000, 64 * KiB, "pwm1" }, + [FSL_IMX8MM_AIPS2_CONFIGURATION] = { 0x305f0000, 64 * KiB, "aips2_configuration" }, + /* AIPS-2 End */ + + /* AIPS-1 Begin */ + [FSL_IMX8MM_CSU] = { 0x303e0000, 64 * KiB, "csu" }, + [FSL_IMX8MM_RDC] = { 0x303d0000, 64 * KiB, "rdc" }, + [FSL_IMX8MM_SEMAPHORE2] = { 0x303c0000, 64 * KiB, "semaphore2" }, + [FSL_IMX8MM_SEMAPHORE1] = { 0x303b0000, 64 * KiB, "semaphore1" }, + [FSL_IMX8MM_GPC] = { 0x303a0000, 64 * KiB, "gpc" }, + [FSL_IMX8MM_SRC] = { 0x30390000, 64 * KiB, "src" }, + [FSL_IMX8MM_CCM] = { 0x30380000, 64 * KiB, "ccm" }, + [FSL_IMX8MM_SNVS_HP] = { 0x30370000, 64 * KiB, "snvs_hp" }, + [FSL_IMX8MM_ANA_PLL] = { 0x30360000, 64 * KiB, "ana_pll" }, + [FSL_IMX8MM_OCOTP_CTRL] = { 0x30350000, 64 * KiB, "ocotp_ctrl" }, + [FSL_IMX8MM_IOMUXC_GPR] = { 0x30340000, 64 * KiB, "iomuxc_gpr" }, + [FSL_IMX8MM_IOMUXC] = { 0x30330000, 64 * KiB, "iomuxc" }, + [FSL_IMX8MM_GPT3] = { 0x302f0000, 64 * KiB, "gpt3" }, + [FSL_IMX8MM_GPT2] = { 0x302e0000, 64 * KiB, "gpt2" }, + [FSL_IMX8MM_GPT1] = { 0x302d0000, 64 * KiB, "gpt1" }, + [FSL_IMX8MM_SDMA2] = { 0x302c0000, 64 * KiB, "sdma2" }, + [FSL_IMX8MM_SDMA3] = { 0x302b0000, 64 * KiB, "sdma3" }, + [FSL_IMX8MM_WDOG3] = { 0x302a0000, 64 * KiB, "wdog3" }, + [FSL_IMX8MM_WDOG2] = { 0x30290000, 64 * KiB, "wdog2" }, + [FSL_IMX8MM_WDOG1] = { 0x30280000, 64 * KiB, "wdog1" }, + [FSL_IMX8MM_ANA_OSC] = { 0x30270000, 64 * KiB, "ana_osc" }, + [FSL_IMX8MM_ANA_TSENSOR] = { 0x30260000, 64 * KiB, "ana_tsensor" }, + [FSL_IMX8MM_GPIO5] = { 0x30240000, 64 * KiB, "gpio5" }, + [FSL_IMX8MM_GPIO4] = { 0x30230000, 64 * KiB, "gpio4" }, + [FSL_IMX8MM_GPIO3] = { 0x30220000, 64 * KiB, "gpio3" }, + [FSL_IMX8MM_GPIO2] = { 0x30210000, 64 * KiB, "gpio2" }, + [FSL_IMX8MM_GPIO1] = { 0x30200000, 64 * KiB, "gpio1" }, + [FSL_IMX8MM_AIPS1_CONFIGURATION] = { 0x301f0000, 64 * KiB, "aips1_configuration" }, + [FSL_IMX8MM_SAI6] = { 0x30060000, 64 * KiB, "sai6" }, + [FSL_IMX8MM_SAI5] = { 0x30050000, 64 * KiB, "sai5" }, + [FSL_IMX8MM_SAI3] = { 0x30030000, 64 * KiB, "sai3" }, + [FSL_IMX8MM_SAI2] = { 0x30020000, 64 * KiB, "sai2" }, + [FSL_IMX8MM_SAI1] = { 0x30010000, 64 * KiB, "sai1" }, + + /* AIPS-1 End */ + + [FSL_IMX8MM_A53_DAP] = { 0x28000000, 16 * MiB, "a53_dap" }, + [FSL_IMX8MM_PCIE1_MEM] = { 0x18000000, 128 * MiB, "pcie1_mem" }, + [FSL_IMX8MM_QSPI_MEM] = { 0x08000000, 256 * MiB, "qspi_mem" }, + [FSL_IMX8MM_OCRAM] = { 0x00900000, 256 * KiB, "ocram" }, + [FSL_IMX8MM_TCM_DTCM] = { 0x00800000, 128 * KiB, "tcm_dtcm" }, + [FSL_IMX8MM_TCM_ITCM] = { 0x007e0000, 128 * KiB, "tcm_itcm" }, + [FSL_IMX8MM_OCRAM_S] = { 0x00180000, 32 * KiB, "ocram_s" }, + [FSL_IMX8MM_CAAM_MEM] = { 0x00100000, 32 * KiB, "caam_mem" }, + [FSL_IMX8MM_BOOT_ROM_PROTECTED] = { 0x0003f000, 4 * KiB, "boot_rom_protected" }, + [FSL_IMX8MM_BOOT_ROM] = { 0x00000000, 252 * KiB, "boot_rom" }, +}; + +static void fsl_imx8mm_init(Object *obj) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + FslImx8mmState *s = FSL_IMX8MM(obj); + const char *cpu_type = ms->cpu_type ?: ARM_CPU_TYPE_NAME("cortex-a53"); + int i; + + for (i = 0; i < MIN(ms->smp.cpus, FSL_IMX8MM_NUM_CPUS); i++) { + g_autofree char *name = g_strdup_printf("cpu%d", i); + object_initialize_child(obj, name, &s->cpu[i], cpu_type); + } + + object_initialize_child(obj, "gic", &s->gic, gicv3_class_name()); + + for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { + g_autofree char *name = g_strdup_printf("uart%d", i + 1); + object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); + } + +} + +static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + FslImx8mmState *s = FSL_IMX8MM(dev); + DeviceState *gicdev = DEVICE(&s->gic); + int i; + + if (ms->smp.cpus > FSL_IMX8MM_NUM_CPUS) { + error_setg(errp, "%s: Only %d CPUs are supported (%d requested)", + TYPE_FSL_IMX8MM, FSL_IMX8MM_NUM_CPUS, ms->smp.cpus); + return; + } + + /* CPUs */ + for (i = 0; i < ms->smp.cpus; i++) { + /* On uniprocessor, the CBAR is set to 0 */ + if (ms->smp.cpus > 1 && + object_property_find(OBJECT(&s->cpu[i]), "reset-cbar")) { + object_property_set_int(OBJECT(&s->cpu[i]), "reset-cbar", + fsl_imx8mm_memmap[FSL_IMX8MM_GIC_DIST].addr, + &error_abort); + } + + /* + * CNTFID0 base frequency in Hz of system counter + */ + object_property_set_int(OBJECT(&s->cpu[i]), "cntfrq", 8000000, + &error_abort); + + if (object_property_find(OBJECT(&s->cpu[i]), "has_el2")) { + object_property_set_bool(OBJECT(&s->cpu[i]), "has_el2", + !kvm_enabled(), &error_abort); + } + + if (object_property_find(OBJECT(&s->cpu[i]), "has_el3")) { + object_property_set_bool(OBJECT(&s->cpu[i]), "has_el3", + !kvm_enabled(), &error_abort); + } + + if (i) { + /* + * Secondary CPUs start in powered-down state (and can be + * powered up via the SRC system reset controller) + */ + object_property_set_bool(OBJECT(&s->cpu[i]), "start-powered-off", + true, &error_abort); + } + + if (!qdev_realize(DEVICE(&s->cpu[i]), NULL, errp)) { + return; + } + } + + /* GIC */ + { + SysBusDevice *gicsbd = SYS_BUS_DEVICE(&s->gic); + QList *redist_region_count; + bool pmu = object_property_get_bool(OBJECT(first_cpu), "pmu", NULL); + + qdev_prop_set_uint32(gicdev, "num-cpu", ms->smp.cpus); + qdev_prop_set_uint32(gicdev, "num-irq", + FSL_IMX8MM_NUM_IRQS + GIC_INTERNAL); + redist_region_count = qlist_new(); + qlist_append_int(redist_region_count, ms->smp.cpus); + qdev_prop_set_array(gicdev, "redist-region-count", redist_region_count); + object_property_set_link(OBJECT(&s->gic), "sysmem", + OBJECT(get_system_memory()), &error_fatal); + if (!sysbus_realize(gicsbd, errp)) { + return; + } + sysbus_mmio_map(gicsbd, 0, fsl_imx8mm_memmap[FSL_IMX8MM_GIC_DIST].addr); + sysbus_mmio_map(gicsbd, 1, fsl_imx8mm_memmap[FSL_IMX8MM_GIC_REDIST].addr); + + /* + * Wire the outputs from each CPU's generic timer and the GICv3 + * maintenance interrupt signal to the appropriate GIC PPI inputs, and + * the GIC's IRQ/FIQ interrupt outputs to the CPU's inputs. + */ + for (i = 0; i < ms->smp.cpus; i++) { + DeviceState *cpudev = DEVICE(&s->cpu[i]); + int intidbase = FSL_IMX8MM_NUM_IRQS + i * GIC_INTERNAL; + qemu_irq irq; + + /* + * Mapping from the output timer irq lines from the CPU to the + * GIC PPI inputs. + */ + static const int timer_irqs[] = { + [GTIMER_PHYS] = ARCH_TIMER_NS_EL1_IRQ, + [GTIMER_VIRT] = ARCH_TIMER_VIRT_IRQ, + [GTIMER_HYP] = ARCH_TIMER_NS_EL2_IRQ, + [GTIMER_SEC] = ARCH_TIMER_S_EL1_IRQ, + }; + + for (int j = 0; j < ARRAY_SIZE(timer_irqs); j++) { + irq = qdev_get_gpio_in(gicdev, intidbase + timer_irqs[j]); + qdev_connect_gpio_out(cpudev, j, irq); + } + + irq = qdev_get_gpio_in(gicdev, intidbase + ARCH_GIC_MAINT_IRQ); + qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt", + 0, irq); + + irq = qdev_get_gpio_in(gicdev, intidbase + VIRTUAL_PMU_IRQ); + qdev_connect_gpio_out_named(cpudev, "pmu-interrupt", 0, irq); + + sysbus_connect_irq(gicsbd, i, + qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); + sysbus_connect_irq(gicsbd, i + ms->smp.cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_FIQ)); + sysbus_connect_irq(gicsbd, i + 2 * ms->smp.cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ)); + sysbus_connect_irq(gicsbd, i + 3 * ms->smp.cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ)); + + if (kvm_enabled()) { + if (pmu) { + assert(arm_feature(&s->cpu[i].env, ARM_FEATURE_PMU)); + if (kvm_irqchip_in_kernel()) { + kvm_arm_pmu_set_irq(&s->cpu[i], VIRTUAL_PMU_IRQ); + } + kvm_arm_pmu_init(&s->cpu[i]); + } + } + } + } + + /* UARTs */ + for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } serial_table[FSL_IMX8MM_NUM_UARTS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_UART1].addr, FSL_IMX8MM_UART1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_UART2].addr, FSL_IMX8MM_UART2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_UART3].addr, FSL_IMX8MM_UART3_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_UART4].addr, FSL_IMX8MM_UART4_IRQ }, + }; + + qdev_prop_set_chr(DEVICE(&s->uart[i]), "chardev", serial_hd(i)); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->uart[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->uart[i]), 0, serial_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart[i]), 0, + qdev_get_gpio_in(gicdev, serial_table[i].irq)); + } + + /* On-Chip RAM */ + if (!memory_region_init_ram(&s->ocram, OBJECT(dev), "imx8mm.ocram", + fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].size, + errp)) { + return; + } + memory_region_add_subregion(get_system_memory(), + fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, + &s->ocram); + + /* Unimplemented devices */ + for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { + switch (i) { + case FSL_IMX8MM_GIC_DIST: + case FSL_IMX8MM_GIC_REDIST: + case FSL_IMX8MM_RAM: + case FSL_IMX8MM_OCRAM: + case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: + /* device implemented and treated above */ + break; + + default: + create_unimplemented_device(fsl_imx8mm_memmap[i].name, + fsl_imx8mm_memmap[i].addr, + fsl_imx8mm_memmap[i].size); + break; + } + } +} + +static void fsl_imx8mm_class_init(ObjectClass *oc, const void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + + dc->realize = fsl_imx8mm_realize; + + dc->desc = "i.MX 8MM SoC"; +} + +static const TypeInfo fsl_imx8mm_types[] = { + { + .name = TYPE_FSL_IMX8MM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(FslImx8mmState), + .instance_init = fsl_imx8mm_init, + .class_init = fsl_imx8mm_class_init, + }, +}; + +DEFINE_TYPES(fsl_imx8mm_types) diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/imx8mm-evk.c @@ -XXX,XX +XXX,XX @@ +/* + * NXP i.MX 8MM Evaluation Kit System Emulation + * + * Copyright (c) 2025, NXP Semiconductors + * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "system/address-spaces.h" +#include "hw/arm/boot.h" +#include "hw/arm/fsl-imx8mm.h" +#include "hw/arm/machines-qom.h" +#include "hw/core/boards.h" +#include "hw/core/qdev-properties.h" +#include "system/kvm.h" +#include "system/qtest.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include <libfdt.h> + +static void imx8mm_evk_modify_dtb(const struct arm_boot_info *info, void *fdt) +{ + int i, offset; + + /* Temporarily disable following nodes until they are implemented */ + const char *nodes_to_remove[] = { + "nxp,imx8mm-fspi", + "fsl,imx8mm-mipi-csi", + "fsl,imx8mm-mipi-dsim" + }; + + for (i = 0; i < ARRAY_SIZE(nodes_to_remove); i++) { + const char *dev_str = nodes_to_remove[i]; + + offset = fdt_node_offset_by_compatible(fdt, -1, dev_str); + while (offset >= 0) { + fdt_nop_node(fdt, offset); + offset = fdt_node_offset_by_compatible(fdt, offset, dev_str); + } + } + + /* Remove cpu-idle-states property from CPU nodes */ + offset = fdt_node_offset_by_compatible(fdt, -1, "arm,cortex-a53"); + while (offset >= 0) { + fdt_nop_property(fdt, offset, "cpu-idle-states"); + offset = fdt_node_offset_by_compatible(fdt, offset, "arm,cortex-a53"); + } + + if (kvm_enabled()) { + /* Use system counter frequency from host CPU to fix time in guest */ + offset = fdt_node_offset_by_compatible(fdt, -1, "arm,armv8-timer"); + while (offset >= 0) { + fdt_nop_property(fdt, offset, "clock-frequency"); + offset = fdt_node_offset_by_compatible(fdt, offset, "arm,armv8-timer"); + } + } +} + +static void imx8mm_evk_init(MachineState *machine) +{ + static struct arm_boot_info boot_info; + FslImx8mmState *s; + + if (machine->ram_size > FSL_IMX8MM_RAM_SIZE_MAX) { + error_report("RAM size " RAM_ADDR_FMT " above max supported (%08" PRIx64 ")", + machine->ram_size, FSL_IMX8MM_RAM_SIZE_MAX); + exit(1); + } + + boot_info = (struct arm_boot_info) { + .loader_start = FSL_IMX8MM_RAM_START, + .board_id = -1, + .ram_size = machine->ram_size, + .psci_conduit = QEMU_PSCI_CONDUIT_SMC, + .modify_dtb = imx8mm_evk_modify_dtb, + }; + + s = FSL_IMX8MM(object_new_with_props(TYPE_FSL_IMX8MM, OBJECT(machine), + "soc", &error_fatal, NULL)); + sysbus_realize_and_unref(SYS_BUS_DEVICE(s), &error_fatal); + + memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START, + machine->ram); + + if (!qtest_enabled()) { + arm_load_kernel(&s->cpu[0], machine, &boot_info); + } +} + +static const char *imx8mm_evk_get_default_cpu_type(const MachineState *ms) +{ + if (kvm_enabled()) { + return ARM_CPU_TYPE_NAME("host"); + } + + return ARM_CPU_TYPE_NAME("cortex-a53"); +} + +static void imx8mm_evk_machine_init(MachineClass *mc) +{ + mc->desc = "NXP i.MX 8MM EVK Board"; + mc->init = imx8mm_evk_init; + mc->max_cpus = FSL_IMX8MM_NUM_CPUS; + mc->default_cpus = FSL_IMX8MM_NUM_CPUS; + mc->default_ram_size = 2 * GiB; + mc->default_ram_id = "imx8mm-evk.ram"; + mc->get_default_cpu_type = imx8mm_evk_get_default_cpu_type; +} + +DEFINE_MACHINE_AARCH64("imx8mm-evk", imx8mm_evk_machine_init) diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_common_ss.add(when: 'CONFIG_ARMSSE', if_true: files('armsse.c')) arm_common_ss.add(when: 'CONFIG_FSL_IMX7', if_true: files('fsl-imx7.c', 'mcimx7d-sabre.c')) arm_common_ss.add(when: 'CONFIG_FSL_IMX8MP', if_true: files('fsl-imx8mp.c')) arm_common_ss.add(when: 'CONFIG_FSL_IMX8MP_EVK', if_true: files('imx8mp-evk.c')) +arm_common_ss.add(when: 'CONFIG_FSL_IMX8MM', if_true: files('fsl-imx8mm.c')) +arm_common_ss.add(when: 'CONFIG_FSL_IMX8MM_EVK', if_true: files('imx8mm-evk.c')) arm_common_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmuv3.c')) arm_common_ss.add(when: 'CONFIG_ARM_SMMUV3_ACCEL', if_true: files('smmuv3-accel.c')) stub_ss.add(files('smmuv3-accel-stubs.c')) diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ +/* + * i.MX 8MM SoC Definitions + * + * Copyright (c) 2025, NXP Semiconductors + * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef FSL_IMX8MM_H +#define FSL_IMX8MM_H + +#include "cpu.h" +#include "hw/char/imx_serial.h" +#include "hw/intc/arm_gicv3_common.h" +#include "qom/object.h" +#include "qemu/units.h" + +#define TYPE_FSL_IMX8MM "fsl-imx8mm" +OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM) + +#define FSL_IMX8MM_RAM_START 0x40000000 +#define FSL_IMX8MM_RAM_SIZE_MAX (4 * GiB) + +enum FslImx8mmConfiguration { + FSL_IMX8MM_NUM_CPUS = 4, + FSL_IMX8MM_NUM_IRQS = 128, + FSL_IMX8MM_NUM_UARTS = 4, +}; + +struct FslImx8mmState { + SysBusDevice parent_obj; + + ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; + GICv3State gic; + IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; + MemoryRegion ocram; +}; + +enum FslImx8mmMemoryRegions { + FSL_IMX8MM_A53_DAP, + FSL_IMX8MM_AIPS1_CONFIGURATION, + FSL_IMX8MM_AIPS2_CONFIGURATION, + FSL_IMX8MM_AIPS3_CONFIGURATION, + FSL_IMX8MM_AIPS4_CONFIGURATION, + FSL_IMX8MM_ANA_OSC, + FSL_IMX8MM_ANA_PLL, + FSL_IMX8MM_ANA_TSENSOR, + FSL_IMX8MM_APBH_DMA, + FSL_IMX8MM_BOOT_ROM, + FSL_IMX8MM_BOOT_ROM_PROTECTED, + FSL_IMX8MM_CAAM, + FSL_IMX8MM_CAAM_MEM, + FSL_IMX8MM_CCM, + FSL_IMX8MM_CSU, + FSL_IMX8MM_DDR_CTL, + FSL_IMX8MM_DDR_PERF_MON, + FSL_IMX8MM_DDR_PHY, + FSL_IMX8MM_DDR_PHY_BROADCAST, + FSL_IMX8MM_ECSPI1, + FSL_IMX8MM_ECSPI2, + FSL_IMX8MM_ECSPI3, + FSL_IMX8MM_ENET1, + FSL_IMX8MM_GIC_DIST, + FSL_IMX8MM_GIC_REDIST, + FSL_IMX8MM_GPC, + FSL_IMX8MM_GPIO1, + FSL_IMX8MM_GPIO2, + FSL_IMX8MM_GPIO3, + FSL_IMX8MM_GPIO4, + FSL_IMX8MM_GPIO5, + FSL_IMX8MM_GPT1, + FSL_IMX8MM_GPT2, + FSL_IMX8MM_GPT3, + FSL_IMX8MM_GPT4, + FSL_IMX8MM_GPT5, + FSL_IMX8MM_GPT6, + FSL_IMX8MM_GPU2D, + FSL_IMX8MM_I2C1, + FSL_IMX8MM_I2C2, + FSL_IMX8MM_I2C3, + FSL_IMX8MM_I2C4, + FSL_IMX8MM_INTERCONNECT, + FSL_IMX8MM_IOMUXC, + FSL_IMX8MM_IOMUXC_GPR, + FSL_IMX8MM_MEDIA_BLK_CTL, + FSL_IMX8MM_LCDIF, + FSL_IMX8MM_MIPI_CSI, + FSL_IMX8MM_MIPI_DSI, + FSL_IMX8MM_MU_A, + FSL_IMX8MM_MU_B, + FSL_IMX8MM_OCOTP_CTRL, + FSL_IMX8MM_OCRAM, + FSL_IMX8MM_OCRAM_S, + FSL_IMX8MM_PCIE1, + FSL_IMX8MM_PCIE1_MEM, + FSL_IMX8MM_PCIE_PHY1, + FSL_IMX8MM_PERFMON1, + FSL_IMX8MM_PERFMON2, + FSL_IMX8MM_PWM1, + FSL_IMX8MM_PWM2, + FSL_IMX8MM_PWM3, + FSL_IMX8MM_PWM4, + FSL_IMX8MM_QOSC, + FSL_IMX8MM_QSPI, + FSL_IMX8MM_QSPI1_RX_BUFFER, + FSL_IMX8MM_QSPI1_TX_BUFFER, + FSL_IMX8MM_QSPI_MEM, + FSL_IMX8MM_RAM, + FSL_IMX8MM_RDC, + FSL_IMX8MM_SAI1, + FSL_IMX8MM_SAI2, + FSL_IMX8MM_SAI3, + FSL_IMX8MM_SAI5, + FSL_IMX8MM_SAI6, + FSL_IMX8MM_SDMA1, + FSL_IMX8MM_SDMA2, + FSL_IMX8MM_SDMA3, + FSL_IMX8MM_SEMAPHORE1, + FSL_IMX8MM_SEMAPHORE2, + FSL_IMX8MM_SEMAPHORE_HS, + FSL_IMX8MM_SNVS_HP, + FSL_IMX8MM_SPBA1, + FSL_IMX8MM_SRC, + FSL_IMX8MM_SYSCNT_CMP, + FSL_IMX8MM_SYSCNT_CTRL, + FSL_IMX8MM_SYSCNT_RD, + FSL_IMX8MM_TCM_DTCM, + FSL_IMX8MM_TCM_ITCM, + FSL_IMX8MM_TZASC, + FSL_IMX8MM_UART1, + FSL_IMX8MM_UART2, + FSL_IMX8MM_UART3, + FSL_IMX8MM_UART4, + FSL_IMX8MM_USB1, + FSL_IMX8MM_USB2, + FSL_IMX8MM_USB1_OTG, + FSL_IMX8MM_USB2_OTG, + FSL_IMX8MM_USDHC1, + FSL_IMX8MM_USDHC2, + FSL_IMX8MM_USDHC3, + FSL_IMX8MM_VPU, + FSL_IMX8MM_VPU_BLK_CTRL, + FSL_IMX8MM_VPU_G1_DECODER, + FSL_IMX8MM_VPU_G2_DECODER, + FSL_IMX8MM_WDOG1, + FSL_IMX8MM_WDOG2, + FSL_IMX8MM_WDOG3, +}; + +enum FslImx8mmIrqs { + FSL_IMX8MM_UART1_IRQ = 26, + FSL_IMX8MM_UART2_IRQ = 27, + FSL_IMX8MM_UART3_IRQ = 28, + FSL_IMX8MM_UART4_IRQ = 29, +}; + +#endif /* FSL_IMX8MM_H */ -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Add configurable properties for register reset values that differ between i.MX 8M variants (Plus, Mini, etc.). This allows the same device implementation to be shared across multiple SoCs. Properties added: - arm-pll-fdiv-ctl0-reset: ARM PLL divider control reset value Default value is set to match i.MX 8MP reset value (0x000FA031). This can be overridden in the variant like iMX8MM with its own reset value. Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx8mp_analog.c | 12 +++++++++++- include/hw/misc/imx8mp_analog.h | 3 +++ 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/hw/misc/imx8mp_analog.c b/hw/misc/imx8mp_analog.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx8mp_analog.c +++ b/hw/misc/imx8mp_analog.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "hw/misc/imx8mp_analog.h" +#include "hw/core/qdev-properties.h" #include "migration/vmstate.h" #define ANALOG_PLL_LOCK BIT(31) @@ -XXX,XX +XXX,XX @@ static void imx8mp_analog_reset(DeviceState *dev) s->analog[ANALOG_VPU_PLL_LOCKD_CTRL] = 0x0010003f; s->analog[ANALOG_VPU_PLL_MNIT_CTRL] = 0x00280081; s->analog[ANALOG_ARM_PLL_GEN_CTRL] = 0x00000810; - s->analog[ANALOG_ARM_PLL_FDIV_CTL0] = 0x000fa031; + + /* Use property value instead of hardcoded */ + s->analog[ANALOG_ARM_PLL_FDIV_CTL0] = s->arm_pll_fdiv_ctl0_reset; + s->analog[ANALOG_ARM_PLL_LOCKD_CTRL] = 0x0010003f; s->analog[ANALOG_ARM_PLL_MNIT_CTRL] = 0x00280081; s->analog[ANALOG_SYS_PLL1_GEN_CTRL] = 0x0aaaa810; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription imx8mp_analog_vmstate = { }, }; +static const Property imx8mp_analog_properties[] = { + DEFINE_PROP_UINT32("arm-pll-fdiv-ctl0-reset", IMX8MPAnalogState, + arm_pll_fdiv_ctl0_reset, 0x000fa031), /* imx8mp default */ +}; + static void imx8mp_analog_class_init(ObjectClass *klass, const void *data) { DeviceClass *dc = DEVICE_CLASS(klass); device_class_set_legacy_reset(dc, imx8mp_analog_reset); + device_class_set_props(dc, imx8mp_analog_properties); dc->vmsd = &imx8mp_analog_vmstate; dc->desc = "i.MX 8M Plus Analog Module"; } diff --git a/include/hw/misc/imx8mp_analog.h b/include/hw/misc/imx8mp_analog.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/imx8mp_analog.h +++ b/include/hw/misc/imx8mp_analog.h @@ -XXX,XX +XXX,XX @@ struct IMX8MPAnalogState { } mmio; uint32_t analog[ANALOG_MAX]; + + /* Property for variant-specific reset values */ + uint32_t arm_pll_fdiv_ctl0_reset; }; #endif /* IMX8MP_ANALOG_H */ -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Add the Analog IP to i.MX8MM SoC. iMX8MM and i.MX8MP uses the same Analog IP so the analog ip source will be shared. The ARM PLL divider control register (arm-pll-fdiv-ctl0) has a different reset value on i.MX8MM (0x000fa030) compared to i.MX8MP (0x000fa031). So iMX8MM will be overriding this property with its own reset-value. Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 12 ++++++++++++ include/hw/arm/fsl-imx8mm.h | 2 ++ 3 files changed, 15 insertions(+) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK config FSL_IMX8MM bool select ARM_GIC + select FSL_IMX8MP_ANALOG select IMX config FSL_IMX8MM_EVK diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, "gic", &s->gic, gicv3_class_name()); + object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG); + for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { g_autofree char *name = g_strdup_printf("uart%d", i + 1); object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) } } + /* Analog */ + object_property_set_uint(OBJECT(&s->analog), "arm-pll-fdiv-ctl0-reset", + 0x000fa030, &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->analog), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->analog), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_ANA_PLL].addr); + /* UARTs */ for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { switch (i) { + case FSL_IMX8MM_ANA_PLL: case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_RAM: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/char/imx_serial.h" #include "hw/intc/arm_gicv3_common.h" +#include "hw/misc/imx8mp_analog.