diff options
| author | Peter Maydell <peter.maydell@linaro.org> | 2018-02-09 13:27:40 +0000 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2018-02-09 13:27:40 +0000 |
| commit | f31cd9e4e2172a4807f390194978c61e717791d2 (patch) | |
| tree | b625ba38f6fa0503edc61a64942a6c1d07e99cd0 | |
| parent | fdcbebe4519ec76cb500ab7698c1ea7ed8ebc962 (diff) | |
| parent | bbba7757bacc9f890a3f028d328b4b429dbe78ec (diff) | |
Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20180209' into staging
target-arm queue:
* Support M profile derived exceptions on exception entry and exit
* Implement AArch64 v8.2 crypto insns (SHA-512, SHA-3, SM3, SM4)
* Implement working i.MX6 SD controller
* Various devices preparatory to i.MX7 support
* Preparatory patches for SVE emulation
* v8M: Fix bug in implementation of 'TT' insn
* Give useful error if user tries to use userspace GICv3 with KVM
# gpg: Signature made Fri 09 Feb 2018 11:01:23 GMT
# gpg: using RSA key 3C2525ED14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg: aka "Peter Maydell <pmaydell@gmail.com>"
# gpg: aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83 15CF 3C25 25ED 1436 0CDE
* remotes/pmaydell/tags/pull-target-arm-20180209: (30 commits)
hw/core/generic-loader: Allow PC to be set on command line
target/arm/translate.c: Fix missing 'break' for TT insns
target/arm/kvm: gic: Prevent creating userspace GICv3 with KVM
target/arm: Add SVE state to TB->FLAGS
target/arm: Add ZCR_ELx
target/arm: Add SVE to migration state
target/arm: Add predicate registers for SVE
target/arm: Expand vector registers for SVE
hw/arm: Move virt's PSCI DT fixup code to arm/boot.c
usb: Add basic code to emulate Chipidea USB IP
i.MX: Add implementation of i.MX7 GPR IP block
i.MX: Add i.MX7 GPT variant
i.MX: Add code to emulate GPCv2 IP block
i.MX: Add code to emulate i.MX7 SNVS IP-block
i.MX: Add code to emulate i.MX2 watchdog IP block
i.MX: Add code to emulate i.MX7 CCM, PMU and ANALOG IP blocks
hw: i.MX: Convert i.MX6 to use TYPE_IMX_USDHC
sdhci: Add i.MX specific subtype of SDHCI
target/arm: enable user-mode SHA-3, SM3, SM4 and SHA-512 instruction support
target/arm: implement SM4 instructions
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
38 files changed, 2928 insertions, 187 deletions
diff --git a/hw/arm/boot.c b/hw/arm/boot.c index bb244ec359..9b174b982c 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -385,6 +385,69 @@ static void set_kernel_args_old(const struct arm_boot_info *info) } } +static void fdt_add_psci_node(void *fdt) +{ + uint32_t cpu_suspend_fn; + uint32_t cpu_off_fn; + uint32_t cpu_on_fn; + uint32_t migrate_fn; + ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(0)); + const char *psci_method; + int64_t psci_conduit; + + psci_conduit = object_property_get_int(OBJECT(armcpu), + "psci-conduit", + &error_abort); + switch (psci_conduit) { + case QEMU_PSCI_CONDUIT_DISABLED: + return; + case QEMU_PSCI_CONDUIT_HVC: + psci_method = "hvc"; + break; + case QEMU_PSCI_CONDUIT_SMC: + psci_method = "smc"; + break; + default: + g_assert_not_reached(); + } + + qemu_fdt_add_subnode(fdt, "/psci"); + if (armcpu->psci_version == 2) { + const char comp[] = "arm,psci-0.2\0arm,psci"; + qemu_fdt_setprop(fdt, "/psci", "compatible", comp, sizeof(comp)); + + cpu_off_fn = QEMU_PSCI_0_2_FN_CPU_OFF; + if (arm_feature(&armcpu->env, ARM_FEATURE_AARCH64)) { + cpu_suspend_fn = QEMU_PSCI_0_2_FN64_CPU_SUSPEND; + cpu_on_fn = QEMU_PSCI_0_2_FN64_CPU_ON; + migrate_fn = QEMU_PSCI_0_2_FN64_MIGRATE; + } else { + cpu_suspend_fn = QEMU_PSCI_0_2_FN_CPU_SUSPEND; + cpu_on_fn = QEMU_PSCI_0_2_FN_CPU_ON; + migrate_fn = QEMU_PSCI_0_2_FN_MIGRATE; + } + } else { + qemu_fdt_setprop_string(fdt, "/psci", "compatible", "arm,psci"); + + cpu_suspend_fn = QEMU_PSCI_0_1_FN_CPU_SUSPEND; + cpu_off_fn = QEMU_PSCI_0_1_FN_CPU_OFF; + cpu_on_fn = QEMU_PSCI_0_1_FN_CPU_ON; + migrate_fn = QEMU_PSCI_0_1_FN_MIGRATE; + } + + /* We adopt the PSCI spec's nomenclature, and use 'conduit' to refer + * to the instruction that should be used to invoke PSCI functions. + * However, the device tree binding uses 'method' instead, so that is + * what we should use here. + */ + qemu_fdt_setprop_string(fdt, "/psci", "method", psci_method); + + qemu_fdt_setprop_cell(fdt, "/psci", "cpu_suspend", cpu_suspend_fn); + qemu_fdt_setprop_cell(fdt, "/psci", "cpu_off", cpu_off_fn); + qemu_fdt_setprop_cell(fdt, "/psci", "cpu_on", cpu_on_fn); + qemu_fdt_setprop_cell(fdt, "/psci", "migrate", migrate_fn); +} + /** * load_dtb() - load a device tree binary image into memory * @addr: the address to load the image at @@ -541,6 +604,8 @@ static int load_dtb(hwaddr addr, const struct arm_boot_info *binfo, } } + fdt_add_psci_node(fdt); + if (binfo->modify_dtb) { binfo->modify_dtb(binfo, fdt); } diff --git a/hw/arm/fsl-imx6.c b/hw/arm/fsl-imx6.c index b0d4088290..e6559a8b12 100644 --- a/hw/arm/fsl-imx6.c +++ b/hw/arm/fsl-imx6.c @@ -93,7 +93,7 @@ static void fsl_imx6_init(Object *obj) } for (i = 0; i < FSL_IMX6_NUM_ESDHCS; i++) { - object_initialize(&s->esdhc[i], sizeof(s->esdhc[i]), TYPE_SYSBUS_SDHCI); + object_initialize(&s->esdhc[i], sizeof(s->esdhc[i]), TYPE_IMX_USDHC); qdev_set_parent_bus(DEVICE(&s->esdhc[i]), sysbus_get_default()); snprintf(name, NAME_SIZE, "sdhc%d", i + 1); object_property_add_child(obj, name, OBJECT(&s->esdhc[i]), NULL); diff --git a/hw/arm/virt.c b/hw/arm/virt.c index b334c82eda..dbb3c8036a 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -244,66 +244,6 @@ static void create_fdt(VirtMachineState *vms) } } -static void fdt_add_psci_node(const VirtMachineState *vms) -{ - uint32_t cpu_suspend_fn; - uint32_t cpu_off_fn; - uint32_t cpu_on_fn; - uint32_t migrate_fn; - void *fdt = vms->fdt; - ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(0)); - const char *psci_method; - - switch (vms->psci_conduit) { - case QEMU_PSCI_CONDUIT_DISABLED: - return; - case QEMU_PSCI_CONDUIT_HVC: - psci_method = "hvc"; - break; - case QEMU_PSCI_CONDUIT_SMC: - psci_method = "smc"; - break; - default: - g_assert_not_reached(); - } - - qemu_fdt_add_subnode(fdt, "/psci"); - if (armcpu->psci_version == 2) { - const char comp[] = "arm,psci-0.2\0arm,psci"; - qemu_fdt_setprop(fdt, "/psci", "compatible", comp, sizeof(comp)); - - cpu_off_fn = QEMU_PSCI_0_2_FN_CPU_OFF; - if (arm_feature(&armcpu->env, ARM_FEATURE_AARCH64)) { - cpu_suspend_fn = QEMU_PSCI_0_2_FN64_CPU_SUSPEND; - cpu_on_fn = QEMU_PSCI_0_2_FN64_CPU_ON; - migrate_fn = QEMU_PSCI_0_2_FN64_MIGRATE; - } else { - cpu_suspend_fn = QEMU_PSCI_0_2_FN_CPU_SUSPEND; - cpu_on_fn = QEMU_PSCI_0_2_FN_CPU_ON; - migrate_fn = QEMU_PSCI_0_2_FN_MIGRATE; - } - } else { - qemu_fdt_setprop_string(fdt, "/psci", "compatible", "arm,psci"); - - cpu_suspend_fn = QEMU_PSCI_0_1_FN_CPU_SUSPEND; - cpu_off_fn = QEMU_PSCI_0_1_FN_CPU_OFF; - cpu_on_fn = QEMU_PSCI_0_1_FN_CPU_ON; - migrate_fn = QEMU_PSCI_0_1_FN_MIGRATE; - } - - /* We adopt the PSCI spec's nomenclature, and use 'conduit' to refer - * to the instruction that should be used to invoke PSCI functions. - * However, the device tree binding uses 'method' instead, so that is - * what we should use here. - */ - qemu_fdt_setprop_string(fdt, "/psci", "method", psci_method); - - qemu_fdt_setprop_cell(fdt, "/psci", "cpu_suspend", cpu_suspend_fn); - qemu_fdt_setprop_cell(fdt, "/psci", "cpu_off", cpu_off_fn); - qemu_fdt_setprop_cell(fdt, "/psci", "cpu_on", cpu_on_fn); - qemu_fdt_setprop_cell(fdt, "/psci", "migrate", migrate_fn); -} - static void fdt_add_timer_nodes(const VirtMachineState *vms) { /* On real hardware these interrupts are level-triggered. @@ -1409,7 +1349,6 @@ static void machvirt_init(MachineState *machine) } fdt_add_timer_nodes(vms); fdt_add_cpu_nodes(vms); - fdt_add_psci_node(vms); memory_region_allocate_system_memory(ram, NULL, "mach-virt.ram", machine->ram_size); diff --git a/hw/core/generic-loader.c b/hw/core/generic-loader.c index 46012673c3..cb0e68486d 100644 --- a/hw/core/generic-loader.c +++ b/hw/core/generic-loader.c @@ -105,7 +105,7 @@ static void generic_loader_realize(DeviceState *dev, Error **errp) error_setg(errp, "data can not be specified when setting a " "program counter"); return; - } else if (!s->cpu_num) { + } else if (s->cpu_num == CPU_NONE) { error_setg(errp, "cpu_num must be specified when setting a " "program counter"); return; diff --git a/hw/intc/Makefile.objs b/hw/intc/Makefile.objs index 571e094a14..0e9963f5ee 100644 --- a/hw/intc/Makefile.objs +++ b/hw/intc/Makefile.objs @@ -6,7 +6,7 @@ common-obj-$(CONFIG_XILINX) += xilinx_intc.o common-obj-$(CONFIG_XLNX_ZYNQMP) += xlnx-pmu-iomod-intc.o common-obj-$(CONFIG_XLNX_ZYNQMP) += xlnx-zynqmp-ipi.o common-obj-$(CONFIG_ETRAXFS) += etraxfs_pic.o -common-obj-$(CONFIG_IMX) += imx_avic.o +common-obj-$(CONFIG_IMX) += imx_avic.o imx_gpcv2.o common-obj-$(CONFIG_LM32) += lm32_pic.o common-obj-$(CONFIG_REALVIEW) += realview_gic.o common-obj-$(CONFIG_SLAVIO) += slavio_intctl.o diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index 8ca6ceeb9b..360889d30b 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -503,8 +503,25 @@ static void armv7m_nvic_clear_pending(void *opaque, int irq, bool secure) } } -void armv7m_nvic_set_pending(void *opaque, int irq, bool secure) +static void do_armv7m_nvic_set_pending(void *opaque, int irq, bool secure, + bool derived) { + /* Pend an exception, including possibly escalating it to HardFault. + * + * This function handles both "normal" pending of interrupts and + * exceptions, and also derived exceptions (ones which occur as + * a result of trying to take some other exception). + * + * If derived == true, the caller guarantees that we are part way through + * trying to take an exception (but have not yet called + * armv7m_nvic_acknowledge_irq() to make it active), and so: + * - s->vectpending is the "original exception" we were trying to take + * - irq is the "derived exception" + * - nvic_exec_prio(s) gives the priority before exception entry + * Here we handle the prioritization logic which the pseudocode puts + * in the DerivedLateArrival() function. + */ + NVICState *s = (NVICState *)opaque; bool banked = exc_is_banked(irq); VecInfo *vec; @@ -514,7 +531,44 @@ void armv7m_nvic_set_pending(void *opaque, int irq, bool secure) vec = (banked && secure) ? &s->sec_vectors[irq] : &s->vectors[irq]; - trace_nvic_set_pending(irq, secure, vec->enabled, vec->prio); + trace_nvic_set_pending(irq, secure, derived, vec->enabled, vec->prio); + + if (derived) { + /* Derived exceptions are always synchronous. */ + assert(irq >= ARMV7M_EXCP_HARD && irq < ARMV7M_EXCP_PENDSV); + + if (irq == ARMV7M_EXCP_DEBUG && + exc_group_prio(s, vec->prio, secure) >= nvic_exec_prio(s)) { + /* DebugMonitorFault, but its priority is lower than the + * preempted exception priority: just ignore it. + */ + return; + } + + if (irq == ARMV7M_EXCP_HARD && vec->prio >= s->vectpending_prio) { + /* If this is a terminal exception (one which means we cannot + * take the original exception, like a failure to read its + * vector table entry), then we must take the derived exception. + * If the derived exception can't take priority over the + * original exception, then we go into Lockup. + * + * For QEMU, we rely on the fact that a derived exception is + * terminal if and only if it's reported to us as HardFault, + * which saves having to have an extra argument is_terminal + * that we'd only use in one place. + */ + cpu_abort(&s->cpu->parent_obj, + "Lockup: can't take terminal derived exception " + "(original exception priority %d)\n", + s->vectpending_prio); + } + /* We now continue with the same code as for a normal pending + * exception, which will cause us to pend the derived exception. + * We'll then take either the original or the derived exception + * based on which is higher priority by the usual mechanism + * for selecting the highest priority pending interrupt. + */ + } if (irq >= ARMV7M_EXCP_HARD && irq < ARMV7M_EXCP_PENDSV) { /* If a synchronous exception is pending then it may be @@ -585,25 +639,31 @@ void armv7m_nvic_set_pending(void *opaque, int irq, bool secure) } } +void armv7m_nvic_set_pending(void *opaque, int irq, bool secure) +{ + do_armv7m_nvic_set_pending(opaque, irq, secure, false); +} + +void armv7m_nvic_set_pending_derived(void *opaque, int irq, bool secure) +{ + do_armv7m_nvic_set_pending(opaque, irq, secure, true); +} + /* Make pending IRQ active. */ -bool armv7m_nvic_acknowledge_irq(void *opaque) +void armv7m_nvic_acknowledge_irq(void *opaque) { NVICState *s = (NVICState *)opaque; CPUARMState *env = &s->cpu->env; const int pending = s->vectpending; const int running = nvic_exec_prio(s); VecInfo *vec; - bool targets_secure; assert(pending > ARMV7M_EXCP_RESET && pending < s->num_irq); if (s->vectpending_is_s_banked) { vec = &s->sec_vectors[pending]; - targets_secure = true; } else { vec = &s->vectors[pending]; - targets_secure = !exc_is_banked(s->vectpending) && - exc_targets_secure(s, s->vectpending); } assert(vec->enabled); @@ -611,7 +671,7 @@ bool armv7m_nvic_acknowledge_irq(void *opaque) assert(s->vectpending_prio < running); - trace_nvic_acknowledge_irq(pending, s->vectpending_prio, targets_secure); + trace_nvic_acknowledge_irq(pending, s->vectpending_prio); vec->active = 1; vec->pending = 0; @@ -619,8 +679,28 @@ bool armv7m_nvic_acknowledge_irq(void *opaque) write_v7m_exception(env, s->vectpending); nvic_irq_update(s); +} + +void armv7m_nvic_get_pending_irq_info(void *opaque, + int *pirq, bool *ptargets_secure) +{ + NVICState *s = (NVICState *)opaque; + const int pending = s->vectpending; + bool targets_secure; + + assert(pending > ARMV7M_EXCP_RESET && pending < s->num_irq); + + if (s->vectpending_is_s_banked) { + targets_secure = true; + } else { + targets_secure = !exc_is_banked(pending) && + exc_targets_secure(s, pending); + } + + trace_nvic_get_pending_irq_info(pending, targets_secure); - return targets_secure; + *ptargets_secure = targets_secure; + *pirq = pending; } int armv7m_nvic_complete_irq(void *opaque, int irq, bool secure) diff --git a/hw/intc/imx_gpcv2.c b/hw/intc/imx_gpcv2.c new file mode 100644 index 0000000000..4eb9ce2668 --- /dev/null +++ b/hw/intc/imx_gpcv2.c @@ -0,0 +1,125 @@ +/* + * Copyright (c) 2018, Impinj, Inc. + * + * i.MX7 GPCv2 block emulation code + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/intc/imx_gpcv2.h" +#include "qemu/log.h" + +#define GPC_PU_PGC_SW_PUP_REQ 0x0f8 +#define GPC_PU_PGC_SW_PDN_REQ 0x104 + +#define USB_HSIC_PHY_SW_Pxx_REQ BIT(4) +#define USB_OTG2_PHY_SW_Pxx_REQ BIT(3) +#define USB_OTG1_PHY_SW_Pxx_REQ BIT(2) +#define PCIE_PHY_SW_Pxx_REQ BIT(1) +#define MIPI_PHY_SW_Pxx_REQ BIT(0) + + +static void imx_gpcv2_reset(DeviceState *dev) +{ + IMXGPCv2State *s = IMX_GPCV2(dev); + + memset(s->regs, 0, sizeof(s->regs)); +} + +static uint64_t imx_gpcv2_read(void *opaque, hwaddr offset, + unsigned size) +{ + IMXGPCv2State *s = opaque; + + return s->regs[offset / sizeof(uint32_t)]; +} + +static void imx_gpcv2_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + IMXGPCv2State *s = opaque; + const size_t idx = offset / sizeof(uint32_t); + + s->regs[idx] = value; + + /* + * Real HW will clear those bits once as a way to indicate that + * power up request is complete + */ + if (offset == GPC_PU_PGC_SW_PUP_REQ || + offset == GPC_PU_PGC_SW_PDN_REQ) { + s->regs[idx] &= ~(USB_HSIC_PHY_SW_Pxx_REQ | + USB_OTG2_PHY_SW_Pxx_REQ | + USB_OTG1_PHY_SW_Pxx_REQ | + PCIE_PHY_SW_Pxx_REQ | + MIPI_PHY_SW_Pxx_REQ); + } +} + +static const struct MemoryRegionOps imx_gpcv2_ops = { + .read = imx_gpcv2_read, + .write = imx_gpcv2_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + /* + * Our device would not work correctly if the guest was doing + * unaligned access. This might not be a limitation on the real + * device but in practice there is no reason for a guest to access + * this device unaligned. + */ + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void imx_gpcv2_init(Object *obj) +{ + SysBusDevice *sd = SYS_BUS_DEVICE(obj); + IMXGPCv2State *s = IMX_GPCV2(obj); + + memory_region_init_io(&s->iomem, + obj, + &imx_gpcv2_ops, + s, + TYPE_IMX_GPCV2 ".iomem", + sizeof(s->regs)); + sysbus_init_mmio(sd, &s->iomem); +} + +static const VMStateDescription vmstate_imx_gpcv2 = { + .name = TYPE_IMX_GPCV2, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, IMXGPCv2State, GPC_NUM), + VMSTATE_END_OF_LIST() + }, +}; + +static void imx_gpcv2_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = imx_gpcv2_reset; + dc->vmsd = &vmstate_imx_gpcv2; + dc->desc = "i.MX GPCv2 Module"; +} + +static const TypeInfo imx_gpcv2_info = { + .name = TYPE_IMX_GPCV2, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(IMXGPCv2State), + .instance_init = imx_gpcv2_init, + .class_init = imx_gpcv2_class_init, +}; + +static void imx_gpcv2_register_type(void) +{ + type_register_static(&imx_gpcv2_info); +} +type_init(imx_gpcv2_register_type) diff --git a/hw/intc/trace-events b/hw/intc/trace-events index be769186fc..4092d2825e 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -177,10 +177,11 @@ nvic_set_prio(int irq, bool secure, uint8_t prio) "NVIC set irq %d secure-bank % nvic_irq_update(int vectpending, int pendprio, int exception_prio, int level) "NVIC vectpending %d pending prio %d exception_prio %d: setting irq line to %d" nvic_escalate_prio(int irq, int irqprio, int runprio) "NVIC escalating irq %d to HardFault: insufficient priority %d >= %d" nvic_escalate_disabled(int irq) "NVIC escalating irq %d to HardFault: disabled" -nvic_set_pending(int irq, bool secure, int en, int prio) "NVIC set pending irq %d secure-bank %d (enabled: %d priority %d)" +nvic_set_pending(int irq, bool secure, bool derived, int en, int prio) "NVIC set pending irq %d secure-bank %d derived %d (enabled: %d priority %d)" nvic_clear_pending(int irq, bool secure, int en, int prio) "NVIC clear pending irq %d secure-bank %d (enabled: %d priority %d)" nvic_set_pending_level(int irq) "NVIC set pending: irq %d higher prio than vectpending: setting irq line to 1" -nvic_acknowledge_irq(int irq, int prio, bool targets_secure) "NVIC acknowledge IRQ: %d now active (prio %d targets_secure %d)" +nvic_acknowledge_irq(int irq, int prio) "NVIC acknowledge IRQ: %d now active (prio %d)" +nvic_get_pending_irq_info(int irq, bool secure) "NVIC next IRQ %d: targets_secure: %d" nvic_complete_irq(int irq, bool secure) "NVIC complete IRQ %d (secure %d)" nvic_set_irq_level(int irq, int level) "NVIC external irq %d level set to %d" nvic_sysreg_read(uint64_t addr, uint32_t value, unsigned size) "NVIC sysreg read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index d517f83e81..fce426eb75 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -33,6 +33,10 @@ obj-$(CONFIG_IMX) += imx31_ccm.o obj-$(CONFIG_IMX) += imx25_ccm.o obj-$(CONFIG_IMX) += imx6_ccm.o obj-$(CONFIG_IMX) += imx6_src.o +obj-$(CONFIG_IMX) += imx7_ccm.o +obj-$(CONFIG_IMX) += imx2_wdt.o +obj-$(CONFIG_IMX) += imx7_snvs.o +obj-$(CONFIG_IMX) += imx7_gpr.o obj-$(CONFIG_MILKYMIST) += milkymist-hpdmc.o obj-$(CONFIG_MILKYMIST) += milkymist-pfpu.o obj-$(CONFIG_MAINSTONE) += mst_fpga.o diff --git a/hw/misc/imx2_wdt.c b/hw/misc/imx2_wdt.c new file mode 100644 index 0000000000..e47e442592 --- /dev/null +++ b/hw/misc/imx2_wdt.c @@ -0,0 +1,89 @@ +/* + * Copyright (c) 2018, Impinj, Inc. + * + * i.MX2 Watchdog IP block + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/bitops.h" +#include "sysemu/watchdog.h" + +#include "hw/misc/imx2_wdt.h" + +#define IMX2_WDT_WCR_WDA BIT(5) /* -> External Reset WDOG_B */ +#define IMX2_WDT_WCR_SRS BIT(4) /* -> Software Reset Signal */ + +static uint64_t imx2_wdt_read(void *opaque, hwaddr addr, + unsigned int size) +{ + return 0; +} + +static void imx2_wdt_write(void *opaque, hwaddr addr, + uint64_t value, unsigned int size) +{ + if (addr == IMX2_WDT_WCR && + (value & (IMX2_WDT_WCR_WDA | IMX2_WDT_WCR_SRS))) { + watchdog_perform_action(); + } +} + +static const MemoryRegionOps imx2_wdt_ops = { + .read = imx2_wdt_read, + .write = imx2_wdt_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + /* + * Our device would not work correctly if the guest was doing + * unaligned access. This might not be a limitation on the + * real device but in practice there is no reason for a guest + * to access this device unaligned. + */ + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void imx2_wdt_realize(DeviceState *dev, Error **errp) +{ + IMX2WdtState *s = IMX2_WDT(dev); + + memory_region_init_io(&s->mmio, OBJECT(dev), + &imx2_wdt_ops, s, + TYPE_IMX2_WDT".mmio", + IMX2_WDT_REG_NUM * sizeof(uint16_t)); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->mmio); +} + +static void imx2_wdt_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = imx2_wdt_realize; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); +} + +static const TypeInfo imx2_wdt_info = { + .name = TYPE_IMX2_WDT, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(IMX2WdtState), + .class_init = imx2_wdt_class_init, +}; + +static WatchdogTimerModel model = { + .wdt_name = "imx2-watchdog", + .wdt_description = "i.MX2 Watchdog", +}; + +static void imx2_wdt_register_type(void) +{ + watchdog_add_model(&model); + type_register_static(&imx2_wdt_info); +} +type_init(imx2_wdt_register_type) diff --git a/hw/misc/imx7_ccm.c b/hw/misc/imx7_ccm.c new file mode 100644 index 0000000000..d90c48bfec --- /dev/null +++ b/hw/misc/imx7_ccm.c @@ -0,0 +1,277 @@ +/* + * Copyright (c) 2018, Impinj, Inc. + * + * i.MX7 CCM, PMU and ANALOG IP blocks emulation code + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" + +#include "hw/misc/imx7_ccm.h" + +static void imx7_analog_reset(DeviceState *dev) +{ + IMX7AnalogState *s = IMX7_ANALOG(dev); + + memset(s->pmu, 0, sizeof(s->pmu)); + memset(s->analog, 0, sizeof(s->analog)); + + s->analog[ANALOG_PLL_ARM] = 0x00002042; + s->analog[ANALOG_PLL_DDR] = 0x0060302c; + s->analog[ANALOG_PLL_DDR_SS] = 0x00000000; + s->analog[ANALOG_PLL_DDR_NUM] = 0x06aaac4d; + s->analog[ANALOG_PLL_DDR_DENOM] = 0x100003ec; + s->analog[ANALOG_PLL_480] = 0x00002000; + s->analog[ANALOG_PLL_480A] = 0x52605a56; + s->analog[ANALOG_PLL_480B] = 0x52525216; + s->analog[ANALOG_PLL_ENET] = 0x00001fc0; + s->analog[ANALOG_PLL_AUDIO] = 0x0001301b; + s->analog[ANALOG_PLL_AUDIO_SS] = 0x00000000; + s->analog[ANALOG_PLL_AUDIO_NUM] = 0x05f5e100; + s->analog[ANALOG_PLL_AUDIO_DENOM] = 0x2964619c; + s->analog[ANALOG_PLL_VIDEO] = 0x0008201b; + s->analog[ANALOG_PLL_VIDEO_SS] = 0x00000000; + s->analog[ANALOG_PLL_VIDEO_NUM] = 0x0000f699; + s->analog[ANALOG_PLL_VIDEO_DENOM] = 0x000f4240; + s->analog[ANALOG_PLL_MISC0] = 0x00000000; + + /* all PLLs need to be locked */ + s->analog[ANALOG_PLL_ARM] |= ANALOG_PLL_LOCK; + s->analog[ANALOG_PLL_DDR] |= ANALOG_PLL_LOCK; + s->analog[ANALOG_PLL_480] |= ANALOG_PLL_LOCK; + s->analog[ANALOG_PLL_480A] |= ANALOG_PLL_LOCK; + s->analog[ANALOG_PLL_480B] |= ANALOG_PLL_LOCK; + s->analog[ANALOG_PLL_ENET] |= ANALOG_PLL_LOCK; + s->analog[ANALOG_PLL_AUDIO] |= ANALOG_PLL_LOCK; + s->analog[ANALOG_PLL_VIDEO] |= ANALOG_PLL_LOCK; + s->analog[ANALOG_PLL_MISC0] |= ANALOG_PLL_LOCK; + + /* + * Since I couldn't find any info about this in the reference + * manual the value of this register is based strictly on matching + * what Linux kernel expects it to be. + */ + s->analog[ANALOG_DIGPROG] = 0x720000; + /* + * Set revision to be 1.0 (Arbitrary choice, no particular + * reason). + */ + s->analog[ANALOG_DIGPROG] |= 0x000010; +} + +static void imx7_ccm_reset(DeviceState *dev) +{ + IMX7CCMState *s = IMX7_CCM(dev); + + memset(s->ccm, 0, sizeof(s->ccm)); +} + +#define CCM_INDEX(offset) (((offset) & ~(hwaddr)0xF) / sizeof(uint32_t)) +#define CCM_BITOP(offset) ((offset) & (hwaddr)0xF) + +enum { + CCM_BITOP_NONE = 0x00, + CCM_BITOP_SET = 0x04, + CCM_BITOP_CLR = 0x08, + CCM_BITOP_TOG = 0x0C, +}; + +static uint64_t imx7_set_clr_tog_read(void *opaque, hwaddr offset, + unsigned size) +{ + const uint32_t *mmio = opaque; + + return mmio[CCM_INDEX(offset)]; +} + +static void imx7_set_clr_tog_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + const uint8_t bitop = CCM_BITOP(offset); + const uint32_t index = CCM_INDEX(offset); + uint32_t *mmio = opaque; + + switch (bitop) { + case CCM_BITOP_NONE: + mmio[index] = value; + break; + case CCM_BITOP_SET: + mmio[index] |= value; + break; + case CCM_BITOP_CLR: + mmio[index] &= ~value; + break; + case CCM_BITOP_TOG: + mmio[index] ^= value; + break; + }; +} + +static const struct MemoryRegionOps imx7_set_clr_tog_ops = { + .read = imx7_set_clr_tog_read, + .write = imx7_set_clr_tog_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + /* + * Our device would not work correctly if the guest was doing + * unaligned access. This might not be a limitation on the real + * device but in practice there is no reason for a guest to access + * this device unaligned. + */ + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static const struct MemoryRegionOps imx7_digprog_ops = { + .read = imx7_set_clr_tog_read, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void imx7_ccm_init(Object *obj) +{ + SysBusDevice *sd = SYS_BUS_DEVICE(obj); + IMX7CCMState *s = IMX7_CCM(obj); + + memory_region_init_io(&s->iomem, + obj, + &imx7_set_clr_tog_ops, + s->ccm, + TYPE_IMX7_CCM ".ccm", + sizeof(s->ccm)); + + sysbus_init_mmio(sd, &s->iomem); +} + +static void imx7_analog_init(Object *obj) +{ + SysBusDevice *sd = SYS_BUS_DEVICE(obj); + IMX7AnalogState *s = IMX7_ANALOG(obj); + + memory_region_init(&s->mmio.container, obj, TYPE_IMX7_ANALOG, + 0x10000); + + memory_region_init_io(&s->mmio.analog, + obj, + &imx7_set_clr_tog_ops, + s->analog, + TYPE_IMX7_ANALOG, + sizeof(s->analog)); + + memory_region_add_subregion(&s->mmio.container, + 0x60, &s->mmio.analog); + + memory_region_init_io(&s->mmio.pmu, + obj, + &imx7_set_clr_tog_ops, + s->pmu, + TYPE_IMX7_ANALOG ".pmu", + sizeof(s->pmu)); + + memory_region_add_subregion(&s->mmio.container, + 0x200, &s->mmio.pmu); + + memory_region_init_io(&s->mmio.digprog, + obj, + &imx7_digprog_ops, + &s->analog[ANALOG_DIGPROG], + TYPE_IMX7_ANALOG ".digprog", + sizeof(uint32_t)); + + memory_region_add_subregion_overlap(&s->mmio.container, + 0x800, &s->mmio.digprog, 10); + + + sysbus_init_mmio(sd, &s->mmio.container); +} + +static const VMStateDescription vmstate_imx7_ccm = { + .name = TYPE_IMX7_CCM, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(ccm, IMX7CCMState, CCM_MAX), + VMSTATE_END_OF_LIST() + }, +}; + +static uint32_t imx7_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock) +{ + /* + * This function is "consumed" by GPT emulation code, however on + * i.MX7 each GPT block can have their own clock root. This means + * that this functions needs somehow to know requester's identity + * and the way to pass it: be it via additional IMXClk constants + * or by adding another argument to this method needs to be + * figured out + */ + qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Not implemented\n", + TYPE_IMX7_CCM, __func__); + return 0; +} + +static void imx7_ccm_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + IMXCCMClass *ccm = IMX_CCM_CLASS(klass); + + dc->reset = imx7_ccm_reset; + dc->vmsd = &vmstate_imx7_ccm; + dc->desc = "i.MX7 Clock Control Module"; + + ccm->get_clock_frequency = imx7_ccm_get_clock_frequency; +} + +static const TypeInfo imx7_ccm_info = { + .name = TYPE_IMX7_CCM, + .parent = TYPE_IMX_CCM, + .instance_size = sizeof(IMX7CCMState), + .instance_init = imx7_ccm_init, + .class_init = imx7_ccm_class_init, +}; + +static const VMStateDescription vmstate_imx7_analog = { + .name = TYPE_IMX7_ANALOG, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(analog, IMX7AnalogState, ANALOG_MAX), + VMSTATE_UINT32_ARRAY(pmu, IMX7AnalogState, PMU_MAX), + VMSTATE_END_OF_LIST() + }, +}; + +static void imx7_analog_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = imx7_analog_reset; + dc->vmsd = &vmstate_imx7_analog; + dc->desc = "i.MX7 Analog Module"; +} + +static const TypeInfo imx7_analog_info = { + .name = TYPE_IMX7_ANALOG, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(IMX7AnalogState), + .instance_init = imx7_analog_init, + .class_init = imx7_analog_class_init, +}; + +static void imx7_ccm_register_type(void) +{ + type_register_static(&imx7_ccm_info); + type_register_static(&imx7_analog_info); +} +type_init(imx7_ccm_register_type) diff --git a/hw/misc/imx7_gpr.c b/hw/misc/imx7_gpr.c new file mode 100644 index 0000000000..c2a9df29c6 --- /dev/null +++ b/hw/misc/imx7_gpr.c @@ -0,0 +1,124 @@ +/* + * Copyright (c) 2018, Impinj, Inc. + * + * i.MX7 GPR IP block emulation code + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + * Bare minimum emulation code needed to support being able to shut + * down linux guest gracefully. + */ + +#include "qemu/osdep.h" +#include "hw/misc/imx7_gpr.h" +#include "qemu/log.h" +#include "sysemu/sysemu.h" + +#include "trace.h" + +enum IMX7GPRRegisters { + IOMUXC_GPR0 = 0x00, + IOMUXC_GPR1 = 0x04, + IOMUXC_GPR2 = 0x08, + IOMUXC_GPR3 = 0x0c, + IOMUXC_GPR4 = 0x10, + IOMUXC_GPR5 = 0x14, + IOMUXC_GPR6 = 0x18, + IOMUXC_GPR7 = 0x1c, + IOMUXC_GPR8 = 0x20, + IOMUXC_GPR9 = 0x24, + IOMUXC_GPR10 = 0x28, + IOMUXC_GPR11 = 0x2c, + IOMUXC_GPR12 = 0x30, + IOMUXC_GPR13 = 0x34, + IOMUXC_GPR14 = 0x38, + IOMUXC_GPR15 = 0x3c, + IOMUXC_GPR16 = 0x40, + IOMUXC_GPR17 = 0x44, + IOMUXC_GPR18 = 0x48, + IOMUXC_GPR19 = 0x4c, + IOMUXC_GPR20 = 0x50, + IOMUXC_GPR21 = 0x54, + IOMUXC_GPR22 = 0x58, +}; + +#define IMX7D_GPR1_IRQ_MASK BIT(12) +#define IMX7D_GPR1_ENET1_TX_CLK_SEL_MASK BIT(13) +#define IMX7D_GPR1_ENET2_TX_CLK_SEL_MASK BIT(14) +#define IMX7D_GPR1_ENET_TX_CLK_SEL_MASK (0x3 << 13) +#define IMX7D_GPR1_ENET1_CLK_DIR_MASK BIT(17) +#define IMX7D_GPR1_ENET2_CLK_DIR_MASK BIT(18) +#define IMX7D_GPR1_ENET_CLK_DIR_MASK (0x3 << 17) + +#define IMX7D_GPR5_CSI_MUX_CONTROL_MIPI BIT(4) +#define IMX7D_GPR12_PCIE_PHY_REFCLK_SEL BIT(5) +#define IMX7D_GPR22_PCIE_PHY_PLL_LOCKED BIT(31) + + +static uint64_t imx7_gpr_read(void *opaque, hwaddr offset, unsigned size) +{ + trace_imx7_gpr_read(offset); + + if (offset == IOMUXC_GPR22) { + return IMX7D_GPR22_PCIE_PHY_PLL_LOCKED; + } + + return 0; +} + +static void imx7_gpr_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + trace_imx7_gpr_write(offset, v); +} + +static const struct MemoryRegionOps imx7_gpr_ops = { + .read = imx7_gpr_read, + .write = imx7_gpr_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + /* + * Our device would not work correctly if the guest was doing + * unaligned access. This might not be a limitation on the + * real device but in practice there is no reason for a guest + * to access this device unaligned. + */ + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void imx7_gpr_init(Object *obj) +{ + SysBusDevice *sd = SYS_BUS_DEVICE(obj); + IMX7GPRState *s = IMX7_GPR(obj); + + memory_region_init_io(&s->mmio, obj, &imx7_gpr_ops, s, + TYPE_IMX7_GPR, 64 * 1024); + sysbus_init_mmio(sd, &s->mmio); +} + +static void imx7_gpr_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "i.MX7 General Purpose Registers Module"; +} + +static const TypeInfo imx7_gpr_info = { + .name = TYPE_IMX7_GPR, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(IMX7GPRState), + .instance_init = imx7_gpr_init, + .class_init = imx7_gpr_class_init, +}; + +static void imx7_gpr_register_type(void) +{ + type_register_static(&imx7_gpr_info); +} +type_init(imx7_gpr_register_type) diff --git a/hw/misc/imx7_snvs.c b/hw/misc/imx7_snvs.c new file mode 100644 index 0000000000..4df482b282 --- /dev/null +++ b/hw/misc/imx7_snvs.c @@ -0,0 +1,83 @@ +/* + * IMX7 Secure Non-Volatile Storage + * + * Copyright (c) 2018, Impinj, Inc. + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + * Bare minimum emulation code needed to support being able to shut + * down linux guest gracefully. + */ + +#include "qemu/osdep.h" +#include "hw/misc/imx7_snvs.h" +#include "qemu/log.h" +#include "sysemu/sysemu.h" + +static uint64_t imx7_snvs_read(void *opaque, hwaddr offset, unsigned size) +{ + return 0; +} + +static void imx7_snvs_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + const uint32_t value = v; + const uint32_t mask = SNVS_LPCR_TOP | SNVS_LPCR_DP_EN; + + if (offset == SNVS_LPCR && ((value & mask) == mask)) { + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + } +} + +static const struct MemoryRegionOps imx7_snvs_ops = { + .read = imx7_snvs_read, + .write = imx7_snvs_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + /* + * Our device would not work correctly if the guest was doing + * unaligned access. This might not be a limitation on the real + * device but in practice there is no reason for a guest to access + * this device unaligned. + */ + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void imx7_snvs_init(Object *obj) +{ + SysBusDevice *sd = SYS_BUS_DEVICE(obj); + IMX7SNVSState *s = IMX7_SNVS(obj); + + memory_region_init_io(&s->mmio, obj, &imx7_snvs_ops, s, + TYPE_IMX7_SNVS, 0x1000); + + sysbus_init_mmio(sd, &s->mmio); +} + +static void imx7_snvs_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "i.MX7 Secure Non-Volatile Storage Module"; +} + +static const TypeInfo imx7_snvs_info = { + .name = TYPE_IMX7_SNVS, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(IMX7SNVSState), + .instance_init = imx7_snvs_init, + .class_init = imx7_snvs_class_init, +}; + +static void imx7_snvs_register_type(void) +{ + type_register_static(&imx7_snvs_info); +} +type_init(imx7_snvs_register_type) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index 616579a403..e6070f280d 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -66,3 +66,7 @@ mps2_scc_cfg_read(unsigned function, unsigned device, uint32_t value) "MPS2 SCC msf2_sysreg_write(uint64_t offset, uint32_t val, uint32_t prev) "msf2-sysreg write: addr 0x%08" HWADDR_PRIx " data 0x%" PRIx32 " prev 0x%" PRIx32 msf2_sysreg_read(uint64_t offset, uint32_t val) "msf2-sysreg read: addr 0x%08" HWADDR_PRIx " data 0x%08" PRIx32 msf2_sysreg_write_pll_status(void) "Invalid write to read only PLL status register" + +#hw/misc/imx7_gpr.c +imx7_gpr_read(uint64_t offset) "addr 0x%08" HWADDR_PRIx +imx7_gpr_write(uint64_t offset, uint64_t value) "addr 0x%08" HWADDR_PRIx "value 0x%08" HWADDR_PRIx diff --git a/hw/sd/sdhci-internal.h b/hw/sd/sdhci-internal.h index fc807f08f3..0991acd724 100644 --- a/hw/sd/sdhci-internal.h +++ b/hw/sd/sdhci-internal.h @@ -84,12 +84,18 @@ /* R/W Host control Register 0x0 */ #define SDHC_HOSTCTL 0x28 +#define SDHC_CTRL_LED 0x01 #define SDHC_CTRL_DMA_CHECK_MASK 0x18 #define SDHC_CTRL_SDMA 0x00 #define SDHC_CTRL_ADMA1_32 0x08 #define SDHC_CTRL_ADMA2_32 0x10 #define SDHC_CTRL_ADMA2_64 0x18 #define SDHC_DMA_TYPE(x) ((x) & SDHC_CTRL_DMA_CHECK_MASK) +#define SDHC_CTRL_4BITBUS 0x02 +#define SDHC_CTRL_8BITBUS 0x20 +#define SDHC_CTRL_CDTEST_INS 0x40 +#define SDHC_CTRL_CDTEST_EN 0x80 + /* R/W Power Control Register 0x0 */ #define SDHC_PWRCON 0x29 @@ -226,4 +232,21 @@ enum { sdhc_gap_write = 2 /* SDHC stopped at block gap during write operation */ }; +extern const VMStateDescription sdhci_vmstate; + + +#define ESDHC_MIX_CTRL 0x48 +#define ESDHC_VENDOR_SPEC 0xc0 +#define ESDHC_DLL_CTRL 0x60 + +#define ESDHC_TUNING_CTRL 0xcc +#define ESDHC_TUNE_CTRL_STATUS 0x68 +#define ESDHC_WTMK_LVL 0x44 + +/* Undocumented register used by guests working around erratum ERR004536 */ +#define ESDHC_UNDOCUMENTED_REG27 0x6c + +#define ESDHC_CTRL_4BITBUS (0x1 << 1) +#define ESDHC_CTRL_8BITBUS (0x2 << 1) + #endif diff --git a/hw/sd/sdhci.c b/hw/sd/sdhci.c index fac7fa5c72..b395ac577d 100644 --- a/hw/sd/sdhci.c +++ b/hw/sd/sdhci.c @@ -244,7 +244,8 @@ static void sdhci_send_command(SDHCIState *s) } } - if ((s->norintstsen & SDHC_NISEN_TRSCMP) && + if (!(s->quirks & SDHCI_QUIRK_NO_BUSY_IRQ) && + (s->norintstsen & SDHC_NISEN_TRSCMP) && (s->cmdreg & SDHC_CMD_RESPONSE) == SDHC_CMD_RSP_WITH_BUSY) { s->norintsts |= SDHC_NIS_TRSCMP; } @@ -1189,6 +1190,8 @@ static void sdhci_initfn(SDHCIState *s) s->insert_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, sdhci_raise_insertion_irq, s); s->transfer_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, sdhci_data_transfer, s); + + s->io_ops = &sdhci_mmio_ops; } static void sdhci_uninitfn(SDHCIState *s) @@ -1396,6 +1399,10 @@ static void sdhci_sysbus_realize(DeviceState *dev, Error ** errp) } sysbus_init_irq(sbd, &s->irq); + + memory_region_init_io(&s->iomem, OBJECT(s), s->io_ops, s, "sdhci", + SDHC_REGISTERS_MAP_SIZE); + sysbus_init_mmio(sbd, &s->iomem); } @@ -1447,11 +1454,232 @@ static const TypeInfo sdhci_bus_info = { .class_init = sdhci_bus_class_init, }; +static uint64_t usdhc_read(void *opaque, hwaddr offset, unsigned size) +{ + SDHCIState *s = SYSBUS_SDHCI(opaque); + uint32_t ret; + uint16_t hostctl; + + switch (offset) { + default: + return sdhci_read(opaque, offset, size); + + case SDHC_HOSTCTL: + /* + * For a detailed explanation on the following bit + * manipulation code see comments in a similar part of + * usdhc_write() + */ + hostctl = SDHC_DMA_TYPE(s->hostctl) << (8 - 3); + + if (s->hostctl & SDHC_CTRL_8BITBUS) { + hostctl |= ESDHC_CTRL_8BITBUS; + } + + if (s->hostctl & SDHC_CTRL_4BITBUS) { + hostctl |= ESDHC_CTRL_4BITBUS; + } + + ret = hostctl; + ret |= (uint32_t)s->blkgap << 16; + ret |= (uint32_t)s->wakcon << 24; + + break; + + case ESDHC_DLL_CTRL: + case ESDHC_TUNE_CTRL_STATUS: + case ESDHC_UNDOCUMENTED_REG27: + case ESDHC_TUNING_CTRL: + case ESDHC_VENDOR_SPEC: + case ESDHC_MIX_CTRL: + case ESDHC_WTMK_LVL: + ret = 0; + break; + } + + return ret; +} + +static void +usdhc_write(void *opaque, hwaddr offset, uint64_t val, unsigned size) +{ + SDHCIState *s = SYSBUS_SDHCI(opaque); + uint8_t hostctl; + uint32_t value = (uint32_t)val; + + switch (offset) { + case ESDHC_DLL_CTRL: + case ESDHC_TUNE_CTRL_STATUS: + case ESDHC_UNDOCUMENTED_REG27: + case ESDHC_TUNING_CTRL: + case ESDHC_WTMK_LVL: + case ESDHC_VENDOR_SPEC: + break; + + case SDHC_HOSTCTL: + /* + * Here's What ESDHCI has at offset 0x28 (SDHC_HOSTCTL) + * + * 7 6 5 4 3 2 1 0 + * |-----------+--------+--------+-----------+----------+---------| + * | Card | Card | Endian | DATA3 | Data | Led | + * | Detect | Detect | Mode | as Card | Transfer | Control | + * | Signal | Test | | Detection | Width | | + * | Selection | Level | | Pin | | | + * |-----------+--------+--------+-----------+----------+---------| + * + * and 0x29 + * + * 15 10 9 8 + * |----------+------| + * | Reserved | DMA | + * | | Sel. | + * | | | + * |----------+------| + * + * and here's what SDCHI spec expects those offsets to be: + * + * 0x28 (Host Control Register) + * + * 7 6 5 4 3 2 1 0 + * |--------+--------+----------+------+--------+----------+---------| + * | Card | Card | Extended | DMA | High | Data | LED | + * | Detect | Detect | Data | Sel. | Speed | Transfer | Control | + * | Signal | Test | Transfer | | Enable | Width | | + * | Sel. | Level | Width | | | | | + * |--------+--------+----------+------+--------+----------+---------| + * + * and 0x29 (Power Control Register) + * + * |----------------------------------| + * | Power Control Register | + * | | + * | Description omitted, | + * | since it has no analog in ESDHCI | + * | | + * |----------------------------------| + * + * Since offsets 0x2A and 0x2B should be compatible between + * both IP specs we only need to reconcile least 16-bit of the + * word we've been given. + */ + + /* + * First, save bits 7 6 and 0 since they are identical + */ + hostctl = value & (SDHC_CTRL_LED | + SDHC_CTRL_CDTEST_INS | + SDHC_CTRL_CDTEST_EN); + /* + * Second, split "Data Transfer Width" from bits 2 and 1 in to + * bits 5 and 1 + */ + if (value & ESDHC_CTRL_8BITBUS) { + hostctl |= SDHC_CTRL_8BITBUS; + } + + if (value & ESDHC_CTRL_4BITBUS) { + hostctl |= ESDHC_CTRL_4BITBUS; + } + + /* + * Third, move DMA select from bits 9 and 8 to bits 4 and 3 + */ + hostctl |= SDHC_DMA_TYPE(value >> (8 - 3)); + + /* + * Now place the corrected value into low 16-bit of the value + * we are going to give standard SDHCI write function + * + * NOTE: This transformation should be the inverse of what can + * be found in drivers/mmc/host/sdhci-esdhc-imx.c in Linux + * kernel + */ + value &= ~UINT16_MAX; + value |= hostctl; + value |= (uint16_t)s->pwrcon << 8; + + sdhci_write(opaque, offset, value, size); + break; + + case ESDHC_MIX_CTRL: + /* + * So, when SD/MMC stack in Linux tries to write to "Transfer + * Mode Register", ESDHC i.MX quirk code will translate it + * into a write to ESDHC_MIX_CTRL, so we do the opposite in + * order to get where we started + * + * Note that Auto CMD23 Enable bit is located in a wrong place + * on i.MX, but since it is not used by QEMU we do not care. + * + * We don't want to call sdhci_write(.., SDHC_TRNMOD, ...) + * here becuase it will result in a call to + * sdhci_send_command(s) which we don't want. + * + */ + s->trnmod = value & UINT16_MAX; + break; + case SDHC_TRNMOD: + /* + * Similar to above, but this time a write to "Command + * Register" will be translated into a 4-byte write to + * "Transfer Mode register" where lower 16-bit of value would + * be set to zero. So what we do is fill those bits with + * cached value from s->trnmod and let the SDHCI + * infrastructure handle the rest + */ + sdhci_write(opaque, offset, val | s->trnmod, size); + break; + case SDHC_BLKSIZE: + /* + * ESDHCI does not implement "Host SDMA Buffer Boundary", and + * Linux driver will try to zero this field out which will + * break the rest of SDHCI emulation. + * + * Linux defaults to maximum possible setting (512K boundary) + * and it seems to be the only option that i.MX IP implements, + * so we artificially set it to that value. + */ + val |= 0x7 << 12; + /* FALLTHROUGH */ + default: + sdhci_write(opaque, offset, val, size); + break; + } +} + + +static const MemoryRegionOps usdhc_mmio_ops = { + .read = usdhc_read, + .write = usdhc_write, + .valid = { + .min_access_size = 1, + .max_access_size = 4, + .unaligned = false + }, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static void imx_usdhc_init(Object *obj) +{ + SDHCIState *s = SYSBUS_SDHCI(obj); + + s->io_ops = &usdhc_mmio_ops; + s->quirks = SDHCI_QUIRK_NO_BUSY_IRQ; +} + +static const TypeInfo imx_usdhc_info = { + .name = TYPE_IMX_USDHC, + .parent = TYPE_SYSBUS_SDHCI, + .instance_init = imx_usdhc_init, +}; + static void sdhci_register_types(void) { type_register_static(&sdhci_pci_info); type_register_static(&sdhci_sysbus_info); type_register_static(&sdhci_bus_info); + type_register_static(&imx_usdhc_info); } type_init(sdhci_register_types) diff --git a/hw/timer/imx_gpt.c b/hw/timer/imx_gpt.c index 4b9b54bf2e..65e4ee6bcf 100644 --- a/hw/timer/imx_gpt.c +++ b/hw/timer/imx_gpt.c @@ -113,6 +113,17 @@ static const IMXClk imx6_gpt_clocks[] = { CLK_HIGH, /* 111 reference clock */ }; +static const IMXClk imx7_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 reference clock */ + CLK_NONE, /* 110 not defined */ + CLK_NONE, /* 111 not defined */ +}; + static void imx_gpt_set_freq(IMXGPTState *s) { uint32_t clksrc = extract32(s->cr, GPT_CR_CLKSRC_SHIFT, 3); @@ -512,6 +523,13 @@ static void imx6_gpt_init(Object *obj) s->clocks = imx6_gpt_clocks; } +static void imx7_gpt_init(Object *obj) +{ + IMXGPTState *s = IMX_GPT(obj); + + s->clocks = imx7_gpt_clocks; +} + static const TypeInfo imx25_gpt_info = { .name = TYPE_IMX25_GPT, .parent = TYPE_SYS_BUS_DEVICE, @@ -532,11 +550,18 @@ static const TypeInfo imx6_gpt_info = { .instance_init = imx6_gpt_init, }; +static const TypeInfo imx7_gpt_info = { + .name = TYPE_IMX7_GPT, + .parent = TYPE_IMX25_GPT, + .instance_init = imx7_gpt_init, +}; + static void imx_gpt_register_types(void) { type_register_static(&imx25_gpt_info); type_register_static(&imx31_gpt_info); type_register_static(&imx6_gpt_info); + type_register_static(&imx7_gpt_info); } type_init(imx_gpt_register_types) diff --git a/hw/usb/Makefile.objs b/hw/usb/Makefile.objs index