From 9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 Mon Sep 17 00:00:00 2001 From: Yunhong Jiang Date: Tue, 4 Aug 2015 12:17:53 -0700 Subject: Add the rt linux 4.1.3-rt3 as base Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang --- kernel/arch/arm/kvm/Kconfig | 58 + kernel/arch/arm/kvm/Makefile | 26 + kernel/arch/arm/kvm/arm.c | 1154 ++++++++++++++++++++ kernel/arch/arm/kvm/coproc.c | 1262 +++++++++++++++++++++ kernel/arch/arm/kvm/coproc.h | 160 +++ kernel/arch/arm/kvm/coproc_a15.c | 51 + kernel/arch/arm/kvm/coproc_a7.c | 54 + kernel/arch/arm/kvm/emulate.c | 402 +++++++ kernel/arch/arm/kvm/guest.c | 292 +++++ kernel/arch/arm/kvm/handle_exit.c | 173 +++ kernel/arch/arm/kvm/init.S | 159 +++ kernel/arch/arm/kvm/interrupts.S | 524 +++++++++ kernel/arch/arm/kvm/interrupts_head.S | 649 +++++++++++ kernel/arch/arm/kvm/mmio.c | 218 ++++ kernel/arch/arm/kvm/mmu.c | 1926 +++++++++++++++++++++++++++++++++ kernel/arch/arm/kvm/perf.c | 68 ++ kernel/arch/arm/kvm/psci.c | 320 ++++++ kernel/arch/arm/kvm/reset.c | 83 ++ kernel/arch/arm/kvm/trace.h | 328 ++++++ 19 files changed, 7907 insertions(+) create mode 100644 kernel/arch/arm/kvm/Kconfig create mode 100644 kernel/arch/arm/kvm/Makefile create mode 100644 kernel/arch/arm/kvm/arm.c create mode 100644 kernel/arch/arm/kvm/coproc.c create mode 100644 kernel/arch/arm/kvm/coproc.h create mode 100644 kernel/arch/arm/kvm/coproc_a15.c create mode 100644 kernel/arch/arm/kvm/coproc_a7.c create mode 100644 kernel/arch/arm/kvm/emulate.c create mode 100644 kernel/arch/arm/kvm/guest.c create mode 100644 kernel/arch/arm/kvm/handle_exit.c create mode 100644 kernel/arch/arm/kvm/init.S create mode 100644 kernel/arch/arm/kvm/interrupts.S create mode 100644 kernel/arch/arm/kvm/interrupts_head.S create mode 100644 kernel/arch/arm/kvm/mmio.c create mode 100644 kernel/arch/arm/kvm/mmu.c create mode 100644 kernel/arch/arm/kvm/perf.c create mode 100644 kernel/arch/arm/kvm/psci.c create mode 100644 kernel/arch/arm/kvm/reset.c create mode 100644 kernel/arch/arm/kvm/trace.h (limited to 'kernel/arch/arm/kvm') diff --git a/kernel/arch/arm/kvm/Kconfig b/kernel/arch/arm/kvm/Kconfig new file mode 100644 index 000000000..f1f79d104 --- /dev/null +++ b/kernel/arch/arm/kvm/Kconfig @@ -0,0 +1,58 @@ +# +# KVM configuration +# + +source "virt/kvm/Kconfig" + +menuconfig VIRTUALIZATION + bool "Virtualization" + ---help--- + Say Y here to get to see options for using your Linux host to run + other operating systems inside virtual machines (guests). + This option alone does not add any kernel code. + + If you say N, all options in this submenu will be skipped and + disabled. + +if VIRTUALIZATION + +config KVM + bool "Kernel-based Virtual Machine (KVM) support" + depends on MMU && OF + select PREEMPT_NOTIFIERS + select ANON_INODES + select HAVE_KVM_CPU_RELAX_INTERCEPT + select HAVE_KVM_ARCH_TLB_FLUSH_ALL + select KVM_MMIO + select KVM_ARM_HOST + select KVM_GENERIC_DIRTYLOG_READ_PROTECT + select SRCU + select MMU_NOTIFIER + select HAVE_KVM_EVENTFD + select HAVE_KVM_IRQFD + depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER + ---help--- + Support hosting virtualized guest machines. + + This module provides access to the hardware capabilities through + a character device node named /dev/kvm. + + If unsure, say N. + +config KVM_ARM_HOST + bool + ---help--- + Provides host support for ARM processors. + +config KVM_ARM_MAX_VCPUS + int "Number maximum supported virtual CPUs per VM" + depends on KVM_ARM_HOST + default 4 + help + Static number of max supported virtual CPUs per VM. + + If you choose a high number, the vcpu structures will be quite + large, so only choose a reasonable number that you expect to + actually use. + +endif # VIRTUALIZATION diff --git a/kernel/arch/arm/kvm/Makefile b/kernel/arch/arm/kvm/Makefile new file mode 100644 index 000000000..139e46c08 --- /dev/null +++ b/kernel/arch/arm/kvm/Makefile @@ -0,0 +1,26 @@ +# +# Makefile for Kernel-based Virtual Machine module +# + +plus_virt := $(call as-instr,.arch_extension virt,+virt) +ifeq ($(plus_virt),+virt) + plus_virt_def := -DREQUIRES_VIRT=1 +endif + +ccflags-y += -Iarch/arm/kvm +CFLAGS_arm.o := -I. $(plus_virt_def) +CFLAGS_mmu.o := -I. + +AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) +AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) + +KVM := ../../../virt/kvm +kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o + +obj-y += kvm-arm.o init.o interrupts.o +obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o +obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o +obj-y += $(KVM)/arm/vgic.o +obj-y += $(KVM)/arm/vgic-v2.o +obj-y += $(KVM)/arm/vgic-v2-emul.o +obj-y += $(KVM)/arm/arch_timer.o diff --git a/kernel/arch/arm/kvm/arm.c b/kernel/arch/arm/kvm/arm.c new file mode 100644 index 000000000..adb19885a --- /dev/null +++ b/kernel/arch/arm/kvm/arm.c @@ -0,0 +1,1154 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include "trace.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef REQUIRES_VIRT +__asm__(".arch_extension virt"); +#endif + +static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); +static kvm_cpu_context_t __percpu *kvm_host_cpu_state; +static unsigned long hyp_default_vectors; + +/* Per-CPU variable containing the currently running vcpu. */ +static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu); + +/* The VMID used in the VTTBR */ +static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); +static u8 kvm_next_vmid; +static DEFINE_SPINLOCK(kvm_vmid_lock); + +static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) +{ + BUG_ON(preemptible()); + __this_cpu_write(kvm_arm_running_vcpu, vcpu); +} + +/** + * kvm_arm_get_running_vcpu - get the vcpu running on the current CPU. + * Must be called from non-preemptible context + */ +struct kvm_vcpu *kvm_arm_get_running_vcpu(void) +{ + BUG_ON(preemptible()); + return __this_cpu_read(kvm_arm_running_vcpu); +} + +/** + * kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus. + */ +struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) +{ + return &kvm_arm_running_vcpu; +} + +int kvm_arch_hardware_enable(void) +{ + return 0; +} + +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; +} + +int kvm_arch_hardware_setup(void) +{ + return 0; +} + +void kvm_arch_check_processor_compat(void *rtn) +{ + *(int *)rtn = 0; +} + + +/** + * kvm_arch_init_vm - initializes a VM data structure + * @kvm: pointer to the KVM struct + */ +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) +{ + int ret = 0; + + if (type) + return -EINVAL; + + ret = kvm_alloc_stage2_pgd(kvm); + if (ret) + goto out_fail_alloc; + + ret = create_hyp_mappings(kvm, kvm + 1); + if (ret) + goto out_free_stage2_pgd; + + kvm_timer_init(kvm); + + /* Mark the initial VMID generation invalid */ + kvm->arch.vmid_gen = 0; + + /* The maximum number of VCPUs is limited by the host's GIC model */ + kvm->arch.max_vcpus = kvm_vgic_get_max_vcpus(); + + return ret; +out_free_stage2_pgd: + kvm_free_stage2_pgd(kvm); +out_fail_alloc: + return ret; +} + +int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +{ + return VM_FAULT_SIGBUS; +} + + +/** + * kvm_arch_destroy_vm - destroy the VM data structure + * @kvm: pointer to the KVM struct + */ +void kvm_arch_destroy_vm(struct kvm *kvm) +{ + int i; + + kvm_free_stage2_pgd(kvm); + + for (i = 0; i < KVM_MAX_VCPUS; ++i) { + if (kvm->vcpus[i]) { + kvm_arch_vcpu_free(kvm->vcpus[i]); + kvm->vcpus[i] = NULL; + } + } + + kvm_vgic_destroy(kvm); +} + +int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) +{ + int r; + switch (ext) { + case KVM_CAP_IRQCHIP: + case KVM_CAP_IRQFD: + case KVM_CAP_IOEVENTFD: + case KVM_CAP_DEVICE_CTRL: + case KVM_CAP_USER_MEMORY: + case KVM_CAP_SYNC_MMU: + case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: + case KVM_CAP_ONE_REG: + case KVM_CAP_ARM_PSCI: + case KVM_CAP_ARM_PSCI_0_2: + case KVM_CAP_READONLY_MEM: + case KVM_CAP_MP_STATE: + r = 1; + break; + case KVM_CAP_COALESCED_MMIO: + r = KVM_COALESCED_MMIO_PAGE_OFFSET; + break; + case KVM_CAP_ARM_SET_DEVICE_ADDR: + r = 1; + break; + case KVM_CAP_NR_VCPUS: + r = num_online_cpus(); + break; + case KVM_CAP_MAX_VCPUS: + r = KVM_MAX_VCPUS; + break; + default: + r = kvm_arch_dev_ioctl_check_extension(ext); + break; + } + return r; +} + +long kvm_arch_dev_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + return -EINVAL; +} + + +struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) +{ + int err; + struct kvm_vcpu *vcpu; + + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) { + err = -EBUSY; + goto out; + } + + if (id >= kvm->arch.max_vcpus) { + err = -EINVAL; + goto out; + } + + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + if (!vcpu) { + err = -ENOMEM; + goto out; + } + + err = kvm_vcpu_init(vcpu, kvm, id); + if (err) + goto free_vcpu; + + err = create_hyp_mappings(vcpu, vcpu + 1); + if (err) + goto vcpu_uninit; + + return vcpu; +vcpu_uninit: + kvm_vcpu_uninit(vcpu); +free_vcpu: + kmem_cache_free(kvm_vcpu_cache, vcpu); +out: + return ERR_PTR(err); +} + +void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ +} + +void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +{ + kvm_mmu_free_memory_caches(vcpu); + kvm_timer_vcpu_terminate(vcpu); + kvm_vgic_vcpu_destroy(vcpu); + kmem_cache_free(kvm_vcpu_cache, vcpu); +} + +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + kvm_arch_vcpu_free(vcpu); +} + +int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) +{ + return kvm_timer_should_fire(vcpu); +} + +int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) +{ + /* Force users to call KVM_ARM_VCPU_INIT */ + vcpu->arch.target = -1; + bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); + + /* Set up the timer */ + kvm_timer_vcpu_init(vcpu); + + return 0; +} + +void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + vcpu->cpu = cpu; + vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state); + + kvm_arm_set_running_vcpu(vcpu); +} + +void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) +{ + /* + * The arch-generic KVM code expects the cpu field of a vcpu to be -1 + * if the vcpu is no longer assigned to a cpu. This is used for the + * optimized make_all_cpus_request path. + */ + vcpu->cpu = -1; + + kvm_arm_set_running_vcpu(NULL); +} + +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + return -EINVAL; +} + + +int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + if (vcpu->arch.pause) + mp_state->mp_state = KVM_MP_STATE_STOPPED; + else + mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + switch (mp_state->mp_state) { + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.pause = false; + break; + case KVM_MP_STATE_STOPPED: + vcpu->arch.pause = true; + break; + default: + return -EINVAL; + } + + return 0; +} + +/** + * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled + * @v: The VCPU pointer + * + * If the guest CPU is not waiting for interrupts or an interrupt line is + * asserted, the CPU is by definition runnable. + */ +int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) +{ + return !!v->arch.irq_lines || kvm_vgic_vcpu_pending_irq(v); +} + +/* Just ensure a guest exit from a particular CPU */ +static void exit_vm_noop(void *info) +{ +} + +void force_vm_exit(const cpumask_t *mask) +{ + smp_call_function_many(mask, exit_vm_noop, NULL, true); +} + +/** + * need_new_vmid_gen - check that the VMID is still valid + * @kvm: The VM's VMID to checkt + * + * return true if there is a new generation of VMIDs being used + * + * The hardware supports only 256 values with the value zero reserved for the + * host, so we check if an assigned value belongs to a previous generation, + * which which requires us to assign a new value. If we're the first to use a + * VMID for the new generation, we must flush necessary caches and TLBs on all + * CPUs. + */ +static bool need_new_vmid_gen(struct kvm *kvm) +{ + return unlikely(kvm->arch.vmid_gen != atomic64_read(&kvm_vmid_gen)); +} + +/** + * update_vttbr - Update the VTTBR with a valid VMID before the guest runs + * @kvm The guest that we are about to run + * + * Called from kvm_arch_vcpu_ioctl_run before entering the guest to ensure the + * VM has a valid VMID, otherwise assigns a new one and flushes corresponding + * caches and TLBs. + */ +static void update_vttbr(struct kvm *kvm) +{ + phys_addr_t pgd_phys; + u64 vmid; + + if (!need_new_vmid_gen(kvm)) + return; + + spin_lock(&kvm_vmid_lock); + + /* + * We need to re-check the vmid_gen here to ensure that if another vcpu + * already allocated a valid vmid for this vm, then this vcpu should + * use the same vmid. + */ + if (!need_new_vmid_gen(kvm)) { + spin_unlock(&kvm_vmid_lock); + return; + } + + /* First user of a new VMID generation? */ + if (unlikely(kvm_next_vmid == 0)) { + atomic64_inc(&kvm_vmid_gen); + kvm_next_vmid = 1; + + /* + * On SMP we know no other CPUs can use this CPU's or each + * other's VMID after force_vm_exit returns since the + * kvm_vmid_lock blocks them from reentry to the guest. + */ + force_vm_exit(cpu_all_mask); + /* + * Now broadcast TLB + ICACHE invalidation over the inner + * shareable domain to make sure all data structures are + * clean. + */ + kvm_call_hyp(__kvm_flush_vm_context); + } + + kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen); + kvm->arch.vmid = kvm_next_vmid; + kvm_next_vmid++; + + /* update vttbr to be used with the new vmid */ + pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm)); + BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK); + vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK; + kvm->arch.vttbr = pgd_phys | vmid; + + spin_unlock(&kvm_vmid_lock); +} + +static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + int ret; + + if (likely(vcpu->arch.has_run_once)) + return 0; + + vcpu->arch.has_run_once = true; + + /* + * Map the VGIC hardware resources before running a vcpu the first + * time on this VM. + */ + if (unlikely(!vgic_ready(kvm))) { + ret = kvm_vgic_map_resources(kvm); + if (ret) + return ret; + } + + /* + * Enable the arch timers only if we have an in-kernel VGIC + * and it has been properly initialized, since we cannot handle + * interrupts from the virtual timer with a userspace gic. + */ + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) + kvm_timer_enable(kvm); + + return 0; +} + +bool kvm_arch_intc_initialized(struct kvm *kvm) +{ + return vgic_initialized(kvm); +} + +static void vcpu_pause(struct kvm_vcpu *vcpu) +{ + struct swait_head *wq = kvm_arch_vcpu_wq(vcpu); + + swait_event_interruptible(*wq, !vcpu->arch.pause); +} + +static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.target >= 0; +} + +/** + * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code + * @vcpu: The VCPU pointer + * @run: The kvm_run structure pointer used for userspace state exchange + * + * This function is called through the VCPU_RUN ioctl called from user space. It + * will execute VM code in a loop until the time slice for the process is used + * or some emulation is needed from user space in which case the function will + * return with return value 0 and with the kvm_run structure filled in with the + * required data for the requested emulation. + */ +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + int ret; + sigset_t sigsaved; + + if (unlikely(!kvm_vcpu_initialized(vcpu))) + return -ENOEXEC; + + ret = kvm_vcpu_first_run_init(vcpu); + if (ret) + return ret; + + if (run->exit_reason == KVM_EXIT_MMIO) { + ret = kvm_handle_mmio_return(vcpu, vcpu->run); + if (ret) + return ret; + } + + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); + + ret = 1; + run->exit_reason = KVM_EXIT_UNKNOWN; + while (ret > 0) { + /* + * Check conditions before entering the guest + */ + cond_resched(); + + update_vttbr(vcpu->kvm); + + if (vcpu->arch.pause) + vcpu_pause(vcpu); + + kvm_vgic_flush_hwstate(vcpu); + kvm_timer_flush_hwstate(vcpu); + + local_irq_disable(); + + /* + * Re-check atomic conditions + */ + if (signal_pending(current)) { + ret = -EINTR; + run->exit_reason = KVM_EXIT_INTR; + } + + if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) { + local_irq_enable(); + kvm_timer_sync_hwstate(vcpu); + kvm_vgic_sync_hwstate(vcpu); + continue; + } + + /************************************************************** + * Enter the guest + */ + trace_kvm_entry(*vcpu_pc(vcpu)); + kvm_guest_enter(); + vcpu->mode = IN_GUEST_MODE; + + ret = kvm_call_hyp(__kvm_vcpu_run, vcpu); + + vcpu->mode = OUTSIDE_GUEST_MODE; + kvm_guest_exit(); + trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); + /* + * We may have taken a host interrupt in HYP mode (ie + * while executing the guest). This interrupt is still + * pending, as we haven't serviced it yet! + * + * We're now back in SVC mode, with interrupts + * disabled. Enabling the interrupts now will have + * the effect of taking the interrupt again, in SVC + * mode this time. + */ + local_irq_enable(); + + /* + * Back from guest + *************************************************************/ + + kvm_timer_sync_hwstate(vcpu); + kvm_vgic_sync_hwstate(vcpu); + + ret = handle_exit(vcpu, run, ret); + } + + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + return ret; +} + +static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level) +{ + int bit_index; + bool set; + unsigned long *ptr; + + if (number == KVM_ARM_IRQ_CPU_IRQ) + bit_index = __ffs(HCR_VI); + else /* KVM_ARM_IRQ_CPU_FIQ */ + bit_index = __ffs(HCR_VF); + + ptr = (unsigned long *)&vcpu->arch.irq_lines; + if (level) + set = test_and_set_bit(bit_index, ptr); + else + set = test_and_clear_bit(bit_index, ptr); + + /* + * If we didn't change anything, no need to wake up or kick other CPUs + */ + if (set == level) + return 0; + + /* + * The vcpu irq_lines field was updated, wake up sleeping VCPUs and + * trigger a world-switch round on the running physical CPU to set the + * virtual IRQ/FIQ fields in the HCR appropriately. + */ + kvm_vcpu_kick(vcpu); + + return 0; +} + +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, + bool line_status) +{ + u32 irq = irq_level->irq; + unsigned int irq_type, vcpu_idx, irq_num; + int nrcpus = atomic_read(&kvm->online_vcpus); + struct kvm_vcpu *vcpu = NULL; + bool level = irq_level->level; + + irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK; + vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK; + irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK; + + trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level); + + switch (irq_type) { + case KVM_ARM_IRQ_TYPE_CPU: + if (irqchip_in_kernel(kvm)) + return -ENXIO; + + if (vcpu_idx >= nrcpus) + return -EINVAL; + + vcpu = kvm_get_vcpu(kvm, vcpu_idx); + if (!vcpu) + return -EINVAL; + + if (irq_num > KVM_ARM_IRQ_CPU_FIQ) + return -EINVAL; + + return vcpu_interrupt_line(vcpu, irq_num, level); + case KVM_ARM_IRQ_TYPE_PPI: + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + + if (vcpu_idx >= nrcpus) + return -EINVAL; + + vcpu = kvm_get_vcpu(kvm, vcpu_idx); + if (!vcpu) + return -EINVAL; + + if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS) + return -EINVAL; + + return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level); + case KVM_ARM_IRQ_TYPE_SPI: + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + + if (irq_num < VGIC_NR_PRIVATE_IRQS) + return -EINVAL; + + return kvm_vgic_inject_irq(kvm, 0, irq_num, level); + } + + return -EINVAL; +} + +static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, + const struct kvm_vcpu_init *init) +{ + unsigned int i; + int phys_target = kvm_target_cpu(); + + if (init->target != phys_target) + return -EINVAL; + + /* + * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must + * use the same target. + */ + if (vcpu->arch.target != -1 && vcpu->arch.target != init->target) + return -EINVAL; + + /* -ENOENT for unknown features, -EINVAL for invalid combinations. */ + for (i = 0; i < sizeof(init->features) * 8; i++) { + bool set = (init->features[i / 32] & (1 << (i % 32))); + + if (set && i >= KVM_VCPU_MAX_FEATURES) + return -ENOENT; + + /* + * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must + * use the same feature set. + */ + if (vcpu->arch.target != -1 && i < KVM_VCPU_MAX_FEATURES && + test_bit(i, vcpu->arch.features) != set) + return -EINVAL; + + if (set) + set_bit(i, vcpu->arch.features); + } + + vcpu->arch.target = phys_target; + + /* Now we know what it is, we can reset it. */ + return kvm_reset_vcpu(vcpu); +} + + +static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, + struct kvm_vcpu_init *init) +{ + int ret; + + ret = kvm_vcpu_set_target(vcpu, init); + if (ret) + return ret; + + /* + * Ensure a rebooted VM will fault in RAM pages and detect if the + * guest MMU is turned off and flush the caches as needed. + */ + if (vcpu->arch.has_run_once) + stage2_unmap_vm(vcpu->kvm); + + vcpu_reset_hcr(vcpu); + + /* + * Handle the "start in power-off" case by marking the VCPU as paused. + */ + if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) + vcpu->arch.pause = true; + else + vcpu->arch.pause = false; + + return 0; +} + +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + + switch (ioctl) { + case KVM_ARM_VCPU_INIT: { + struct kvm_vcpu_init init; + + if (copy_from_user(&init, argp, sizeof(init))) + return -EFAULT; + + return kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init); + } + case KVM_SET_ONE_REG: + case KVM_GET_ONE_REG: { + struct kvm_one_reg reg; + + if (unlikely(!kvm_vcpu_initialized(vcpu))) + return -ENOEXEC; + + if (copy_from_user(®, argp, sizeof(reg))) + return -EFAULT; + if (ioctl == KVM_SET_ONE_REG) + return kvm_arm_set_reg(vcpu, ®); + else + return kvm_arm_get_reg(vcpu, ®); + } + case KVM_GET_REG_LIST: { + struct kvm_reg_list __user *user_list = argp; + struct kvm_reg_list reg_list; + unsigned n; + + if (unlikely(!kvm_vcpu_initialized(vcpu))) + return -ENOEXEC; + + if (copy_from_user(®_list, user_list, sizeof(reg_list))) + return -EFAULT; + n = reg_list.n; + reg_list.n = kvm_arm_num_regs(vcpu); + if (copy_to_user(user_list, ®_list, sizeof(reg_list))) + return -EFAULT; + if (n < reg_list.n) + return -E2BIG; + return kvm_arm_copy_reg_indices(vcpu, user_list->reg); + } + default: + return -EINVAL; + } +} + +/** + * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot + * @kvm: kvm instance + * @log: slot id and address to which we copy the log + * + * Steps 1-4 below provide general overview of dirty page logging. See + * kvm_get_dirty_log_protect() function description for additional details. + * + * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we + * always flush the TLB (step 4) even if previous step failed and the dirty + * bitmap may be corrupt. Regardless of previous outcome the KVM logging API + * does not preclude user space subsequent dirty log read. Flushing TLB ensures + * writes will be marked dirty for next log read. + * + * 1. Take a snapshot of the bit and clear it if needed. + * 2. Write protect the corresponding page. + * 3. Copy the snapshot to the userspace. + * 4. Flush TLB's if needed. + */ +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +{ + bool is_dirty = false; + int r; + + mutex_lock(&kvm->slots_lock); + + r = kvm_get_dirty_log_protect(kvm, log, &is_dirty); + + if (is_dirty) + kvm_flush_remote_tlbs(kvm); + + mutex_unlock(&kvm->slots_lock); + return r; +} + +static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, + struct kvm_arm_device_addr *dev_addr) +{ + unsigned long dev_id, type; + + dev_id = (dev_addr->id & KVM_ARM_DEVICE_ID_MASK) >> + KVM_ARM_DEVICE_ID_SHIFT; + type = (dev_addr->id & KVM_ARM_DEVICE_TYPE_MASK) >> + KVM_ARM_DEVICE_TYPE_SHIFT; + + switch (dev_id) { + case KVM_ARM_DEVICE_VGIC_V2: + return kvm_vgic_addr(kvm, type, &dev_addr->addr, true); + default: + return -ENODEV; + } +} + +long kvm_arch_vm_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm *kvm = filp->private_data; + void __user *argp = (void __user *)arg; + + switch (ioctl) { + case KVM_CREATE_IRQCHIP: { + return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + } + case KVM_ARM_SET_DEVICE_ADDR: { + struct kvm_arm_device_addr dev_addr; + + if (copy_from_user(&dev_addr, argp, sizeof(dev_addr))) + return -EFAULT; + return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr); + } + case KVM_ARM_PREFERRED_TARGET: { + int err; + struct kvm_vcpu_init init; + + err = kvm_vcpu_preferred_target(&init); + if (err) + return err; + + if (copy_to_user(argp, &init, sizeof(init))) + return -EFAULT; + + return 0; + } + default: + return -EINVAL; + } +} + +static void cpu_init_hyp_mode(void *dummy) +{ + phys_addr_t boot_pgd_ptr; + phys_addr_t