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; GICv3State gic; + IMX8MPAnalogState analog; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; }; -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Add the Clock Control Module (CCM) device to i.MX8MM SoC. The CCM implementation is shared with i.MX8MP as the register layout is identical between the two variants.Hence iMX8MM will be using the source of iMX8MP CCM. Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 10 ++++++++++ include/hw/arm/fsl-imx8mm.h | 2 ++ 3 files changed, 13 insertions(+) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM bool select ARM_GIC select FSL_IMX8MP_ANALOG + select FSL_IMX8MP_CCM select IMX config FSL_IMX8MM_EVK diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, "gic", &s->gic, gicv3_class_name()); + object_initialize_child(obj, "ccm", &s->ccm, TYPE_IMX8MP_CCM); + object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG); for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) } } + /* CCM */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->ccm), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_CCM].addr); + /* Analog */ object_property_set_uint(OBJECT(&s->analog), "arm-pll-fdiv-ctl0-reset", 0x000fa030, &error_abort); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { switch (i) { case FSL_IMX8MM_ANA_PLL: + case FSL_IMX8MM_CCM: case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_RAM: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/char/imx_serial.h" #include "hw/intc/arm_gicv3_common.h" #include "hw/misc/imx8mp_analog.h" +#include "hw/misc/imx8mp_ccm.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; GICv3State gic; + IMX8MPCCMState ccm; IMX8MPAnalogState analog; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> SNVS contains an RTC which allows Linux to deal correctly with time Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx8mm.c | 10 ++++++++++ include/hw/arm/fsl-imx8mm.h | 2 ++ 2 files changed, 12 insertions(+) diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG); + object_initialize_child(obj, "snvs", &s->snvs, TYPE_IMX7_SNVS); + for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { g_autofree char *name = g_strdup_printf("uart%d", i + 1); object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* SNVS */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { switch (i) { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_RAM: case FSL_IMX8MM_OCRAM: + case FSL_IMX8MM_SNVS_HP: case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: /* device implemented and treated above */ break; diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/char/imx_serial.h" #include "hw/intc/arm_gicv3_common.h" +#include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { GICv3State gic; IMX8MPCCMState ccm; IMX8MPAnalogState analog; + IMX7SNVSState snvs; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; }; -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of SD/MMC cards through a virtual SDHCI interface The emulated SDHCI controller allows guest OS to use emulated storage as a standard block device. This will allow running the images such as those generated by Buildroot. Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 25 +++++++++++++++++++++++++ hw/arm/imx8mm-evk.c | 17 +++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 7 +++++++ 4 files changed, 50 insertions(+) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM select FSL_IMX8MP_ANALOG select FSL_IMX8MP_CCM select IMX + select SDHCI config FSL_IMX8MM_EVK bool diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); } + for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { + g_autofree char *name = g_strdup_printf("usdhc%d", i + 1); + object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); + } } static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* USDHCs */ + for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } usdhc_table[FSL_IMX8MM_NUM_USDHCS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC1].addr, FSL_IMX8MM_USDHC1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC2].addr, FSL_IMX8MM_USDHC2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC3].addr, FSL_IMX8MM_USDHC3_IRQ }, + }; + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->usdhc[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->usdhc[i]), 0, usdhc_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->usdhc[i]), 0, + qdev_get_gpio_in(gicdev, usdhc_table[i].irq)); + } + /* SNVS */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) { return; @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_OCRAM: case FSL_IMX8MM_SNVS_HP: case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: + case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3: /* device implemented and treated above */ break; diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx8mm-evk.c +++ b/hw/arm/imx8mm-evk.c @@ -XXX,XX +XXX,XX @@ static void imx8mm_evk_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START, machine->ram); + for (int i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { + BusState *bus; + DeviceState *carddev; + BlockBackend *blk; + DriveInfo *di = drive_get(IF_SD, i, 0); + + if (!di) { + continue; + } + + blk = blk_by_legacy_dinfo(di); + bus = qdev_get_child_bus(DEVICE(&s->usdhc[i]), "sd-bus"); + carddev = qdev_new(TYPE_SD_CARD); + qdev_prop_set_drive_err(carddev, "drive", blk, &error_fatal); + qdev_realize_and_unref(carddev, bus, &error_fatal); + } + if (!qtest_enabled()) { arm_load_kernel(&s->cpu[0], machine, &boot_info); } diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" +#include "hw/sd/sdhci.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, + FSL_IMX8MM_NUM_USDHCS = 3, }; struct FslImx8mmState { @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMX7SNVSState snvs; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; + SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; }; enum FslImx8mmMemoryRegions { @@ -XXX,XX +XXX,XX @@ enum FslImx8mmMemoryRegions { }; enum FslImx8mmIrqs { + FSL_IMX8MM_USDHC1_IRQ = 22, + FSL_IMX8MM_USDHC2_IRQ = 23, + FSL_IMX8MM_USDHC3_IRQ = 24, + FSL_IMX8MM_UART1_IRQ = 26, FSL_IMX8MM_UART2_IRQ = 27, FSL_IMX8MM_UART3_IRQ = 28, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> This enables support for Designware PCI Express Controller emulation It provides a controlled environment to debug the linux pci subsystem Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 3 +++ hw/arm/fsl-imx8mm.c | 30 ++++++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 10 ++++++++++ 3 files changed, 43 insertions(+) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK config FSL_IMX8MM bool + imply PCI_DEVICES select ARM_GIC select FSL_IMX8MP_ANALOG select FSL_IMX8MP_CCM select IMX select SDHCI + select PCI_EXPRESS_DESIGNWARE + select PCI_EXPRESS_FSL_IMX8M_PHY config FSL_IMX8MM_EVK bool diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) g_autofree char *name = g_strdup_printf("usdhc%d", i + 1); object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); } + + object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); + object_initialize_child(obj, "pcie_phy", &s->pcie_phy, + TYPE_FSL_IMX8M_PCIE_PHY); } static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr); + /* PCIe */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_PCIE1].addr); + + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 0, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTA_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 1, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTB_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 2, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTC_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 3, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTD_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 4, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_MSI_IRQ)); + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie_phy), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie_phy), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_PCIE_PHY1].addr); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { switch (i) { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_CCM: case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: + case FSL_IMX8MM_PCIE1: + case FSL_IMX8MM_PCIE_PHY1: case FSL_IMX8MM_RAM: case FSL_IMX8MM_OCRAM: case FSL_IMX8MM_SNVS_HP: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" +#include "hw/pci-host/designware.h" +#include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; + DesignwarePCIEHost pcie; + FslImx8mPciePhyState pcie_phy; }; enum FslImx8mmMemoryRegions { @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_UART2_IRQ = 27, FSL_IMX8MM_UART3_IRQ = 28, FSL_IMX8MM_UART4_IRQ = 29, + + FSL_IMX8MM_PCI_INTA_IRQ = 122, + FSL_IMX8MM_PCI_INTB_IRQ = 123, + FSL_IMX8MM_PCI_INTC_IRQ = 124, + FSL_IMX8MM_PCI_INTD_IRQ = 125, + FSL_IMX8MM_PCI_MSI_IRQ = 127, }; #endif /* FSL_IMX8MM_H */ -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Enabled GPIO controller emulation Also updated the GPIO IRQ lines of iMX8MM Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx8mm.c | 54 +++++++++++++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 14 ++++++++++ 2 files changed, 68 insertions(+) diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); } + for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) { + g_autofree char *name = g_strdup_printf("gpio%d", i + 1); + object_initialize_child(obj, name, &s->gpio[i], TYPE_IMX_GPIO); + } + for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { g_autofree char *name = g_strdup_printf("usdhc%d", i + 1); object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* GPIOs */ + for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) { + static const struct { + hwaddr addr; + unsigned int irq_low; + unsigned int irq_high; + } gpio_table[FSL_IMX8MM_NUM_GPIOS] = { + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO1].addr, + FSL_IMX8MM_GPIO1_LOW_IRQ, + FSL_IMX8MM_GPIO1_HIGH_IRQ + }, + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO2].addr, + FSL_IMX8MM_GPIO2_LOW_IRQ, + FSL_IMX8MM_GPIO2_HIGH_IRQ + }, + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO3].addr, + FSL_IMX8MM_GPIO3_LOW_IRQ, + FSL_IMX8MM_GPIO3_HIGH_IRQ + }, + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO4].addr, + FSL_IMX8MM_GPIO4_LOW_IRQ, + FSL_IMX8MM_GPIO4_HIGH_IRQ + }, + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO5].addr, + FSL_IMX8MM_GPIO5_LOW_IRQ, + FSL_IMX8MM_GPIO5_HIGH_IRQ + }, + }; + object_property_set_bool(OBJECT(&s->gpio[i]), "has-edge-sel", true, + &error_abort); + object_property_set_bool(OBJECT(&s->gpio[i]), "has-upper-pin-irq", + true, &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->gpio[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpio[i]), 0, gpio_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 0, + qdev_get_gpio_in(gicdev, gpio_table[i].irq_low)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 1, + qdev_get_gpio_in(gicdev, gpio_table[i].irq_high)); + } + /* USDHCs */ for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_CCM: case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: + case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: case FSL_IMX8MM_PCIE1: case FSL_IMX8MM_PCIE_PHY1: case FSL_IMX8MM_RAM: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/char/imx_serial.h" +#include "hw/gpio/imx_gpio.h" #include "hw/intc/arm_gicv3_common.h" #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM) enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, + FSL_IMX8MM_NUM_GPIOS = 5, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, FSL_IMX8MM_NUM_USDHCS = 3, @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; GICv3State gic; + IMXGPIOState gpio[FSL_IMX8MM_NUM_GPIOS]; IMX8MPCCMState ccm; IMX8MPAnalogState analog; IMX7SNVSState snvs; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_UART3_IRQ = 28, FSL_IMX8MM_UART4_IRQ = 29, + FSL_IMX8MM_GPIO1_LOW_IRQ = 64, + FSL_IMX8MM_GPIO1_HIGH_IRQ = 65, + FSL_IMX8MM_GPIO2_LOW_IRQ = 66, + FSL_IMX8MM_GPIO2_HIGH_IRQ = 67, + FSL_IMX8MM_GPIO3_LOW_IRQ = 68, + FSL_IMX8MM_GPIO3_HIGH_IRQ = 69, + FSL_IMX8MM_GPIO4_LOW_IRQ = 70, + FSL_IMX8MM_GPIO4_HIGH_IRQ = 71, + FSL_IMX8MM_GPIO5_LOW_IRQ = 72, + FSL_IMX8MM_GPIO5_HIGH_IRQ = 73, + FSL_IMX8MM_PCI_INTA_IRQ = 122, FSL_IMX8MM_PCI_INTB_IRQ = 123, FSL_IMX8MM_PCI_INTC_IRQ = 124, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> This can be used to test and debug I2C device drivers. Added I2C interrupts Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 2 ++ hw/arm/fsl-imx8mm.c | 27 +++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 8 ++++++++ 3 files changed, 37 insertions(+) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK config FSL_IMX8MM bool imply PCI_DEVICES + imply I2C_DEVICES select ARM_GIC select FSL_IMX8MP_ANALOG select FSL_IMX8MP_CCM select IMX + select IMX_I2C select SDHCI select PCI_EXPRESS_DESIGNWARE select PCI_EXPRESS_FSL_IMX8M_PHY diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); } + for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) { + g_autofree char *name = g_strdup_printf("i2c%d", i + 1); + object_initialize_child(obj, name, &s->i2c[i], TYPE_IMX_I2C); + } + for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) { g_autofree char *name = g_strdup_printf("gpio%d", i + 1); object_initialize_child(obj, name, &s->gpio[i], TYPE_IMX_GPIO); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* I2Cs */ + for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } i2c_table[FSL_IMX8MM_NUM_I2CS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_I2C1].addr, FSL_IMX8MM_I2C1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_I2C2].addr, FSL_IMX8MM_I2C2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_I2C3].addr, FSL_IMX8MM_I2C3_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_I2C4].addr, FSL_IMX8MM_I2C4_IRQ }, + }; + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->i2c[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c[i]), 0, i2c_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c[i]), 0, + qdev_get_gpio_in(gicdev, i2c_table[i].irq)); + } + /* GPIOs */ for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: + case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4: case FSL_IMX8MM_PCIE1: case FSL_IMX8MM_PCIE_PHY1: case FSL_IMX8MM_RAM: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/char/imx_serial.h" #include "hw/gpio/imx_gpio.h" +#include "hw/i2c/imx_i2c.h" #include "hw/intc/arm_gicv3_common.h" #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM) enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, FSL_IMX8MM_NUM_GPIOS = 5, + FSL_IMX8MM_NUM_I2CS = 4, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, FSL_IMX8MM_NUM_USDHCS = 3, @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMX8MPCCMState ccm; IMX8MPAnalogState analog; IMX7SNVSState snvs; + IMXI2CState i2c[FSL_IMX8MM_NUM_I2CS]; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_UART3_IRQ = 28, FSL_IMX8MM_UART4_IRQ = 29, + FSL_IMX8MM_I2C1_IRQ = 35, + FSL_IMX8MM_I2C2_IRQ = 36, + FSL_IMX8MM_I2C3_IRQ = 37, + FSL_IMX8MM_I2C4_IRQ = 38, + FSL_IMX8MM_GPIO1_LOW_IRQ = 64, FSL_IMX8MM_GPIO1_HIGH_IRQ = 65, FSL_IMX8MM_GPIO2_LOW_IRQ = 66, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of ECSPI in iMX8MM Added SPI IRQ lines Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx8mm.c | 26 ++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 7 +++++++ 2 files changed, 33 insertions(+) diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); } + for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) { + g_autofree char *name = g_strdup_printf("spi%d", i + 1); + object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI); + } + object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); object_initialize_child(obj, "pcie_phy", &s->pcie_phy, TYPE_FSL_IMX8M_PCIE_PHY); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(gicdev, usdhc_table[i].irq)); } + /* ECSPIs */ + for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } spi_table[FSL_IMX8MM_NUM_ECSPIS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI1].addr, FSL_IMX8MM_ECSPI1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI2].addr, FSL_IMX8MM_ECSPI2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI3].addr, FSL_IMX8MM_ECSPI3_IRQ }, + }; + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->spi[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 0, spi_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->spi[i]), 0, + qdev_get_gpio_in(gicdev, spi_table[i].irq)); + } + /* SNVS */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) { return; @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: + case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3: case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4: case FSL_IMX8MM_PCIE1: case FSL_IMX8MM_PCIE_PHY1: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/pci-host/designware.h" #include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" +#include "hw/ssi/imx_spi.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM) enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, + FSL_IMX8MM_NUM_ECSPIS = 3, FSL_IMX8MM_NUM_GPIOS = 5, FSL_IMX8MM_NUM_I2CS = 4, FSL_IMX8MM_NUM_IRQS = 128, @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMX8MPCCMState ccm; IMX8MPAnalogState analog; IMX7SNVSState snvs; + IMXSPIState spi[FSL_IMX8MM_NUM_ECSPIS]; IMXI2CState i2c[FSL_IMX8MM_NUM_I2CS]; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_UART3_IRQ = 28, FSL_IMX8MM_UART4_IRQ = 29, + FSL_IMX8MM_ECSPI1_IRQ = 31, + FSL_IMX8MM_ECSPI2_IRQ = 32, + FSL_IMX8MM_ECSPI3_IRQ = 33, + FSL_IMX8MM_I2C1_IRQ = 35, FSL_IMX8MM_I2C2_IRQ = 36, FSL_IMX8MM_I2C3_IRQ = 37, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of WDT in iMX8MM Added WDT IRQ lines Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 28 ++++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 7 +++++++ 3 files changed, 36 insertions(+) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM select SDHCI select PCI_EXPRESS_DESIGNWARE select PCI_EXPRESS_FSL_IMX8M_PHY + select WDT_IMX2 config FSL_IMX8MM_EVK bool diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI); } + for (i = 0; i < FSL_IMX8MM_NUM_WDTS; i++) { + g_autofree char *name = g_strdup_printf("wdt%d", i); + object_initialize_child(obj, name, &s->wdt[i], TYPE_IMX2_WDT); + } + object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); object_initialize_child(obj, "pcie_phy", &s->pcie_phy, TYPE_FSL_IMX8M_PCIE_PHY); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr); + /* Watchdogs */ + for (i = 0; i < FSL_IMX8MM_NUM_WDTS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } wdog_table[FSL_IMX8MM_NUM_WDTS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG1].addr, FSL_IMX8MM_WDOG1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG2].addr, FSL_IMX8MM_WDOG2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG3].addr, FSL_IMX8MM_WDOG3_IRQ }, + }; + + object_property_set_bool(OBJECT(&s->wdt[i]), "pretimeout-support", + true, &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->wdt[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt[i]), 0, wdog_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->wdt[i]), 0, + qdev_get_gpio_in(gicdev, wdog_table[i].irq)); + } + /* PCIe */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie), errp)) { return; @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_SNVS_HP: case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3: + case FSL_IMX8MM_WDOG1 ... FSL_IMX8MM_WDOG3: /* device implemented and treated above */ break; diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" #include "hw/ssi/imx_spi.h" +#include "hw/watchdog/wdt_imx2.