fbcd498c59..41be700812 100644 --- a/hw/usb/Makefile.objs +++ b/hw/usb/Makefile.objs @@ -12,6 +12,7 @@ common-obj-$(CONFIG_USB_XHCI_NEC) += hcd-xhci-nec.o common-obj-$(CONFIG_USB_MUSB) += hcd-musb.o obj-$(CONFIG_TUSB6010) += tusb6010.o +obj-$(CONFIG_IMX) += chipidea.o # emulated usb devices common-obj-$(CONFIG_USB) += dev-hub.o diff --git a/hw/usb/chipidea.c b/hw/usb/chipidea.c new file mode 100644 index 0000000000..60d67f88b8 --- /dev/null +++ b/hw/usb/chipidea.c @@ -0,0 +1,176 @@ +/* + * Copyright (c) 2018, Impinj, Inc. + * + * Chipidea USB block emulation code + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/usb/hcd-ehci.h" +#include "hw/usb/chipidea.h" +#include "qemu/log.h" + +enum { + CHIPIDEA_USBx_DCIVERSION = 0x000, + CHIPIDEA_USBx_DCCPARAMS = 0x004, + CHIPIDEA_USBx_DCCPARAMS_HC = BIT(8), +}; + +static uint64_t chipidea_read(void *opaque, hwaddr offset, + unsigned size) +{ + return 0; +} + +static void chipidea_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ +} + +static const struct MemoryRegionOps chipidea_ops = { + .read = chipidea_read, + .write = chipidea_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + /* + * Our device would not work correctly if the guest was doing + * unaligned access. This might not be a limitation on the + * real device but in practice there is no reason for a guest + * to access this device unaligned. + */ + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static uint64_t chipidea_dc_read(void *opaque, hwaddr offset, + unsigned size) +{ + switch (offset) { + case CHIPIDEA_USBx_DCIVERSION: + return 0x1; + case CHIPIDEA_USBx_DCCPARAMS: + /* + * Real hardware (at least i.MX7) will also report the + * controller as "Device Capable" (and 8 supported endpoints), + * but there doesn't seem to be much point in doing so, since + * we don't emulate that part. + */ + return CHIPIDEA_USBx_DCCPARAMS_HC; + } + + return 0; +} + +static void chipidea_dc_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ +} + +static const struct MemoryRegionOps chipidea_dc_ops = { + .read = chipidea_dc_read, + .write = chipidea_dc_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + /* + * Our device would not work correctly if the guest was doing + * unaligned access. This might not be a limitation on the real + * device but in practice there is no reason for a guest to access + * this device unaligned. + */ + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void chipidea_init(Object *obj) +{ + EHCIState *ehci = &SYS_BUS_EHCI(obj)->ehci; + ChipideaState *ci = CHIPIDEA(obj); + int i; + + for (i = 0; i < ARRAY_SIZE(ci->iomem); i++) { + const struct { + const char *name; + hwaddr offset; + uint64_t size; + const struct MemoryRegionOps *ops; + } regions[ARRAY_SIZE(ci->iomem)] = { + /* + * Registers located between offsets 0x000 and 0xFC + */ + { + .name = TYPE_CHIPIDEA ".misc", + .offset = 0x000, + .size = 0x100, + .ops = &chipidea_ops, + }, + /* + * Registers located between offsets 0x1A4 and 0x1DC + */ + { + .name = TYPE_CHIPIDEA ".endpoints", + .offset = 0x1A4, + .size = 0x1DC - 0x1A4 + 4, + .ops = &chipidea_ops, + }, + /* + * USB_x_DCIVERSION and USB_x_DCCPARAMS + */ + { + .name = TYPE_CHIPIDEA ".dc", + .offset = 0x120, + .size = 8, + .ops = &chipidea_dc_ops, + }, + }; + + memory_region_init_io(&ci->iomem[i], + obj, + regions[i].ops, + ci, + regions[i].name, + regions[i].size); + + memory_region_add_subregion(&ehci->mem, + regions[i].offset, + &ci->iomem[i]); + } +} + +static void chipidea_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + SysBusEHCIClass *sec = SYS_BUS_EHCI_CLASS(klass); + + /* + * Offsets used were taken from i.MX7Dual Applications Processor + * Reference Manual, Rev 0.1, p. 3177, Table 11-59 + */ + sec->capsbase = 0x100; + sec->opregbase = 0x140; + sec->portnr = 1; + + set_bit(DEVICE_CATEGORY_USB, dc->categories); + dc->desc = "Chipidea USB Module"; +} + +static const TypeInfo chipidea_info = { + .name = TYPE_CHIPIDEA, + .parent = TYPE_SYS_BUS_EHCI, + .instance_size = sizeof(ChipideaState), + .instance_init = chipidea_init, + .class_init = chipidea_class_init, +}; + +static void chipidea_register_type(void) +{ + type_register_static(&chipidea_info); +} +type_init(chipidea_register_type) diff --git a/include/hw/intc/imx_gpcv2.h b/include/hw/intc/imx_gpcv2.h new file mode 100644 index 0000000000..ed978b24bb --- /dev/null +++ b/include/hw/intc/imx_gpcv2.h @@ -0,0 +1,22 @@ +#ifndef IMX_GPCV2_H +#define IMX_GPCV2_H + +#include "hw/sysbus.h" + +enum IMXGPCv2Registers { + GPC_NUM = 0xE00 / sizeof(uint32_t), +}; + +typedef struct IMXGPCv2State { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + MemoryRegion iomem; + uint32_t regs[GPC_NUM]; +} IMXGPCv2State; + +#define TYPE_IMX_GPCV2 "imx-gpcv2" +#define IMX_GPCV2(obj) OBJECT_CHECK(IMXGPCv2State, (obj), TYPE_IMX_GPCV2) + +#endif /* IMX_GPCV2_H */ diff --git a/include/hw/misc/imx2_wdt.h b/include/hw/misc/imx2_wdt.h new file mode 100644 index 0000000000..8afc99a10e --- /dev/null +++ b/include/hw/misc/imx2_wdt.h @@ -0,0 +1,33 @@ +/* + * Copyright (c) 2017, Impinj, Inc. + * + * i.MX2 Watchdog IP block + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef IMX2_WDT_H +#define IMX2_WDT_H + +#include "hw/sysbus.h" + +#define TYPE_IMX2_WDT "imx2.wdt" +#define IMX2_WDT(obj) OBJECT_CHECK(IMX2WdtState, (obj), TYPE_IMX2_WDT) + +enum IMX2WdtRegisters { + IMX2_WDT_WCR = 0x0000, + IMX2_WDT_REG_NUM = 0x0008 / sizeof(uint16_t) + 1, +}; + + +typedef struct IMX2WdtState { + /* <private> */ + SysBusDevice parent_obj; + + MemoryRegion mmio; +} IMX2WdtState; + +#endif /* IMX7_SNVS_H */ diff --git a/include/hw/misc/imx7_ccm.h b/include/hw/misc/imx7_ccm.h new file mode 100644 index 0000000000..9538f37d98 --- /dev/null +++ b/include/hw/misc/imx7_ccm.h @@ -0,0 +1,139 @@ +/* + * Copyright (c) 2017, Impinj, Inc. + * + * i.MX7 CCM, PMU and ANALOG IP blocks emulation code + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef IMX7_CCM_H +#define IMX7_CCM_H + +#include "hw/misc/imx_ccm.h" +#include "qemu/bitops.h" + +enum IMX7AnalogRegisters { + ANALOG_PLL_ARM, + ANALOG_PLL_ARM_SET, + ANALOG_PLL_ARM_CLR, + ANALOG_PLL_ARM_TOG, + ANALOG_PLL_DDR, + ANALOG_PLL_DDR_SET, + ANALOG_PLL_DDR_CLR, + ANALOG_PLL_DDR_TOG, + ANALOG_PLL_DDR_SS, + ANALOG_PLL_DDR_SS_SET, + ANALOG_PLL_DDR_SS_CLR, + ANALOG_PLL_DDR_SS_TOG, + ANALOG_PLL_DDR_NUM, + ANALOG_PLL_DDR_NUM_SET, + ANALOG_PLL_DDR_NUM_CLR, + ANALOG_PLL_DDR_NUM_TOG, + ANALOG_PLL_DDR_DENOM, + ANALOG_PLL_DDR_DENOM_SET, + ANALOG_PLL_DDR_DENOM_CLR, + ANALOG_PLL_DDR_DENOM_TOG, + ANALOG_PLL_480, + ANALOG_PLL_480_SET, + ANALOG_PLL_480_CLR, + ANALOG_PLL_480_TOG, + ANALOG_PLL_480A, + ANALOG_PLL_480A_SET, + ANALOG_PLL_480A_CLR, + ANALOG_PLL_480A_TOG, + ANALOG_PLL_480B, + ANALOG_PLL_480B_SET, + ANALOG_PLL_480B_CLR, + ANALOG_PLL_480B_TOG, + ANALOG_PLL_ENET, + ANALOG_PLL_ENET_SET, + ANALOG_PLL_ENET_CLR, + ANALOG_PLL_ENET_TOG, + ANALOG_PLL_AUDIO, + ANALOG_PLL_AUDIO_SET, + ANALOG_PLL_AUDIO_CLR, + ANALOG_PLL_AUDIO_TOG, + ANALOG_PLL_AUDIO_SS, + ANALOG_PLL_AUDIO_SS_SET, + ANALOG_PLL_AUDIO_SS_CLR, + ANALOG_PLL_AUDIO_SS_TOG, + ANALOG_PLL_AUDIO_NUM, + ANALOG_PLL_AUDIO_NUM_SET, + ANALOG_PLL_AUDIO_NUM_CLR, + ANALOG_PLL_AUDIO_NUM_TOG, + ANALOG_PLL_AUDIO_DENOM, + ANALOG_PLL_AUDIO_DENOM_SET, + ANALOG_PLL_AUDIO_DENOM_CLR, + ANALOG_PLL_AUDIO_DENOM_TOG, + ANALOG_PLL_VIDEO, + ANALOG_PLL_VIDEO_SET, + ANALOG_PLL_VIDEO_CLR, + ANALOG_PLL_VIDEO_TOG, + ANALOG_PLL_VIDEO_SS, + ANALOG_PLL_VIDEO_SS_SET, + ANALOG_PLL_VIDEO_SS_CLR, + ANALOG_PLL_VIDEO_SS_TOG, + ANALOG_PLL_VIDEO_NUM, + ANALOG_PLL_VIDEO_NUM_SET, + ANALOG_PLL_VIDEO_NUM_CLR, + ANALOG_PLL_VIDEO_NUM_TOG, + ANALOG_PLL_VIDEO_DENOM, + ANALOG_PLL_VIDEO_DENOM_SET, + ANALOG_PLL_VIDEO_DENOM_CLR, + ANALOG_PLL_VIDEO_DENOM_TOG, + ANALOG_PLL_MISC0, + ANALOG_PLL_MISC0_SET, + ANALOG_PLL_MISC0_CLR, + ANALOG_PLL_MISC0_TOG, + + ANALOG_DIGPROG = 0x800 / sizeof(uint32_t), + ANALOG_MAX, + + ANALOG_PLL_LOCK = BIT(31) +}; + +enum IMX7CCMRegisters { + CCM_MAX = 0xBE00 / sizeof(uint32_t) + 1, +}; + +enum IMX7PMURegisters { + PMU_MAX = 0x140 / sizeof(uint32_t), +}; + +#define TYPE_IMX7_CCM "imx7.ccm" +#define IMX7_CCM(obj) OBJECT_CHECK(IMX7CCMState, (obj), TYPE_IMX7_CCM) + +typedef struct IMX7CCMState { + /* <private> */ + IMXCCMState parent_obj; + + /* <public> */ + MemoryRegion iomem; + + uint32_t ccm[CCM_MAX]; +} IMX7CCMState; + + +#define TYPE_IMX7_ANALOG "imx7.analog" +#define IMX7_ANALOG(obj) OBJECT_CHECK(IMX7AnalogState, (obj), TYPE_IMX7_ANALOG) + +typedef struct IMX7AnalogState { + /* <private> */ + IMXCCMState parent_obj; + + /* <public> */ + struct { + MemoryRegion container; + MemoryRegion analog; + MemoryRegion digprog; + MemoryRegion pmu; + } mmio; + + uint32_t analog[ANALOG_MAX]; + uint32_t pmu[PMU_MAX]; +} IMX7AnalogState; + +#endif /* IMX7_CCM_H */ diff --git a/include/hw/misc/imx7_gpr.h b/include/hw/misc/imx7_gpr.h new file mode 100644 index 0000000000..e19373d274 --- /dev/null +++ b/include/hw/misc/imx7_gpr.h @@ -0,0 +1,28 @@ +/* + * Copyright (c) 2017, Impinj, Inc. + * + * i.MX7 GPR IP block emulation code + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef IMX7_GPR_H +#define IMX7_GPR_H + +#include "qemu/bitops.h" +#include "hw/sysbus.h" + +#define TYPE_IMX7_GPR "imx7.gpr" +#define IMX7_GPR(obj) OBJECT_CHECK(IMX7GPRState, (obj), TYPE_IMX7_GPR) + +typedef struct IMX7GPRState { + /* <private> */ + SysBusDevice parent_obj; + + MemoryRegion mmio; +} IMX7GPRState; + +#endif /* IMX7_GPR_H */ diff --git a/include/hw/misc/imx7_snvs.h b/include/hw/misc/imx7_snvs.h new file mode 100644 index 0000000000..255f8f26f9 --- /dev/null +++ b/include/hw/misc/imx7_snvs.h @@ -0,0 +1,35 @@ +/* + * Copyright (c) 2017, Impinj, Inc. + * + * i.MX7 SNVS block emulation code + * + * Author: Andrey Smirnov <andrew.smirnov@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef IMX7_SNVS_H +#define IMX7_SNVS_H + +#include "qemu/bitops.h" +#include "hw/sysbus.h" + + +enum IMX7SNVSRegisters { + SNVS_LPCR = 0x38, + SNVS_LPCR_TOP = BIT(6), + SNVS_LPCR_DP_EN = BIT(5) +}; + +#define TYPE_IMX7_SNVS "imx7.snvs" +#define IMX7_SNVS(obj) OBJECT_CHECK(IMX7SNVSState, (obj), TYPE_IMX7_SNVS) + +typedef struct IMX7SNVSState { + /* <private> */ + SysBusDevice parent_obj; + + MemoryRegion mmio; +} IMX7SNVSState; + +#endif /* IMX7_SNVS_H */ diff --git a/include/hw/sd/sdhci.h b/include/hw/sd/sdhci.h index 1cf70f8c23..f8d1ba3538 100644 --- a/include/hw/sd/sdhci.h +++ b/include/hw/sd/sdhci.h @@ -44,6 +44,7 @@ typedef struct SDHCIState { AddressSpace sysbus_dma_as; AddressSpace *dma_as; MemoryRegion *dma_mr; + const MemoryRegionOps *io_ops; QEMUTimer *insert_timer; /* timer for 'changing' sd card. */ QEMUTimer *transfer_timer; @@ -91,8 +92,18 @@ typedef struct SDHCIState { /* Configurable properties */ bool pending_insert_quirk; /* Quirk for Raspberry Pi card insert int */ + uint32_t quirks; } SDHCIState; +/* + * Controller does not provide transfer-complete interrupt when not + * busy. + * + * NOTE: This definition is taken out of Linux kernel and so the + * original bit number is preserved + */ +#define SDHCI_QUIRK_NO_BUSY_IRQ BIT(14) + #define TYPE_PCI_SDHCI "sdhci-pci" #define PCI_SDHCI(obj) OBJECT_CHECK(SDHCIState, (obj), TYPE_PCI_SDHCI) @@ -100,4 +111,6 @@ typedef struct SDHCIState { #define SYSBUS_SDHCI(obj) \ OBJECT_CHECK(SDHCIState, (obj), TYPE_SYSBUS_SDHCI) +#define TYPE_IMX_USDHC "imx-usdhc" + #endif /* SDHCI_H */ diff --git a/include/hw/timer/imx_gpt.h b/include/hw/timer/imx_gpt.h index eac59b2a70..20ccb327c4 100644 --- a/include/hw/timer/imx_gpt.h +++ b/include/hw/timer/imx_gpt.h @@ -77,6 +77,7 @@ #define TYPE_IMX25_GPT "imx25.gpt" #define TYPE_IMX31_GPT "imx31.gpt" #define TYPE_IMX6_GPT "imx6.gpt" +#define TYPE_IMX7_GPT "imx7.gpt" #define TYPE_IMX_GPT TYPE_IMX25_GPT diff --git a/include/hw/usb/chipidea.h b/include/hw/usb/chipidea.h new file mode 100644 index 0000000000..1ec2e9dbda --- /dev/null +++ b/include/hw/usb/chipidea.h @@ -0,0 +1,16 @@ +#ifndef CHIPIDEA_H +#define CHIPIDEA_H + +#include "hw/usb/hcd-ehci.h" + +typedef struct ChipideaState { + /*< private >*/ + EHCISysBusState parent_obj; + + MemoryRegion iomem[3]; +} ChipideaState; + +#define TYPE_CHIPIDEA "usb-chipidea" +#define CHIPIDEA(obj) OBJECT_CHECK(ChipideaState, (obj), TYPE_CHIPIDEA) + +#endif /* CHIPIDEA_H */ diff --git a/linux-user/elfload.c b/linux-user/elfload.c index 32a47674e6..8bb9a2c3e8 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -512,6 +512,21 @@ enum { ARM_HWCAP_A64_SHA1 = 1 << 5, ARM_HWCAP_A64_SHA2 = 1 << 6, ARM_HWCAP_A64_CRC32 = 1 << 7, + ARM_HWCAP_A64_ATOMICS = 1 << 8, + ARM_HWCAP_A64_FPHP = 1 << 9, + ARM_HWCAP_A64_ASIMDHP = 1 << 10, + ARM_HWCAP_A64_CPUID = 1 << 11, + ARM_HWCAP_A64_ASIMDRDM = 1 << 12, + ARM_HWCAP_A64_JSCVT = 1 << 13, + ARM_HWCAP_A64_FCMA = 1 << 14, + ARM_HWCAP_A64_LRCPC = 1 << 15, + ARM_HWCAP_A64_DCPOP = 1 << 16, + ARM_HWCAP_A64_SHA3 = 1 << 17, + ARM_HWCAP_A64_SM3 = 1 << 18, + ARM_HWCAP_A64_SM4 = 1 << 19, + ARM_HWCAP_A64_ASIMDDP = 1 << 20, + ARM_HWCAP_A64_SHA512 = 1 << 21, + ARM_HWCAP_A64_SVE = 1 << 22, }; #define ELF_HWCAP get_elf_hwcap() @@ -532,6 +547,10 @@ static uint32_t get_elf_hwcap(void) GET_FEATURE(ARM_FEATURE_V8_SHA1, ARM_HWCAP_A64_SHA1); GET_FEATURE(ARM_FEATURE_V8_SHA256, ARM_HWCAP_A64_SHA2); GET_FEATURE(ARM_FEATURE_CRC, ARM_HWCAP_A64_CRC32); + GET_FEATURE(ARM_FEATURE_V8_SHA3, ARM_HWCAP_A64_SHA3); + GET_FEATURE(ARM_FEATURE_V8_SM3, ARM_HWCAP_A64_SM3); + GET_FEATURE(ARM_FEATURE_V8_SM4, ARM_HWCAP_A64_SM4); + GET_FEATURE(ARM_FEATURE_V8_SHA512, ARM_HWCAP_A64_SHA512); #undef GET_FEATURE return hwcaps; diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 8d41f783dc..521444a5a1 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -153,6 +153,49 @@ typedef struct { uint32_t base_mask; } TCR; +/* Define a maximum sized vector register. + * For 32-bit, this is a 128-bit NEON/AdvSIMD register. + * For 64-bit, this is a 2048-bit SVE register. + * + * Note that the mapping between S, D, and Q views of the register bank + * differs between AArch64 and AArch32. + * In AArch32: + * Qn = regs[n].d[1]:regs[n].d[0] + * Dn = regs[n / 2].d[n & 1] + * Sn = regs[n / 4].d[n % 4 / 2], + * bits 31..0 for even n, and bits 63..32 for odd n + * (and regs[16] to regs[31] are inaccessible) + * In AArch64: + * Zn = regs[n].d[*] + * Qn = regs[n].d[1]:regs[n].d[0] + * Dn = regs[n].d[0] + * Sn = regs[n].d[0] bits 31..0 + * + * This corresponds to the architecturally defined mapping between + * the two execution states, and means we do not need to explicitly + * map these registers when changing states. + * + * Align the data for use with TCG host vector operations. + */ + +#ifdef