pgd_ptr; + unsigned long hyp_stack_ptr; + unsigned long stack_page; + unsigned long vector_ptr; + + /* Switch from the HYP stub to our own HYP init vector */ + __hyp_set_vectors(kvm_get_idmap_vector()); + + boot_pgd_ptr = kvm_mmu_get_boot_httbr(); + pgd_ptr = kvm_mmu_get_httbr(); + stack_page = __this_cpu_read(kvm_arm_hyp_stack_page); + hyp_stack_ptr = stack_page + PAGE_SIZE; + vector_ptr = (unsigned long)__kvm_hyp_vector; + + __cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr); +} + +static int hyp_init_cpu_notify(struct notifier_block *self, + unsigned long action, void *cpu) +{ + switch (action) { + case CPU_STARTING: + case CPU_STARTING_FROZEN: + if (__hyp_get_vectors() == hyp_default_vectors) + cpu_init_hyp_mode(NULL); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block hyp_init_cpu_nb = { + .notifier_call = hyp_init_cpu_notify, +}; + +#ifdef CONFIG_CPU_PM +static int hyp_init_cpu_pm_notifier(struct notifier_block *self, + unsigned long cmd, + void *v) +{ + if (cmd == CPU_PM_EXIT && + __hyp_get_vectors() == hyp_default_vectors) { + cpu_init_hyp_mode(NULL); + return NOTIFY_OK; + } + + return NOTIFY_DONE; +} + +static struct notifier_block hyp_init_cpu_pm_nb = { + .notifier_call = hyp_init_cpu_pm_notifier, +}; + +static void __init hyp_cpu_pm_init(void) +{ + cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); +} +#else +static inline void hyp_cpu_pm_init(void) +{ +} +#endif + +/** + * Inits Hyp-mode on all online CPUs + */ +static int init_hyp_mode(void) +{ + int cpu; + int err = 0; + + /* + * Allocate Hyp PGD and setup Hyp identity mapping + */ + err = kvm_mmu_init(); + if (err) + goto out_err; + + /* + * It is probably enough to obtain the default on one + * CPU. It's unlikely to be different on the others. + */ + hyp_default_vectors = __hyp_get_vectors(); + + /* + * Allocate stack pages for Hypervisor-mode + */ + for_each_possible_cpu(cpu) { + unsigned long stack_page; + + stack_page = __get_free_page(GFP_KERNEL); + if (!stack_page) { + err = -ENOMEM; + goto out_free_stack_pages; + } + + per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page; + } + + /* + * Map the Hyp-code called directly from the host + */ + err = create_hyp_mappings(__kvm_hyp_code_start, __kvm_hyp_code_end); + if (err) { + kvm_err("Cannot map world-switch code\n"); + goto out_free_mappings; + } + + /* + * Map the Hyp stack pages + */ + for_each_possible_cpu(cpu) { + char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu); + err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE); + + if (err) { + kvm_err("Cannot map hyp stack\n"); + goto out_free_mappings; + } + } + + /* + * Map the host CPU structures + */ + kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t); + if (!kvm_host_cpu_state) { + err = -ENOMEM; + kvm_err("Cannot allocate host CPU state\n"); + goto out_free_mappings; + } + + for_each_possible_cpu(cpu) { + kvm_cpu_context_t *cpu_ctxt; + + cpu_ctxt = per_cpu_ptr(kvm_host_cpu_state, cpu); + err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1); + + if (err) { + kvm_err("Cannot map host CPU state: %d\n", err); + goto out_free_context; + } + } + + /* + * Execute the init code on each CPU. + */ + on_each_cpu(cpu_init_hyp_mode, NULL, 1); + + /* + * Init HYP view of VGIC + */ + err = kvm_vgic_hyp_init(); + if (err) + goto out_free_context; + + /* + * Init HYP architected timer support + */ + err = kvm_timer_hyp_init(); + if (err) + goto out_free_mappings; + +#ifndef CONFIG_HOTPLUG_CPU + free_boot_hyp_pgd(); +#endif + + kvm_perf_init(); + + kvm_info("Hyp mode initialized successfully\n"); + + return 0; +out_free_context: + free_percpu(kvm_host_cpu_state); +out_free_mappings: + free_hyp_pgds(); +out_free_stack_pages: + for_each_possible_cpu(cpu) + free_page(per_cpu(kvm_arm_hyp_stack_page, cpu)); +out_err: + kvm_err("error initializing Hyp mode: %d\n", err); + return err; +} + +static void check_kvm_target_cpu(void *ret) +{ + *(int *)ret = kvm_target_cpu(); +} + +struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) +{ + struct kvm_vcpu *vcpu; + int i; + + mpidr &= MPIDR_HWID_BITMASK; + kvm_for_each_vcpu(i, vcpu, kvm) { + if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu)) + return vcpu; + } + return NULL; +} + +/** + * Initialize Hyp-mode and memory mappings on all CPUs. + */ +int kvm_arch_init(void *opaque) +{ + int err; + int ret, cpu; + + if (!is_hyp_mode_available()) { + kvm_err("HYP mode not available\n"); + return -ENODEV; + } + + for_each_online_cpu(cpu) { + smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); + if (ret < 0) { + kvm_err("Error, CPU %d not supported!\n", cpu); + return -ENODEV; + } + } + + cpu_notifier_register_begin(); + + err = init_hyp_mode(); + if (err) + goto out_err; + + err = __register_cpu_notifier(&hyp_init_cpu_nb); + if (err) { + kvm_err("Cannot register HYP init CPU notifier (%d)\n", err); + goto out_err; + } + + cpu_notifier_register_done(); + + hyp_cpu_pm_init(); + + kvm_coproc_table_init(); + return 0; +out_err: + cpu_notifier_register_done(); + return err; +} + +/* NOP: Compiling as a module not supported */ +void kvm_arch_exit(void) +{ + kvm_perf_teardown(); +} + +static int arm_init(void) +{ + int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + return rc; +} + +module_init(arm_init); diff --git a/kernel/arch/arm/kvm/coproc.c b/kernel/arch/arm/kvm/coproc.c new file mode 100644 index 000000000..f3d88dc38 --- /dev/null +++ b/kernel/arch/arm/kvm/coproc.c @@ -0,0 +1,1262 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Authors: Rusty Russell + * Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "../vfp/vfpinstr.h" + +#include "trace.h" +#include "coproc.h" + + +/****************************************************************************** + * Co-processor emulation + *****************************************************************************/ + +/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */ +static u32 cache_levels; + +/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */ +#define CSSELR_MAX 12 + +/* + * kvm_vcpu_arch.cp15 holds cp15 registers as an array of u32, but some + * of cp15 registers can be viewed either as couple of two u32 registers + * or one u64 register. Current u64 register encoding is that least + * significant u32 word is followed by most significant u32 word. + */ +static inline void vcpu_cp15_reg64_set(struct kvm_vcpu *vcpu, + const struct coproc_reg *r, + u64 val) +{ + vcpu->arch.cp15[r->reg] = val & 0xffffffff; + vcpu->arch.cp15[r->reg + 1] = val >> 32; +} + +static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu, + const struct coproc_reg *r) +{ + u64 val; + + val = vcpu->arch.cp15[r->reg + 1]; + val = val << 32; + val = val | vcpu->arch.cp15[r->reg]; + return val; +} + +int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + kvm_inject_undefined(vcpu); + return 1; +} + +int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* + * We can get here, if the host has been built without VFPv3 support, + * but the guest attempted a floating point operation. + */ + kvm_inject_undefined(vcpu); + return 1; +} + +int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + kvm_inject_undefined(vcpu); + return 1; +} + +int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + kvm_inject_undefined(vcpu); + return 1; +} + +static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) +{ + /* + * Compute guest MPIDR. We build a virtual cluster out of the + * vcpu_id, but we read the 'U' bit from the underlying + * hardware directly. + */ + vcpu->arch.cp15[c0_MPIDR] = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) | + ((vcpu->vcpu_id >> 2) << MPIDR_LEVEL_BITS) | + (vcpu->vcpu_id & 3)); +} + +/* TRM entries A7:4.3.31 A15:4.3.28 - RO WI */ +static bool access_actlr(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + + *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR]; + return true; +} + +/* TRM entries A7:4.3.56, A15:4.3.60 - R/O. */ +static bool access_cbar(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return write_to_read_only(vcpu, p); + return read_zero(vcpu, p); +} + +/* TRM entries A7:4.3.49, A15:4.3.48 - R/O WI */ +static bool access_l2ctlr(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + + *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR]; + return true; +} + +static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) +{ + u32 l2ctlr, ncores; + + asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr)); + l2ctlr &= ~(3 << 24); + ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1; + /* How many cores in the current cluster and the next ones */ + ncores -= (vcpu->vcpu_id & ~3); + /* Cap it to the maximum number of cores in a single cluster */ + ncores = min(ncores, 3U); + l2ctlr |= (ncores & 3) << 24; + + vcpu->arch.cp15[c9_L2CTLR] = l2ctlr; +} + +static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) +{ + u32 actlr; + + /* ACTLR contains SMP bit: make sure you create all cpus first! */ + asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr)); + /* Make the SMP bit consistent with the guest configuration */ + if (atomic_read(&vcpu->kvm->online_vcpus) > 1) + actlr |= 1U << 6; + else + actlr &= ~(1U << 6); + + vcpu->arch.cp15[c1_ACTLR] = actlr; +} + +/* + * TRM entries: A7:4.3.50, A15:4.3.49 + * R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored). + */ +static bool access_l2ectlr(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + + *vcpu_reg(vcpu, p->Rt1) = 0; + return true; +} + +/* + * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). + */ +static bool access_dcsw(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (!p->is_write) + return read_from_write_only(vcpu, p); + + kvm_set_way_flush(vcpu); + return true; +} + +/* + * Generic accessor for VM registers. Only called as long as HCR_TVM + * is set. If the guest enables the MMU, we stop trapping the VM + * sys_regs and leave it in complete control of the caches. + * + * Used by the cpu-specific code. + */ +bool access_vm_reg(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + bool was_enabled = vcpu_has_cache_enabled(vcpu); + + BUG_ON(!p->is_write); + + vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1); + if (p->is_64bit) + vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2); + + kvm_toggle_cache(vcpu, was_enabled); + return true; +} + +/* + * We could trap ID_DFR0 and tell the guest we don't support performance + * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was + * NAKed, so it will read the PMCR anyway. + * + * Therefore we tell the guest we have 0 counters. Unfortunately, we + * must always support PMCCNTR (the cycle counter): we just RAZ/WI for + * all PM registers, which doesn't crash the guest kernel at least. + */ +static bool pm_fake(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + else + return read_zero(vcpu, p); +} + +#define access_pmcr pm_fake +#define access_pmcntenset pm_fake +#define access_pmcntenclr pm_fake +#define access_pmovsr pm_fake +#define access_pmselr pm_fake +#define access_pmceid0 pm_fake +#define access_pmceid1 pm_fake +#define access_pmccntr pm_fake +#define access_pmxevtyper pm_fake +#define access_pmxevcntr pm_fake +#define access_pmuserenr pm_fake +#define access_pmintenset pm_fake +#define access_pmintenclr pm_fake + +/* Architected CP15 registers. + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. + */ +static const struct coproc_reg cp15_regs[] = { + /* MPIDR: we use VMPIDR for guest access. */ + { CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32, + NULL, reset_mpidr, c0_MPIDR }, + + /* CSSELR: swapped by interrupt.S. */ + { CRn( 0), CRm( 0), Op1( 2), Op2( 0), is32, + NULL, reset_unknown, c0_CSSELR }, + + /* ACTLR: trapped by HCR.TAC bit. */ + { CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32, + access_actlr, reset_actlr, c1_ACTLR }, + + /* CPACR: swapped by interrupt.S. */ + { CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32, + NULL, reset_val, c1_CPACR, 0x00000000 }, + + /* TTBR0/TTBR1/TTBCR: swapped by interrupt.S. */ + { CRm64( 2), Op1( 0), is64, access_vm_reg, reset_unknown64, c2_TTBR0 }, + { CRn(2), CRm( 0), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_unknown, c2_TTBR0 }, + { CRn(2), CRm( 0), Op1( 0), Op2( 1), is32, + access_vm_reg, reset_unknown, c2_TTBR1 }, + { CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32, + access_vm_reg, reset_val, c2_TTBCR, 0x00000000 }, + { CRm64( 2), Op1( 1), is64, access_vm_reg, reset_unknown64, c2_TTBR1 }, + + + /* DACR: swapped by interrupt.S. */ + { CRn( 3), CRm( 0), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_unknown, c3_DACR }, + + /* DFSR/IFSR/ADFSR/AIFSR: swapped by interrupt.S. */ + { CRn( 5), CRm( 0), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_unknown, c5_DFSR }, + { CRn( 5), CRm( 0), Op1( 0), Op2( 1), is32, + access_vm_reg, reset_unknown, c5_IFSR }, + { CRn( 5), CRm( 1), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_unknown, c5_ADFSR }, + { CRn( 5), CRm( 1), Op1( 0), Op2( 1), is32, + access_vm_reg, reset_unknown, c5_AIFSR }, + + /* DFAR/IFAR: swapped by interrupt.S. */ + { CRn( 6), CRm( 0), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_unknown, c6_DFAR }, + { CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32, + access_vm_reg, reset_unknown, c6_IFAR }, + + /* PAR swapped by interrupt.S */ + { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, + + /* + * DC{C,I,CI}SW operations: + */ + { CRn( 7), CRm( 6), Op1( 0), Op2( 2), is32, access_dcsw}, + { CRn( 7), CRm(10), Op1( 0), Op2( 2), is32, access_dcsw}, + { CRn( 7), CRm(14), Op1( 0), Op2( 2), is32, access_dcsw}, + /* + * L2CTLR access (guest wants to know #CPUs). + */ + { CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32, + access_l2ctlr, reset_l2ctlr, c9_L2CTLR }, + { CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr}, + + /* + * Dummy performance monitor implementation. + */ + { CRn( 9), CRm(12), Op1( 0), Op2( 0), is32, access_pmcr}, + { CRn( 9), CRm(12), Op1( 0), Op2( 1), is32, access_pmcntenset}, + { CRn( 9), CRm(12), Op1( 0), Op2( 2), is32, access_pmcntenclr}, + { CRn( 9), CRm(12), Op1( 0), Op2( 3), is32, access_pmovsr}, + { CRn( 9), CRm(12), Op1( 0), Op2( 5), is32, access_pmselr}, + { CRn( 9), CRm(12), Op1( 0), Op2( 6), is32, access_pmceid0}, + { CRn( 9), CRm(12), Op1( 0), Op2( 7), is32, access_pmceid1}, + { CRn( 9), CRm(13), Op1( 0), Op2( 0), is32, access_pmccntr}, + { CRn( 9), CRm(13), Op1( 0), Op2( 1), is32, access_pmxevtyper}, + { CRn( 9), CRm(13), Op1( 0), Op2( 2), is32, access_pmxevcntr}, + { CRn( 9), CRm(14), Op1( 0), Op2( 0), is32, access_pmuserenr}, + { CRn( 9), CRm(14), Op1( 0), Op2( 1), is32, access_pmintenset}, + { CRn( 9), CRm(14), Op1( 0), Op2( 2), is32, access_pmintenclr}, + + /* PRRR/NMRR (aka MAIR0/MAIR1): swapped by interrupt.S. */ + { CRn(10), CRm( 2), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_unknown, c10_PRRR}, + { CRn(10), CRm( 2), Op1( 0), Op2( 1), is32, + access_vm_reg, reset_unknown, c10_NMRR}, + + /* AMAIR0/AMAIR1: swapped by interrupt.S. */ + { CRn(10), CRm( 3), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_unknown, c10_AMAIR0}, + { CRn(10), CRm( 3), Op1( 0), Op2( 1), is32, + access_vm_reg, reset_unknown, c10_AMAIR1}, + + /* VBAR: swapped by interrupt.S. */ + { CRn(12), CRm( 0), Op1( 0), Op2( 0), is32, + NULL, reset_val, c12_VBAR, 0x00000000 }, + + /* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */ + { CRn(13), CRm( 0), Op1( 0), Op2( 1), is32, + access_vm_reg, reset_val, c13_CID, 0x00000000 }, + { CRn(13), CRm( 0), Op1( 0), Op2( 2), is32, + NULL, reset_unknown, c13_TID_URW }, + { CRn(13), CRm( 0), Op1( 0), Op2( 3), is32, + NULL, reset_unknown, c13_TID_URO }, + { CRn(13), CRm( 0), Op1( 0), Op2( 4), is32, + NULL, reset_unknown, c13_TID_PRIV }, + + /* CNTKCTL: swapped by interrupt.S. */ + { CRn(14), CRm( 1), Op1( 0), Op2( 0), is32, + NULL, reset_val, c14_CNTKCTL, 0x00000000 }, + + /* The Configuration Base Address Register. */ + { CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar}, +}; + +/* Target specific emulation tables */ +static struct kvm_coproc_target_table *target_tables[KVM_ARM_NUM_TARGETS]; + +void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table) +{ + unsigned int i; + + for (i = 1; i < table->num; i++) + BUG_ON(cmp_reg(&table->table[i-1], + &table->table[i]) >= 0); + + target_tables[table->target] = table; +} + +/* Get specific register