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, FSL_IMX8MM_NUM_USDHCS = 3, + FSL_IMX8MM_NUM_WDTS = 3, }; struct FslImx8mmState { @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; + IMX2WdtState wdt[FSL_IMX8MM_NUM_WDTS]; DesignwarePCIEHost pcie; FslImx8mPciePhyState pcie_phy; }; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_GPIO5_LOW_IRQ = 72, FSL_IMX8MM_GPIO5_HIGH_IRQ = 73, + FSL_IMX8MM_WDOG1_IRQ = 78, + FSL_IMX8MM_WDOG2_IRQ = 79, + FSL_IMX8MM_WDOG3_IRQ = 10, + FSL_IMX8MM_PCI_INTA_IRQ = 122, FSL_IMX8MM_PCI_INTB_IRQ = 123, FSL_IMX8MM_PCI_INTC_IRQ = 124, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of GPT in iMX8MM Added GPT IRQ lines Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 54 +++++++++++++++++++++++++++++++++++++ hw/timer/imx_gpt.c | 26 ++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 11 ++++++++ include/hw/timer/imx_gpt.h | 2 ++ 5 files changed, 94 insertions(+) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM select FSL_IMX8MP_CCM select IMX select IMX_I2C + select OR_IRQ select SDHCI select PCI_EXPRESS_DESIGNWARE select PCI_EXPRESS_FSL_IMX8M_PHY diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); } + for (i = 0; i < FSL_IMX8MM_NUM_GPTS; i++) { + g_autofree char *name = g_strdup_printf("gpt%d", i + 1); + object_initialize_child(obj, name, &s->gpt[i], TYPE_IMX8MM_GPT); + } + object_initialize_child(obj, "gpt5-gpt6-irq", &s->gpt5_gpt6_irq, + TYPE_OR_IRQ); + for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) { g_autofree char *name = g_strdup_printf("i2c%d", i + 1); object_initialize_child(obj, name, &s->i2c[i], TYPE_IMX_I2C); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* GPTs */ + object_property_set_int(OBJECT(&s->gpt5_gpt6_irq), "num-lines", 2, + &error_abort); + if (!qdev_realize(DEVICE(&s->gpt5_gpt6_irq), NULL, errp)) { + return; + } + + qdev_connect_gpio_out(DEVICE(&s->gpt5_gpt6_irq), 0, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_GPT5_GPT6_IRQ)); + + for (i = 0; i < FSL_IMX8MM_NUM_GPTS; i++) { + hwaddr gpt_addrs[FSL_IMX8MM_NUM_GPTS] = { + fsl_imx8mm_memmap[FSL_IMX8MM_GPT1].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT2].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT3].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT4].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT5].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT6].addr, + }; + + s->gpt[i].ccm = IMX_CCM(&s->ccm); + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->gpt[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpt[i]), 0, gpt_addrs[i]); + + if (i < FSL_IMX8MM_NUM_GPTS - 2) { + static const unsigned int gpt_irqs[FSL_IMX8MM_NUM_GPTS - 2] = { + FSL_IMX8MM_GPT1_IRQ, + FSL_IMX8MM_GPT2_IRQ, + FSL_IMX8MM_GPT3_IRQ, + FSL_IMX8MM_GPT4_IRQ, + }; + + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0, + qdev_get_gpio_in(gicdev, gpt_irqs[i])); + } else { + int irq = i - FSL_IMX8MM_NUM_GPTS + 2; + + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0, + qdev_get_gpio_in(DEVICE(&s->gpt5_gpt6_irq), irq)); + } + } + /* I2Cs */ for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: + case FSL_IMX8MM_GPT1 ... FSL_IMX8MM_GPT6: case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3: case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4: case FSL_IMX8MM_PCIE1: diff --git a/hw/timer/imx_gpt.c b/hw/timer/imx_gpt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/imx_gpt.c +++ b/hw/timer/imx_gpt.c @@ -XXX,XX +XXX,XX @@ * Originally written by Hans Jiang * Updated by Peter Chubb * Updated by Jean-Christophe Dubois <jcd@tribudubois.net> + * Updated by Gaurav Sharma <gaurav.sharma_7@nxp.com> * * This code is licensed under GPL version 2 or later. See * the COPYING file in the top-level directory. @@ -XXX,XX +XXX,XX @@ static const IMXClk imx8mp_gpt_clocks[] = { CLK_NONE, /* 111 not defined */ }; +static const IMXClk imx8mm_gpt_clocks[] = { + CLK_NONE, /* 000 No clock source */ + CLK_IPG, /* 001 ipg_clk, 532MHz */ + CLK_IPG_HIGH, /* 010 ipg_clk_highfreq */ + CLK_EXT, /* 011 External clock */ + CLK_32k, /* 100 ipg_clk_32k */ + CLK_HIGH, /* 101 ipg_clk_16M */ + CLK_NONE, /* 110 not defined */ + CLK_NONE, /* 111 not defined */ +}; + /* Must be called from within ptimer_transaction_begin/commit block */ static void imx_gpt_set_freq(IMXGPTState *s) { @@ -XXX,XX +XXX,XX @@ static void imx8mp_gpt_init(Object *obj) s->clocks = imx8mp_gpt_clocks; } +static void imx8mm_gpt_init(Object *obj) +{ + IMXGPTState *s = IMX_GPT(obj); + + s->clocks = imx8mm_gpt_clocks; +} + static const TypeInfo imx25_gpt_info = { .name = TYPE_IMX25_GPT, .parent = TYPE_SYS_BUS_DEVICE, @@ -XXX,XX +XXX,XX @@ static const TypeInfo imx8mp_gpt_info = { .instance_init = imx8mp_gpt_init, }; +static const TypeInfo imx8mm_gpt_info = { + .name = TYPE_IMX8MM_GPT, + .parent = TYPE_IMX25_GPT, + .instance_init = imx8mm_gpt_init, +}; + static void imx_gpt_register_types(void) { type_register_static(&imx25_gpt_info); @@ -XXX,XX +XXX,XX @@ static void imx_gpt_register_types(void) type_register_static(&imx6ul_gpt_info); type_register_static(&imx7_gpt_info); type_register_static(&imx8mp_gpt_info); + type_register_static(&imx8mm_gpt_info); } type_init(imx_gpt_register_types) diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" +#include "hw/or-irq.h" #include "hw/pci-host/designware.h" #include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" #include "hw/ssi/imx_spi.h" +#include "hw/timer/imx_gpt.h" #include "hw/watchdog/wdt_imx2.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, FSL_IMX8MM_NUM_ECSPIS = 3, FSL_IMX8MM_NUM_GPIOS = 5, + FSL_IMX8MM_NUM_GPTS = 6, FSL_IMX8MM_NUM_I2CS = 4, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; GICv3State gic; + IMXGPTState gpt[FSL_IMX8MM_NUM_GPTS]; IMXGPIOState gpio[FSL_IMX8MM_NUM_GPIOS]; IMX8MPCCMState ccm; IMX8MPAnalogState analog; @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMX2WdtState wdt[FSL_IMX8MM_NUM_WDTS]; DesignwarePCIEHost pcie; FslImx8mPciePhyState pcie_phy; + OrIRQState gpt5_gpt6_irq; }; enum FslImx8mmMemoryRegions { @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_I2C3_IRQ = 37, FSL_IMX8MM_I2C4_IRQ = 38, + FSL_IMX8MM_GPT1_IRQ = 55, + FSL_IMX8MM_GPT2_IRQ = 54, + FSL_IMX8MM_GPT3_IRQ = 53, + FSL_IMX8MM_GPT4_IRQ = 52, + FSL_IMX8MM_GPT5_GPT6_IRQ = 51, + FSL_IMX8MM_GPIO1_LOW_IRQ = 64, FSL_IMX8MM_GPIO1_HIGH_IRQ = 65, FSL_IMX8MM_GPIO2_LOW_IRQ = 66, diff --git a/include/hw/timer/imx_gpt.h b/include/hw/timer/imx_gpt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/timer/imx_gpt.h +++ b/include/hw/timer/imx_gpt.h @@ -XXX,XX +XXX,XX @@ * Originally written by Hans Jiang * Updated by Peter Chubb * Updated by Jean-Christophe Dubois <jcd@tribudubois.net> + * Updated by Gaurav Sharma <gaurav.sharma_7@nxp.com> * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -XXX,XX +XXX,XX @@ #define TYPE_IMX6UL_GPT "imx6ul.gpt" #define TYPE_IMX7_GPT "imx7.gpt" #define TYPE_IMX8MP_GPT "imx8mp.gpt" +#define TYPE_IMX8MM_GPT "imx8mm.gpt" #define TYPE_IMX_GPT TYPE_IMX25_GPT -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of ENET ethernet controller in iMX8MM Enables testing and debugging of network dependent drivers Added ENET MAC IRQ lines Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 24 ++++++++++++++++++++++++ hw/arm/imx8mm-evk.c | 1 + include/hw/arm/fsl-imx8mm.h | 10 +++++++++- 4 files changed, 35 insertions(+), 1 deletion(-) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM select FSL_IMX8MP_ANALOG select FSL_IMX8MP_CCM select IMX + select IMX_FEC select IMX_I2C select OR_IRQ select SDHCI diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->wdt[i], TYPE_IMX2_WDT); } + object_initialize_child(obj, "eth0", &s->enet, TYPE_IMX_ENET); + object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); object_initialize_child(obj, "pcie_phy", &s->pcie_phy, TYPE_FSL_IMX8M_PCIE_PHY); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(gicdev, spi_table[i].irq)); } + /* ENET1 */ + object_property_set_uint(OBJECT(&s->enet), "phy-num", s->phy_num, + &error_abort); + object_property_set_uint(OBJECT(&s->enet), "tx-ring-num", 3, &error_abort); + qemu_configure_nic_device(DEVICE(&s->enet), true, NULL); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->enet), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->enet), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_ENET1].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->enet), 0, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_ENET1_MAC_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->enet), 1, + qdev_get_gpio_in(gicdev, FSL_IMX6_ENET1_MAC_1588_IRQ)); + /* SNVS */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) { return; @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: case FSL_IMX8MM_GPT1 ... FSL_IMX8MM_GPT6: case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3: + case FSL_IMX8MM_ENET1: case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4: case FSL_IMX8MM_PCIE1: case FSL_IMX8MM_PCIE_PHY1: @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) } } +static const Property fsl_imx8mm_properties[] = { + DEFINE_PROP_UINT32("fec1-phy-num", FslImx8mmState, phy_num, 0), + DEFINE_PROP_BOOL("fec1-phy-connected", FslImx8mmState, phy_connected, true), +}; + static void fsl_imx8mm_class_init(ObjectClass *oc, const void *data) { DeviceClass *dc = DEVICE_CLASS(oc); + device_class_set_props(dc, fsl_imx8mm_properties); dc->realize = fsl_imx8mm_realize; dc->desc = "i.MX 8MM SoC"; diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx8mm-evk.c +++ b/hw/arm/imx8mm-evk.c @@ -XXX,XX +XXX,XX @@ static void imx8mm_evk_init(MachineState *machine) s = FSL_IMX8MM(object_new_with_props(TYPE_FSL_IMX8MM, OBJECT(machine), "soc", &error_fatal, NULL)); + object_property_set_uint(OBJECT(s), "fec1-phy-num", 1, &error_fatal); sysbus_realize_and_unref(SYS_BUS_DEVICE(s), &error_fatal); memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START, diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" -#include "hw/or-irq.h" +#include "hw/net/imx_fec.h" +#include "hw/core/or-irq.h" #include "hw/pci-host/designware.h" #include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMXI2CState i2c[FSL_IMX8MM_NUM_I2CS]; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; + IMXFECState enet; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; IMX2WdtState wdt[FSL_IMX8MM_NUM_WDTS]; DesignwarePCIEHost pcie; FslImx8mPciePhyState pcie_phy; OrIRQState gpt5_gpt6_irq; + + uint32_t phy_num; + bool phy_connected; }; enum FslImx8mmMemoryRegions { @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_WDOG2_IRQ = 79, FSL_IMX8MM_WDOG3_IRQ = 10, + FSL_IMX8MM_ENET1_MAC_IRQ = 118, + FSL_IMX6_ENET1_MAC_1588_IRQ = 121, + FSL_IMX8MM_PCI_INTA_IRQ = 122, FSL_IMX8MM_PCI_INTB_IRQ = 123, FSL_IMX8MM_PCI_INTC_IRQ = 124, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of USB on iMX8MM Enables testing and debugging of USB drivers Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 27 +++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 6 ++++++ 3 files changed, 34 insertions(+) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM select SDHCI select PCI_EXPRESS_DESIGNWARE select PCI_EXPRESS_FSL_IMX8M_PHY + select USB_DWC3 select WDT_IMX2 config FSL_IMX8MM_EVK diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); } + for (i = 0; i < FSL_IMX8MM_NUM_USBS; i++) { + g_autofree char *name = g_strdup_printf("usb%d", i); + object_initialize_child(obj, name, &s->usb[i], TYPE_USB_DWC3); + } + for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) { g_autofree char *name = g_strdup_printf("spi%d", i + 1); object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(gicdev, usdhc_table[i].irq)); } + /* USBs */ + for (i = 0; i < FSL_IMX8MM_NUM_USBS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } usb_table[FSL_IMX8MM_NUM_USBS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_USB1].addr, FSL_IMX8MM_USB1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_USB2].addr, FSL_IMX8MM_USB2_IRQ }, + }; + + qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "p2", 1); + qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "p3", 1); + qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "slots", 2); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->usb[i]), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, usb_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i].sysbus_xhci), 0, + qdev_get_gpio_in(gicdev, usb_table[i].irq)); + } + /* ECSPIs */ for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_OCRAM: case FSL_IMX8MM_SNVS_HP: case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: + case FSL_IMX8MM_USB1 ... FSL_IMX8MM_USB2: case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3: case FSL_IMX8MM_WDOG1 ... FSL_IMX8MM_WDOG3: /* device implemented and treated above */ diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/sdhci.h" #include "hw/ssi/imx_spi.h" #include "hw/timer/imx_gpt.h" +#include "hw/usb/hcd-dwc3.h" #include "hw/watchdog/wdt_imx2.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_I2CS = 4, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, + FSL_IMX8MM_NUM_USBS = 2, FSL_IMX8MM_NUM_USDHCS = 3, FSL_IMX8MM_NUM_WDTS = 3, }; @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMXFECState enet; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; IMX2WdtState wdt[FSL_IMX8MM_NUM_WDTS]; + USBDWC3 usb[FSL_IMX8MM_NUM_USBS]; DesignwarePCIEHost pcie; FslImx8mPciePhyState pcie_phy; OrIRQState gpt5_gpt6_irq; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_I2C3_IRQ = 37, FSL_IMX8MM_I2C4_IRQ = 38, + FSL_IMX8MM_USB1_IRQ = 40, + FSL_IMX8MM_USB2_IRQ = 41, + FSL_IMX8MM_GPT1_IRQ = 55, FSL_IMX8MM_GPT2_IRQ = 54, FSL_IMX8MM_GPT3_IRQ = 53, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Added script that would validate the iMX8MM emulation by checking the linux console log. If it succeeds, it will return:- ok 1 test_imx8mm_evk.Imx8mmEvkMachine.test_aarch64_imx8mm_evk_usdhc Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Bernhard Beschow <shentey@gmail.com> [PMM: Add missing blank lines that flake8 wants] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 1 + tests/functional/aarch64/meson.build | 2 + tests/functional/aarch64/test_imx8mm_evk.py | 69 +++++++++++++++++++++ 3 files changed, 72 insertions(+) create mode 100755 tests/functional/aarch64/test_imx8mm_evk.py diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/arm/fsl-imx8mm.c F: hw/arm/imx8mm-evk.c F: include/hw/arm/fsl-imx8mm.h F: docs/system/arm/imx8m.rst +F: tests/functional/aarch64/test_imx8mm_evk.py MCIMX8MP-EVK / i.MX8MP M: Bernhard Beschow <shentey@gmail.com> diff --git a/tests/functional/aarch64/meson.build b/tests/functional/aarch64/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/functional/aarch64/meson.build +++ b/tests/functional/aarch64/meson.build @@ -XXX,XX +XXX,XX @@ test_aarch64_timeouts = { 'aspeed_ast2700a2' : 600, 'aspeed_ast2700fc' : 600, 'device_passthrough' : 720, + 'imx8mm_evk' : 240, 'imx8mp_evk' : 240, 'raspi4' : 480, 'reverse_debug' : 180, @@ -XXX,XX +XXX,XX @@ tests_aarch64_system_thorough = [ 'aspeed_ast2700fc', 'device_passthrough', 'hotplug_pci', + 'imx8mm_evk', 'imx8mp_evk', 'kvm', 'multiprocess', diff --git a/tests/functional/aarch64/test_imx8mm_evk.py b/tests/functional/aarch64/test_imx8mm_evk.py new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/functional/aarch64/test_imx8mm_evk.py @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# Functional test that boots a Linux kernel and checks the console +# +# SPDX-License-Identifier: GPL-2.0-or-later + +from qemu_test import LinuxKernelTest, Asset + + +class Imx8mmEvkMachine(LinuxKernelTest): + + ASSET_IMAGE = Asset( + ('https://cloud.debian.org/images/cloud/bookworm/20231210-1590/' + 'debian-12-generic-arm64-20231210-1590.tar.xz'), + '7ebf1577b32d5af6204df74b54ca2e4675de9b5a9fa14f3ff70b88eeb7b3b359') + + KERNEL_OFFSET = 0x51000000 + KERNEL_SIZE = 32622528 + INITRD_OFFSET = 0x76000000 + INITRD_SIZE = 30987766 + DTB_OFFSET = 0x64DB5000 + DTB_SIZE = 36812 + + def extract(self, in_path, out_path, offset, size): + try: + with open(in_path, "rb") as source: + source.seek(offset) + data = source.read(size) + with open(out_path, "wb") as target: + target.write(data) + except (IOError, ValueError) as e: + self.log.error(f"Failed to extract {out_path}: {e}") + raise + + def setUp(self): + super().setUp() + + self.image_path = self.scratch_file("disk.raw") + self.kernel_path = self.scratch_file("linux") + self.initrd_path = self.scratch_file("initrd.zstd") + self.dtb_path = self.scratch_file("imx8mm-evk.dtb") + + self.archive_extract(self.ASSET_IMAGE) + self.extract(self.image_path, self.kernel_path, + self.KERNEL_OFFSET, self.KERNEL_SIZE) + self.extract(self.image_path, self.initrd_path, + self.INITRD_OFFSET, self.INITRD_SIZE) + self.extract(self.image_path, self.dtb_path, + self.DTB_OFFSET, self.DTB_SIZE) + + def test_aarch64_imx8mm_evk_usdhc(self): + self.require_accelerator("tcg") + self.set_machine('imx8mm-evk') + self.vm.set_console(console_index=1) + self.vm.add_args('-m', '2G', + '-smp', '4', + '-kernel', self.kernel_path, + '-initrd', self.initrd_path, + '-dtb', self.dtb_path, + '-append', 'root=/dev/mmcblk2p1', + '-drive', f'file={self.image_path},if=sd,bus=2,' + 'format=raw,id=mmcblk2,snapshot=on') + + self.vm.launch() + self.wait_for_console_pattern('Welcome to ') + + +if __name__ == '__main__': + LinuxKernelTest.main() -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> As mentioned by Richard in [*]: We don't actually need any specific endianness here, because every byte has the same value. So we could simply drop MO_TE. That would produce a store in host-endianness, which will be fractionally more efficient on some hosts. [*] https://lore.kernel.org/qemu-devel/d64d3576-9188-4e74-afdc-3492c9feb8e0@linaro.org/ Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260414005348.4767-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ static uint64_t set_step_tags(CPUARMState *env, uint64_t toaddr, * the page dirty and will use the fast path. */ uint64_t repldata = data * 0x0101010101010101ULL; - MemOpIdx oi16 = make_memop_idx(MO_TE | MO_128, memidx); + MemOpIdx oi16 = make_memop_idx(MO_128, memidx); cpu_st16_mmu(env, toaddr, int128_make128(repldata, repldata), oi16, ra); mte_mops_set_tags(env, toaddr, 16, *mtedesc); return 16; -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Extract the implicit MO_TE definition in order to replace it in the next commit. Mechanical change using: $ for n in UW UL UQ UO SW SL SQ; do \ sed -i -e "s/MO_TE$n/MO_TE | MO_$n/" \ $(git grep -l MO_TE$n target/arm); \ done Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/m_helper.c | 6 +-- target/arm/tcg/mve_helper.c | 79 ++++++++++++++++++++----------------- 2 files changed, 45 insertions(+), 40 deletions(-) diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) /* Note that these stores can throw exceptions on MPU faults */ ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); cpu_stl_mmu(env, sp, nextinst, oi, GETPC()); cpu_stl_mmu(env, sp + 4, saved_psr, oi, GETPC()); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK; uintptr_t ra = GETPC(); ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); assert(env->v7m.secure); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) ARMCPU *cpu = env_archcpu(env); uintptr_t ra = GETPC(); ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); /* fptr is the value of Rn, the frame pointer we load the FP regs from */ diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) } DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t) -DO_VLDR(vldrh, MO_TEUW, 2, uint16_t, ldw, 2, uint16_t) -DO_VLDR(vldrw, MO_TEUL, 4, uint32_t, ldl, 4, uint32_t) +DO_VLDR(vldrh, MO_TE | MO_UW, 2, uint16_t, ldw, 2, uint16_t) +DO_VLDR(vldrw, MO_TE | MO_UL, 4, uint32_t, ldl, 4, uint32_t) DO_VSTR(vstrb, MO_UB, 1, stb, 1, uint8_t) -DO_VSTR(vstrh, MO_TEUW, 2, stw, 2, uint16_t) -DO_VSTR(vstrw, MO_TEUL, 4, stl, 4, uint32_t) +DO_VSTR(vstrh, MO_TE | MO_UW, 2, stw, 2, uint16_t) +DO_VSTR(vstrw, MO_TE | MO_UL, 4, stl, 4, uint32_t) DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t) DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t) DO_VLDR(vldrb_uh, MO_UB, 1, uint8_t, ldb, 2, uint16_t) DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t) -DO_VLDR(vldrh_sw, MO_TESW, 2, int16_t, ldw, 4, int32_t) -DO_VLDR(vldrh_uw, MO_TEUW, 2, uint16_t, ldw, 4, uint32_t) +DO_VLDR(vldrh_sw, MO_TE | MO_SW, 2, int16_t, ldw, 4, int32_t) +DO_VLDR(vldrh_uw, MO_TE | MO_UW, 2, uint16_t, ldw, 4, uint32_t) DO_VSTR(vstrb_h, MO_UB, 1, stb, 2, int16_t) DO_VSTR(vstrb_w, MO_UB, 