TARGET_AARCH64 +# define ARM_MAX_VQ 16 +#else +# define ARM_MAX_VQ 1 +#endif + +typedef struct ARMVectorReg { + uint64_t d[2 * ARM_MAX_VQ] QEMU_ALIGNED(16); +} ARMVectorReg; + +/* In AArch32 mode, predicate registers do not exist at all. */ +#ifdef TARGET_AARCH64 +typedef struct ARMPredicateReg { + uint64_t p[2 * ARM_MAX_VQ / 8] QEMU_ALIGNED(16); +} ARMPredicateReg; +#endif + + typedef struct CPUARMState { /* Regs for current mode. */ uint32_t regs[16]; @@ -477,22 +520,12 @@ typedef struct CPUARMState { /* VFP coprocessor state. */ struct { - /* VFP/Neon register state. Note that the mapping between S, D and Q - * views of the register bank differs between AArch64 and AArch32: - * In AArch32: - * Qn = regs[2n+1]:regs[2n] - * Dn = regs[n] - * Sn = regs[n/2] bits 31..0 for even n, and bits 63..32 for odd n - * (and regs[32] to regs[63] are inaccessible) - * In AArch64: - * Qn = regs[2n+1]:regs[2n] - * Dn = regs[2n] - * Sn = regs[2n] bits 31..0 - * This corresponds to the architecturally defined mapping between - * the two execution states, and means we do not need to explicitly - * map these registers when changing states. - */ - uint64_t regs[64] QEMU_ALIGNED(16); + ARMVectorReg zregs[32]; + +#ifdef TARGET_AARCH64 + /* Store FFR as pregs[16] to make it easier to treat as any other. */ + ARMPredicateReg pregs[17]; +#endif uint32_t xregs[16]; /* We store these fpcsr fields separately for convenience. */ @@ -516,6 +549,9 @@ typedef struct CPUARMState { */ float_status fp_status; float_status standard_fp_status; + + /* ZCR_EL[1-3] */ + uint64_t zcr_el[4]; } vfp; uint64_t exclusive_addr; uint64_t exclusive_val; @@ -890,6 +926,8 @@ void pmccntr_sync(CPUARMState *env); #define CPTR_TCPAC (1U << 31) #define CPTR_TTA (1U << 20) #define CPTR_TFP (1U << 10) +#define CPTR_TZ (1U << 8) /* CPTR_EL2 */ +#define CPTR_EZ (1U << 8) /* CPTR_EL3 */ #define MDCR_EPMAD (1U << 21) #define MDCR_EDAD (1U << 20) @@ -1341,6 +1379,10 @@ enum arm_features { ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ ARM_FEATURE_JAZELLE, /* has (trivial) Jazelle implementation */ ARM_FEATURE_SVE, /* has Scalable Vector Extension */ + ARM_FEATURE_V8_SHA512, /* implements SHA512 part of v8 Crypto Extensions */ + ARM_FEATURE_V8_SHA3, /* implements SHA3 part of v8 Crypto Extensions */ + ARM_FEATURE_V8_SM3, /* implements SM3 part of v8 Crypto Extensions */ + ARM_FEATURE_V8_SM4, /* implements SM4 part of v8 Crypto Extensions */ }; static inline int arm_feature(CPUARMState *env, int feature) @@ -1506,16 +1548,42 @@ static inline bool armv7m_nvic_can_take_pending_exception(void *opaque) */ void armv7m_nvic_set_pending(void *opaque, int irq, bool secure); /** + * armv7m_nvic_set_pending_derived: mark this derived exception as pending + * @opaque: the NVIC + * @irq: the exception number to mark pending + * @secure: false for non-banked exceptions or for the nonsecure + * version of a banked exception, true for the secure version of a banked + * exception. + * + * Similar to armv7m_nvic_set_pending(), but specifically for derived + * exceptions (exceptions generated in the course of trying to take + * a different exception). + */ +void armv7m_nvic_set_pending_derived(void *opaque, int irq, bool secure); +/** + * armv7m_nvic_get_pending_irq_info: return highest priority pending + * exception, and whether it targets Secure state + * @opaque: the NVIC + * @pirq: set to pending exception number + * @ptargets_secure: set to whether pending exception targets Secure + * + * This function writes the number of the highest priority pending + * exception (the one which would be made active by + * armv7m_nvic_acknowledge_irq()) to @pirq, and sets @ptargets_secure + * to true if the current highest priority pending exception should + * be taken to Secure state, false for NS. + */ +void armv7m_nvic_get_pending_irq_info(void *opaque, int *pirq, + bool *ptargets_secure); +/** * armv7m_nvic_acknowledge_irq: make highest priority pending exception active * @opaque: the NVIC * * Move the current highest priority pending exception from the pending * state to the active state, and update v7m.exception to indicate that * it is the exception currently being handled. - * - * Returns: true if exception should be taken to Secure state, false for NS */ -bool armv7m_nvic_acknowledge_irq(void *opaque); +void armv7m_nvic_acknowledge_irq(void *opaque); /** * armv7m_nvic_complete_irq: complete specified interrupt or exception * @opaque: the NVIC @@ -2610,6 +2678,10 @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env) #define ARM_TBFLAG_TBI0_MASK (0x1ull << ARM_TBFLAG_TBI0_SHIFT) #define ARM_TBFLAG_TBI1_SHIFT 1 /* TBI1 for EL0/1 */ #define ARM_TBFLAG_TBI1_MASK (0x1ull << ARM_TBFLAG_TBI1_SHIFT) +#define ARM_TBFLAG_SVEEXC_EL_SHIFT 2 +#define ARM_TBFLAG_SVEEXC_EL_MASK (0x3 << ARM_TBFLAG_SVEEXC_EL_SHIFT) +#define ARM_TBFLAG_ZCR_LEN_SHIFT 4 +#define ARM_TBFLAG_ZCR_LEN_MASK (0xf << ARM_TBFLAG_ZCR_LEN_SHIFT) /* some convenience accessor macros */ #define ARM_TBFLAG_AARCH64_STATE(F) \ @@ -2646,6 +2718,10 @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env) (((F) & ARM_TBFLAG_TBI0_MASK) >> ARM_TBFLAG_TBI0_SHIFT) #define ARM_TBFLAG_TBI1(F) \ (((F) & ARM_TBFLAG_TBI1_MASK) >> ARM_TBFLAG_TBI1_SHIFT) +#define ARM_TBFLAG_SVEEXC_EL(F) \ + (((F) & ARM_TBFLAG_SVEEXC_EL_MASK) >> ARM_TBFLAG_SVEEXC_EL_SHIFT) +#define ARM_TBFLAG_ZCR_LEN(F) \ + (((F) & ARM_TBFLAG_ZCR_LEN_MASK) >> ARM_TBFLAG_ZCR_LEN_SHIFT) static inline bool bswap_code(bool sctlr_b) { @@ -2769,7 +2845,7 @@ static inline void *arm_get_el_change_hook_opaque(ARMCPU *cpu) */ static inline uint64_t *aa32_vfp_dreg(CPUARMState *env, unsigned regno) { - return &env->vfp.regs[regno]; + return &env->vfp.zregs[regno >> 1].d[regno & 1]; } /** @@ -2778,7 +2854,7 @@ static inline uint64_t *aa32_vfp_dreg(CPUARMState *env, unsigned regno) */ static inline uint64_t *aa32_vfp_qreg(CPUARMState *env, unsigned regno) { - return &env->vfp.regs[2 * regno]; + return &env->vfp.zregs[regno].d[0]; } /** @@ -2787,7 +2863,7 @@ static inline uint64_t *aa32_vfp_qreg(CPUARMState *env, unsigned regno) */ static inline uint64_t *aa64_vfp_qreg(CPUARMState *env, unsigned regno) { - return &env->vfp.regs[2 * regno]; + return &env->vfp.zregs[regno].d[0]; } #endif diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index 670c07ab6e..1c330adc28 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -224,6 +224,10 @@ static void aarch64_any_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8_AES); set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); + set_feature(&cpu->env, ARM_FEATURE_V8_SHA512); + set_feature(&cpu->env, ARM_FEATURE_V8_SHA3); + set_feature(&cpu->env, ARM_FEATURE_V8_SM3); + set_feature(&cpu->env, ARM_FEATURE_V8_SM4); set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); set_feature(&cpu->env, ARM_FEATURE_CRC); cpu->ctr = 0x80038003; /* 32 byte I and D cacheline size, VIPT icache */ diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index 9ca0bdead7..cc339ea7e0 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -1,7 +1,7 @@ /* * crypto_helper.c - emulate v8 Crypto Extensions instructions * - * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2013 - 2018 Linaro Ltd <ard.biesheuvel@linaro.org> * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public @@ -419,3 +419,278 @@ void HELPER(crypto_sha256su1)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; } + +/* + * The SHA-512 logical functions (same as above but using 64-bit operands) + */ + +static uint64_t cho512(uint64_t x, uint64_t y, uint64_t z) +{ + return (x & (y ^ z)) ^ z; +} + +static uint64_t maj512(uint64_t x, uint64_t y, uint64_t z) +{ + return (x & y) | ((x | y) & z); +} + +static uint64_t S0_512(uint64_t x) +{ + return ror64(x, 28) ^ ror64(x, 34) ^ ror64(x, 39); +} + +static uint64_t S1_512(uint64_t x) +{ + return ror64(x, 14) ^ ror64(x, 18) ^ ror64(x, 41); +} + +static uint64_t s0_512(uint64_t x) +{ + return ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7); +} + +static uint64_t s1_512(uint64_t x) +{ + return ror64(x, 19) ^ ror64(x, 61) ^ (x >> 6); +} + +void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm) +{ + uint64_t *rd = vd; + uint64_t *rn = vn; + uint64_t *rm = vm; + uint64_t d0 = rd[0]; + uint64_t d1 = rd[1]; + + d1 += S1_512(rm[1]) + cho512(rm[1], rn[0], rn[1]); + d0 += S1_512(d1 + rm[0]) + cho512(d1 + rm[0], rm[1], rn[0]); + + rd[0] = d0; + rd[1] = d1; +} + +void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm) +{ + uint64_t *rd = vd; + uint64_t *rn = vn; + uint64_t *rm = vm; + uint64_t d0 = rd[0]; + uint64_t d1 = rd[1]; + + d1 += S0_512(rm[0]) + maj512(rn[0], rm[1], rm[0]); + d0 += S0_512(d1) + maj512(d1, rm[0], rm[1]); + + rd[0] = d0; + rd[1] = d1; +} + +void HELPER(crypto_sha512su0)(void *vd, void *vn) +{ + uint64_t *rd = vd; + uint64_t *rn = vn; + uint64_t d0 = rd[0]; + uint64_t d1 = rd[1]; + + d0 += s0_512(rd[1]); + d1 += s0_512(rn[0]); + + rd[0] = d0; + rd[1] = d1; +} + +void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm) +{ + uint64_t *rd = vd; + uint64_t *rn = vn; + uint64_t *rm = vm; + + rd[0] += s1_512(rn[0]) + rm[0]; + rd[1] += s1_512(rn[1]) + rm[1]; +} + +void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm) +{ + uint64_t *rd = vd; + uint64_t *rn = vn; + uint64_t *rm = vm; + union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; + union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; + union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; + uint32_t t; + + t = CR_ST_WORD(d, 0) ^ CR_ST_WORD(n, 0) ^ ror32(CR_ST_WORD(m, 1), 17); + CR_ST_WORD(d, 0) = t ^ ror32(t, 17) ^ ror32(t, 9); + + t = CR_ST_WORD(d, 1) ^ CR_ST_WORD(n, 1) ^ ror32(CR_ST_WORD(m, 2), 17); + CR_ST_WORD(d, 1) = t ^ ror32(t, 17) ^ ror32(t, 9); + + t = CR_ST_WORD(d, 2) ^ CR_ST_WORD(n, 2) ^ ror32(CR_ST_WORD(m, 3), 17); + CR_ST_WORD(d, 2) = t ^ ror32(t, 17) ^ ror32(t, 9); + + t = CR_ST_WORD(d, 3) ^ CR_ST_WORD(n, 3) ^ ror32(CR_ST_WORD(d, 0), 17); + CR_ST_WORD(d, 3) = t ^ ror32(t, 17) ^ ror32(t, 9); + + rd[0] = d.l[0]; + rd[1] = d.l[1]; +} + +void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm) +{ + uint64_t *rd = vd; + uint64_t *rn = vn; + uint64_t *rm = vm; + union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; + union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; + union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; + uint32_t t = CR_ST_WORD(n, 0) ^ ror32(CR_ST_WORD(m, 0), 25); + + CR_ST_WORD(d, 0) ^= t; + CR_ST_WORD(d, 1) ^= CR_ST_WORD(n, 1) ^ ror32(CR_ST_WORD(m, 1), 25); + CR_ST_WORD(d, 2) ^= CR_ST_WORD(n, 2) ^ ror32(CR_ST_WORD(m, 2), 25); + CR_ST_WORD(d, 3) ^= CR_ST_WORD(n, 3) ^ ror32(CR_ST_WORD(m, 3), 25) ^ + ror32(t, 17) ^ ror32(t, 2) ^ ror32(t, 26); + + rd[0] = d.l[0]; + rd[1] = d.l[1]; +} + +void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2, + uint32_t opcode) +{ + uint64_t *rd = vd; + uint64_t *rn = vn; + uint64_t *rm = vm; + union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; + union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; + union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; + uint32_t t; + + assert(imm2 < 4); + + if (opcode == 0 || opcode == 2) { + /* SM3TT1A, SM3TT2A */ + t = par(CR_ST_WORD(d, 3), CR_ST_WORD(d, 2), CR_ST_WORD(d, 1)); + } else if (opcode == 1) { + /* SM3TT1B */ + t = maj(CR_ST_WORD(d, 3), CR_ST_WORD(d, 2), CR_ST_WORD(d, 1)); + } else if (opcode == 3) { + /* SM3TT2B */ + t = cho(CR_ST_WORD(d, 3), CR_ST_WORD(d, 2), CR_ST_WORD(d, 1)); + } else { + g_assert_not_reached(); + } + + t += CR_ST_WORD(d, 0) + CR_ST_WORD(m, imm2); + + CR_ST_WORD(d, 0) = CR_ST_WORD(d, 1); + + if (opcode < 2) { + /* SM3TT1A, SM3TT1B */ + t += CR_ST_WORD(n, 3) ^ ror32(CR_ST_WORD(d, 3), 20); + + CR_ST_WORD(d, 1) = ror32(CR_ST_WORD(d, 2), 23); + } else { + /* SM3TT2A, SM3TT2B */ + t += CR_ST_WORD(n, 3); + t ^= rol32(t, 9) ^ rol32(t, 17); + + CR_ST_WORD(d, 1) = ror32(CR_ST_WORD(d, 2), 13); + } + + CR_ST_WORD(d, 2) = CR_ST_WORD(d, 3); + CR_ST_WORD(d, 3) = t; + + rd[0] = d.l[0]; + rd[1] = d.l[1]; +} + +static uint8_t const sm4_sbox[] = { + 0xd6, 0x90, 0xe9, 0xfe, 0xcc, 0xe1, 0x3d, 0xb7, + 0x16, 0xb6, 0x14, 0xc2, 0x28, 0xfb, 0x2c, 0x05, + 0x2b, 0x67, 0x9a, 0x76, 0x2a, 0xbe, 0x04, 0xc3, + 0xaa, 0x44, 0x13, 0x26, 0x49, 0x86, 0x06, 0x99, + 0x9c, 0x42, 0x50, 0xf4, 0x91, 0xef, 0x98, 0x7a, + 0x33, 0x54, 0x0b, 0x43, 0xed, 0xcf, 0xac, 0x62, + 0xe4, 0xb3, 0x1c, 0xa9, 0xc9, 0x08, 0xe8, 0x95, + 0x80, 0xdf, 0x94, 0xfa, 0x75, 0x8f, 0x3f, 0xa6, + 0x47, 0x07, 0xa7, 0xfc, 0xf3, 0x73, 0x17, 0xba, + 0x83, 0x59, 0x3c, 0x19, 0xe6, 0x85, 0x4f, 0xa8, + 0x68, 0x6b, 0x81, 0xb2, 0x71, 0x64, 0xda, 0x8b, + 0xf8, 0xeb, 0x0f, 0x4b, 0x70, 0x56, 0x9d, 0x35, + 0x1e, 0x24, 0x0e, 0x5e, 0x63, 0x58, 0xd1, 0xa2, + 0x25, 0x22, 0x7c, 0x3b, 0x01, 0x21, 0x78, 0x87, + 0xd4, 0x00, 0x46, 0x57, 0x9f, 0xd3, 0x27, 0x52, + 0x4c, 0x36, 0x02, 0xe7, 0xa0, 0xc4, 0xc8, 0x9e, + 0xea, 0xbf, 0x8a, 0xd2, 0x40, 0xc7, 0x38, 0xb5, + 0xa3, 0xf7, 0xf2, 0xce, 0xf9, 0x61, 0x15, 0xa1, + 0xe0, 0xae, 0x5d, 0xa4, 0x9b, 0x34, 0x1a, 0x55, + 0xad, 0x93, 0x32, 0x30, 0xf5, 0x8c, 0xb1, 0xe3, + 0x1d, 0xf6, 0xe2, 0x2e, 0x82, 0x66, 0xca, 0x60, + 0xc0, 0x29, 0x23, 0xab, 0x0d, 0x53, 0x4e, 0x6f, + 0xd5, 0xdb, 0x37, 0x45, 0xde, 0xfd, 0x8e, 0x2f, + 0x03, 0xff, 0x6a, 0x72, 0x6d, 0x6c, 0x5b, 0x51, + 0x8d, 0x1b, 0xaf, 0x92, 0xbb, 0xdd, 0xbc, 0x7f, + 0x11, 0xd9, 0x5c, 0x41, 0x1f, 0x10, 0x5a, 0xd8, + 0x0a, 0xc1, 0x31, 0x88, 0xa5, 0xcd, 0x7b, 0xbd, + 0x2d, 0x74, 0xd0, 0x12, 0xb8, 0xe5, 0xb4, 0xb0, + 0x89, 0x69, 0x97, 0x4a, 0x0c, 0x96, 0x77, 0x7e, + 0x65, 0xb9, 0xf1, 0x09, 0xc5, 0x6e, 0xc6, 0x84, + 0x18, 0xf0, 0x7d, 0xec, 0x3a, 0xdc, 0x4d, 0x20, + 0x79, 0xee, 0x5f, 0x3e, 0xd7, 0xcb, 0x39, 0x48, +}; + +void HELPER(crypto_sm4e)(void *vd, void *vn) +{ + uint64_t *rd = vd; + uint64_t *rn = vn; + union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; + union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; + uint32_t t, i; + + for (i = 0; i < 4; i++) { + t = CR_ST_WORD(d, (i + 1) % 4) ^ + CR_ST_WORD(d, (i + 2) % 4) ^ + CR_ST_WORD(d, (i + 3) % 4) ^ + CR_ST_WORD(n, i); + + t = sm4_sbox[t & 0xff] | + sm4_sbox[(t >> 8) & 0xff] << 8 | + sm4_sbox[(t >> 16) & 0xff] << 16 | + sm4_sbox[(t >> 24) & 0xff] << 24; + + CR_ST_WORD(d, i) ^= t ^ rol32(t, 2) ^ rol32(t, 10) ^ rol32(t, 18) ^ + rol32(t, 24); + } + + rd[0] = d.l[0]; + rd[1] = d.l[1]; +} + +void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm) +{ + uint64_t *rd = vd; + uint64_t *rn = vn; + uint64_t *rm = vm; + union CRYPTO_STATE d; + union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; + union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; + uint32_t t, i; + + d = n; + for (i = 0; i < 4; i++) { + t = CR_ST_WORD(d, (i + 1) % 4) ^ + CR_ST_WORD(d, (i + 2) % 4) ^ + CR_ST_WORD(d, (i + 3) % 4) ^ + CR_ST_WORD(m, i); + + t = sm4_sbox[t & 0xff] | + sm4_sbox[(t >> 8) & 0xff] << 8 | + sm4_sbox[(t >> 16) & 0xff] << 16 | + sm4_sbox[(t >> 24) & 0xff] << 24; + + CR_ST_WORD(d, i) ^= t ^ rol32(t, 13) ^ rol32(t, 23); + } + + rd[0] = d.l[0]; + rd[1] = d.l[1]; +} diff --git a/target/arm/helper.c b/target/arm/helper.c index bfce09643b..180ab75458 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -4266,6 +4266,125 @@ static const ARMCPRegInfo debug_lpae_cp_reginfo[] = { REGINFO_SENTINEL }; +/* Return the exception level to which SVE-disabled exceptions should + * be taken, or 0 if SVE is enabled. + */ +static int sve_exception_el(CPUARMState *env) +{ +#ifndef CONFIG_USER_ONLY + unsigned current_el = arm_current_el(env); + + /* The CPACR.ZEN controls traps to EL1: + * 0, 2 : trap EL0 and EL1 accesses + * 1 : trap only EL0 accesses + * 3 : trap no accesses + */ + switch (extract32(env->cp15.cpacr_el1, 16, 2)) { + default: + if (current_el <= 1) { + /* Trap to PL1, which might be EL1 or EL3 */ + if (arm_is_secure(env) && !arm_el_is_aa64(env, 3)) { + return 3; + } + return 1; + } + break; + case 1: + if (current_el == 0) { + return 1; + } + break; + case 3: + break; + } + + /* Similarly for CPACR.FPEN, after having checked ZEN. */ + switch (extract32(env->cp15.cpacr_el1, 20, 2)) { + default: + if (current_el <= 1) { + if (arm_is_secure(env) && !arm_el_is_aa64(env, 3)) { + return 3; + } + return 1; + } + break; + case 1: + if (current_el == 0) { + return 1; + } + break; + case 3: + break; + } + + /* CPTR_EL2. Check both TZ and TFP. */ + if (current_el <= 2 + && (env->cp15.cptr_el[2] & (CPTR_TFP | CPTR_TZ)) + && !arm_is_secure_below_el3(env)) { + return 2; + } + + /* CPTR_EL3. Check both EZ and TFP. */ + if (!