1, stb, 4, int32_t) -DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) +DO_VSTR(vstrh_w, MO_TE | MO_UW, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_sw, MO_TESW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, MO_TE | MO_SW, int16_t, ldw, 4, + int32_t, uint32_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uh, MO_TEUW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uw, MO_TEUW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrw_sg_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, MO_TE | MO_UW, uint16_t, ldw, 2, + uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, MO_TE | MO_UW, uint16_t, ldw, 4, + uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, MO_TE | MO_UL, uint32_t, ldl, 4, + uint32_t, uint32_t, ADDR_ADD, false) DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, MO_TESW, int16_t, ldw, 4, +DO_VLDR_SG(vldrh_sg_os_sw, MO_TE | MO_SW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uh, MO_TEUW, uint16_t, ldw, 2, +DO_VLDR_SG(vldrh_sg_os_uh, MO_TE | MO_UW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uw, MO_TEUW, uint16_t, ldw, 4, +DO_VLDR_SG(vldrh_sg_os_uw, MO_TE | MO_UW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 4, +DO_VLDR_SG(vldrw_sg_os_uw, MO_TE | MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false) DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false) DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrw_sg_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, false) DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrh_sg_os_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrw_sg_os_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR_SG(vstrh_sg_os_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false) DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR_SG(vldrw_sg_wb_uw, MO_TE | MO_UL, uint32_t, ldl, 4, + uint32_t, uint32_t, ADDR_ADD, true) DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) -DO_VSTR_SG(vstrw_sg_wb_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t *qd; \ int y; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ uint8_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) int e; \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ uint32_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint32_t *qd; \ int y; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ uint8_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) int e; \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ uint32_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + mmu_idx); \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ * beats so we don't care if we update part of the dest and \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) uint16_t mask = mve_element_mask(env); \ unsigned b, e; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + mmu_idx); \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ if (mask & (1 << b)) { \ cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) } DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t) -DO_VLDR(vldrh, MO_TE | MO_UW, 2, uint16_t, ldw, 2, uint16_t) -DO_VLDR(vldrw, MO_TE | MO_UL, 4, uint32_t, ldl, 4, uint32_t) +DO_VLDR(vldrh, MO_UW, 2, uint16_t, ldw, 2, uint16_t) +DO_VLDR(vldrw, MO_UL, 4, uint32_t, ldl, 4, uint32_t) DO_VSTR(vstrb, MO_UB, 1, stb, 1, uint8_t) -DO_VSTR(vstrh, MO_TE | MO_UW, 2, stw, 2, uint16_t) -DO_VSTR(vstrw, MO_TE | MO_UL, 4, stl, 4, uint32_t) +DO_VSTR(vstrh, MO_UW, 2, stw, 2, uint16_t) +DO_VSTR(vstrw, MO_UL, 4, stl, 4, uint32_t) DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t) DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t) DO_VLDR(vldrb_uh, MO_UB, 1, uint8_t, ldb, 2, uint16_t) DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t) -DO_VLDR(vldrh_sw, MO_TE | MO_SW, 2, int16_t, ldw, 4, int32_t) -DO_VLDR(vldrh_uw, MO_TE | MO_UW, 2, uint16_t, ldw, 4, uint32_t) +DO_VLDR(vldrh_sw, MO_SW, 2, int16_t, ldw, 4, int32_t) +DO_VLDR(vldrh_uw, MO_UW, 2, uint16_t, ldw, 4, uint32_t) DO_VSTR(vstrb_h, MO_UB, 1, stb, 2, int16_t) DO_VSTR(vstrb_w, MO_UB, 1, stb, 4, int32_t) -DO_VSTR(vstrh_w, MO_TE | MO_UW, 2, stw, 4, int32_t) +DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 43 +++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 23 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_sw, MO_TE | MO_SW, int16_t, ldw, 4, - int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, MO_SW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uh, MO_TE | MO_UW, uint16_t, ldw, 2, - uint16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uw, MO_TE | MO_UW, uint16_t, ldw, 4, - uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrw_sg_uw, MO_TE | MO_UL, uint32_t, ldl, 4, - uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, MO_UW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, MO_UW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, MO_TE | MO_SW, int16_t, ldw, 4, +DO_VLDR_SG(vldrh_sg_os_sw, MO_SW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uh, MO_TE | MO_UW, uint16_t, ldw, 2, +DO_VLDR_SG(vldrh_sg_os_uh, MO_UW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uw, MO_TE | MO_UW, uint16_t, ldw, 4, +DO_VLDR_SG(vldrh_sg_os_uw, MO_UW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrw_sg_os_uw, MO_TE | MO_UL, uint32_t, ldl, 4, +DO_VLDR_SG(vldrw_sg_os_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false) DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false) DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrw_sg_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, MO_UW, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, MO_UW, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD, false) DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrh_sg_os_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrw_sg_os_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR_SG(vstrh_sg_os_uh, MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false) DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VLDR_SG(vldrw_sg_wb_uw, MO_TE | MO_UL, uint32_t, ldl, 4, - uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR_SG(vldrw_sg_wb_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) -DO_VSTR_SG(vstrw_sg_wb_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Suggested-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 6 ++++++ target/arm/tcg/mve_helper.c | 3 ++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ #include "exec/hwaddr.h" #include "exec/vaddr.h" #include "exec/breakpoint.h" +#include "exec/memop.h" #include "accel/tcg/tb-cpu-state.h" #include "hw/core/registerfields.h" #include "tcg/tcg-gvec-desc.h" @@ -XXX,XX +XXX,XX @@ #define BANK_HYP 6 #define BANK_MON 7 +static inline MemOp mo_endian(CPUARMState *env) +{ + return EX_TBFLAG_ANY(env->hflags, BE_DATA) ? MO_BE : MO_LE; +} + static inline int arm_env_mmu_index(CPUARMState *env) { return EX_TBFLAG_ANY(env->hflags, MMUIDX); diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 47 +++++++++++++++++++++++-------------- 1 file changed, 30 insertions(+), 17 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \ mmu_idx); \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) uint16_t mask = mve_element_mask(env); \ unsigned b, e; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \ mmu_idx); \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ if (mask & (1 << b)) { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \ mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \ mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t *qd; \ int y; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ uint8_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) int e; \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ uint32_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint32_t *qd; \ int y; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ uint8_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) int e; \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ uint32_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/meson.build | 3 ++- target/arm/tcg/mve_helper.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_false: files('stubs32.c')) arm_ss.add(files( 'cpu32.c', 'm_helper.c', - 'mve_helper.c', )) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( @@ -XXX,XX +XXX,XX @@ arm_common_system_ss.add( 'debug.c', 'hflags.c', 'gengvec.c', + 'mve_helper.c', 'neon_helper.c', 'op_helper.c', 'psci.c', @@ -XXX,XX +XXX,XX @@ arm_user_ss.add( 'debug.c', 'gengvec.c', 'hflags.c', + 'mve_helper.c', 'neon_helper.c', 'op_helper.c', 'tlb_helper.c', diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ #include "helper-mve.h" #include "internals.h" #include "vec_internal.h" -#include "accel/tcg/cpu-ldst.h" +#include "accel/tcg/cpu-ldst-common.h" #include "tcg/tcg.h" #include "fpu/softfloat.h" #include "crypto/clmul.h" -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/m_helper.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) /* Note that these stores can throw exceptions on MPU faults */ ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); cpu_stl_mmu(env, sp, nextinst, oi, GETPC()); cpu_stl_mmu(env, sp + 4, saved_psr, oi, GETPC()); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK; uintptr_t ra = GETPC(); ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); assert(env->v7m.secure); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) ARMCPU *cpu = env_archcpu(env); uintptr_t ra = GETPC(); ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); /* fptr is the value of Rn, the frame pointer we load the FP regs from */ -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/m_helper.c | 2 +- target/arm/tcg/meson.build | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "exec/page-protection.h" #ifdef CONFIG_TCG -#include "accel/tcg/cpu-ldst.h" +#include "accel/tcg/cpu-ldst-common.h" #include "semihosting/common-semi.h" #endif #if !defined(CONFIG_USER_ONLY) diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_false: files('stubs32.c')) arm_ss.add(files( 'cpu32.c', - 'm_helper.c', )) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( @@ -XXX,XX +XXX,XX @@ arm_common_system_ss.add( 'debug.c', 'hflags.c', 'gengvec.c', + 'm_helper.c', 'mve_helper.c', 'neon_helper.c', 'op_helper.c', @@ -XXX,XX +XXX,XX @@ arm_user_ss.add( 'debug.c', 'gengvec.c', 'hflags.c', + 'm_helper.c', 'mve_helper.c', 'neon_helper.c', 'op_helper.c', -- 2.43.0 From: Thomas Huth <thuth@redhat.com> When writing to this register, QEMU currently aborts: $ echo "readl 0x10000018" | ./qemu-system-arm -audiodev none,id=snd0 \ -M integratorcp,accel=qtest,audiodev=snd0 -display none -qtest stdio [I 0.000000] OPENED [R +0.001907] readl 0x10000018 qemu: hardware error: integratorcm_read: CM_LMBUSCNT [...] Aborted (core dumped) This is bad, a guest should ideally never be able to kill QEMU like this. Now, according to the "Intergrator/CP User Guide" from: https://developer.arm.com/documentation/dui0159/b/porting-integrator-ap-and-im-pd1/registers "The Integrator/AP CM_LMBUSCNT has been removed." That means this register does not seem to be implemented on real CP boards at all, only for older AP boards. Thus it should be fine if we simply ignore this register in QEMU and handle it like all other unimplemented registers in the "default" handler of the case statement. Resolves: https://gitlab.com/qemu-project/qemu/-/work_items/3407 Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260420064933.64765-1-thuth@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/integratorcp.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/hw/arm/integratorcp.c b/hw/arm/integratorcp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/integratorcp.c +++ b/hw/arm/integratorcp.c @@ -XXX,XX +XXX,XX @@ static uint64_t integratorcm_read(void *opaque, hwaddr offset, } else { return s->cm_lock; } - case 6: /* CM_LMBUSCNT */ - /* ??? High frequency timer. */ - hw_error("integratorcm_read: CM_LMBUSCNT"); case 7: /* CM_AUXOSC */ return s->cm_auxosc; case 8: /* CM_SDRAM */ -- 2.43.0 include/hw/arm/primecell.h used to be more expansive, but now the only thing it defines is the ARM_SYSCTL_GPIO_* constants for the GPIO lines for the arm-sysctl system-control device used on the Realview, Versatile and Versatile Express boards. Replace it with a header file specific to that device. virt.c and vmapple.c included primecell.h despite not using the constants it defined; there we can simply drop the include entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260416172627.690396-1-peter.maydell@linaro.org --- MAINTAINERS | 2 +- hw/arm/realview.c | 2 +- hw/arm/vexpress.c | 2 +- hw/arm/virt.c | 1 - hw/misc/arm_sysctl.c | 2 +- hw/vmapple/vmapple.c | 1 - include/hw/arm/primecell.h | 12 ------------ include/hw/misc/arm_sysctl.h | 16 ++++++++++++++++ 8 files changed, 20 insertions(+), 18 deletions(-) delete mode 100644 include/hw/arm/primecell.h create mode 100644 include/hw/misc/arm_sysctl.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/ssi/pl022.c F: include/hw/ssi/pl022.h F: hw/rtc/pl031.c F: include/hw/rtc/pl031.h -F: include/hw/arm/primecell.h F: hw/timer/cmsdk-apb-timer.c F: include/hw/timer/cmsdk-apb-timer.h F: tests/qtest/cmsdk-apb-timer-test.c @@ -XXX,XX +XXX,XX @@ F: hw/*/versatile* F: hw/i2c/arm_sbcon_i2c.c F: include/hw/i2c/arm_sbcon_i2c.h F: hw/misc/arm_sysctl.c +F: include/hw/misc/arm_sysctl.h F: docs/system/arm/versatile.rst Virt diff --git a/hw/arm/realview.c b/hw/arm/realview.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/realview.c +++ b/hw/arm/realview.c @@ -XXX,XX +XXX,XX @@ #include "target/arm/cpu.h" #include "hw/core/sysbus.h" #include "hw/arm/boot.h" -#include "hw/arm/primecell.h" #include "hw/arm/machines-qom.h" #include "hw/core/split-irq.h" +#include "hw/misc/arm_sysctl.h" #include "hw/net/lan9118.h" #include "hw/net/smc91c111.h" #include "hw/pci/pci.h" diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/vexpress.c +++ b/hw/arm/vexpress.c @@ -XXX,XX +XXX,XX @@ #include "qemu/datadir.h" #include "hw/core/sysbus.h" #include "hw/arm/boot.h" -#include "hw/arm/primecell.h" #include "hw/arm/machines-qom.h" +#include "hw/misc/arm_sysctl.h" #include "hw/net/lan9118.h" #include "hw/i2c/i2c.h" #include "net/net.h" diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ #include "monitor/qdev.h" #include "hw/core/sysbus.h" #include "hw/arm/boot.h" -#include "hw/arm/primecell.h" #include "hw/arm/virt.h" #include "hw/arm/machines-qom.h" #include "hw/block/flash.h" diff --git a/hw/misc/arm_sysctl.c b/hw/misc/arm_sysctl.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/arm_sysctl.c +++ b/hw/misc/arm_sysctl.c @@ -XXX,XX +XXX,XX @@ #include "system/runstate.h" #include "qemu/bitops.h" #include "hw/core/sysbus.h" +#include "hw/misc/arm_sysctl.h" #include "migration/vmstate.h" -#include "hw/arm/primecell.h" #include "qemu/log.h" #include "qemu/module.h" #include "qom/object.h" diff --git a/hw/vmapple/vmapple.c b/hw/vmapple/vmapple.c index XXXXXXX..XXXXXXX 100644 --- a/hw/vmapple/vmapple.c +++ b/hw/vmapple/vmapple.c @@ -XXX,XX +XXX,XX @@ #include "hw/core/sysbus.h" #include "hw/usb/usb.h" #include "hw/arm/boot.h" -#include "hw/arm/primecell.h" #include "hw/char/pl011.h" #include "hw/intc/arm_gic.h" #include "hw/intc/arm_gicv3_common.h" diff --git a/include/hw/arm/primecell.h b/include/hw/arm/primecell.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/hw/arm/primecell.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -#ifndef PRIMECELL_H -#define PRIMECELL_H - -/* Declarations for ARM PrimeCell based periperals. */ -/* Also includes some devices that are currently only used by the - ARM boards. */ - -/* arm_sysctl GPIO lines */ -#define ARM_SYSCTL_GPIO_MMC_WPROT 0 -#define ARM_SYSCTL_GPIO_MMC_CARDIN 1 - -#endif diff --git a/include/hw/misc/arm_sysctl.h b/include/hw/misc/arm_sysctl.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/arm_sysctl.h @@ -XXX,XX +XXX,XX @@ +/* + * Status and system control registers for ARM RealView/Versatile boards. + * + * Copyright (c) Linaro Ltd + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_MISC_ARM_SYSCTL_H +#define HW_MISC_ARM_SYSCTL_H + +/* arm_sysctl inbound GPIO lines */ +#define ARM_SYSCTL_GPIO_MMC_WPROT 0 +#define ARM_SYSCTL_GPIO_MMC_CARDIN 1 + +#endif -- 2.43.0 If we create a normally-AArch64 CPU and configure it with aarch64=off, this will by default leave all the AArch64 ID register values in its ARMISARegisters struct untouched. That in turn means that tests of cpu_isar_feature(aa64_something, cpu) will return true. Until now we have had a design policy that you shouldn't check an aa64_ feature unless you know that the CPU has AArch64; but this is quite fragile as it's easy to forget and only causes a problem in the corner case where AArch64 was turned off. In particular, when we extend the ability to disable AArch64 from only KVM to also TCG there are many more aa64 feature check points which we would otherwise have to audit for whether they needed to be guarded with a check on ARM_FEATURE_AARCH64. Instead, make the CPU realize function zero out all the 64-bit ID registers if a TCG CPU doesn't have AArch64; this will make aa64_ feature tests generally return false. We only do this for TCG because only TCG really needs it, and for KVM it might be confusing to have QEMU's idea of the ID registers be different from KVM's. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260416165353.589569-2-peter.maydell@linaro.org --- target/arm/cpu.c | 35 +++++++++++++++++++++++++++++++++++ target/arm/cpu.h | 3 ++- 2 files changed, 37 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp) } } +static void arm_clear_aarch64_idregs(ARMCPU *cpu) +{ + /* Zero out all the AArch64 ID registers in ARMISARegisters */ + SET_IDREG(&cpu->isar, ID_AA64ISAR0, 0); + SET_IDREG(&cpu->isar, ID_AA64ISAR1, 0); + SET_IDREG(&cpu->isar, ID_AA64ISAR2, 0); + SET_IDREG(&cpu->isar, ID_AA64PFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64PFR1, 0); + SET_IDREG(&cpu->isar, ID_AA64PFR2, 0); + SET_IDREG(&cpu->isar, ID_AA64MMFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64MMFR1, 0); + SET_IDREG(&cpu->isar, ID_AA64MMFR2, 0); + SET_IDREG(&cpu->isar, ID_AA64MMFR3, 0); + SET_IDREG(&cpu->isar, ID_AA64DFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64DFR1, 0); + SET_IDREG(&cpu->isar, ID_AA64AFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64AFR1, 0); + SET_IDREG(&cpu->isar, ID_AA64ZFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64SMFR0, 0); +} + static void arm_cpu_realizefn(DeviceState *dev, Error **errp) { CPUState *cs = CPU(dev); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } #endif + /* + * A TCG aarch64=off CPU has no AArch64 at all, so we clear out the + * ID registers to avoid cpu_isar_feature(aa64_something, cpu) tests + * incorrectly returning true. We don't do this for other accelerators + * (which in practice means "for KVM", since no others have AArch32 + * guest support) because from KVM's point of view the AArch64 ID + * registers still exist and must have their correct values. So we + * avoid clearing them out so that we don't have QEMU and KVM with + * different ideas of the ID registers. + */ + if (tcg_enabled() && !arm_feature(env, ARM_FEATURE_AARCH64)) { + arm_clear_aarch64_idregs(cpu); + } + #ifdef CONFIG_USER_ONLY /* * User mode relies on IC IVAU instructions to catch modification of diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ArchCPU { * Note that if you add an ID register to the ARMISARegisters struct * you need to also update the 32-bit and 64-bit versions of the * kvm_arm_get_host_cpu_features() function to correctly populate the - * field by reading the value from the KVM vCPU. + * field by reading the value from the KVM vCPU. If it is an AArch64 + * ID register then you also must update arm_clear_aarch64_idregs(). */ struct ARMISARegisters { uint32_t mvfr0; -- 2.43.0 Allow the 'aarch64=off' property, which is currently KVM-only, to be set for TCG CPUs also. Note that we don't permit it on the qemu-aarch64 user-mode binary: this makes no sense as that executable can only handle AArch64 syscalls (and it would also assert at startup since it doesn't compile in the A32-specific GDB xml files like arm-neon.xml). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Clément Chigot <chigot@adacore.