(env->cp15.cptr_el[3] & CPTR_EZ) + || (env->cp15.cptr_el[3] & CPTR_TFP)) { + return 3; + } +#endif + return 0; +} + +static CPAccessResult zcr_access(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) +{ + switch (sve_exception_el(env)) { + case 3: + return CP_ACCESS_TRAP_EL3; + case 2: + return CP_ACCESS_TRAP_EL2; + case 1: + return CP_ACCESS_TRAP; + } + return CP_ACCESS_OK; +} + +static void zcr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Bits other than [3:0] are RAZ/WI. */ + raw_write(env, ri, value & 0xf); +} + +static const ARMCPRegInfo zcr_el1_reginfo = { + .name = "ZCR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 1, .crm = 2, .opc2 = 0, + .access = PL1_RW, .accessfn = zcr_access, .type = ARM_CP_64BIT, + .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[1]), + .writefn = zcr_write, .raw_writefn = raw_write +}; + +static const ARMCPRegInfo zcr_el2_reginfo = { + .name = "ZCR_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 2, .opc2 = 0, + .access = PL2_RW, .accessfn = zcr_access, .type = ARM_CP_64BIT, + .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[2]), + .writefn = zcr_write, .raw_writefn = raw_write +}; + +static const ARMCPRegInfo zcr_no_el2_reginfo = { + .name = "ZCR_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 2, .opc2 = 0, + .access = PL2_RW, .type = ARM_CP_64BIT, + .readfn = arm_cp_read_zero, .writefn = arm_cp_write_ignore +}; + +static const ARMCPRegInfo zcr_el3_reginfo = { + .name = "ZCR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 2, .opc2 = 0, + .access = PL3_RW, .accessfn = zcr_access, .type = ARM_CP_64BIT, + .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[3]), + .writefn = zcr_write, .raw_writefn = raw_write +}; + void hw_watchpoint_update(ARMCPU *cpu, int n) { CPUARMState *env = &cpu->env; @@ -5332,6 +5451,18 @@ void register_cp_regs_for_features(ARMCPU *cpu) } define_one_arm_cp_reg(cpu, &sctlr); } + + if (arm_feature(env, ARM_FEATURE_SVE)) { + define_one_arm_cp_reg(cpu, &zcr_el1_reginfo); + if (arm_feature(env, ARM_FEATURE_EL2)) { + define_one_arm_cp_reg(cpu, &zcr_el2_reginfo); + } else { + define_one_arm_cp_reg(cpu, &zcr_no_el2_reginfo); + } + if (arm_feature(env, ARM_FEATURE_EL3)) { + define_one_arm_cp_reg(cpu, &zcr_el3_reginfo); + } + } } void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) @@ -6161,12 +6292,127 @@ uint32_t arm_phys_excp_target_el(CPUState *cs, uint32_t excp_idx, return target_el; } -static void v7m_push(CPUARMState *env, uint32_t val) +static bool v7m_stack_write(ARMCPU *cpu, uint32_t addr, uint32_t value, + ARMMMUIdx mmu_idx, bool ignfault) { - CPUState *cs = CPU(arm_env_get_cpu(env)); + CPUState *cs = CPU(cpu); + CPUARMState *env = &cpu->env; + MemTxAttrs attrs = {}; + MemTxResult txres; + target_ulong page_size; + hwaddr physaddr; + int prot; + ARMMMUFaultInfo fi; + bool secure = mmu_idx & ARM_MMU_IDX_M_S; + int exc; + bool exc_secure; + + if (get_phys_addr(env, addr, MMU_DATA_STORE, mmu_idx, &physaddr, + &attrs, &prot, &page_size, &fi, NULL)) { + /* MPU/SAU lookup failed */ + if (fi.type == ARMFault_QEMU_SFault) { + qemu_log_mask(CPU_LOG_INT, + "...SecureFault with SFSR.AUVIOL during stacking\n"); + env->v7m.sfsr |= R_V7M_SFSR_AUVIOL_MASK | R_V7M_SFSR_SFARVALID_MASK; + env->v7m.sfar = addr; + exc = ARMV7M_EXCP_SECURE; + exc_secure = false; + } else { + qemu_log_mask(CPU_LOG_INT, "...MemManageFault with CFSR.MSTKERR\n"); + env->v7m.cfsr[secure] |= R_V7M_CFSR_MSTKERR_MASK; + exc = ARMV7M_EXCP_MEM; + exc_secure = secure; + } + goto pend_fault; + } + address_space_stl_le(arm_addressspace(cs, attrs), physaddr, value, + attrs, &txres); + if (txres != MEMTX_OK) { + /* BusFault trying to write the data */ + qemu_log_mask(CPU_LOG_INT, "...BusFault with BFSR.STKERR\n"); + env->v7m.cfsr[M_REG_NS] |= R_V7M_CFSR_STKERR_MASK; + exc = ARMV7M_EXCP_BUS; + exc_secure = false; + goto pend_fault; + } + return true; + +pend_fault: + /* By pending the exception at this point we are making + * the IMPDEF choice "overridden exceptions pended" (see the + * MergeExcInfo() pseudocode). The other choice would be to not + * pend them now and then make a choice about which to throw away + * later if we have two derived exceptions. + * The only case when we must not pend the exception but instead + * throw it away is if we are doing the push of the callee registers + * and we've already generated a derived exception. Even in this + * case we will still update the fault status registers. + */ + if (!ignfault) { + armv7m_nvic_set_pending_derived(env->nvic, exc, exc_secure); + } + return false; +} + +static bool v7m_stack_read(ARMCPU *cpu, uint32_t *dest, uint32_t addr, + ARMMMUIdx mmu_idx) +{ + CPUState *cs = CPU(cpu); + CPUARMState *env = &cpu->env; + MemTxAttrs attrs = {}; + MemTxResult txres; + target_ulong page_size; + hwaddr physaddr; + int prot; + ARMMMUFaultInfo fi; + bool secure = mmu_idx & ARM_MMU_IDX_M_S; + int exc; + bool exc_secure; + uint32_t value; + + if (get_phys_addr(env, addr, MMU_DATA_LOAD, mmu_idx, &physaddr, + &attrs, &prot, &page_size, &fi, NULL)) { + /* MPU/SAU lookup failed */ + if (fi.type == ARMFault_QEMU_SFault) { + qemu_log_mask(CPU_LOG_INT, + "...SecureFault with SFSR.AUVIOL during unstack\n"); + env->v7m.sfsr |= R_V7M_SFSR_AUVIOL_MASK | R_V7M_SFSR_SFARVALID_MASK; + env->v7m.sfar = addr; + exc = ARMV7M_EXCP_SECURE; + exc_secure = false; + } else { + qemu_log_mask(CPU_LOG_INT, + "...MemManageFault with CFSR.MUNSTKERR\n"); + env->v7m.cfsr[secure] |= R_V7M_CFSR_MUNSTKERR_MASK; + exc = ARMV7M_EXCP_MEM; + exc_secure = secure; + } + goto pend_fault; + } - env->regs[13] -= 4; - stl_phys(cs->as, env->regs[13], val); + value = address_space_ldl(arm_addressspace(cs, attrs), physaddr, + attrs, &txres); + if (txres != MEMTX_OK) { + /* BusFault trying to read the data */ + qemu_log_mask(CPU_LOG_INT, "...BusFault with BFSR.UNSTKERR\n"); + env->v7m.cfsr[M_REG_NS] |= R_V7M_CFSR_UNSTKERR_MASK; + exc = ARMV7M_EXCP_BUS; + exc_secure = false; + goto pend_fault; + } + + *dest = value; + return true; + +pend_fault: + /* By pending the exception at this point we are making + * the IMPDEF choice "overridden exceptions pended" (see the + * MergeExcInfo() pseudocode). The other choice would be to not + * pend them now and then make a choice about which to throw away + * later if we have two derived exceptions. + */ + armv7m_nvic_set_pending(env->nvic, exc, exc_secure); + return false; } /* Return true if we're using the process stack pointer (not the MSP) */ @@ -6395,65 +6641,126 @@ static uint32_t *get_v7m_sp_ptr(CPUARMState *env, bool secure, bool threadmode, } } -static uint32_t arm_v7m_load_vector(ARMCPU *cpu, bool targets_secure) +static bool arm_v7m_load_vector(ARMCPU *cpu, int exc, bool targets_secure, + uint32_t *pvec) { CPUState *cs = CPU(cpu); CPUARMState *env = &cpu->env; MemTxResult result; - hwaddr vec = env->v7m.vecbase[targets_secure] + env->v7m.exception * 4; - uint32_t addr; + uint32_t addr = env->v7m.vecbase[targets_secure] + exc * 4; + uint32_t vector_entry; + MemTxAttrs attrs = {}; + ARMMMUIdx mmu_idx; + bool exc_secure; + + mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, targets_secure, true); + + /* We don't do a get_phys_addr() here because the rules for vector + * loads are special: they always use the default memory map, and + * the default memory map permits reads from all addresses. + * Since there's no easy way to pass through to pmsav8_mpu_lookup() + * that we want this special case which would always say "yes", + * we just do the SAU lookup here followed by a direct physical load. + */ + attrs.secure = targets_secure; + attrs.user = false; - addr = address_space_ldl(cs->as, vec, - MEMTXATTRS_UNSPECIFIED, &result); + if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { + V8M_SAttributes sattrs = {}; + + v8m_security_lookup(env, addr, MMU_DATA_LOAD, mmu_idx, &sattrs); + if (sattrs.ns) { + attrs.secure = false; + } else if (!targets_secure) { + /* NS access to S memory */ + goto load_fail; + } + } + + vector_entry = address_space_ldl(arm_addressspace(cs, attrs), addr, + attrs, &result); if (result != MEMTX_OK) { - /* Architecturally this should cause a HardFault setting HSFR.VECTTBL, - * which would then be immediately followed by our failing to load - * the entry vector for that HardFault, which is a Lockup case. - * Since we don't model Lockup, we just report this guest error - * via cpu_abort(). - */ - cpu_abort(cs, "Failed to read from %s exception vector table " - "entry %08x\n", targets_secure ? "secure" : "nonsecure", - (unsigned)vec); + goto load_fail; } - return addr; + *pvec = vector_entry; + return true; + +load_fail: + /* All vector table fetch fails are reported as HardFault, with + * HFSR.VECTTBL and .FORCED set. (FORCED is set because + * technically the underlying exception is a MemManage or BusFault + * that is escalated to HardFault.) This is a terminal exception, + * so we will either take the HardFault immediately or else enter + * lockup (the latter case is handled in armv7m_nvic_set_pending_derived()). + */ + exc_secure = targets_secure || + !(cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK); + env->v7m.hfsr |= R_V7M_HFSR_VECTTBL_MASK | R_V7M_HFSR_FORCED_MASK; + armv7m_nvic_set_pending_derived(env->nvic, ARMV7M_EXCP_HARD, exc_secure); + return false; } -static void v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain) +static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, + bool ignore_faults) { /* For v8M, push the callee-saves register part of the stack frame. * Compare the v8M pseudocode PushCalleeStack(). * In the tailchaining case this may not be the current stack. */ CPUARMState *env = &cpu->env; - CPUState *cs = CPU(cpu); uint32_t *frame_sp_p; uint32_t frameptr; + ARMMMUIdx mmu_idx; + bool stacked_ok; if (dotailchain) { - frame_sp_p = get_v7m_sp_ptr(env, true, - lr & R_V7M_EXCRET_MODE_MASK, + bool mode = lr & R_V7M_EXCRET_MODE_MASK; + bool priv = !(env->v7m.control[M_REG_S] & R_V7M_CONTROL_NPRIV_MASK) || + !mode; + + mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, M_REG_S, priv); + frame_sp_p = get_v7m_sp_ptr(env, M_REG_S, mode, lr & R_V7M_EXCRET_SPSEL_MASK); } else { + mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); frame_sp_p = &env->regs[13]; } frameptr = *frame_sp_p - 0x28; - stl_phys(cs->as, frameptr, 0xfefa125b); - stl_phys(cs->as, frameptr + 0x8, env->regs[4]); - stl_phys(cs->as, frameptr + 0xc, env->regs[5]); - stl_phys(cs->as, frameptr + 0x10, env->regs[6]); - stl_phys(cs->as, frameptr + 0x14, env->regs[7]); - stl_phys(cs->as, frameptr + 0x18, env->regs[8]); - stl_phys(cs->as, frameptr + 0x1c, env->regs[9]); - stl_phys(cs->as, frameptr + 0x20, env->regs[10]); - stl_phys(cs->as, frameptr + 0x24, env->regs[11]); - + /* Write as much of the stack frame as we can. A write failure may + * cause us to pend a derived exception. + */ + stacked_ok = + v7m_stack_write(cpu, frameptr, 0xfefa125b, mmu_idx, ignore_faults) && + v7m_stack_write(cpu, frameptr + 0x8, env->regs[4], mmu_idx, + ignore_faults) && + v7m_stack_write(cpu, frameptr + 0xc, env->regs[5], mmu_idx, + ignore_faults) && + v7m_stack_write(cpu, frameptr + 0x10, env->regs[6], mmu_idx, + ignore_faults) && + v7m_stack_write(cpu, frameptr + 0x14, env->regs[7], mmu_idx, + ignore_faults) && + v7m_stack_write(cpu, frameptr + 0x18, env->regs[8], mmu_idx, + ignore_faults) && + v7m_stack_write(cpu, frameptr + 0x1c, env->regs[9], mmu_idx, + ignore_faults) && + v7m_stack_write(cpu, frameptr + 0x20, env->regs[10], mmu_idx, + ignore_faults) && + v7m_stack_write(cpu, frameptr + 0x24, env->regs[11], mmu_idx, + ignore_faults); + + /* Update SP regardless of whether any of the stack accesses failed. + * When we implement v8M stack limit checking then this attempt to + * update SP might also fail and result in a derived exception. + */ *frame_sp_p = frameptr; + + return !stacked_ok; } -static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain) +static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, + bool ignore_stackfaults) { /* Do the "take the exception" parts of exception entry, * but not the pushing of state to the stack. This is @@ -6462,8 +6769,10 @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain) CPUARMState *env = &cpu->env; uint32_t addr; bool targets_secure; + int exc; + bool push_failed = false; - targets_secure = armv7m_nvic_acknowledge_irq(env->nvic); + armv7m_nvic_get_pending_irq_info(env->nvic, &exc, &targets_secure); if (arm_feature(env, ARM_FEATURE_V8)) { if (arm_feature(env, ARM_FEATURE_M_SECURITY) && @@ -6489,7 +6798,8 @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain) */ if (lr & R_V7M_EXCRET_DCRS_MASK && !(dotailchain && (lr & R_V7M_EXCRET_ES_MASK))) { - v7m_push_callee_stack(cpu, lr, dotailchain); + push_failed = v7m_push_callee_stack(cpu, lr, dotailchain, + ignore_stackfaults); } lr |= R_V7M_EXCRET_DCRS_MASK; } @@ -6531,6 +6841,27 @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain) } } + if (push_failed && !ignore_stackfaults) { + /* Derived exception on callee-saves register stacking: + * we might now want to take a different exception which + * targets a different security state, so try again from the top. + */ + v7m_exception_taken(cpu, lr, true, true); + return; + } + + if (!arm_v7m_load_vector(cpu, exc, targets_secure, &addr)) { + /* Vector load failed: derived exception */ + v7m_exception_taken(cpu, lr, true, true); + return; + } + + /* Now we've done everything that might cause a derived exception + * we can go ahead and activate whichever exception we're going to + * take (which might now be the derived exception). + */ + armv7m_nvic_acknowledge_irq(env->nvic); + /* Switch to target security state -- must do this before writing SPSEL */ switch_v7m_security_state(env, targets_secure); write_v7m_control_spsel(env, 0); @@ -6538,34 +6869,55 @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain) /* Clear IT bits */ env->condexec_bits = 0; env->regs[14] = lr; - addr = arm_v7m_load_vector(cpu, targets_secure); env->regs[15] = addr & 0xfffffffe; env->thumb = addr & 1; } -static void v7m_push_stack(ARMCPU *cpu) +static bool v7m_push_stack(ARMCPU *cpu) { /* Do the "set up stack frame" part of exception entry, * similar to pseudocode PushStack(). + * Return true if we generate a derived exception (and so + * should ignore further stack faults trying to process + * that derived exception.) */ + bool stacked_ok; CPUARMState *env = &cpu->env; uint32_t xpsr = xpsr_read(env); + uint32_t frameptr = env->regs[13]; + ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); /* Align stack pointer if the guest wants that */ - if ((env->regs[13] & 4) && + if ((frameptr & 4) && (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_STKALIGN_MASK)) { - env->regs[13] -= 4; + frameptr -= 4; xpsr |= XPSR_SPREALIGN; } - /* Switch to the handler mode. */ - v7m_push(env, xpsr); - v7m_push(env, env->regs[15]); - v7m_push(env, env->regs[14]); - v7m_push(env, env->regs[12]); - v7m_push(env, env->regs[3]); - v7m_push(env, env->regs[2]); - v7m_push(env, env->regs[1]); - v7m_push(env, env->regs[0]); + + frameptr -= 0x20; + + /* Write as much of the stack frame as we can. If we fail a stack + * write this will result in a derived exception being pended + * (which may be taken in preference to the one we started with + * if it has higher priority). + */ + stacked_ok = + v7m_stack_write(cpu, frameptr, env->regs[0], mmu_idx, false) && + v7m_stack_write(cpu, frameptr + 4, env->regs[1], mmu_idx, false) && + v7m_stack_write(cpu, frameptr + 8, env->regs[2], mmu_idx, false) && + v7m_stack_write(cpu, frameptr + 12, env->regs[3], mmu_idx, false) && + v7m_stack_write(cpu, frameptr + 16, env->regs[12], mmu_idx, false) && + v7m_stack_write(cpu, frameptr + 20, env->regs[14], mmu_idx, false) && + v7m_stack_write(cpu, frameptr + 24, env->regs[15], mmu_idx, false) && + v7m_stack_write(cpu, frameptr + 28, xpsr, mmu_idx, false); + + /* Update SP regardless of whether any of the stack accesses failed. + * When we implement v8M stack limit checking then this attempt to + * update SP might also fail and result in a derived exception. + */ + env->regs[13] = frameptr; + + return !stacked_ok; } static void do_v7m_exception_exit(ARMCPU *cpu) @@ -6711,7 +7063,7 @@ static void do_v7m_exception_exit(ARMCPU *cpu) if (sfault) { env->v7m.sfsr |= R_V7M_SFSR_INVER_MASK; armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SECURE, false); - v7m_exception_taken(cpu, excret, true); + v7m_exception_taken(cpu, excret, true, false); qemu_log_mask(CPU_LOG_INT, "...taking SecureFault on existing " "stackframe: failed EXC_RETURN.ES validity check\n"); return; @@ -6723,7 +7075,7 @@ static void do_v7m_exception_exit(ARMCPU *cpu) */ env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_INVPC_MASK; armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); - v7m_exception_taken(cpu, excret, true); + v7m_exception_taken(cpu, excret, true, false); qemu_log_mask(CPU_LOG_INT, "...taking UsageFault on existing " "stackframe: failed exception return integrity check\n"); return; @@ -6752,6 +7104,11 @@ static void do_v7m_exception_exit(ARMCPU *cpu) !return_to_handler, return_to_sp_process); uint32_t frameptr = *frame_sp_p; + bool pop_ok = true; + ARMMMUIdx mmu_idx; + + mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, return_to_secure, + !return_to_handler); if (!QEMU_IS_ALIGNED(frameptr, 8) && arm_feature(env, ARM_FEATURE_V8)) { @@ -6771,36 +7128,45 @@ static void do_v7m_exception_exit(ARMCPU *cpu) /* Take a SecureFault on the current stack */ env->v7m.sfsr |= R_V7M_SFSR_INVIS_MASK; armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SECURE, false); - v7m_exception_taken(cpu, excret, true); + v7m_exception_taken(cpu, excret, true, false); qemu_log_mask(CPU_LOG_INT, "...taking SecureFault on existing " "stackframe: failed exception return integrity " "signature check\n"); return; } - env->regs[4] = ldl_phys(cs->as, frameptr + 0x8); - env->regs[5] = ldl_phys(cs->as, frameptr + 0xc); - env->regs[6] = ldl_phys(cs->as, frameptr + 0x10); - env->regs[7] = ldl_phys(cs->as, frameptr + 0x14); - env->regs[8] = ldl_phys(cs->as, frameptr + 0x18); - env->regs[9] = ldl_phys(cs->as, frameptr + 0x1c); - env->regs[10] = ldl_phys(cs->as, frameptr + 0x20); - env->regs[11] = ldl_phys(cs->as, frameptr + 0x24); + pop_ok = + v7m_stack_read(cpu, &env->regs[4], frameptr + 0x8, mmu_idx) && + v7m_stack_read(cpu, &env->regs[4], frameptr + 0x8, mmu_idx) && + v7m_stack_read(cpu, &env->regs[5], frameptr + 0xc, mmu_idx) && + v7m_stack_read(cpu, &env->regs[6], frameptr + 0x10, mmu_idx) && + v7m_stack_read(cpu, &env->regs[7], frameptr + 0x14, mmu_idx) && + v7m_stack_read(cpu, &env->regs[8], frameptr + 0x18, mmu_idx) && + v7m_stack_read(cpu, &env->regs[9], frameptr + 0x1c, mmu_idx) && + v7m_stack_read(cpu, &env->regs[10], frameptr + 0x20, mmu_idx) && + v7m_stack_read(cpu, &env->regs[11], frameptr + 0x24, mmu_idx); frameptr += 0x28; } - /* Pop registers. TODO: make these accesses use the correct - * attributes and address space (S/NS, priv/unpriv) and handle - * memory transaction failures. - */ - env->regs[0] = ldl_phys(cs->as, frameptr); - env->regs[1] = ldl_phys(cs->as, frameptr + 0x4); - env->regs[2] = ldl_phys(cs->as, frameptr + 0x8); - env->regs[3] = ldl_phys(cs->as, frameptr + 0xc); - env->regs[12] = ldl_phys(cs->as, frameptr + 0x10); - env->regs[14] = ldl_phys(cs->as, frameptr + 0x14); - env->regs[15] = ldl_phys(cs->as, frameptr + 0x18); + /* Pop registers */ + pop_ok = pop_ok && + v7m_stack_read(cpu, &env->regs[0], frameptr, mmu_idx) && + v7m_stack_read(cpu, &env->regs[1], frameptr + 0x4, mmu_idx) && + v7m_stack_read(cpu, &env->regs[2], frameptr + 0x8, mmu_idx) && + v7m_stack_read(cpu, &env->regs[3], frameptr + 0xc, mmu_idx) && + v7m_stack_read(cpu, &env->regs[12], frameptr + 0x10, mmu_idx) && + v7m_stack_read(cpu, &env->regs[14], frameptr + 0x14, mmu_idx) && + v7m_stack_read(cpu, &env->regs[15], frameptr + 0x18, mmu_idx) && + v7m_stack_read(cpu, &xpsr, frameptr + 0x1c, mmu_idx); + + if (!pop_ok) { + /* v7m_stack_read() pended a fault, so take it (as a tail + * chained exception on the same stack frame) + */ + v7m_exception_taken(cpu, excret, true, false); + return; + } /* Returning from an exception with a PC with bit 0 set is defined * behaviour on v8M (bit 0 is ignored), but for v7M it was specified @@ -6819,8 +7185,6 @@ static void do_v7m_exception_exit(ARMCPU *cpu) } } - xpsr = ldl_phys(cs->as, frameptr + 0x1c); - if (arm_feature(env, ARM_FEATURE_V8)) { /* For v8M we have to check whether the xPSR exception field * matches the EXCRET value for return to handler/thread @@ -6836,7 +7200,7 @@ static void do_v7m_exception_exit(ARMCPU *cpu) armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_INVPC_MASK; - v7m_exception_taken(cpu, excret, true); + v7m_exception_taken(cpu, excret, true, false); qemu_log_mask(CPU_LOG_INT, "...taking UsageFault on existing " "stackframe: failed exception return integrity " "check\n"); @@ -6869,11 +7233,13 @@ static void do_v7m_exception_exit(ARMCPU *cpu) /* Take an INVPC UsageFault by pushing the stack again; * we know we're v7M so this is never a Secure UsageFault. */ + bool ignore_stackfaults; + assert(!arm_feature(env, ARM_FEATURE_V8)); armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, false); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_INVPC_MASK; - v7m_push_stack(cpu); - v7m_exception_taken(cpu, excret, false); + ignore_stackfaults = v7m_push_stack(cpu); + v7m_exception_taken(cpu, excret, false, ignore_stackfaults); qemu_log_mask(CPU_LOG_INT, "...taking UsageFault on new stackframe: " "failed exception return integrity check\n"); return; @@ -7114,6 +7480,7 @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) ARMCPU *cpu = ARM_CPU(cs); CPUARMState *env = &cpu->env; uint32_t lr; + bool ignore_stackfaults; arm_log_exception(cs->exception_index); @@ -7288,8 +7655,8 @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) lr |= R_V7M_EXCRET_MODE_MASK; } - v7m_push_stack(cpu); - v7m_exception_taken(cpu, lr, false); + ignore_stackfaults = v7m_push_stack(cpu); + v7m_exception_taken(cpu, lr, false, ignore_stackfaults); qemu_log_mask(CPU_LOG_INT, "... as %d\n", env->v7m.exception); } @@ -11692,14 +12059,37 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); + int fp_el = fp_exception_el(env); uint32_t flags; if (is_a64(env)) { + int sve_el = sve_exception_el(env); + uint32_t zcr_len; + *pc = env->pc; flags = ARM_TBFLAG_AARCH64_STATE_MASK; /* Get control bits for tagged addresses */ flags |= (arm_regime_tbi0(env, mmu_idx) << ARM_TBFLAG_TBI0_SHIFT); flags |= (arm_regime_tbi1(env, mmu_idx) << ARM_TBFLAG_TBI1_SHIFT); + flags |= sve_el << ARM_TBFLAG_SVEEXC_EL_SHIFT; + + /* If SVE is disabled, but FP is enabled, + then the effective len is 0. */ + if (sve_el != 0 && fp_el == 0) { + zcr_len = 0; + } else { + int current_el = arm_current_el(env); + + zcr_len = env->vfp.zcr_el[current_el <= 1 ? 1 : current_el]; + zcr_len &= 0xf; + if (current_el < 2 && arm_feature(env, ARM_FEATURE_EL2)) { + zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[2]); + } + if (current_el < 3 && arm_feature(env, ARM_FEATURE_EL3)) { + zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[3]); + } + } + flags |= zcr_len << ARM_TBFLAG_ZCR_LEN_SHIFT; } else { *pc = env->regs[15]; flags = (env->thumb << ARM_TBFLAG_THUMB_SHIFT) @@ -11742,7 +12132,7 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, if (arm_cpu_data_is_big_endian(env)) { flags |= ARM_TBFLAG_BE_DATA_MASK; } - flags |= fp_exception_el(env) << ARM_TBFLAG_FPEXC_EL_SHIFT; + flags |= fp_el << ARM_TBFLAG_FPEXC_EL_SHIFT; if (arm_v7m_is_handler_mode(env)) { flags |= ARM_TBFLAG_HANDLER_MASK; diff --git a/target/arm/helper.h b/target/arm/helper.h index 5dec2e6262..6383d7d09e 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -534,6 +534,18 @@ DEF_HELPER_FLAGS_3(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) DEF_HELPER_FLAGS_2(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_3(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_3(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_3(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_2(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_3(crypto_sha512su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_5(crypto_sm3tt, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) +DEF_HELPER_FLAGS_3(crypto_sm3partw1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_3(crypto_sm3partw2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_2(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_3(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) + DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_2(dc_zva, void, env, i64) diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index ff53e9fafb..cfb7e5af72 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -234,6 +234,10 @@ static inline const char *gicv3_class_name(void) exit(1); #endif } else { + if (kvm_enabled()) { + error_report("Userspace GICv3 is not supported with KVM"); + exit(1); + } return "arm-gicv3"; } } diff --git a/target/arm/machine.c b/target/arm/machine.c index a85c2430d3..2c8b43062f 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -50,7 +50,40 @@ static const VMStateDescription vmstate_vfp = { .minimum_version_id = 3, .needed = vfp_needed, .fields = (VMStateField[]) { - VMSTATE_UINT64_ARRAY(env.vfp.regs, ARMCPU, 64), + /* For compatibility, store Qn out of Zn here. */ + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[0].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[1].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[2].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[3].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[4].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[5].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[6].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[7].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[8].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[9].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[10].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[11].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[12].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[13].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[14].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[15].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[16].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[17].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[18].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[19].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[20].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[21].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[22].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[23].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[24].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[25].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[26].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[27].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[28].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[29].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[30].