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260416165353.589569-3-peter.maydell@linaro.org --- docs/system/arm/cpu-features.rst | 10 +++++---- target/arm/cpu-features.h | 5 +++++ target/arm/cpu.c | 36 ++++++++++++++++++++++++++++---- tests/qtest/arm-cpu-features.c | 8 ++----- 4 files changed, 45 insertions(+), 14 deletions(-) diff --git a/docs/system/arm/cpu-features.rst b/docs/system/arm/cpu-features.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/cpu-features.rst +++ b/docs/system/arm/cpu-features.rst @@ -XXX,XX +XXX,XX @@ not implement ARMv8-A, will not have the ``aarch64`` CPU property. QEMU's support may be limited for some CPU features, only partially supporting the feature or only supporting the feature under certain configurations. For example, the ``aarch64`` CPU feature, which, when -disabled, enables the optional AArch32 CPU feature, is only supported -when using the KVM accelerator and when running on a host CPU type that -supports the feature. While ``aarch64`` currently only works with KVM, -it could work with TCG. CPU features that are specific to KVM are +disabled, enables the optional AArch32 CPU feature, can only be set to +``off`` on the TCG and KVM accelerators, and it cannot be set to +``off`` under KVM unless running on a host CPU type that supports +running guests in AArch32. + +CPU features that are inherently specific to KVM are prefixed with "kvm-" and are described in "KVM VCPU Features". CPU Feature Probing diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_aa32_el2(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64PFR0, EL2) >= 2; } +static inline bool isar_feature_aa64_aa32_el3(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64PFR0, EL3) >= 2; +} + static inline bool isar_feature_aa64_ras(const ARMISARegisters *id) { return FIELD_EX64_IDREG(id, ID_AA64PFR0, RAS) != 0; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp) * uniform execution state like do_interrupt. */ if (value == false) { - if (!kvm_enabled() || !kvm_arm_aarch32_supported()) { - error_setg(errp, "'aarch64' feature cannot be disabled " - "unless KVM is enabled and 32-bit EL1 " - "is supported"); + if (kvm_enabled()) { + if (!kvm_arm_aarch32_supported()) { + error_setg(errp, "'aarch64' feature cannot be disabled for KVM " + "because this host does not support 32-bit EL1"); + return; + } + } else if (tcg_enabled()) { +#ifdef CONFIG_USER_ONLY + error_setg(errp, "'aarch64' feature cannot be disabled for " + "usermode emulator qemu-aarch64; use qemu-arm instead"); + return; +#else + bool aa32_at_highest_el; + if (arm_feature(&cpu->env, ARM_FEATURE_EL3)) { + aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el3, cpu); + } else if (arm_feature(&cpu->env, ARM_FEATURE_EL2)) { + aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el2, cpu); + } else { + aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el1, cpu); + } + + if (!aa32_at_highest_el) { + error_setg(errp, "'aarch64' feature cannot be disabled for " + "this TCG CPU because it does not support 32-bit " + "execution at its highest implemented exception " + "level"); + return; + } +#endif + } else { + error_setg(errp, "'aarch64' feature cannot be disabled for " + "this accelerator"); return; } unset_feature(&cpu->env, ARM_FEATURE_AARCH64); diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/arm-cpu-features.c +++ b/tests/qtest/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion(const void *data) sve_tests_default(qts, "max"); pauth_tests_default(qts, "max"); - /* Test that features that depend on KVM generate errors without. */ - assert_error(qts, "max", - "'aarch64' feature cannot be disabled " - "unless KVM is enabled and 32-bit EL1 " - "is supported", - "{ 'aarch64': false }"); + /* TCG allows us to turn off AArch64 on the 'max' CPU type */ + assert_set_feature(qts, "max", "aarch64", false); } qtest_quit(qts); -- 2.43.0 Add a basic test of the TCG 'aarch64=off' functionality; this is the same as our existing arm/test_virt test, but it runs the AArch32 guest kernel on qemu-system-aarch64 with -cpu max,aarch64=off. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260416165353.589569-4-peter.maydell@linaro.org --- tests/functional/aarch64/meson.build | 1 + .../aarch64/test_virt_aarch64_off.py | 37 +++++++++++++++++++ 2 files changed, 38 insertions(+) create mode 100755 tests/functional/aarch64/test_virt_aarch64_off.py diff --git a/tests/functional/aarch64/meson.build b/tests/functional/aarch64/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/functional/aarch64/meson.build +++ b/tests/functional/aarch64/meson.build @@ -XXX,XX +XXX,XX @@ tests_aarch64_system_thorough = [ 'tcg_plugins', 'tuxrun', 'virt', + 'virt_aarch64_off', 'virt_gpu', 'virt_vbsa', 'xen', diff --git a/tests/functional/aarch64/test_virt_aarch64_off.py b/tests/functional/aarch64/test_virt_aarch64_off.py new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/functional/aarch64/test_virt_aarch64_off.py @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# Functional test that boots an AArch32 Linux kernel and checks the console +# on a TCG aarch64 CPU with aarch64=off. This is the same image etc +# as we use in tests/functional/arm/test_virt.py. +# +# SPDX-License-Identifier: GPL-2.0-or-later + +from qemu_test import LinuxKernelTest, Asset + +class ArmVirtMachine(LinuxKernelTest): + + ASSET_KERNEL = Asset( + ('https://archives.fedoraproject.org/pub/archive/fedora/linux/' + 'releases/29/Everything/armhfp/os/images/pxeboot/vmlinuz'), + '18dd5f1a9a28bd539f9d047f7c0677211bae528e8712b40ca5a229a4ad8e2591') + + def test_arm_virt(self): + self.set_machine('virt') + # KVM aarch64=off requires a host CPU that supports it, so + # restrict the test to TCG only + self.require_accelerator('tcg') + self.vm.add_args('-cpu', 'max,aarch64=off') + + kernel_path = self.ASSET_KERNEL.fetch() + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyAMA0') + self.vm.add_args('-kernel', kernel_path, + '-append', kernel_command_line) + self.vm.launch() + console_pattern = 'Kernel command line: %s' % kernel_command_line + self.wait_for_console_pattern(console_pattern) + +if __name__ == '__main__': + LinuxKernelTest.main() -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> We introduce a datatype for a tolerance with respect to a given cpreg migration issue. The tolerance applies to a given cpreg kvm index, and can be of different types: a) mismatch in cpreg indexes - ToleranceNotOnBothEnds (cpreg index is allowed to be only present on one end) - ToleranceOnlySrcTestValue (cpreg index is allowed to be only present in source if its value @mask field matches @value) b) mismatch in cpreg values - ToleranceDiffInMask (value differences are allowed only within a mask) - ToleranceFieldLT (incoming field value must be less than a given value) - ToleranceFieldGT (incoming field value must be greater than a given value) A QLIST of such tolerances can be populated using a new helper: arm_register_cpreg_mig_tolerance() and arm_cpu_match_cpreg_mig_tolerance() allows to check whether a tolerance exists for a given kvm index and its criterion is matched. callers for those helpers will be introduced in subsequent patches. Only registration of migration tolerances related to cpreg index mismatch is currently allowed. Signed-off-by: Eric Auger <eric.auger@redhat.com> Message-id: 20260420140552.104369-2-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 82 ++++++++++++++++++++++++++++++++++++++++++ target/arm/cpu.h | 1 + target/arm/internals.h | 54 ++++++++++++++++++++++++++++ 3 files changed, 137 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, QLIST_INSERT_HEAD(&cpu->el_change_hooks, entry, node); } +static ARMCPRegMigTolerance *find_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx) +{ + ARMCPRegMigTolerance *t; + QLIST_FOREACH(t, &cpu->cpreg_mig_tolerances, node) { + if (t->kvmidx == kvmidx) { + return t; + } + } + return NULL; +} + +void arm_register_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx, + uint64_t mask, uint64_t value, + ARMCPRegMigToleranceType type) +{ + ARMCPRegMigTolerance *entry; + + /* make sure the kvmidx has not tolerance already registered */ + assert(!find_mig_tolerance(cpu, kvmidx)); + + assert(type == ToleranceNotOnBothEnds || + type == ToleranceOnlySrcTestValue); + + entry = g_new0(ARMCPRegMigTolerance, 1); + + entry->kvmidx = kvmidx; + entry->mask = mask; + entry->value = value; + entry->type = type; + + QLIST_INSERT_HEAD(&cpu->cpreg_mig_tolerances, entry, node); +} + +bool arm_cpu_match_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx, + uint64_t vmstate_value, uint64_t local_value, + ARMCPRegMigToleranceType type) +{ + ARMCPRegMigTolerance *t = find_mig_tolerance(cpu, kvmidx); + uint64_t diff, diff_outside_mask, field; + + if (!t || t->type != type) { + return false; + } + + if (type == ToleranceNotOnBothEnds) { + return true; + } + + if (type == ToleranceOnlySrcTestValue && + ((vmstate_value & t->mask) == t->value)) { + return true; + } + + /* Need to check the mask */ + diff = vmstate_value ^ local_value; + diff_outside_mask = diff & ~t->mask; + + if (diff_outside_mask) { + /* there are differences outside of the mask */ + return false; + } + if (type == ToleranceDiffInMask) { + /* differences only in the field, tolerance matched */ + return true; + } + /* need to compare field value against authorized ones */ + field = vmstate_value & t->mask; + if (type == ToleranceFieldLT && (field < t->value)) { + return true; + } + if (type == ToleranceFieldGT && (field > t->value)) { + return true; + } + return false; +} + static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque) { /* Reset a single ARMCPRegInfo register */ @@ -XXX,XX +XXX,XX @@ static void arm_cpu_initfn(Object *obj) QLIST_INIT(&cpu->pre_el_change_hooks); QLIST_INIT(&cpu->el_change_hooks); + QLIST_INIT(&cpu->cpreg_mig_tolerances); #ifdef CONFIG_USER_ONLY # ifdef TARGET_AARCH64 @@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); ARMELChangeHook *hook, *next; + ARMCPRegMigTolerance *t, *n; g_hash_table_destroy(cpu->cp_regs); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj) QLIST_REMOVE(hook, node); g_free(hook); } + QLIST_FOREACH_SAFE(t, &cpu->cpreg_mig_tolerances, node, n) { + QLIST_REMOVE(t, node); + g_free(t); + } #ifndef CONFIG_USER_ONLY if (cpu->pmu_timer) { timer_free(cpu->pmu_timer); diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ArchCPU { QLIST_HEAD(, ARMELChangeHook) pre_el_change_hooks; QLIST_HEAD(, ARMELChangeHook) el_change_hooks; + QLIST_HEAD(, ARMCPRegMigTolerance) cpreg_mig_tolerances; int32_t node_id; /* NUMA node this CPU belongs to */ diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ int compare_u64(const void *a, const void *b); /* Used in FEAT_MEC to set the MECIDWidthm1 field in the MECIDR_EL2 register. */ #define MECID_WIDTH 16 +typedef enum { + ToleranceNotOnBothEnds, + ToleranceOnlySrcTestValue, + ToleranceDiffInMask, + ToleranceFieldLT, + ToleranceFieldGT, +} ARMCPRegMigToleranceType; + +typedef struct ARMCPRegMigTolerance { + uint64_t kvmidx; + uint64_t mask; + uint64_t value; + ARMCPRegMigToleranceType type; + QLIST_ENTRY(ARMCPRegMigTolerance) node; +} ARMCPRegMigTolerance; + +/** + * arm_register_cpreg_mig_tolerance: + * Register a migration tolerance wrt one given cpreg identified by its + * @kvmidx. Calling this function twice for the same @kvmidx is a + * programming error and will cause an assertion failure. + * + * @cpu: vcpu to apply the migration tolerance on + * @kvmidx: kvm index of the cpreg the tolerance applies to + * @mask: bitmask where a difference is tolerated + * (relevant with ToleranceDiffInMask) + * @value: value the bitmask field is compared with + * (relevant with ToleranceFieldLT and ToleranceFieldGT) + * @type: type of the migration tolerance: + * - ToleranceNotOnBothEnds (cpreg index is allowed to be only present + * on one end) + * - ToleranceOnlySrcTestValue (cpreg index is allowed to be only + * present in source if its value @mask field matches @value) + * - ToleranceDiffInMask (mismatch in cpreg values are only tolerated + * if differences are within @mask) + * - ToleranceFieldLT (mismatch in cpreg values are only tolerated + * if incoming @bitmask field value is less than @value) + * - ToleranceFieldGT (mismatch in cpreg values are only tolerated + * if incoming @bitmask field value is greater than @value) + */ +void arm_register_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx, + uint64_t mask, uint64_t value, + ARMCPRegMigToleranceType type); + +/** + * arm_cpu_match_cpreg_mig_tolerance: + * Check whether a tolerance of type @type exists for a given @kvmidx + * and the tolerance criterion is satisfied + */ +bool arm_cpu_match_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx, + uint64_t vmstate_value, uint64_t local_value, + ARMCPRegMigToleranceType type); + + #endif -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> If there is a mismatch between the cpreg indexes found on both ends, check whether a tolerance was registered for the given kvmidx. If any, silence warning/errors. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-3-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/machine.c | 21 +++++++++++++++------ target/arm/trace-events | 2 ++ 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static void handle_cpreg_missing_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx { g_autofree gchar *name = print_register_name(kvmidx); + if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx, + 0, 0, ToleranceNotOnBothEnds)) { + trace_tolerate_cpreg_missing_in_incoming_stream(name); + return; + } warn_report("%s: %s " "expected by the destination but not in the incoming stream: " "skip it", __func__, name); } /* - * Handle the situation where @kvmidx is in the incoming stream - * but not on destination. This currently fails the migration but - * we plan to accomodate some exceptions, hence the boolean returned value. + * Handle the situation where @kvmidx is in the incoming + * stream but not on destination. This fails the migration if + * no cpreg mig tolerance is matched for this @kvmidx + * Return true if the migration should eventually fail */ static bool handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx) { g_autofree gchar *name = print_register_name(kvmidx); - bool fail = true; + if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx, + 0, 0, ToleranceNotOnBothEnds)) { + trace_tolerate_cpreg_only_in_incoming_stream(name); + return false; + } error_report("%s: %s in the incoming stream but unknown on the " "destination: fail migration", __func__, name); - - return fail; + return true; } static int cpu_post_load(void *opaque, int version_id) diff --git a/target/arm/trace-events b/target/arm/trace-events index XXXXXXX..XXXXXXX 100644 --- a/target/arm/trace-events +++ b/target/arm/trace-events @@ -XXX,XX +XXX,XX @@ arm_psci_call(uint64_t x0, uint64_t x1, uint64_t x2, uint64_t x3, uint32_t cpuid # machine.c cpu_post_load(uint32_t cpreg_vmstate_array_len, uint32_t cpreg_array_len) "cpreg_vmstate_array_len=%d cpreg_array_len=%d" +tolerate_cpreg_missing_in_incoming_stream(char *name) "%s is missing in incoming stream but this is explicitly tolerated" +tolerate_cpreg_only_in_incoming_stream(char *name) "%s is in incoming stream but not on destination but this is explicitly tolerated" -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> Pass the value of the incoming register to handle_cpreg_only_in_incoming_stream and check whether there is a matching ToleranceOnlySrcTestValue tolerance. Signed-off-by: Eric Auger <eric.auger@redhat.com> Message-id: 20260420140552.104369-4-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/machine.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static void handle_cpreg_missing_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx * no cpreg mig tolerance is matched for this @kvmidx * Return true if the migration should eventually fail */ -static bool handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx) +static bool +handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx, uint64_t value) { g_autofree gchar *name = print_register_name(kvmidx); if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx, - 0, 0, ToleranceNotOnBothEnds)) { + 0, 0, ToleranceNotOnBothEnds) || + arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx, + value, 0, ToleranceOnlySrcTestValue)) { trace_tolerate_cpreg_only_in_incoming_stream(name); return false; } @@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id) } if (cpu->cpreg_vmstate_indexes[v] < cpu->cpreg_indexes[i]) { fail = handle_cpreg_only_in_incoming_stream(cpu, - cpu->cpreg_vmstate_indexes[v++]); + cpu->cpreg_vmstate_indexes[v], + cpu->cpreg_vmstate_values[v]); + v++; continue; } /* matching register, copy the value over */ @@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id) */ for ( ; v < cpu->cpreg_vmstate_array_len; v++) { fail = handle_cpreg_only_in_incoming_stream(cpu, - cpu->cpreg_vmstate_indexes[v]); + cpu->cpreg_vmstate_indexes[v], + cpu->cpreg_vmstate_values[v]); } if (fail) { return -1; -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> Before linux v6.13 those registers were erroneously unconditionally exposed and this was fixed by commits: - 0fcb4eea5345 ("KVM: arm64: Hide TCR2_EL1 from userspace when disabled for guests") - a68cddbe47ef ("KVM: arm64: Hide S1PIE registers from userspace when disabled for guests") in v6.13. This means if we migrate from an old kernel host to a >= 6.13 kernel host, migration currently fails. Declare cpreg migration tolerance for those registers. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Sebastian Ott <sebott@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-5-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) define_cortex_a72_a57_a53_cp_reginfo(cpu); } +#if defined(CONFIG_KVM) +static void kvm_arm_set_cpreg_mig_tolerances(ARMCPU *cpu) +{ + /* + * Registers that may be in the incoming stream and not exposed + * on the destination + */ + + /* + * TCR_EL1 was erroneously unconditionnally exposed before linux v6.13. + * See commit 0fcb4eea5345 ("KVM: arm64: Hide TCR2_EL1 from userspace + * when disabled for guests") + */ + arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 2, 0, 3), + 0, 0, ToleranceNotOnBothEnds); + /* + * PIRE0_EL1 and PIR_EL1 were erroneously unconditionnally exposed + * before linux v6.13. See commit a68cddbe47ef ("KVM: arm64: Hide + * S1PIE registers from userspace when disabled for guests") + */ + arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 2), + 0, 0, ToleranceNotOnBothEnds); + arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 3), + 0, 0, ToleranceNotOnBothEnds); +} +#endif + static void aarch64_host_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); @@ -XXX,XX +XXX,XX @@ static void aarch64_host_initfn(Object *obj) #endif #if defined(CONFIG_KVM) + kvm_arm_set_cpreg_mig_tolerances(cpu); kvm_arm_set_cpu_features_from_host(cpu); aarch64_add_sve_properties(obj); #elif defined(CONFIG_HVF) -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> KVM_REG_ARM_VENDOR_HYP_BMAP_2 pseudo FW register is exposed from v6.15 onwards. Backward migration from a >= v6.15 to an older kernel would fail without cpreg migration tolerance definition for this register. If the register is present on source but not on destination, its value must be checked to make sure it matches the reset value, ie. 0, meaning no service is exposed to the guest, hence the choice of a ToleranceOnlySrcTestValue migration tolerance. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-6-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_set_cpreg_mig_tolerances(ARMCPU *cpu) 0, 0, ToleranceNotOnBothEnds); arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 3), 0, 0, ToleranceNotOnBothEnds); + + /* + * KVM_REG_ARM_VENDOR_HYP_BMAP_2 pseudo FW register is exposed + * from v6.15 onwards. Backward migration from a >= v6.15 to an older + * kernel would fail without cpreg migration tolerance definition. + * If the register is present on source but not on destination, make + * sure it has its reset value, ie. 0, meaning no service is exposed + * to the guest. + */ + arm_register_cpreg_mig_tolerance(cpu, KVM_REG_ARM_FW_FEAT_BMAP_REG(3), + UINT64_MAX, 0, ToleranceOnlySrcTestValue); } #endif -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> We want to remove AArch32 DBGDTRTX which was erroneously exposed. This was attempted by 655659a74a36b ("target/arm: Correct encoding of Debug Communications Channel registers") but it was discovered that the removal of this debug register broke forward migration on TCG. Now we have the cpreg migration tolerance infrastructure, we can declare one for the DBGDTRTX. This allow to revert the reinstate patch. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Sebastian Ott <sebott@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-7-eric.auger@redhat.com [PMM: revised comment, included note about when we can drop the workaround] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .fgt = FGT_CLIDR_EL1, .resetvalue = GET_IDREG(isar, CLIDR) }; + uint64_t dbgtr_el0_kvmidx = + cpreg_to_kvm_id(ENCODE_CP_REG(14, 0, 1, 0, 5, 3, 0)); + define_one_arm_cp_reg(cpu, &clidr); define_arm_cp_regs(cpu, v7_cp_reginfo); define_debug_regs(cpu); + /* + * We used to incorrectly expose a non-existent AArch32 "DBGDTRTX" + * register with this encoding. This has been fixed by commit + * 655659a74a36 ("target/arm: Correct encoding of Debug + * Communications Channel registers") by the introduction of correct + * separate cpreg definitions for AA64 and AA32 versions. However, + * the old cpreg definition couldn't be removed without breaking + * migration, so commit 4f2b82f604 reinstated the bogus encoding + * for migration data only. + * + * Now that we have migration tolerance infrastructure, we can use + * this to allow forward migration from the buggy QEMU versions, + * accepting and ignoring the bogus register if it is in the + * source data. QEMU 11.0 was the last version that sent the + * bogus encoding, so this workaround can be removed at the point + * where we no longer care about migration from that version + * (i.e. when we remove the "virt-11.0" machine type). + */ + arm_register_cpreg_mig_tolerance(cpu, dbgtr_el0_kvmidx, + 0, 0, ToleranceNotOnBothEnds); } else { define_arm_cp_regs(cpu, not_v7_cp_reginfo); } -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> This reverts commit 4f2b82f60431 ("target/arm: Reinstate bogus AArch32 DBGDTRTX register for migration compat). We don't need that commit anymore as the AArch32 DBGDTRTX register is declared to be safe to ignore in the incoming migration stream. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Sebastian Ott <sebott@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-8-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/debug_helper.c | 29 ----------------------------- 1 file changed, 29 deletions(-) diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/debug_helper.c +++ b/target/arm/debug_helper.c @@ -XXX,XX +XXX,XX @@ static void dbgclaimclr_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.dbgclaim &= ~(value & 0xFF); } -static CPAccessResult access_bogus(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) -{ - /* Always UNDEF, as if this cpreg didn't exist */ - return CP_ACCESS_UNDEFINED; -} - static const ARMCPRegInfo debug_cp_reginfo[] = { /* * DBGDRAR, DBGDSAR: always RAZ since we don't implement memory mapped @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo debug_cp_reginfo[] = { .opc0 = 2, .opc1 = 3, .crn = 0, .crm = 4, .opc2 = 0, .access = PL0_RW, .accessfn = access_tdcc, .type = ARM_CP_CONST, .resetvalue = 0 }, - /* - * This is not a real AArch32 register. We used to incorrectly expose - * this due to a QEMU bug; to avoid breaking migration compatibility we - * need to continue to provide it so that we don't fail the inbound - * migration when it tells us about a sysreg that we don't have. - * We set an always-fails .accessfn, which means that the guest doesn't - * actually see this register (it will always UNDEF, identically to if - * there were no cpreg definition for it other than that we won't print - * a LOG_UNIMP message about it), and we set the ARM_CP_NO_GDB flag so the - * gdbstub won't see it either. - * (We can't just set .access = 0, because add_cpreg_to_hashtable() - * helpfully ignores cpregs which aren't accessible to the highest - * implemented EL.) - * - * TODO: implement a system for being able to describe "this register - * can be ignored if it appears in the inbound stream"; then we can - * remove this temporary hack. - */ - { .name = "BOGUS_DBGDTR_EL0", .state = ARM_CP_STATE_AA32, - .cp = 14, .opc1 = 3, .crn = 0, .crm = 5, .opc2 = 0, - .access = PL0_RW, .accessfn = access_bogus, - .type = ARM_CP_CONST | ARM_CP_NO_GDB, .resetvalue = 0 }, /* * OSECCR_EL1 provides a mechanism for an operating system * to access the contents of EDECCR. EDECCR is not implemented though, -- 2.43.0 From: Osama Abdelkader <osama.abdelkader@gmail.com> fdt_node_offset_by_compatible(fdt, -1, compat) only finds the first match. If the blob has more than one node with the same compatible string, extra nodes will remain active. Remove all the matching nodes, using the same loop as imx8mp-evk.c does for this purpose. Signed-off-by: Osama Abdelkader <osama.abdelkader@gmail.com> Message-id: 20260420162114.308519-1-osama.abdelkader@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/raspi4b.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/hw/arm/raspi4b.c b/hw/arm/raspi4b.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/raspi4b.c +++ b/hw/arm/raspi4b.c @@ -XXX,XX +XXX,XX @@ static void raspi4_modify_dtb(const struct arm_boot_info *info, void *fdt) for (int i = 0; i < ARRAY_SIZE(nodes_to_remove); i++) { const char *dev_str = nodes_to_remove[i]; + int offset; - int offset = fdt_node_offset_by_compatible(fdt, -1, dev_str); - if (offset >= 0) { - if (!fdt_nop_node(fdt, offset)) { - warn_report("bcm2711 dtc: %s has been disabled!", dev_str); + offset = fdt_node_offset_by_compatible(fdt, -1, dev_str); + while (offset >= 0) { + if (fdt_nop_node(fdt, offset) == 0) { + warn_report("bcm2711 dtb: %s has been disabled!", dev_str); } + offset = fdt_node_offset_by_compatible(fdt, offset, dev_str); } } -- 2.43.0 From: Yucai Liu <1486344514@qq.com> Implement a basic i.MX6UL LCDIF controller model with MMIO registers, frame-done interrupt behavior, and framebuffer-backed display updates for RGB565 and XRGB8888 input formats. Place the LCDIF device under hw/display and build it via a dedicated CONFIG_IMX6UL_LCDIF symbol. Model register fields with registerfields.h helpers and provide migration support via vmstate. Signed-off-by: Yucai Liu <1486344514@qq.com> Message-id: 20260412110240.93116-2-yangyanglan718@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 2 + hw/display/Kconfig | 4 + hw/display/imx6ul_lcdif.c | 453 ++++++++++++++++++++++++++++++ hw/display/meson.build | 1 + include/hw/display/imx6ul_lcdif.h | 37 +++ 5 files changed, 497 insertions(+) create mode 100644 hw/display/imx6ul_lcdif.c create mode 100644 include/hw/display/imx6ul_lcdif.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Odd Fixes F: hw/arm/mcimx6ul-evk.c F: hw/arm/fsl-imx6ul.c +F: hw/display/imx6ul_lcdif.c F: hw/misc/imx6ul_ccm.c F: include/hw/arm/fsl-imx6ul.h +F: include/hw/display/imx6ul_lcdif.h F: include/hw/misc/imx6ul_ccm.h F: docs/system/arm/mcimx6ul-evk.rst diff --git a/hw/display/Kconfig b/hw/display/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/display/Kconfig +++ b/hw/display/Kconfig @@ -XXX,XX +XXX,XX @@ config PL110 bool select FRAMEBUFFER +config IMX6UL_LCDIF + bool + select FRAMEBUFFER + config SII9022 bool depends on I2C diff --git a/hw/display/imx6ul_lcdif.c b/hw/display/imx6ul_lcdif.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/display/imx6ul_lcdif.c @@ -XXX,XX +XXX,XX @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * + * i.MX6UL LCDIF controller + * + * Copyright (c) 2026 Yucai Liu <1486344514@qq.com> + */ + +#include "qemu/osdep.h" +#include "hw/display/imx6ul_lcdif.h" +#include "hw/core/irq.h" +#include "hw/core/registerfields.h" +#include "hw/display/framebuffer.h" +#include "migration/vmstate.h" +#include "system/address-spaces.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "ui/pixel_ops.h" + +#define LCDIF_MMIO_SIZE (16 * KiB) +#define LCDIF_RESET_CTRL1 0x000f0000 + +REG32(CTRL, 0x00) + FIELD(CTRL, RUN, 0, 1) + FIELD(CTRL, WORD_LENGTH, 8, 2) +REG32(CTRL1, 0x10) + FIELD(CTRL1, CUR_FRAME_DONE_IRQ, 9, 1) + FIELD(CTRL1, CUR_FRAME_DONE_IRQ_EN, 13, 1) + FIELD(CTRL1, BYTE_PACKING_FORMAT, 16, 4) +REG32(V4_TRANSFER_COUNT, 0x30) + FIELD(V4_TRANSFER_COUNT, H_COUNT, 0, 16) + FIELD(V4_TRANSFER_COUNT, V_COUNT, 16, 16) +REG32(V4_CUR_BUF, 0x40) +REG32(V4_NEXT_BUF, 0x50) +REG32(AS_NEXT_BUF, 0x230) + +#define REG_SET 0x4 +#define REG_CLR 0x8 +#define REG_TOG 0xc + +#define CTRL_WORD_LENGTH_16 0 +#define CTRL_WORD_LENGTH_24 3 + +#define FRAME_PERIOD_NS (16 * 1000 * 1000ULL) + +enum IMX6ULLCDIFReg { + IMX6UL_LCDIF_REG_CTRL = A_CTRL >> 4, + IMX6UL_LCDIF_REG_CTRL1 = A_CTRL1 >> 4, + IMX6UL_LCDIF_REG_V4_TRANSFER_COUNT = A_V4_TRANSFER_COUNT >> 4, + IMX6UL_LCDIF_REG_V4_CUR_BUF = A_V4_CUR_BUF >> 4, + IMX6UL_LCDIF_REG_V4_NEXT_BUF = A_V4_NEXT_BUF >> 4, + IMX6UL_LCDIF_REG_AS_NEXT_BUF = A_AS_NEXT_BUF >> 4, +}; + +static inline bool imx6ul_lcdif_reg_exists(hwaddr reg) +{ + return (reg >> 4) < IMX6UL_LCDIF_REGS_NUM; +} + +static inline bool imx6ul_lcdif_reg_has_setclr(hwaddr reg) +{ + switch (reg) { + case A_CTRL: + case A_CTRL1: + return true; + default: + return false; + } +} + +static inline bool imx6ul_lcdif_is_running(IMX6ULLCDIFState *s) +{ + uint32_t ctrl = s->regs[IMX6UL_LCDIF_REG_CTRL]; + + return FIELD_EX32(ctrl, CTRL, RUN); +} + +static inline bool imx6ul_lcdif_frame_done_pending(IMX6ULLCDIFState *s) +{ + uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1]; + + return FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ); +} + +static void imx6ul_lcdif_schedule_frame(IMX6ULLCDIFState *s) +{ + int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + timer_mod(s->frame_timer, now + FRAME_PERIOD_NS); +} + +static void imx6ul_lcdif_maybe_schedule_frame(IMX6ULLCDIFState *s) +{ + if (imx6ul_lcdif_is_running(s) && !imx6ul_lcdif_frame_done_pending(s)) { + imx6ul_lcdif_schedule_frame(s); + } else { + timer_del(s->frame_timer); + } +} + +static void imx6ul_lcdif_update_irq(IMX6ULLCDIFState *s) +{ + uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1]; + bool level = FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ_EN) && + FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ); + + qemu_set_irq(s->irq, level); +} + +static void imx6ul_lcdif_frame_done(IMX6ULLCDIFState *s) +{ + uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1]; + + ctrl1 = FIELD_DP32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ, 1); + s->regs[IMX6UL_LCDIF_REG_CTRL1] = ctrl1; + imx6ul_lcdif_update_irq(s); +} + +static void imx6ul_lcdif_draw_line_rgb565(void *opaque, uint8_t *dst, + const uint8_t *src, int width, + int dststep) +{ + uint32_t *dst32 = (uint32_t *)dst; + int i; + + for (i = 0; i < width; i++) { + uint16_t pixel = lduw_le_p(src); + uint8_t r = ((pixel >> 11) & 0x1f) << 3; + uint8_t g = ((pixel >> 5) & 0x3f) << 2; + uint8_t b = (pixel & 0x1f) << 3; + + *dst32++ = rgb_to_pixel32(r, g, b); + src += 2; + } +} + +static void imx6ul_lcdif_draw_line_xrgb8888(void *opaque, uint8_t *dst, + const uint8_t *src, int width, + int dststep) +{ + uint32_t *dst32 = (uint32_t *)dst; + int i; + + for (i = 0; i < width; i++) { + uint32_t pixel = ldl_le_p(src); + uint8_t r = (pixel >> 16) & 0xff; + uint8_t g = (pixel >> 8) & 0xff; + uint8_t b = pixel & 0xff; + + *dst32++ = rgb_to_pixel32(r, g, b); + src += 4; + } +} + +static void imx6ul_lcdif_update_display(void *opaque) +{ + IMX6ULLCDIFState *s = opaque; + DisplaySurface *surface = qemu_console_surface(s->con); + uint32_t transfer_count = s->regs[IMX6UL_LCDIF_REG_V4_TRANSFER_COUNT]; + uint32_t width = FIELD_EX32(transfer_count, V4_TRANSFER_COUNT, H_COUNT); + uint32_t height = FIELD_EX32(transfer_count, V4_TRANSFER_COUNT, V_COUNT); + uint32_t ctrl = s->regs[IMX6UL_LCDIF_REG_CTRL]; + uint32_t frame_base = s->regs[IMX6UL_LCDIF_REG_V4_CUR_BUF]; + drawfn fn; + int first = 0; + int last = 0; + int src_width; + + if (!imx6ul_lcdif_is_running(s) || width == 0 || height == 0) { + return; + } + + switch (FIELD_EX32(ctrl, CTRL, WORD_LENGTH)) { + case CTRL_WORD_LENGTH_16: + s->src_bpp = 2; + fn = imx6ul_lcdif_draw_line_rgb565; + break; + case CTRL_WORD_LENGTH_24: + s->src_bpp = 4; + fn = imx6ul_lcdif_draw_line_xrgb8888; + break; + default: + return; + } + + if (surface_width(surface) != width || surface_height(surface) != height) { + qemu_console_resize(s->con, width, height); + surface = qemu_console_surface(s->con); + s->invalidate = true; + } + + src_width = width * s->src_bpp; + if (s->invalidate || s->fb_base != frame_base || + s->src_width != src_width || s->rows != height) { + framebuffer_update_memory_section(&s->fbsection, get_system_memory(), + frame_base, height, src_width); + s->fb_base = frame_base; + s->src_width = src_width; + s->rows = height; + } + + framebuffer_update_display(surface, &s->fbsection, width, height, + src_width, surface_stride(surface), 0, + s->invalidate, fn, s, &first, &last); + if (first >= 0) { + dpy_gfx_update(s->con, 0, first, width, last - first + 1); + } + + s->invalidate = false; +} + +static void imx6ul_lcdif_invalidate_display(void *opaque) +{ + IMX6ULLCDIFState *s = opaque; + + s->invalidate = true; +} + +static const GraphicHwOps imx6ul_lcdif_graphic_ops = { + .invalidate = imx6ul_lcdif_invalidate_display, + .gfx_update = imx6ul_lcdif_update_display, +}; + +static void imx6ul_lcdif_frame_timer_cb(void *opaque) +{ + IMX6ULLCDIFState *s = opaque; + + if (!imx6ul_lcdif_is_running(s) || imx6ul_lcdif_frame_done_pending(s)) { + return; + } + + imx6ul_lcdif_frame_done(s); +} + +static uint64_t imx6ul_lcdif_read(void *opaque, hwaddr offset, unsigned size) +{ + IMX6ULLCDIFState *s = opaque; + hwaddr reg = offset & ~0xf; + uint32_t idx; + + assert(size == 4); + assert(!(offset & 0x3)); + assert(offset < LCDIF_MMIO_SIZE); + + idx = reg >> 4; + if (idx >= ARRAY_SIZE(s->regs)) { + return 0; + } + + return s->regs[idx]; +} + +static void imx6ul_lcdif_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + IMX6ULLCDIFState *s = opaque; + hwaddr reg = offset & ~0xf; + uint32_t idx; + uint32_t oldv; + + assert(size == 4); + assert(!(offset & 0x3)); + assert(offset < LCDIF_MMIO_SIZE); + + if (!imx6ul_lcdif_reg_exists(reg)) { + return; + } + + idx = reg >> 4; + oldv = s->regs[idx]; + + switch (offset & 0xf) { + case 0: + s->regs[idx] = (uint32_t)value; + break; + case REG_SET: + if (!imx6ul_lcdif_reg_has_setclr(reg)) { + return; + } + s->regs[idx] = oldv | (uint32_t)value; + break; + case REG_CLR: + if (!imx6ul_lcdif_reg_has_setclr(reg)) { + return; + } + s->regs[idx] = oldv & ~(uint32_t)value; + break; + case REG_TOG: + if (!imx6ul_lcdif_reg_has_setclr(reg)) { + return; + } + s->regs[idx] = oldv ^ (uint32_t)value; + break; + default: + g_assert_not_reached(); + } + + switch (reg) { + case A_CTRL: + if (!FIELD_EX32(oldv, CTRL, RUN) && + FIELD_EX32(s->regs[idx], CTRL, RUN)) { + s->invalidate = true; + graphic_hw_invalidate(s->con); + imx6ul_lcdif_maybe_schedule_frame(s); + break; + } + if (FIELD_EX32(oldv, CTRL, RUN) && + !FIELD_EX32(s->regs[idx], CTRL, RUN)) { + timer_del(s->frame_timer); + } + break; + case A_CTRL1: + if (FIELD_EX32(oldv, CTRL1, CUR_FRAME_DONE_IRQ) && + !FIELD_EX32(s->regs[idx], CTRL1, CUR_FRAME_DONE_IRQ)) { + imx6ul_lcdif_maybe_schedule_frame(s); + } + break; + case A_V4_TRANSFER_COUNT: + s->invalidate = true; + graphic_hw_invalidate(s->con); + break; + case A_V4_CUR_BUF: + s->invalidate = true; + graphic_hw_invalidate(s->con); + break; + case A_V4_NEXT_BUF: + s->regs[IMX6UL_LCDIF_REG_V4_CUR_BUF] = s->regs[idx]; + imx6ul_lcdif_frame_done(s); + s->invalidate = true; + graphic_hw_invalidate(s->con); + imx6ul_lcdif_maybe_schedule_frame(s); + return; + case A_AS_NEXT_BUF: + imx6ul_lcdif_frame_done(s); + imx6ul_lcdif_maybe_schedule_frame(s); + return; + default: + break; + } + + imx6ul_lcdif_update_irq(s); +} + +static const MemoryRegionOps imx6ul_lcdif_ops = { + .read = imx6ul_lcdif_read, + .write = imx6ul_lcdif_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void imx6ul_lcdif_reset(DeviceState *dev) +{ + IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev); + + memset(s->regs, 0, sizeof(s->regs)); + s->regs[IMX6UL_LCDIF_REG_CTRL1] = LCDIF_RESET_CTRL1; + s->fb_base = 0; + s->src_width = 0; + s->rows = 0; + s->src_bpp = 0; + s->invalidate = true; + timer_del(s->frame_timer); + imx6ul_lcdif_update_irq(s); +} + +static int imx6ul_lcdif_post_load(void *opaque, int version_id) +{ + IMX6ULLCDIFState *s = opaque; + + s->fb_base = 0; + s->src_width = 0; + s->rows = 0; + s->src_bpp = 0; + s->invalidate = true; + + imx6ul_lcdif_update_irq(s); + if (imx6ul_lcdif_is_running(s) && + !imx6ul_lcdif_frame_done_pending(s) && + !timer_pending(s->frame_timer)) { + imx6ul_lcdif_schedule_frame(s); + } + + return 0; +} + +static const VMStateDescription vmstate_imx6ul_lcdif = { + .name = TYPE_IMX6UL_LCDIF, + .version_id = 1, + .minimum_version_id = 1, + .post_load = imx6ul_lcdif_post_load, + .fields = (const VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, IMX6ULLCDIFState, IMX6UL_LCDIF_REGS_NUM), + VMSTATE_TIMER_PTR(frame_timer, IMX6ULLCDIFState), + VMSTATE_END_OF_LIST() + }, +}; + +static void imx6ul_lcdif_realize(DeviceState *dev, Error **errp) +{ + IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev); + + s->frame_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, + imx6ul_lcdif_frame_timer_cb, s); + s->invalidate = true; + memory_region_init_io(&s->iomem, OBJECT(dev), &imx6ul_lcdif_ops, s, + TYPE_IMX6UL_LCDIF, LCDIF_MMIO_SIZE); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq); + s->con = graphic_console_init(dev, 0, &imx6ul_lcdif_graphic_ops, s); +} + +static void imx6ul_lcdif_unrealize(DeviceState *dev) +{ + IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev); + + timer_del(s->frame_timer); + timer_free(s->frame_timer); + s->frame_timer = NULL; + + if (s->con) { + graphic_console_close(s->con); + s->con = NULL; + } +} + +static void imx6ul_lcdif_class_init(ObjectClass *klass, const void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = imx6ul_lcdif_realize; + dc->unrealize = imx6ul_lcdif_unrealize; + dc->vmsd = &vmstate_imx6ul_lcdif; + device_class_set_legacy_reset(dc, imx6ul_lcdif_reset); + dc->desc = "i.MX6UL LCDIF"; +} + +static const TypeInfo imx6ul_lcdif_info = { + .name = TYPE_IMX6UL_LCDIF, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(IMX6ULLCDIFState), + .class_init = imx6ul_lcdif_class_init, +}; + +static void imx6ul_lcdif_register_types(void) +{ + type_register_static(&imx6ul_lcdif_info); +} + +type_init(imx6ul_lcdif_register_types) diff --git a/hw/display/meson.build b/hw/display/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: ['CONFIG_VGA_CIRRUS', 'CONFIG_VGA_ISA'], if_true: files('cir system_ss.add(when: 'CONFIG_G364FB', if_true: files('g364fb.c')) system_ss.add(when: 'CONFIG_JAZZ_LED', if_true: files('jazz_led.c')) system_ss.add(when: 'CONFIG_PL110', if_true: files('pl110.c')) +system_ss.add(when: 'CONFIG_IMX6UL_LCDIF', if_true: files('imx6ul_lcdif.c')) system_ss.add(when: 'CONFIG_SII9022', if_true: files('sii9022.c')) system_ss.add(when: 'CONFIG_SSD0303', if_true: files('ssd0303.c')) system_ss.add(when: 'CONFIG_SSD0323', if_true: files('ssd0323.c')) diff --git a/include/hw/display/imx6ul_lcdif.h b/include/hw/display/imx6ul_lcdif.