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[31].d, ARMCPU, 0, 2), + /* The xregs array is a little awkward because element 1 (FPSCR) * requires a specific accessor, so we have to split it up in * the vmstate: @@ -89,6 +122,56 @@ static const VMStateDescription vmstate_iwmmxt = { } }; +#ifdef TARGET_AARCH64 +/* The expression ARM_MAX_VQ - 2 is 0 for pure AArch32 build, + * and ARMPredicateReg is actively empty. This triggers errors + * in the expansion of the VMSTATE macros. + */ + +static bool sve_needed(void *opaque) +{ + ARMCPU *cpu = opaque; + CPUARMState *env = &cpu->env; + + return arm_feature(env, ARM_FEATURE_SVE); +} + +/* The first two words of each Zreg is stored in VFP state. */ +static const VMStateDescription vmstate_zreg_hi_reg = { + .name = "cpu/sve/zreg_hi", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT64_SUB_ARRAY(d, ARMVectorReg, 2, ARM_MAX_VQ - 2), + VMSTATE_END_OF_LIST() + } +}; + +static const VMStateDescription vmstate_preg_reg = { + .name = "cpu/sve/preg", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT64_ARRAY(p, ARMPredicateReg, 2 * ARM_MAX_VQ / 8), + VMSTATE_END_OF_LIST() + } +}; + +static const VMStateDescription vmstate_sve = { + .name = "cpu/sve", + .version_id = 1, + .minimum_version_id = 1, + .needed = sve_needed, + .fields = (VMStateField[]) { + VMSTATE_STRUCT_ARRAY(env.vfp.zregs, ARMCPU, 32, 0, + vmstate_zreg_hi_reg, ARMVectorReg), + VMSTATE_STRUCT_ARRAY(env.vfp.pregs, ARMCPU, 17, 0, + vmstate_preg_reg, ARMPredicateReg), + VMSTATE_END_OF_LIST() + } +}; +#endif /* AARCH64 */ + static bool m_needed(void *opaque) { ARMCPU *cpu = opaque; @@ -553,6 +636,9 @@ const VMStateDescription vmstate_arm_cpu = { &vmstate_pmsav7, &vmstate_pmsav8, &vmstate_m_security, +#ifdef TARGET_AARCH64 + &vmstate_sve, +#endif NULL } }; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 0830c3f1c8..fb1a4cb532 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -525,8 +525,8 @@ static inline int vec_reg_offset(DisasContext *s, int regno, { int offs = 0; #ifdef HOST_WORDS_BIGENDIAN - /* This is complicated slightly because vfp.regs[2n] is - * still the low half and vfp.regs[2n+1] the high half + /* This is complicated slightly because vfp.zregs[n].d[0] is + * still the low half and vfp.zregs[n].d[1] the high half * of the 128 bit vector, even on big endian systems. * Calculate the offset assuming a fully bigendian 128 bits, * then XOR to account for the order of the two 64 bit halves. @@ -536,7 +536,7 @@ static inline int vec_reg_offset(DisasContext *s, int regno, #else offs += element * (1 << size); #endif - offs += offsetof(CPUARMState, vfp.regs[regno * 2]); + offs += offsetof(CPUARMState, vfp.zregs[regno]); assert_fp_access_checked(s); return offs; } @@ -545,7 +545,7 @@ static inline int vec_reg_offset(DisasContext *s, int regno, static inline int vec_full_reg_offset(DisasContext *s, int regno) { assert_fp_access_checked(s); - return offsetof(CPUARMState, vfp.regs[regno * 2]); + return offsetof(CPUARMState, vfp.zregs[regno]); } /* Return a newly allocated pointer to the vector register. */ @@ -11587,6 +11587,341 @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(tcg_rn_ptr); } +/* Crypto three-reg SHA512 + * 31 21 20 16 15 14 13 12 11 10 9 5 4 0 + * +-----------------------+------+---+---+-----+--------+------+------+ + * | 1 1 0 0 1 1 1 0 0 1 1 | Rm | 1 | O | 0 0 | opcode | Rn | Rd | + * +-----------------------+------+---+---+-----+--------+------+------+ + */ +static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) +{ + int opcode = extract32(insn, 10, 2); + int o = extract32(insn, 14, 1); + int rm = extract32(insn, 16, 5); + int rn = extract32(insn, 5, 5); + int rd = extract32(insn, 0, 5); + int feature; + CryptoThreeOpFn *genfn; + + if (o == 0) { + switch (opcode) { + case 0: /* SHA512H */ + feature = ARM_FEATURE_V8_SHA512; + genfn = gen_helper_crypto_sha512h; + break; + case 1: /* SHA512H2 */ + feature = ARM_FEATURE_V8_SHA512; + genfn = gen_helper_crypto_sha512h2; + break; + case 2: /* SHA512SU1 */ + feature = ARM_FEATURE_V8_SHA512; + genfn = gen_helper_crypto_sha512su1; + break; + case 3: /* RAX1 */ + feature = ARM_FEATURE_V8_SHA3; + genfn = NULL; + break; + } + } else { + switch (opcode) { + case 0: /* SM3PARTW1 */ + feature = ARM_FEATURE_V8_SM3; + genfn = gen_helper_crypto_sm3partw1; + break; + case 1: /* SM3PARTW2 */ + feature = ARM_FEATURE_V8_SM3; + genfn = gen_helper_crypto_sm3partw2; + break; + case 2: /* SM4EKEY */ + feature = ARM_FEATURE_V8_SM4; + genfn = gen_helper_crypto_sm4ekey; + break; + default: + unallocated_encoding(s); + return; + } + } + + if (!arm_dc_feature(s, feature)) { + unallocated_encoding(s); + return; + } + + if (!fp_access_check(s)) { + return; + } + + if (genfn) { + TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; + + tcg_rd_ptr = vec_full_reg_ptr(s, rd); + tcg_rn_ptr = vec_full_reg_ptr(s, rn); + tcg_rm_ptr = vec_full_reg_ptr(s, rm); + + genfn(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr); + + tcg_temp_free_ptr(tcg_rd_ptr); + tcg_temp_free_ptr(tcg_rn_ptr); + tcg_temp_free_ptr(tcg_rm_ptr); + } else { + TCGv_i64 tcg_op1, tcg_op2, tcg_res[2]; + int pass; + + tcg_op1 = tcg_temp_new_i64(); + tcg_op2 = tcg_temp_new_i64(); + tcg_res[0] = tcg_temp_new_i64(); + tcg_res[1] = tcg_temp_new_i64(); + + for (pass = 0; pass < 2; pass++) { + read_vec_element(s, tcg_op1, rn, pass, MO_64); + read_vec_element(s, tcg_op2, rm, pass, MO_64); + + tcg_gen_rotli_i64(tcg_res[pass], tcg_op2, 1); + tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1); + } + write_vec_element(s, tcg_res[0], rd, 0, MO_64); + write_vec_element(s, tcg_res[1], rd, 1, MO_64); + + tcg_temp_free_i64(tcg_op1); + tcg_temp_free_i64(tcg_op2); + tcg_temp_free_i64(tcg_res[0]); + tcg_temp_free_i64(tcg_res[1]); + } +} + +/* Crypto two-reg SHA512 + * 31 12 11 10 9 5 4 0 + * +-----------------------------------------+--------+------+------+ + * | 1 1 0 0 1 1 1 0 1 1 0 0 0 0 0 0 1 0 0 0 | opcode | Rn | Rd | + * +-----------------------------------------+--------+------+------+ + */ +static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) +{ + int opcode = extract32(insn, 10, 2); + int rn = extract32(insn, 5, 5); + int rd = extract32(insn, 0, 5); + TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; + int feature; + CryptoTwoOpFn *genfn; + + switch (opcode) { + case 0: /* SHA512SU0 */ + feature = ARM_FEATURE_V8_SHA512; + genfn = gen_helper_crypto_sha512su0; + break; + case 1: /* SM4E */ + feature = ARM_FEATURE_V8_SM4; + genfn = gen_helper_crypto_sm4e; + break; + default: + unallocated_encoding(s); + return; + } + + if (!arm_dc_feature(s, feature)) { + unallocated_encoding(s); + return; + } + + if (!fp_access_check(s)) { + return; + } + + tcg_rd_ptr = vec_full_reg_ptr(s, rd); + tcg_rn_ptr = vec_full_reg_ptr(s, rn); + + genfn(tcg_rd_ptr, tcg_rn_ptr); + + tcg_temp_free_ptr(tcg_rd_ptr); + tcg_temp_free_ptr(tcg_rn_ptr); +} + +/* Crypto four-register + * 31 23 22 21 20 16 15 14 10 9 5 4 0 + * +-------------------+-----+------+---+------+------+------+ + * | 1 1 0 0 1 1 1 0 0 | Op0 | Rm | 0 | Ra | Rn | Rd | + * +-------------------+-----+------+---+------+------+------+ + */ +static void disas_crypto_four_reg(DisasContext *s, uint32_t insn) +{ + int op0 = extract32(insn, 21, 2); + int rm = extract32(insn, 16, 5); + int ra = extract32(insn, 10, 5); + int rn = extract32(insn, 5, 5); + int rd = extract32(insn, 0, 5); + int feature; + + switch (op0) { + case 0: /* EOR3 */ + case 1: /* BCAX */ + feature = ARM_FEATURE_V8_SHA3; + break; + case 2: /* SM3SS1 */ + feature = ARM_FEATURE_V8_SM3; + break; + default: + unallocated_encoding(s); + return; + } + + if (!arm_dc_feature(s, feature)) { + unallocated_encoding(s); + return; + } + + if (!fp_access_check(s)) { + return; + } + + if (op0 < 2) { + TCGv_i64 tcg_op1, tcg_op2, tcg_op3, tcg_res[2]; + int pass; + + tcg_op1 = tcg_temp_new_i64(); + tcg_op2 = tcg_temp_new_i64(); + tcg_op3 = tcg_temp_new_i64(); + tcg_res[0] = tcg_temp_new_i64(); + tcg_res[1] = tcg_temp_new_i64(); + + for (pass = 0; pass < 2; pass++) { + read_vec_element(s, tcg_op1, rn, pass, MO_64); + read_vec_element(s, tcg_op2, rm, pass, MO_64); + read_vec_element(s, tcg_op3, ra, pass, MO_64); + + if (op0 == 0) { + /* EOR3 */ + tcg_gen_xor_i64(tcg_res[pass], tcg_op2, tcg_op3); + } else { + /* BCAX */ + tcg_gen_andc_i64(tcg_res[pass], tcg_op2, tcg_op3); + } + tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1); + } + write_vec_element(s, tcg_res[0], rd, 0, MO_64); + write_vec_element(s, tcg_res[1], rd, 1, MO_64); + + tcg_temp_free_i64(tcg_op1); + tcg_temp_free_i64(tcg_op2); + tcg_temp_free_i64(tcg_op3); + tcg_temp_free_i64(tcg_res[0]); + tcg_temp_free_i64(tcg_res[1]); + } else { + TCGv_i32 tcg_op1, tcg_op2, tcg_op3, tcg_res, tcg_zero; + + tcg_op1 = tcg_temp_new_i32(); + tcg_op2 = tcg_temp_new_i32(); + tcg_op3 = tcg_temp_new_i32(); + tcg_res = tcg_temp_new_i32(); + tcg_zero = tcg_const_i32(0); + + read_vec_element_i32(s, tcg_op1, rn, 3, MO_32); + read_vec_element_i32(s, tcg_op2, rm, 3, MO_32); + read_vec_element_i32(s, tcg_op3, ra, 3, MO_32); + + tcg_gen_rotri_i32(tcg_res, tcg_op1, 20); + tcg_gen_add_i32(tcg_res, tcg_res, tcg_op2); + tcg_gen_add_i32(tcg_res, tcg_res, tcg_op3); + tcg_gen_rotri_i32(tcg_res, tcg_res, 25); + + write_vec_element_i32(s, tcg_zero, rd, 0, MO_32); + write_vec_element_i32(s, tcg_zero, rd, 1, MO_32); + write_vec_element_i32(s, tcg_zero, rd, 2, MO_32); + write_vec_element_i32(s, tcg_res, rd, 3, MO_32); + + tcg_temp_free_i32(tcg_op1); + tcg_temp_free_i32(tcg_op2); + tcg_temp_free_i32(tcg_op3); + tcg_temp_free_i32(tcg_res); + tcg_temp_free_i32(tcg_zero); + } +} + +/* Crypto XAR + * 31 21 20 16 15 10 9 5 4 0 + * +-----------------------+------+--------+------+------+ + * | 1 1 0 0 1 1 1 0 1 0 0 | Rm | imm6 | Rn | Rd | + * +-----------------------+------+--------+------+------+ + */ +static void disas_crypto_xar(DisasContext *s, uint32_t insn) +{ + int rm = extract32(insn, 16, 5); + int imm6 = extract32(insn, 10, 6); + int rn = extract32(insn, 5, 5); + int rd = extract32(insn, 0, 5); + TCGv_i64 tcg_op1, tcg_op2, tcg_res[2]; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA3)) { + unallocated_encoding(s); + return; + } + + if (!fp_access_check(s)) { + return; + } + + tcg_op1 = tcg_temp_new_i64(); + tcg_op2 = tcg_temp_new_i64(); + tcg_res[0] = tcg_temp_new_i64(); + tcg_res[1] = tcg_temp_new_i64(); + + for (pass = 0; pass < 2; pass++) { + read_vec_element(s, tcg_op1, rn, pass, MO_64); + read_vec_element(s, tcg_op2, rm, pass, MO_64); + + tcg_gen_xor_i64(tcg_res[pass], tcg_op1, tcg_op2); + tcg_gen_rotri_i64(tcg_res[pass], tcg_res[pass], imm6); + } + write_vec_element(s, tcg_res[0], rd, 0, MO_64); + write_vec_element(s, tcg_res[1], rd, 1, MO_64); + + tcg_temp_free_i64(tcg_op1); + tcg_temp_free_i64(tcg_op2); + tcg_temp_free_i64(tcg_res[0]); + tcg_temp_free_i64(tcg_res[1]); +} + +/* Crypto three-reg imm2 + * 31 21 20 16 15 14 13 12 11 10 9 5 4 0 + * +-----------------------+------+-----+------+--------+------+------+ + * | 1 1 0 0 1 1 1 0 0 1 0 | Rm | 1 0 | imm2 | opcode | Rn | Rd | + * +-----------------------+------+-----+------+--------+------+------+ + */ +static void disas_crypto_three_reg_imm2(DisasContext *s, uint32_t insn) +{ + int opcode = extract32(insn, 10, 2); + int imm2 = extract32(insn, 12, 2); + int rm = extract32(insn, 16, 5); + int rn = extract32(insn, 5, 5); + int rd = extract32(insn, 0, 5); + TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; + TCGv_i32 tcg_imm2, tcg_opcode; + + if (!arm_dc_feature(s, ARM_FEATURE_V8_SM3)) { + unallocated_encoding(s); + return; + } + + if (!fp_access_check(s)) { + return; + } + + tcg_rd_ptr = vec_full_reg_ptr(s, rd); + tcg_rn_ptr = vec_full_reg_ptr(s, rn); + tcg_rm_ptr = vec_full_reg_ptr(s, rm); + tcg_imm2 = tcg_const_i32(imm2); + tcg_opcode = tcg_const_i32(opcode); + + gen_helper_crypto_sm3tt(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr, tcg_imm2, + tcg_opcode); + + tcg_temp_free_ptr(tcg_rd_ptr); + tcg_temp_free_ptr(tcg_rn_ptr); + tcg_temp_free_ptr(tcg_rm_ptr); + tcg_temp_free_i32(tcg_imm2); + tcg_temp_free_i32(tcg_opcode); +} + /* C3.6 Data processing - SIMD, inc Crypto * * As the decode gets a little complex we are using a table based @@ -11616,6 +11951,11 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x4e280800, 0xff3e0c00, disas_crypto_aes }, { 0x5e000000, 0xff208c00, disas_crypto_three_reg_sha }, { 0x5e280800, 0xff3e0c00, disas_crypto_two_reg_sha }, + { 0xce608000, 0xffe0b000, disas_crypto_three_reg_sha512 }, + { 0xcec08000, 0xfffff000, disas_crypto_two_reg_sha512 }, + { 0xce000000, 0xff808000, disas_crypto_four_reg }, + { 0xce800000, 0xffe00000, disas_crypto_xar }, + { 0xce408000, 0xffe0c000, disas_crypto_three_reg_imm2 }, { 0x00000000, 0x00000000, NULL } }; @@ -11718,6 +12058,8 @@ static int aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->user = (dc->current_el == 0); #endif dc->fp_excp_el = ARM_TBFLAG_FPEXC_EL(dc->base.tb->flags); + dc->sve_excp_el = ARM_TBFLAG_SVEEXC_EL(dc->base.tb->flags); + dc->sve_len = (ARM_TBFLAG_ZCR_LEN(dc->base.tb->flags) + 1) * 16; dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = arm_cpu->cp_regs; diff --git a/target/arm/translate.c b/target/arm/translate.c index 55826b7e5a..1270022289 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -1512,13 +1512,12 @@ static inline void gen_vfp_st(DisasContext *s, int dp, TCGv_i32 addr) } } -static inline long -vfp_reg_offset (int dp, int reg) +static inline long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { - return offsetof(CPUARMState, vfp.regs[reg]); + return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); } else { - long ofs = offsetof(CPUARMState, vfp.regs[reg >> 1]); + long ofs = offsetof(CPUARMState, vfp.zregs[reg >> 2].d[(reg >> 1) & 1]); if (reg & 1) { ofs += offsetof(CPU_DoubleU, l.upper); } else { @@ -9926,6 +9925,7 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(addr); tcg_temp_free_i32(op); store_reg(s, rd, ttresp); + break; } goto illegal_op; } diff --git a/target/arm/translate.h b/target/arm/translate.h index 3f4df91e5e..c47febf99d 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -29,6 +29,8 @@ typedef struct DisasContext { bool tbi1; /* TBI1 for EL0/1, not used for EL2/3 */ bool ns; /* Use non-secure CPREG bank on access */ int fp_excp_el; /* FP exception EL or 0 if enabled */ + int sve_excp_el; /* SVE exception EL or 0 if enabled */ + int sve_len; /* SVE vector length in bytes */ /* Flag indicating that exceptions from secure mode are routed to EL3. */ bool secure_routed_to_el3; bool vfp_enabled; /* FP enabled via FPSCR.EN */ |