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/display/imx6ul_lcdif.h @@ -XXX,XX +XXX,XX @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * + * i.MX6UL LCDIF controller + * + * Copyright (c) 2026 Yucai Liu <1486344514@qq.com> + */ + +#ifndef IMX6UL_LCDIF_H +#define IMX6UL_LCDIF_H + +#include "hw/core/sysbus.h" +#include "qom/object.h" +#include "qemu/timer.h" +#include "ui/console.h" + +#define TYPE_IMX6UL_LCDIF "imx6ul-lcdif" +#define IMX6UL_LCDIF_REGS_NUM ((0x230 >> 4) + 1) +OBJECT_DECLARE_SIMPLE_TYPE(IMX6ULLCDIFState, IMX6UL_LCDIF) + +struct IMX6ULLCDIFState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + MemoryRegionSection fbsection; + qemu_irq irq; + QemuConsole *con; + QEMUTimer *frame_timer; + uint32_t fb_base; + uint32_t src_width; + uint32_t rows; + uint8_t src_bpp; + bool invalidate; + uint32_t regs[IMX6UL_LCDIF_REGS_NUM]; +}; + +#endif /* IMX6UL_LCDIF_H */ -- 2.43.0 From: Yucai Liu <1486344514@qq.com> Instantiate LCDIF as a child object of the i.MX6UL SoC in init and realize it in the SoC realize path before MMIO/IRQ hookup. Also make FSL_IMX6UL select CONFIG_IMX6UL_LCDIF and map the LCDIF region with a 16 KiB size to match the SoC memory map. Signed-off-by: Yucai Liu <1486344514@qq.com> Message-id: 20260412110240.93116-3-yangyanglan718@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx6ul.c | 12 ++++++++++-- include/hw/arm/fsl-imx6ul.h | 4 +++- 3 files changed, 14 insertions(+), 3 deletions(-) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX6UL imply I2C_DEVICES select A15MPCORE select IMX + select IMX6UL_LCDIF select IMX_FEC select IMX_I2C select IMX_USBPHY diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx6ul.h" +#include "hw/display/imx6ul_lcdif.h" #include "hw/misc/unimp.h" #include "hw/usb/imx-usb-phy.h" #include "hw/core/boards.h" @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) object_initialize_child(obj, name, &s->usb[i], TYPE_CHIPIDEA); } + /* + * LCDIF + */ + object_initialize_child(obj, "lcdif", &s->lcdif, TYPE_IMX6UL_LCDIF); + /* * SDHCIs */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) /* * LCD */ - create_unimplemented_device("lcdif", FSL_IMX6UL_LCDIF_ADDR, - FSL_IMX6UL_LCDIF_SIZE); + sysbus_realize(SYS_BUS_DEVICE(&s->lcdif), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->lcdif), 0, FSL_IMX6UL_LCDIF_ADDR); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->lcdif), 0, + qdev_get_gpio_in(gic, FSL_IMX6UL_LCDIF_IRQ)); /* * CSU diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6ul.h +++ b/include/hw/arm/fsl-imx6ul.h @@ -XXX,XX +XXX,XX @@ #include "hw/net/imx_fec.h" #include "hw/usb/chipidea.h" #include "hw/usb/imx-usb-phy.h" +#include "hw/display/imx6ul_lcdif.h" #include "system/memory.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct FslIMX6ULState { IMX2WdtState wdt[FSL_IMX6UL_NUM_WDTS]; IMXUSBPHYState usbphy[FSL_IMX6UL_NUM_USB_PHYS]; ChipideaState usb[FSL_IMX6UL_NUM_USBS]; + IMX6ULLCDIFState lcdif; MemoryRegion rom; MemoryRegion caam; MemoryRegion ocram; @@ -XXX,XX +XXX,XX @@ enum FslIMX6ULMemoryMap { FSL_IMX6UL_PXP_SIZE = (16 * KiB), FSL_IMX6UL_LCDIF_ADDR = 0x021C8000, - FSL_IMX6UL_LCDIF_SIZE = 0x100, + FSL_IMX6UL_LCDIF_SIZE = (16 * KiB), FSL_IMX6UL_CSI_ADDR = 0x021C4000, FSL_IMX6UL_CSI_SIZE = 0x100, -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> We have a registerfields interface which we can use for defining fields alongside helpers to access them. Define the basic syndrome layout and convert the helpers that take the imm16 data directly. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-2-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 75 ++++++++++++++++++++++++++++++++----------- 1 file changed, 57 insertions(+), 18 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ #ifndef TARGET_ARM_SYNDROME_H #define TARGET_ARM_SYNDROME_H -#include "qemu/bitops.h" +#include "hw/core/registerfields.h" /* Valid Syndrome Register EC field values */ enum arm_exception_class { @@ -XXX,XX +XXX,XX @@ enum arm_exception_class { EC_AA64_BKPT = 0x3c, }; +/* Generic syndrome encoding layout for HSR and lower 32 bits of ESR_EL2 */ +FIELD(SYNDROME, EC, 26, 6) +FIELD(SYNDROME, IL, 25, 1) +FIELD(SYNDROME, ISS, 0, 25) + typedef enum { SME_ET_AccessTrap, SME_ET_Streaming, @@ -XXX,XX +XXX,XX @@ typedef enum { static inline uint32_t syn_get_ec(uint32_t syn) { - return syn >> ARM_EL_EC_SHIFT; + return FIELD_EX32(syn, SYNDROME, EC); } static inline uint32_t syn_set_ec(uint32_t syn, uint32_t ec) { - return deposit32(syn, ARM_EL_EC_SHIFT, ARM_EL_EC_LENGTH, ec); + return FIELD_DP32(syn, SYNDROME, EC, ec); } /* @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_set_ec(uint32_t syn, uint32_t ec) */ static inline uint32_t syn_uncategorized(void) { - return (EC_UNCATEGORIZED << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_UNCATEGORIZED); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } +FIELD(ISS_IMM16, IMM16, 0, 16) + static inline uint32_t syn_aa64_svc(uint32_t imm16) { - return (EC_AA64_SVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA64_SVC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa64_hvc(uint32_t imm16) { - return (EC_AA64_HVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA64_HVC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa64_smc(uint32_t imm16) { - return (EC_AA64_SMC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA64_SMC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa32_svc(uint32_t imm16, bool is_16bit) { - return (EC_AA32_SVC << ARM_EL_EC_SHIFT) | (imm16 & 0xffff) - | (is_16bit ? 0 : ARM_EL_IL); + uint32_t res = syn_set_ec(0, EC_AA32_SVC); + res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa32_hvc(uint32_t imm16) { - return (EC_AA32_HVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA32_HVC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa32_smc(void) { - return (EC_AA32_SMC << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_AA32_SMC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } static inline uint32_t syn_aa64_bkpt(uint32_t imm16) { - return (EC_AA64_BKPT << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA64_BKPT); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa32_bkpt(uint32_t imm16, bool is_16bit) { - return (EC_AA32_BKPT << ARM_EL_EC_SHIFT) | (imm16 & 0xffff) - | (is_16bit ? 0 : ARM_EL_IL); + uint32_t res = syn_set_ec(0, EC_AA32_BKPT); + res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa64_sysregtrap(int op0, int op1, int op2, @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit) static inline uint32_t syn_sve_access_trap(void) { - return (EC_SVEACCESSTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_SVEACCESSTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } /* @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) static inline uint32_t syn_illegalstate(void) { - return (EC_ILLEGALSTATE << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_ILLEGALSTATE); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } static inline uint32_t syn_pcalignment(void) { - return (EC_PCALIGNMENT << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_PCALIGNMENT); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } static inline uint32_t syn_gcs_data_check(GCSInstructionType it, int rn) @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_gcs_gcsstr(int ra, int rn) static inline uint32_t syn_serror(uint32_t extra) { - return (EC_SERROR << ARM_EL_EC_SHIFT) | ARM_EL_IL | extra; + uint32_t res = syn_set_ec(0, EC_SERROR); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, SYNDROME, ISS, extra); + return res; } static inline uint32_t syn_mop(bool is_set, bool is_setg, int options, -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Migrate syn_aa64_sysregtrap and co-processor register trap syndromes to the registerfields API. The co-processor syndromes are split between single and duel register moves. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-3-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 124 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 102 insertions(+), 22 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ enum arm_exception_class { /* Generic syndrome encoding layout for HSR and lower 32 bits of ESR_EL2 */ FIELD(SYNDROME, EC, 26, 6) -FIELD(SYNDROME, IL, 25, 1) +FIELD(SYNDROME, IL, 25, 1) /* IL=1 for 32 bit instructions */ FIELD(SYNDROME, ISS, 0, 25) typedef enum { @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_aa64_smc(uint32_t imm16) static inline uint32_t syn_aa32_svc(uint32_t imm16, bool is_16bit) { uint32_t res = syn_set_ec(0, EC_AA32_SVC); - res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); return res; } @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_aa64_bkpt(uint32_t imm16) static inline uint32_t syn_aa32_bkpt(uint32_t imm16, bool is_16bit) { uint32_t res = syn_set_ec(0, EC_AA32_BKPT); - res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); return res; } +/* + * ISS encoding for an exception from MSR, MRS, or System instruction + * in AArch64 state. + */ +FIELD(SYSREG_ISS, ISREAD, 0, 1) /* Direction, 1 is read */ +FIELD(SYSREG_ISS, CRM, 1, 4) +FIELD(SYSREG_ISS, RT, 5, 5) +FIELD(SYSREG_ISS, CRN, 10, 4) +FIELD(SYSREG_ISS, OP1, 14, 3) +FIELD(SYSREG_ISS, OP2, 17, 3) +FIELD(SYSREG_ISS, OP0, 20, 2) + static inline uint32_t syn_aa64_sysregtrap(int op0, int op1, int op2, int crn, int crm, int rt, int isread) { - return (EC_SYSTEMREGISTERTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL - | (op0 << 20) | (op2 << 17) | (op1 << 14) | (crn << 10) | (rt << 5) - | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_SYSTEMREGISTERTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, SYSREG_ISS, OP0, op0); + res = FIELD_DP32(res, SYSREG_ISS, OP2, op2); + res = FIELD_DP32(res, SYSREG_ISS, OP1, op1); + res = FIELD_DP32(res, SYSREG_ISS, CRN, crn); + res = FIELD_DP32(res, SYSREG_ISS, RT, rt); + res = FIELD_DP32(res, SYSREG_ISS, CRM, crm); + res = FIELD_DP32(res, SYSREG_ISS, ISREAD, isread); + + return res; } +/* + * ISS encoding for an exception from an MCR or MRC access + * (move to/from co-processor) + */ +FIELD(COPROC_ISS, ISREAD, 0, 1) +FIELD(COPROC_ISS, CRM, 1, 4) +FIELD(COPROC_ISS, RT, 5, 5) +FIELD(COPROC_ISS, CRN, 10, 4) +FIELD(COPROC_ISS, OP1, 14, 3) +FIELD(COPROC_ISS, OP2, 17, 3) +FIELD(COPROC_ISS, COND, 20, 4) +FIELD(COPROC_ISS, CV, 24, 1) + static inline uint32_t syn_cp14_rt_trap(int cv, int cond, int opc1, int opc2, int crn, int crm, int rt, int isread, bool is_16bit) { - return (EC_CP14RTTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (opc2 << 17) | (opc1 << 14) - | (crn << 10) | (rt << 5) | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_CP14RTTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, COPROC_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_ISS, OP2, opc2); + res = FIELD_DP32(res, COPROC_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_ISS, CRN, crn); + res = FIELD_DP32(res, COPROC_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_ISS, CRM, crm); + res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread); + + return res; } static inline uint32_t syn_cp15_rt_trap(int cv, int cond, int opc1, int opc2, int crn, int crm, int rt, int isread, bool is_16bit) { - return (EC_CP15RTTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (opc2 << 17) | (opc1 << 14) - | (crn << 10) | (rt << 5) | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_CP15RTTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, COPROC_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_ISS, OP2, opc2); + res = FIELD_DP32(res, COPROC_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_ISS, CRN, crn); + res = FIELD_DP32(res, COPROC_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_ISS, CRM, crm); + res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread); + + return res; } +/* + * ISS encoding for an exception from an MCRR or MRRC access + * (move to/from co-processor with 2 regs) + */ +FIELD(COPROC_R2_ISS, ISREAD, 0, 1) +FIELD(COPROC_R2_ISS, CRM, 1, 4) +FIELD(COPROC_R2_ISS, RT, 5, 5) +FIELD(COPROC_R2_ISS, RT2, 10, 5) +FIELD(COPROC_R2_ISS, OP1, 16, 4) +FIELD(COPROC_R2_ISS, COND, 20, 4) +FIELD(COPROC_R2_ISS, CV, 24, 1) + static inline uint32_t syn_cp14_rrt_trap(int cv, int cond, int opc1, int crm, int rt, int rt2, int isread, bool is_16bit) { - return (EC_CP14RRTTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (opc1 << 16) - | (rt2 << 10) | (rt << 5) | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_CP14RRTTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, COPROC_R2_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_R2_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_R2_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_R2_ISS, RT2, rt2); + res = FIELD_DP32(res, COPROC_R2_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_R2_ISS, CRM, crm); + res = FIELD_DP32(res, COPROC_R2_ISS, ISREAD, isread); + + return res; } static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm, int rt, int rt2, int isread, bool is_16bit) { - return (EC_CP15RRTTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (opc1 << 16) - | (rt2 << 10) | (rt << 5) | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_CP15RRTTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, COPROC_R2_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_R2_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_R2_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_R2_ISS, RT2, rt2); + res = FIELD_DP32(res, COPROC_R2_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_R2_ISS, CRM, crm); + res = FIELD_DP32(res, COPROC_R2_ISS, ISREAD, isread); + + return res; } static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit, -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> The syn_simd_access trap was never used so remove it. We should only see the COPROC encoding on v7 architectures. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-4-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm, return res; } +/* + * ISS encoding for an exception from an access to a register of + * instruction resulting from the FPEN or TFP traps. + */ +FIELD(FP_ISS, COPROC, 0, 4) /* ARMv7 only */ +FIELD(FP_ISS, COND, 20, 4) +FIELD(FP_ISS, CV, 24, 1) + static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit, int coproc) { /* AArch32 FP trap or any AArch64 FP/SIMD trap: TA == 0 */ - return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | coproc; -} + uint32_t res = syn_set_ec(0, EC_ADVSIMDFPACCESSTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); -static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit) -{ - /* AArch32 SIMD trap: TA == 1 coproc == 0 */ - return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (1 << 5); + res = FIELD_DP32(res, FP_ISS, CV, cv); + res = FIELD_DP32(res, FP_ISS, COND, cond); + res = FIELD_DP32(res, FP_ISS, COPROC, coproc); + + return res; } static inline uint32_t syn_sve_access_trap(void) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> For simplicity keep the OP as a two bit field rather than the two interlinked fields in the docs (ERET/ERETA). Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-5-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_sve_access_trap(void) } /* + * ISS encoding for an exception from an ERET, ERETAA or ERETAB + * instructions. + * * eret_op is bits [1:0] of the ERET instruction, so: * 0 for ERET, 2 for ERETAA, 3 for ERETAB. */ +FIELD(ERET_ISS, OP, 0, 2) + static inline uint32_t syn_erettrap(int eret_op) { - return (EC_ERETTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | eret_op; + uint32_t res = syn_set_ec(0, EC_ERETTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ERET_ISS, OP, eret_op); + + return res; } static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-6-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_erettrap(int eret_op) return res; } +/* + * ISS encoding for an exception due to SME functionality + */ +FIELD(SME_ISS, SMTC, 0, 2) + static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit) { - return (EC_SMETRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) | etype; + uint32_t res = syn_set_ec(0, EC_SMETRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + res = FIELD_DP32(res, SME_ISS, SMTC, etype); + + return res; } static inline uint32_t syn_pacfail(bool data, int keynumber) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> syn_pactrap is fairly simple as the ISS is all RES0. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-7-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit) return res; } +/* + * ISS encoding for a PAC Fail exceptions + */ +FIELD(PACFAIL_ISS, BnA, 0, 1) /* B key or A key */ +FIELD(PACFAIL_ISS, DnI, 1, 1) /* Data or Instruction */ + static inline uint32_t syn_pacfail(bool data, int keynumber) { - int error_code = (data << 1) | keynumber; - return (EC_PACFAIL << ARM_EL_EC_SHIFT) | ARM_EL_IL | error_code; + uint32_t res = syn_set_ec(0, EC_PACFAIL); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, PACFAIL_ISS, DnI, data); + res = FIELD_DP32(res, PACFAIL_ISS, BnA, keynumber); + + return res; } +/* + * ISS encoding for an exception from a trapped Pointer + * Authentication instruction is RES0 + */ static inline uint32_t syn_pactrap(void) { - return (EC_PACTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_PACTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } static inline uint32_t syn_btitrap(int btype) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-8-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pactrap(void) return res; } +/* + * ISS encoding for an exception from a Branch Target Identification + * instruction. + */ +FIELD(BTI_ISS, BTYPE, 0, 2) + static inline uint32_t syn_btitrap(int btype) { - return (EC_BTITRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | btype; + uint32_t res = syn_set_ec(0, EC_BTITRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, BTI_ISS, BTYPE, btype); + return res; } static inline uint32_t syn_bxjtrap(int cv, int cond, int rm) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> This is an Armv7 specific syndrome for chips with Jazelle functionality. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-9-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_btitrap(int btype) return res; } +/* + * ISS encoding for trapped BXJ execution + * + * This is an Armv7 encoding. + */ +FIELD(BXJ_ISS, RM, 0, 4) +/* bits 4:19 are Reserved, UNK/SBZP */ +FIELD(BXJ_ISS, COND, 20, 4) +FIELD(BXJ_ISS, CV, 24, 1) + static inline uint32_t syn_bxjtrap(int cv, int cond, int rm) { - return (EC_BXJTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | - (cv << 24) | (cond << 20) | rm; + uint32_t res = syn_set_ec(0, EC_BXJTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, BXJ_ISS, CV, cv); + res = FIELD_DP32(res, BXJ_ISS, COND, cond); + res = FIELD_DP32(res, BXJ_ISS, RM, rm); + + return res; } static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr, -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-10-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_bxjtrap(int cv, int cond, int rm) return res; } +/* + * ISS encoding for a Granule Protection Check exception + * + * These are only reported to EL3 + */ +FIELD(GPC_ISS, xFSC, 0, 6) +FIELD(GPC_ISS, WnR, 6, 1) /* Write not Read */ +FIELD(GPC_ISS, S1PTW, 7, 1) +FIELD(GPC_ISS, CM, 8, 1) +FIELD(GPC_ISS, VNCR, 13, 1) +FIELD(GPC_ISS, GPCSC, 14, 6) +FIELD(GPC_ISS, InD, 20, 1) /* Instruction not Data access */ +FIELD(GPC_ISS, S2PTW, 21, 1) + static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr, int cm, int s1ptw, int wnr, int fsc) { - return (EC_GPC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (s2ptw << 21) - | (ind << 20) | (gpcsc << 14) | (vncr << 13) | (cm << 8) - | (s1ptw << 7) | (wnr << 6) | fsc; + uint32_t res = syn_set_ec(0, EC_GPC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, GPC_ISS, S2PTW, s2ptw); + res = FIELD_DP32(res, GPC_ISS, InD, ind); + res = FIELD_DP32(res, GPC_ISS, GPCSC, gpcsc); + res = FIELD_DP32(res, GPC_ISS, VNCR, vncr); + res = FIELD_DP32(res, GPC_ISS, CM, cm); + res = FIELD_DP32(res, GPC_ISS, S1PTW, s1ptw); + res = FIELD_DP32(res, GPC_ISS, WnR, wnr); + res = FIELD_DP32(res, GPC_ISS, xFSC, fsc); + + return res; } static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Migrate syn_insn_abort and syn_data_abort_* to the registerfields API. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260422125250.1303100-11-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 87 ++++++++++++++++++++++++++++++++++++------- 1 file changed, 74 insertions(+), 13 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr, return res; } +/* + * ISS encoding for an exception from an Instruction Abort + * + * (aka instruction abort) + */ +FIELD(IABORT_ISS, IFSC, 0, 6) +FIELD(IABORT_ISS, S1PTW, 7, 1) +FIELD(IABORT_ISS, EA, 9, 1) +FIELD(IABORT_ISS, FnV, 10, 1) /* FAR not Valid */ +FIELD(IABORT_ISS, SET, 11, 2) +FIELD(IABORT_ISS, PFV, 14, 1) +FIELD(IABORT_ISS, TopLevel, 21, 1) /* FEAT_THE */ + static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) { - return (EC_INSNABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL | (ea << 9) | (s1ptw << 7) | fsc; + uint32_t res = syn_set_ec(0, EC_INSNABORT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, IABORT_ISS, EA, ea); + res = FIELD_DP32(res, IABORT_ISS, S1PTW, s1ptw); + res = FIELD_DP32(res, IABORT_ISS, IFSC, fsc); + + return res; } +/* + * ISS encoding for an exception from a Data Abort + */ +FIELD(DABORT_ISS, DFSC, 0, 6) +FIELD(DABORT_ISS, WNR, 6, 1) +FIELD(DABORT_ISS, S1PTW, 7, 1) +FIELD(DABORT_ISS, CM, 8, 1) +FIELD(DABORT_ISS, EA, 9, 1) +FIELD(DABORT_ISS, FnV, 10, 1) +FIELD(DABORT_ISS, LST, 11, 2) +FIELD(DABORT_ISS, VNCR, 13, 1) +FIELD(DABORT_ISS, AR, 14, 1) +FIELD(DABORT_ISS, SF, 15, 1) +FIELD(DABORT_ISS, SRT, 16, 5) +FIELD(DABORT_ISS, SSE, 21, 1) +FIELD(DABORT_ISS, SAS, 22, 2) +FIELD(DABORT_ISS, ISV, 24, 1) + static inline uint32_t syn_data_abort_no_iss(int same_el, int fnv, int ea, int cm, int s1ptw, int wnr, int fsc) { - return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL - | (fnv << 10) | (ea << 9) | (cm << 8) | (s1ptw << 7) - | (wnr << 6) | fsc; + uint32_t res = syn_set_ec(0, EC_DATAABORT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, DABORT_ISS, FnV, fnv); + res = FIELD_DP32(res, DABORT_ISS, EA, ea); + res = FIELD_DP32(res, DABORT_ISS, CM, cm); + res = FIELD_DP32(res, DABORT_ISS, S1PTW, s1ptw); + res = FIELD_DP32(res, DABORT_ISS, WNR, wnr); + res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc); + + return res; } static inline uint32_t syn_data_abort_with_iss(int same_el, @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_with_iss(int same_el, int wnr, int fsc, bool is_16bit) { - return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | ARM_EL_ISV | (sas << 22) | (sse << 21) | (srt << 16) - | (sf << 15) | (ar << 14) - | (ea << 9) | (cm << 8) | (s1ptw << 7) | (wnr << 6) | fsc; + uint32_t res = syn_set_ec(0, EC_DATAABORT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, DABORT_ISS, ISV, 1); + res = FIELD_DP32(res, DABORT_ISS, SAS, sas); + res = FIELD_DP32(res, DABORT_ISS, SSE, sse); + res = FIELD_DP32(res, DABORT_ISS, SRT, srt); + res = FIELD_DP32(res, DABORT_ISS, SF, sf); + res = FIELD_DP32(res, DABORT_ISS, AR, ar); + res = FIELD_DP32(res, DABORT_ISS, EA, ea); + res = FIELD_DP32(res, DABORT_ISS, CM, cm); + res = FIELD_DP32(res, DABORT_ISS, S1PTW, s1ptw); + res = FIELD_DP32(res, DABORT_ISS, WNR, wnr); + res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc); + + return res; } /* @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_with_iss(int same_el, */ static inline uint32_t syn_data_abort_vncr(int ea, int wnr, int fsc) { - return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (1 << ARM_EL_EC_SHIFT) - | ARM_EL_IL | ARM_EL_VNCR | (wnr << 6) | fsc; + uint32_t res = syn_set_ec(0, EC_DATAABORT_SAME_EL); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, DABORT_ISS, VNCR, 1); + res = FIELD_DP32(res, DABORT_ISS, WNR, wnr); + res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc); + + return res; } static inline uint32_t syn_swstep(int same_el, int isv, int ex) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Migrate syn_swstep, syn_watchpoint and syn_breakpoint to the registerfields API. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-12-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 54 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 48 insertions(+), 6 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_vncr(int ea, int wnr, int fsc) return res; } +/* + * ISS encoding for an exception from a Software Step exception. + */ +FIELD(SOFTSTEP_ISS, IFSC, 0, 6) +FIELD(SOFTSTEP_ISS, EX, 6, 1) +FIELD(SOFTSTEP_ISS, ISV, 24, 1) + static inline uint32_t syn_swstep(int same_el, int isv, int ex) { - return (EC_SOFTWARESTEP << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL | (isv << 24) | (ex << 6) | 0x22; + uint32_t res = syn_set_ec(0, EC_SOFTWARESTEP + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, SOFTSTEP_ISS, ISV, isv); + res = FIELD_DP32(res, SOFTSTEP_ISS, EX, ex); + res = FIELD_DP32(res, SOFTSTEP_ISS, IFSC, 0x22); + + return res; } +/* + * ISS encoding for an exception from a Watchpoint exception + */ +FIELD(WATCHPOINT_ISS, DFSC, 0, 6) +FIELD(WATCHPOINT_ISS, WNR, 6, 1) +FIELD(WATCHPOINT_ISS, CM, 8, 1) +FIELD(WATCHPOINT_ISS, FnV, 10, 1) +FIELD(WATCHPOINT_ISS, VNCR, 13, 1) /* FEAT_NV2 */ +FIELD(WATCHPOINT_ISS, FnP, 15, 1) +FIELD(WATCHPOINT_ISS, WPF, 16, 1) +/* bellow mandatory from FEAT_Debugv8p9 */ +FIELD(WATCHPOINT_ISS, WPTV, 17, 1) /* FEAT_Debugv8p2 - WPT valid */ +FIELD(WATCHPOINT_ISS, WPT, 18, 6) /* FEAT_Debugv8p2 - missing WP number */ + static inline uint32_t syn_watchpoint(int same_el, int cm, int wnr) { - return (EC_WATCHPOINT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL | (cm << 8) | (wnr << 6) | 0x22; + uint32_t res = syn_set_ec(0, EC_WATCHPOINT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, WATCHPOINT_ISS, CM, cm); + res = FIELD_DP32(res, WATCHPOINT_ISS, WNR, wnr); + res = FIELD_DP32(res, WATCHPOINT_ISS, DFSC, 0x22); + + return res; } +/* + * ISS encoding for an exception from a Breakpoint or a Vector Catch + * debug exception. + */ +FIELD(BREAKPOINT_ISS, IFSC, 0, 6) + static inline uint32_t syn_breakpoint(int same_el) { - return (EC_BREAKPOINT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL | 0x22; + uint32_t res = syn_set_ec(0, EC_BREAKPOINT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, BREAKPOINT_ISS, IFSC, 0x22); + + return res; } static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> This will help later when we expand the fields we report. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-13-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_breakpoint(int same_el) return res; } +/* + * ISS encoding for an exception from a WF* instruction + */ +FIELD(WFX_ISS, TI, 0, 2) +FIELD(WFX_ISS, RV, 2, 1) +FIELD(WFX_ISS, RN, 5, 5) +FIELD(WFX_ISS, COND, 20, 4) +FIELD(WFX_ISS, CV, 24, 1) + static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) { - return (EC_WFX_TRAP << ARM_EL_EC_SHIFT) | - (is_16bit ? 0 : (1 << ARM_EL_IL_SHIFT)) | - (cv << 24) | (cond << 20) | ti; + uint32_t res = syn_set_ec(0, EC_WFX_TRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, WFX_ISS, CV, cv); + res = FIELD_DP32(res, WFX_ISS, COND, cond); + res = FIELD_DP32(res, WFX_ISS, TI, ti); + + return res; } static inline uint32_t syn_illegalstate(void) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Tweak arg names to make it clear raddr is the data address register number. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-14-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 39 +++++++++++++++++++++++++++++++++------ 1 file changed, 33 insertions(+), 6 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pcalignment(void) return res; } +/* + * ISS encoding for a GCS exception + * + * Field validity depends on EXTYPE + */ +FIELD(GCS_ISS, IT, 0, 5) +FIELD(GCS_ISS, RN, 5, 5) /* only for non EXLOCK exceptions */ +FIELD(GCS_ISS, RADDR, 10, 5) /* only for GCSSTR/GCSSTTR traps */ +FIELD(GCS_ISS, EXTYPE, 20, 4) + static inline uint32_t syn_gcs_data_check(GCSInstructionType it, int rn) { - return ((EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL | - (GCS_ET_DataCheck << 20) | (rn << 5) | it); + uint32_t res = syn_set_ec(0, EC_GCS); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_DataCheck); + res = FIELD_DP32(res, GCS_ISS, RN, rn); + res = FIELD_DP32(res, GCS_ISS, IT, it); + + return res; } static inline uint32_t syn_gcs_exlock(void) { - return (EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL | (GCS_ET_EXLOCK << 20); + uint32_t res = syn_set_ec(0, EC_GCS); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_EXLOCK); + + return res; } -static inline uint32_t syn_gcs_gcsstr(int ra, int rn) +static inline uint32_t syn_gcs_gcsstr(int raddr, int rn) { - return ((EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL | - (GCS_ET_GCSSTR_GCSSTTR << 20) | (ra << 10) | (rn << 5)); + uint32_t res = syn_set_ec(0, EC_GCS); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_GCSSTR_GCSSTTR); + res = FIELD_DP32(res, GCS_ISS, RADDR, raddr); + res = FIELD_DP32(res, GCS_ISS, RN, rn); + + return res; } static inline uint32_t syn_serror(uint32_t extra) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-15-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_serror(uint32_t extra) return res; } +/* + * ISS encoding for an exception from the Memory Copy and Memory Set + * instructions. + */ +FIELD(MOP_ISS, SIZEREG, 0, 5) +FIELD(MOP_ISS, SRCREG, 5, 5) +FIELD(MOP_ISS, DESTREG, 10, 5) +FIELD(MOP_ISS, FORMATOPT, 16, 2) +FIELD(MOP_ISS, OPT_A, 16, 1) +FIELD(MOP_ISS, WRONG_OPT, 17, 1) +FIELD(MOP_ISS, EPILOGUE, 18, 1) +FIELD(MOP_ISS, OPTIONS, 19, 4) +FIELD(MOP_ISS, IS_SETG, 23, 1) +FIELD(MOP_ISS, MEMINST, 24, 1) + static inline uint32_t syn_mop(bool is_set, bool is_setg, int options, bool epilogue, bool wrong_option, bool option_a, int destreg, int srcreg, int sizereg) { - return (EC_MOP << ARM_EL_EC_SHIFT) | ARM_EL_IL | - (is_set << 24) | (is_setg << 23) | (options << 19) | - (epilogue << 18) | (wrong_option << 17) | (option_a << 16) | - (destreg << 10) | (srcreg << 5) | sizereg; + uint32_t res = syn_set_ec(0, EC_MOP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, MOP_ISS, MEMINST, is_set); + res = FIELD_DP32(res, MOP_ISS, IS_SETG, is_setg); + res = FIELD_DP32(res, MOP_ISS, OPTIONS, options); + res = FIELD_DP32(res, MOP_ISS, EPILOGUE, epilogue); + res = FIELD_DP32(res, MOP_ISS, WRONG_OPT, wrong_option); + res = FIELD_DP32(res, MOP_ISS, OPT_A, option_a); + res = FIELD_DP32(res, MOP_ISS, DESTREG, destreg); + res = FIELD_DP32(res, MOP_ISS, SRCREG, srcreg); + res = FIELD_DP32(res, MOP_ISS, SIZEREG, sizereg); + + return res; } -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> It shares the same COPROC_ISS encoding as the other CP traps although not all the fields are used. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-16-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 16 ++++++++++++++++ target/arm/tcg/vfp_helper.c | 5 +---- 2 files changed, 17 insertions(+), 4 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ FIELD(COPROC_ISS, OP2, 17, 3) FIELD(COPROC_ISS, COND, 20, 4) FIELD(COPROC_ISS, CV, 24, 1) +static inline uint32_t syn_cp10_rt_trap(int cv, int cond, int opc1, + int crn, int rt, int isread) +{ + uint32_t res = syn_set_ec(0, EC_FPIDTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, COPROC_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_ISS, CRN, crn); + res = FIELD_DP32(res, COPROC_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread); + + return res; +} + static inline uint32_t syn_cp14_rt_trap(int cv, int cond, int opc1, int opc2, int crn, int crm, int rt, int isread, bool is_16bit) diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vfp_helper.c +++ b/target/arm/tcg/vfp_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(check_hcr_el2_trap)(CPUARMState *env, uint32_t rt, uint32_t reg) g_assert_not_reached(); } - syndrome = ((EC_FPIDTRAP << ARM_EL_EC_SHIFT) - | ARM_EL_IL - | (1 << 24) | (0xe << 20) | (7 << 14) - | (reg << 10) | (rt << 5) | 1); + syndrome = syn_cp10_rt_trap(1, 0xe, 7, reg, rt, 1); raise_exception(env, EXCP_HYP_TRAP, syndrome, 2); } -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> One more step towards dropping the old #defines. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-17-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch32_hyp(CPUState *cs) */ if (cs->exception_index == EXCP_PREFETCH_ABORT || (cs->exception_index == EXCP_DATA_ABORT && - !(env->exception.syndrome & ARM_EL_ISV)) || + !FIELD_EX32(env->exception.syndrome, SYNDROME, IL)) || syn_get_ec(env->exception.syndrome) == EC_UNCATEGORIZED) { - env->exception.syndrome &= ~ARM_EL_IL; + env->exception.syndrome = FIELD_DP32(env->exception.syndrome, SYNDROME, IL, 0); } } env->cp15.esr_el[2] = env->exception.syndrome; -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> This removes the last use of ARM_EL_EC_SHIFT. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-18-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 1 - target/arm/tcg/debug.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ typedef enum { } GCSInstructionType; #define ARM_EL_EC_LENGTH 6 -#define ARM_EL_EC_SHIFT 26 #define ARM_EL_IL_SHIFT 25 #define ARM_EL_ISV_SHIFT 24 #define ARM_EL_IL (1 << ARM_EL_IL_SHIFT) diff --git a/target/arm/tcg/debug.c b/target/arm/tcg/debug.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/debug.c +++ b/target/arm/tcg/debug.c @@ -XXX,XX +XXX,XX @@ raise_exception_debug(CPUARMState *env, uint32_t excp, uint32_t syndrome) * Similarly for watchpoint and breakpoint matches. */ assert(debug_el >= cur_el); - syndrome |= (debug_el == cur_el) << ARM_EL_EC_SHIFT; + syndrome |= (debug_el == cur_el) << R_SYNDROME_EC_SHIFT; raise_exception(env, excp, syndrome, debug_el); } -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Rather than open coding a bunch of shifts and masks we can use the syndrome definitions. While we are at it assert it really is a EC_DATAABORT. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-19-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/whpx/whpx-all.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/target/arm/whpx/whpx-all.c b/target/arm/whpx/whpx-all.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/whpx/whpx-all.c +++ b/target/arm/whpx/whpx-all.c @@ -XXX,XX +XXX,XX @@ static int whpx_handle_mmio(CPUState *cpu, WHV_MEMORY_ACCESS_CONTEXT *ctx) { uint64_t syndrome = ctx->Syndrome; - bool isv = syndrome & ARM_EL_ISV; - bool iswrite = (syndrome >> 6) & 1; - bool sse = (syndrome >> 21) & 1; - uint32_t sas = (syndrome >> 22) & 3; + bool isv = FIELD_EX32(syndrome, DABORT_ISS, ISV); + bool iswrite = FIELD_EX32(syndrome, DABORT_ISS, WNR); + bool sse = FIELD_EX32(syndrome, DABORT_ISS, SSE); + uint32_t sas = FIELD_EX32(syndrome, DABORT_ISS, SAS); uint32_t len = 1 << sas; - uint32_t srt = (syndrome >> 16) & 0x1f; - uint32_t cm = (syndrome >> 8) & 0x1; + uint32_t srt = FIELD_EX32(syndrome, DABORT_ISS, SRT); + uint32_t cm = FIELD_EX32(syndrome, DABORT_ISS, CM); uint64_t val = 0; + assert(syn_get_ec(syndrome) == EC_DATAABORT); assert(!cm); assert(isv); -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Rather than open coding a bunch of shifts and masks we can use the syndrome definitions. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260422125250.1303100-20-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/hvf/hvf.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ static int hvf_handle_exception(CPUState *cpu, hv_vcpu_exit_exception_t *excp) break; } case EC_DATAABORT: { - bool isv = syndrome & ARM_EL_ISV; - bool iswrite = (syndrome >> 6) & 1; - bool s1ptw = (syndrome >> 7) & 1; - bool sse = (syndrome >> 21) & 1; - uint32_t sas = (syndrome >> 22) & 3; + bool isv = FIELD_EX32(syndrome, DABORT_ISS, ISV); + bool iswrite = FIELD_EX32(syndrome, DABORT_ISS, WNR); + bool s1ptw = FIELD_EX32(syndrome, DABORT_ISS, S1PTW); + bool sse = FIELD_EX32(syndrome, DABORT_ISS, SSE); + uint32_t sas = FIELD_EX32(syndrome, DABORT_ISS, SAS); uint32_t len = 1 << sas; - uint32_t srt = (syndrome >> 16) & 0x1f; - uint32_t cm = (syndrome >> 8) & 0x1; + uint32_t srt = FIELD_EX32(syndrome, DABORT_ISS, SRT); + uint32_t cm = FIELD_EX32(syndrome, DABORT_ISS, CM); uint64_t val = 0; uint64_t ipa = excp->physical_address; AddressSpace *as = cpu_get_address_space(cpu, ARMASIdx_NS); -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> One more step to removing the old defines. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-21-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/tlb_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/tlb_helper.c +++ b/target/arm/tcg/tlb_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t merge_syn_data_abort(uint32_t template_syn, */ assert(!fi->stage2); syn = syn_data_abort_vncr(fi->ea, is_write, fsc); - } else if (!(template_syn & ARM_EL_ISV) || target_el != 2 + } else if (!FIELD_EX32(template_syn, DABORT_ISS, ISV) || target_el != 2 || fi->s1ptw || !fi->stage2) { syn = syn_data_abort_no_iss(same_el, 0, fi->ea, 0, fi->s1ptw, is_write, fsc); -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> These are only valid for data abort syndromes. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-22-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/tlb_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/tlb_helper.c +++ b/target/arm/tcg/tlb_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t merge_syn_data_abort(uint32_t template_syn, * ST64BV, or ST64BV0 insns report syndrome info even for stage-1 * faults and regardless of the target EL. */ - if (template_syn & ARM_EL_VNCR) { + if (FIELD_EX32(template_syn, DABORT_ISS, VNCR)) { /* * FEAT_NV2 faults on accesses via VNCR_EL2 are a special case: * they are always reported as "same EL", even though we are going @@ -XXX,XX +XXX,XX @@ void arm_deliver_fault(ARMCPU *cpu, vaddr addr, * because we masked that out in disas_set_insn_syndrome()) */ bool is_vncr = (access_type != MMU_INST_FETCH) && - (env->exception.syndrome & ARM_EL_VNCR); + FIELD_EX32(env->exception.syndrome, DABORT_ISS, VNCR); if (is_vncr) { /* FEAT_NV2 faults on accesses via VNCR_EL2 go to EL2 */ -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Now everything is defined with registerfields we can drop the old defines. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-23-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 9 --------- 1 file changed, 9 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ typedef enum { GCS_IT_GCSPOPX = 9, } GCSInstructionType; -#define ARM_EL_EC_LENGTH 6 -#define ARM_EL_IL_SHIFT 25 -#define ARM_EL_ISV_SHIFT 24 -#define ARM_EL_IL (1 << ARM_EL_IL_SHIFT) -#define ARM_EL_ISV (1 << ARM_EL_ISV_SHIFT) - -/* In the Data Abort syndrome */ -#define ARM_EL_VNCR (1 << 13) - static inline uint32_t syn_get_ec(uint32_t syn) { return FIELD_EX32(syn, SYNDROME, EC); -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Pass the register number (rd) to the wfit helper and report it in the syndrome ISS. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-24-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 11 ++++++++++- target/arm/tcg/helper-defs.h | 2 +- target/arm/tcg/op_helper.c | 7 ++++--- target/arm/tcg/translate-a64.c | 2 +- 4 files changed, 16 insertions(+), 6 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ FIELD(WFX_ISS, RN, 5, 5) FIELD(WFX_ISS, COND, 20, 4) FIELD(WFX_ISS, CV, 24, 1) -static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) +typedef enum { + WFI = 0b00, + WFE = 0b01, + WFIT = 0b10, + WFET = 0xb11 +} wfx_ti; + +static inline uint32_t syn_wfx(int cv, int cond, int rn, bool rv, wfx_ti ti, bool is_16bit) { uint32_t res = syn_set_ec(0, EC_WFX_TRAP); res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) res = FIELD_DP32(res, WFX_ISS, CV, cv); res = FIELD_DP32(res, WFX_ISS, COND, cond); res = FIELD_DP32(res, WFX_ISS, TI, ti); + res = FIELD_DP32(res, WFX_ISS, RN, rn); + res = FIELD_DP32(res, WFX_ISS, RV, rv); return res; } diff --git a/target/arm/tcg/helper-defs.h b/target/arm/tcg/helper-defs.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-defs.h +++ b/target/arm/tcg/helper-defs.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(exception_pc_alignment, noreturn, env, vaddr) DEF_HELPER_1(setend, void, env) DEF_HELPER_2(wfi, void, env, i32) DEF_HELPER_1(wfe, void, env) -DEF_HELPER_2(wfit, void, env, i64) +DEF_HELPER_2(wfit, void, env, i32) DEF_HELPER_1(yield, void, env) DEF_HELPER_1(pre_hvc, void, env) DEF_HELPER_2(pre_smc, void, env, i32) diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) env->regs[15] -= insn_len; } - raise_exception(env, excp, syn_wfx(1, 0xe, 0, insn_len == 2), + raise_exception(env, excp, syn_wfx(1, 0xe, 0, false, WFI, insn_len == 2), target_el); } @@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) #endif } -void HELPER(wfit)(CPUARMState *env, uint64_t timeout) +void HELPER(wfit)(CPUARMState *env, uint32_t rd) { #ifdef CONFIG_USER_ONLY /* @@ -XXX,XX +XXX,XX @@ void HELPER(wfit)(CPUARMState *env, uint64_t timeout) int target_el = check_wfx_trap(env, false, &excp); /* The WFIT should time out when CNTVCT_EL0 >= the specified value. */ uint64_t cntval = gt_get_countervalue(env); + uint64_t timeout = env->xregs[rd]; /* * We want the value that we would get if we read CNTVCT_EL0 from * the current exception level, so the direct_access offset, not @@ -XXX,XX +XXX,XX @@ void HELPER(wfit)(CPUARMState *env, uint64_t timeout) if (target_el) { env->pc -= 4; - raise_exception(env, excp, syn_wfx(1, 0xe, 2, false), target_el); + raise_exception(env, excp, syn_wfx(1, 0xe, rd, true, WFIT, false), target_el); } if (uadd64_overflow(timeout, offset, &nexttick)) { diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_WFIT(DisasContext *s, arg_WFIT *a) } gen_a64_update_pc(s, 4); - gen_helper_wfit(tcg_env, cpu_reg(s, a->rd)); + gen_helper_wfit(tcg_env, tcg_constant_i32(a->rd)); /* Go back to the main loop to check for interrupts */ s->base.is_jmp = DISAS_EXIT; return true; -- 2.43.0