table for this target. */ +static const struct coproc_reg *get_target_table(unsigned target, size_t *num) +{ + struct kvm_coproc_target_table *table; + + table = target_tables[target]; + *num = table->num; + return table->table; +} + +static const struct coproc_reg *find_reg(const struct coproc_params *params, + const struct coproc_reg table[], + unsigned int num) +{ + unsigned int i; + + for (i = 0; i < num; i++) { + const struct coproc_reg *r = &table[i]; + + if (params->is_64bit != r->is_64) + continue; + if (params->CRn != r->CRn) + continue; + if (params->CRm != r->CRm) + continue; + if (params->Op1 != r->Op1) + continue; + if (params->Op2 != r->Op2) + continue; + + return r; + } + return NULL; +} + +static int emulate_cp15(struct kvm_vcpu *vcpu, + const struct coproc_params *params) +{ + size_t num; + const struct coproc_reg *table, *r; + + trace_kvm_emulate_cp15_imp(params->Op1, params->Rt1, params->CRn, + params->CRm, params->Op2, params->is_write); + + table = get_target_table(vcpu->arch.target, &num); + + /* Search target-specific then generic table. */ + r = find_reg(params, table, num); + if (!r) + r = find_reg(params, cp15_regs, ARRAY_SIZE(cp15_regs)); + + if (likely(r)) { + /* If we don't have an accessor, we should never get here! */ + BUG_ON(!r->access); + + if (likely(r->access(vcpu, params, r))) { + /* Skip instruction, since it was emulated */ + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; + } + /* If access function fails, it should complain. */ + } else { + kvm_err("Unsupported guest CP15 access at: %08lx\n", + *vcpu_pc(vcpu)); + print_cp_instr(params); + } + kvm_inject_undefined(vcpu); + return 1; +} + +/** + * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access + * @vcpu: The VCPU pointer + * @run: The kvm_run struct + */ +int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + struct coproc_params params; + + params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; + params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; + params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); + params.is_64bit = true; + + params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf; + params.Op2 = 0; + params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; + params.CRm = 0; + + return emulate_cp15(vcpu, ¶ms); +} + +static void reset_coproc_regs(struct kvm_vcpu *vcpu, + const struct coproc_reg *table, size_t num) +{ + unsigned long i; + + for (i = 0; i < num; i++) + if (table[i].reset) + table[i].reset(vcpu, &table[i]); +} + +/** + * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access + * @vcpu: The VCPU pointer + * @run: The kvm_run struct + */ +int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + struct coproc_params params; + + params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; + params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; + params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); + params.is_64bit = false; + + params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; + params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 14) & 0x7; + params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7; + params.Rt2 = 0; + + return emulate_cp15(vcpu, ¶ms); +} + +/****************************************************************************** + * Userspace API + *****************************************************************************/ + +static bool index_to_params(u64 id, struct coproc_params *params) +{ + switch (id & KVM_REG_SIZE_MASK) { + case KVM_REG_SIZE_U32: + /* Any unused index bits means it's not valid. */ + if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK + | KVM_REG_ARM_COPROC_MASK + | KVM_REG_ARM_32_CRN_MASK + | KVM_REG_ARM_CRM_MASK + | KVM_REG_ARM_OPC1_MASK + | KVM_REG_ARM_32_OPC2_MASK)) + return false; + + params->is_64bit = false; + params->CRn = ((id & KVM_REG_ARM_32_CRN_MASK) + >> KVM_REG_ARM_32_CRN_SHIFT); + params->CRm = ((id & KVM_REG_ARM_CRM_MASK) + >> KVM_REG_ARM_CRM_SHIFT); + params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK) + >> KVM_REG_ARM_OPC1_SHIFT); + params->Op2 = ((id & KVM_REG_ARM_32_OPC2_MASK) + >> KVM_REG_ARM_32_OPC2_SHIFT); + return true; + case KVM_REG_SIZE_U64: + /* Any unused index bits means it's not valid. */ + if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK + | KVM_REG_ARM_COPROC_MASK + | KVM_REG_ARM_CRM_MASK + | KVM_REG_ARM_OPC1_MASK)) + return false; + params->is_64bit = true; + /* CRm to CRn: see cp15_to_index for details */ + params->CRn = ((id & KVM_REG_ARM_CRM_MASK) + >> KVM_REG_ARM_CRM_SHIFT); + params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK) + >> KVM_REG_ARM_OPC1_SHIFT); + params->Op2 = 0; + params->CRm = 0; + return true; + default: + return false; + } +} + +/* Decode an index value, and find the cp15 coproc_reg entry. */ +static const struct coproc_reg *index_to_coproc_reg(struct kvm_vcpu *vcpu, + u64 id) +{ + size_t num; + const struct coproc_reg *table, *r; + struct coproc_params params; + + /* We only do cp15 for now. */ + if ((id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT != 15) + return NULL; + + if (!index_to_params(id, ¶ms)) + return NULL; + + table = get_target_table(vcpu->arch.target, &num); + r = find_reg(¶ms, table, num); + if (!r) + r = find_reg(¶ms, cp15_regs, ARRAY_SIZE(cp15_regs)); + + /* Not saved in the cp15 array? */ + if (r && !r->reg) + r = NULL; + + return r; +} + +/* + * These are the invariant cp15 registers: we let the guest see the host + * versions of these, so they're part of the guest state. + * + * A future CPU may provide a mechanism to present different values to + * the guest, or a future kvm may trap them. + */ +/* Unfortunately, there's no register-argument for mrc, so generate. */ +#define FUNCTION_FOR32(crn, crm, op1, op2, name) \ + static void get_##name(struct kvm_vcpu *v, \ + const struct coproc_reg *r) \ + { \ + u32 val; \ + \ + asm volatile("mrc p15, " __stringify(op1) \ + ", %0, c" __stringify(crn) \ + ", c" __stringify(crm) \ + ", " __stringify(op2) "\n" : "=r" (val)); \ + ((struct coproc_reg *)r)->val = val; \ + } + +FUNCTION_FOR32(0, 0, 0, 0, MIDR) +FUNCTION_FOR32(0, 0, 0, 1, CTR) +FUNCTION_FOR32(0, 0, 0, 2, TCMTR) +FUNCTION_FOR32(0, 0, 0, 3, TLBTR) +FUNCTION_FOR32(0, 0, 0, 6, REVIDR) +FUNCTION_FOR32(0, 1, 0, 0, ID_PFR0) +FUNCTION_FOR32(0, 1, 0, 1, ID_PFR1) +FUNCTION_FOR32(0, 1, 0, 2, ID_DFR0) +FUNCTION_FOR32(0, 1, 0, 3, ID_AFR0) +FUNCTION_FOR32(0, 1, 0, 4, ID_MMFR0) +FUNCTION_FOR32(0, 1, 0, 5, ID_MMFR1) +FUNCTION_FOR32(0, 1, 0, 6, ID_MMFR2) +FUNCTION_FOR32(0, 1, 0, 7, ID_MMFR3) +FUNCTION_FOR32(0, 2, 0, 0, ID_ISAR0) +FUNCTION_FOR32(0, 2, 0, 1, ID_ISAR1) +FUNCTION_FOR32(0, 2, 0, 2, ID_ISAR2) +FUNCTION_FOR32(0, 2, 0, 3, ID_ISAR3) +FUNCTION_FOR32(0, 2, 0, 4, ID_ISAR4) +FUNCTION_FOR32(0, 2, 0, 5, ID_ISAR5) +FUNCTION_FOR32(0, 0, 1, 1, CLIDR) +FUNCTION_FOR32(0, 0, 1, 7, AIDR) + +/* ->val is filled in by kvm_invariant_coproc_table_init() */ +static struct coproc_reg invariant_cp15[] = { + { CRn( 0), CRm( 0), Op1( 0), Op2( 0), is32, NULL, get_MIDR }, + { CRn( 0), CRm( 0), Op1( 0), Op2( 1), is32, NULL, get_CTR }, + { CRn( 0), CRm( 0), Op1( 0), Op2( 2), is32, NULL, get_TCMTR }, + { CRn( 0), CRm( 0), Op1( 0), Op2( 3), is32, NULL, get_TLBTR }, + { CRn( 0), CRm( 0), Op1( 0), Op2( 6), is32, NULL, get_REVIDR }, + + { CRn( 0), CRm( 1), Op1( 0), Op2( 0), is32, NULL, get_ID_PFR0 }, + { CRn( 0), CRm( 1), Op1( 0), Op2( 1), is32, NULL, get_ID_PFR1 }, + { CRn( 0), CRm( 1), Op1( 0), Op2( 2), is32, NULL, get_ID_DFR0 }, + { CRn( 0), CRm( 1), Op1( 0), Op2( 3), is32, NULL, get_ID_AFR0 }, + { CRn( 0), CRm( 1), Op1( 0), Op2( 4), is32, NULL, get_ID_MMFR0 }, + { CRn( 0), CRm( 1), Op1( 0), Op2( 5), is32, NULL, get_ID_MMFR1 }, + { CRn( 0), CRm( 1), Op1( 0), Op2( 6), is32, NULL, get_ID_MMFR2 }, + { CRn( 0), CRm( 1), Op1( 0), Op2( 7), is32, NULL, get_ID_MMFR3 }, + + { CRn( 0), CRm( 2), Op1( 0), Op2( 0), is32, NULL, get_ID_ISAR0 }, + { CRn( 0), CRm( 2), Op1( 0), Op2( 1), is32, NULL, get_ID_ISAR1 }, + { CRn( 0), CRm( 2), Op1( 0), Op2( 2), is32, NULL, get_ID_ISAR2 }, + { CRn( 0), CRm( 2), Op1( 0), Op2( 3), is32, NULL, get_ID_ISAR3 }, + { CRn( 0), CRm( 2), Op1( 0), Op2( 4), is32, NULL, get_ID_ISAR4 }, + { CRn( 0), CRm( 2), Op1( 0), Op2( 5), is32, NULL, get_ID_ISAR5 }, + + { CRn( 0), CRm( 0), Op1( 1), Op2( 1), is32, NULL, get_CLIDR }, + { CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR }, +}; + +/* + * Reads a register value from a userspace address to a kernel + * variable. Make sure that register size matches sizeof(*__val). + */ +static int reg_from_user(void *val, const void __user *uaddr, u64 id) +{ + if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0) + return -EFAULT; + return 0; +} + +/* + * Writes a register value to a userspace address from a kernel variable. + * Make sure that register size matches sizeof(*__val). + */ +static int reg_to_user(void __user *uaddr, const void *val, u64 id) +{ + if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0) + return -EFAULT; + return 0; +} + +static int get_invariant_cp15(u64 id, void __user *uaddr) +{ + struct coproc_params params; + const struct coproc_reg *r; + int ret; + + if (!index_to_params(id, ¶ms)) + return -ENOENT; + + r = find_reg(¶ms, invariant_cp15, ARRAY_SIZE(invariant_cp15)); + if (!r) + return -ENOENT; + + ret = -ENOENT; + if (KVM_REG_SIZE(id) == 4) { + u32 val = r->val; + + ret = reg_to_user(uaddr, &val, id); + } else if (KVM_REG_SIZE(id) == 8) { + ret = reg_to_user(uaddr, &r->val, id); + } + return ret; +} + +static int set_invariant_cp15(u64 id, void __user *uaddr) +{ + struct coproc_params params; + const struct coproc_reg *r; + int err; + u64 val; + + if (!index_to_params(id, ¶ms)) + return -ENOENT; + r = find_reg(¶ms, invariant_cp15, ARRAY_SIZE(invariant_cp15)); + if (!r) + return -ENOENT; + + err = -ENOENT; + if (KVM_REG_SIZE(id) == 4) { + u32 val32; + + err = reg_from_user(&val32, uaddr, id); + if (!err) + val = val32; + } else if (KVM_REG_SIZE(id) == 8) { + err = reg_from_user(&val, uaddr, id); + } + if (err) + return err; + + /* This is what we mean by invariant: you can't change it. */ + if (r->val != val) + return -EINVAL; + + return 0; +} + +static bool is_valid_cache(u32 val) +{ + u32 level, ctype; + + if (val >= CSSELR_MAX) + return false; + + /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */ + level = (val >> 1); + ctype = (cache_levels >> (level * 3)) & 7; + + switch (ctype) { + case 0: /* No cache */ + return false; + case 1: /* Instruction cache only */ + return (val & 1); + case 2: /* Data cache only */ + case 4: /* Unified cache */ + return !(val & 1); + case 3: /* Separate instruction and data caches */ + return true; + default: /* Reserved: we can't know instruction or data. */ + return false; + } +} + +/* Which cache CCSIDR represents depends on CSSELR value. */ +static u32 get_ccsidr(u32 csselr) +{ + u32 ccsidr; + + /* Make sure noone else changes CSSELR during this! */ + local_irq_disable(); + /* Put value into CSSELR */ + asm volatile("mcr p15, 2, %0, c0, c0, 0" : : "r" (csselr)); + isb(); + /* Read result out of CCSIDR */ + asm volatile("mrc p15, 1, %0, c0, c0, 0" : "=r" (ccsidr)); + local_irq_enable(); + + return ccsidr; +} + +static int demux_c15_get(u64 id, void __user *uaddr) +{ + u32 val; + u32 __user *uval = uaddr; + + /* Fail if we have unknown bits set. */ + if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK + | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) + return -ENOENT; + + switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { + case KVM_REG_ARM_DEMUX_ID_CCSIDR: + if (KVM_REG_SIZE(id) != 4) + return -ENOENT; + val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) + >> KVM_REG_ARM_DEMUX_VAL_SHIFT; + if (!is_valid_cache(val)) + return -ENOENT; + + return put_user(get_ccsidr(val), uval); + default: + return -ENOENT; + } +} + +static int demux_c15_set(u64 id, void __user *uaddr) +{ + u32 val, newval; + u32 __user *uval = uaddr; + + /* Fail if we have unknown bits set. */ + if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK + | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) + return -ENOENT; + + switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { + case KVM_REG_ARM_DEMUX_ID_CCSIDR: + if (KVM_REG_SIZE(id) != 4) + return -ENOENT; + val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) + >> KVM_REG_ARM_DEMUX_VAL_SHIFT; + if (!is_valid_cache(val)) + return -ENOENT; + + if (get_user(newval, uval)) + return -EFAULT; + + /* This is also invariant: you can't change it. */ + if (newval != get_ccsidr(val)) + return -EINVAL; + return 0; + default: + return -ENOENT; + } +} + +#ifdef CONFIG_VFPv3 +static const int vfp_sysregs[] = { KVM_REG_ARM_VFP_FPEXC, + KVM_REG_ARM_VFP_FPSCR, + KVM_REG_ARM_VFP_FPINST, + KVM_REG_ARM_VFP_FPINST2, + KVM_REG_ARM_VFP_MVFR0, + KVM_REG_ARM_VFP_MVFR1, + KVM_REG_ARM_VFP_FPSID }; + +static unsigned int num_fp_regs(void) +{ + if (((fmrx(MVFR0) & MVFR0_A_SIMD_MASK) >> MVFR0_A_SIMD_BIT) == 2) + return 32; + else + return 16; +} + +static unsigned int num_vfp_regs(void) +{ + /* Normal FP regs + control regs. */ + return num_fp_regs() + ARRAY_SIZE(vfp_sysregs); +} + +static int copy_vfp_regids(u64 __user *uindices) +{ + unsigned int i; + const u64 u32reg = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP; + const u64 u64reg = KVM_REG_ARM | KVM_REG_SIZE_U64 | KVM_REG_ARM_VFP; + + for (i = 0; i < num_fp_regs(); i++) { + if (put_user((u64reg | KVM_REG_ARM_VFP_BASE_REG) + i, + uindices)) + return -EFAULT; + uindices++; + } + + for (i = 0; i < ARRAY_SIZE(vfp_sysregs); i++) { + if (put_user(u32reg | vfp_sysregs[i], uindices)) + return -EFAULT; + uindices++; + } + + return num_vfp_regs(); +} + +static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) +{ + u32 vfpid = (id & KVM_REG_ARM_VFP_MASK); + u32 val; + + /* Fail if we have unknown bits set. */ + if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK + | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) + return -ENOENT; + + if (vfpid < num_fp_regs()) { + if (KVM_REG_SIZE(id) != 8) + return -ENOENT; + return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpregs[vfpid], + id); + } + + /* FP control registers are all 32 bit. */ + if (KVM_REG_SIZE(id) != 4) + return -ENOENT; + + switch (vfpid) { + case KVM_REG_ARM_VFP_FPEXC: + return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpexc, id); + case KVM_REG_ARM_VFP_FPSCR: + return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpscr, id); + case KVM_REG_ARM_VFP_FPINST: + return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpinst, id); + case KVM_REG_ARM_VFP_FPINST2: + return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpinst2, id); + case KVM_REG_ARM_VFP_MVFR0: + val = fmrx(MVFR0); + return reg_to_user(uaddr, &val, id); + case KVM_REG_ARM_VFP_MVFR1: + val = fmrx(MVFR1); + return reg_to_user(uaddr, &val, id); + case KVM_REG_ARM_VFP_FPSID: + val = fmrx(FPSID); + return reg_to_user(uaddr, &val, id); + default: + return -ENOENT; + } +} + +static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr) +{ + u32 vfpid = (id & KVM_REG_ARM_VFP_MASK); + u32 val; + + /* Fail if we have unknown bits set. */ + if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK + | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) + return -ENOENT; + + if (vfpid < num_fp_regs()) { + if (KVM_REG_SIZE(id) != 8) + return -ENOENT; + return reg_from_user(&vcpu->arch.vfp_guest.fpregs[vfpid], + uaddr, id); + } + + /* FP control registers are all 32 bit. */ + if (KVM_REG_SIZE(id) != 4) + return -ENOENT; + + switch (vfpid) { + case KVM_REG_ARM_VFP_FPEXC: + return reg_from_user(&vcpu->arch.vfp_guest.fpexc, uaddr, id); + case KVM_REG_ARM_VFP_FPSCR: + return reg_from_user(&vcpu->arch.vfp_guest.fpscr, uaddr, id); + case KVM_REG_ARM_VFP_FPINST: + return reg_from_user(&vcpu->arch.vfp_guest.fpinst, uaddr, id); + case KVM_REG_ARM_VFP_FPINST2: + return reg_from_user(&vcpu->arch.vfp_guest.fpinst2, uaddr, id); + /* These are invariant. */ + case KVM_REG_ARM_VFP_MVFR0: + if (reg_from_user(&val, uaddr, id)) + return -EFAULT; + if (val != fmrx(MVFR0)) + return -EINVAL; + return 0; + case KVM_REG_ARM_VFP_MVFR1: + if (reg_from_user(&val, uaddr, id)) + return -EFAULT; + if (val != fmrx(MVFR1)) + return -EINVAL; + return 0; + case KVM_REG_ARM_VFP_FPSID: + if (reg_from_user(&val, uaddr, id)) + return -EFAULT; + if (val != fmrx(FPSID)) + return -EINVAL; + return 0; + default: + return -ENOENT; + } +} +#else /* !CONFIG_VFPv3 */ +static unsigned int num_vfp_regs(void) +{ + return 0; +} + +static int copy_vfp_regids(u64 __user *uindices) +{ + return 0; +} + +static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) +{ + return -ENOENT; +} + +static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr) +{ + return -ENOENT; +} +#endif /* !CONFIG_VFPv3 */ + +int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + const struct coproc_reg *r; + void __user *uaddr = (void __user *)(long)reg->addr; + int ret; + + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) + return demux_c15_get(reg->id, uaddr); + + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_VFP) + return vfp_get_reg(vcpu, reg->id, uaddr); + + r = index_to_coproc_reg(vcpu, reg->id); + if (!r) + return get_invariant_cp15(reg->id, uaddr); + + ret = -ENOENT; + if (KVM_REG_SIZE(reg->id) == 8) { + u64 val; + + val = vcpu_cp15_reg64_get(vcpu, r); + ret = reg_to_user(uaddr, &val, reg->id); + } else if (KVM_REG_SIZE(reg->id) == 4) { + ret = reg_to_user(uaddr, &vcpu->arch.cp15[r->reg], reg->id); + } + + return ret; +} + +int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + const struct coproc_reg *r; + void __user *uaddr = (void __user *)(long)reg->addr; + int ret; + + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) + return demux_c15_set(reg->id, uaddr); + + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_VFP) + return vfp_set_reg(vcpu, reg->id, uaddr); + + r = index_to_coproc_reg(vcpu, reg->id); + if (!r) + return set_invariant_cp15(reg->id, uaddr); + + ret = -ENOENT; + if (KVM_REG_SIZE(reg->id) == 8) { + u64 val; + + ret = reg_from_user(&val, uaddr, reg->id); + if (!ret) + vcpu_cp15_reg64_set(vcpu, r, val); + } else if (KVM_REG_SIZE(reg->id) == 4) { + ret = reg_from_user(&vcpu->arch.cp15[r->reg], uaddr, reg->id); + } + + return ret; +} + +static unsigned int num_demux_regs(void) +{ + unsigned int i, count = 0; + + for (i = 0; i < CSSELR_MAX; i++) + if (is_valid_cache(i)) + count++; + + return count; +} + +static int write_demux_regids(u64 __user *uindices) +{ + u64 val = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX; + unsigned int i; + + val |= KVM_REG_ARM_DEMUX_ID_CCSIDR; + for (i = 0; i < CSSELR_MAX; i++) { + if (!is_valid_cache(i)) + continue; + if (put_user(val | i, uindices)) + return -EFAULT; + uindices++; + } + return 0; +} + +static u64 cp15_to_index(const struct coproc_reg *reg) +{ + u64 val = KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT); + if (reg->is_64) { + val |= KVM_REG_SIZE_U64; + val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); + /* + * CRn always denotes the primary coproc. reg. nr. for the + * in-kernel representation, but the user space API uses the + * CRm for the encoding, because it is modelled after the + * MRRC/MCRR instructions: see the ARM ARM rev. c page + * B3-1445 + */ + val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT); + } else { + val |= KVM_REG_SIZE_U32; + val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); + val |= (reg->Op2 << KVM_REG_ARM_32_OPC2_SHIFT); + val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT); + val |= (reg->CRn << KVM_REG_ARM_32_CRN_SHIFT); + } + return val; +} + +static bool copy_reg_to_user(const struct coproc_reg *reg, u64 __user **uind) +{ + if (!*uind) + return true; + + if (put_user(cp15_to_index(reg), *uind)) + return false; + + (*uind)++; + return true; +} + +/* Assumed ordered tables, see kvm_coproc_table_init. */ +static int walk_cp15(struct kvm_vcpu *vcpu, u64 __user *uind) +{ + const struct coproc_reg *i1, *i2, *end1, *end2; + unsigned int total = 0; + size_t num; + + /* We check for duplicates here, to allow arch-specific overrides. */ + i1 = get_target_table(vcpu->arch.target, &num); + end1 = i1 + num; + i2 = cp15_regs; + end2 = cp15_regs + ARRAY_SIZE(cp15_regs); + + BUG_ON(i1 == end1 || i2 == end2); + + /* Walk carefully, as both tables may refer to the same register. */ + while (i1 || i2) { + int cmp = cmp_reg(i1, i2); + /* target-specific overrides generic entry. */ + if (cmp <= 0) { + /* Ignore registers we trap but don't save. */ + if (i1->reg) { + if (!copy_reg_to_user(i1, &uind)) + return -EFAULT; + total++; + } + } else { + /* Ignore registers we trap but don't save. */ + if (i2->reg) { + if (!copy_reg_to_user(i2, &uind)) + return -EFAULT; + total++; + } + } + + if (cmp <= 0 && ++i1 == end1) + i1 = NULL; + if (cmp >= 0 && ++i2 == end2) + i2 = NULL; + } + return total; +} + +unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu) +{ + return ARRAY_SIZE(invariant_cp15) + + num_demux_regs() + + num_vfp_regs() + + walk_cp15(vcpu, (u64 __user *)NULL); +} + +int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + unsigned int i; + int err; + + /* Then give them all the invariant registers' indices. */ + for (i = 0; i < ARRAY_SIZE(invariant_cp15); i++) { + if (put_user(cp15_to_index(&invariant_cp15[i]), uindices)) + return -EFAULT; + uindices++; + } + + err = walk_cp15(vcpu, uindices); + if (err < 0) + return err; + uindices += err; + + err = copy_vfp_regids(uindices); + if (err < 0) + return err; + uindices += err; + + return write_demux_regids(uindices); +} + +void kvm_coproc_table_init(void) +{ + unsigned int i; + + /* Make sure tables are unique and in order. */ + for (i = 1; i < ARRAY_SIZE(cp15_regs); i++) + BUG_ON(cmp_reg(&cp15_regs[i-1], &cp15_regs[i]) >= 0); + + /* We abuse the reset function to overwrite the table itself. */ + for (i = 0; i < ARRAY_SIZE(invariant_cp15); i++) + invariant_cp15[i].reset(NULL, &invariant_cp15[i]); + + /* + * CLIDR format is awkward, so clean it up. See ARM B4.1.20: + * + * If software reads the Cache Type fields from Ctype1 + * upwards, once it has seen a value of 0b000, no caches + * exist at further-out levels of the hierarchy. So, for + * example, if Ctype3 is the first Cache Type field with a + * value of 0b000, the values of Ctype4 to Ctype7 must be + * ignored. + */ + asm volatile("mrc p15, 1, %0, c0, c0, 1" : "=r" (cache_levels)); + for (i = 0; i < 7; i++) + if (((cache_levels >> (i*3)) & 7) == 0) + break; + /* Clear all higher bits. */ + cache_levels &= (1 << (i*3))-1; +} + +/** + * kvm_reset_coprocs - sets cp15 registers to reset value + * @vcpu: The VCPU pointer + * + * This function finds the right table above and sets the registers on the + * virtual CPU struct to their architecturally defined reset values. + */ +void kvm_reset_coprocs(struct kvm_vcpu *vcpu) +{ + size_t num; + const struct coproc_reg *table; + + /* Catch someone adding a register without putting in reset entry. */ + memset(vcpu->arch.cp15, 0x42, sizeof(vcpu->arch.cp15)); + + /* Generic chip reset first (so target could override). */ + reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs)); + + table = get_target_table(vcpu->arch.target, &num); + reset_coproc_regs(vcpu, table, num); + + for (num = 1; num < NR_CP15_REGS; num++) + if (vcpu->arch.cp15[num] == 0x42424242) + panic("Didn't reset vcpu->arch.cp15[%zi]", num); +} diff --git a/kernel/arch/arm/kvm/coproc.h b/kernel/arch/arm/kvm/coproc.h new file mode 100644 index 000000000..88d24a3a9 --- /dev/null +++ b/kernel/arch/arm/kvm/coproc.h @@ -0,0 +1,160 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Authors: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#ifndef __ARM_KVM_COPROC_LOCAL_H__ +#define __ARM_KVM_COPROC_LOCAL_H__ + +struct coproc_params { + unsigned long CRn; + unsigned long CRm; + unsigned long Op1; + unsigned long Op2; + unsigned long Rt1; + unsigned long Rt2; + bool is_64bit; + bool is_write; +}; + +struct coproc_reg { + /* MRC/MCR/MRRC/MCRR instruction which accesses it. */ + unsigned long CRn; + unsigned long CRm; + unsigned long Op1; + unsigned long Op2; + + bool is_64; + + /* Trapped access from guest, if non-NULL. */ + bool (*access)(struct kvm_vcpu *, + const struct coproc_params *, + const struct coproc_reg *); + + /* Initialization for vcpu. */ + void (*reset)(struct kvm_vcpu *, const struct coproc_reg *); + + /* Index into vcpu->arch.cp15[], or 0 if we don't need to save it. */ + unsigned long reg; + + /* Value (usually reset value) */ + u64 val; +}; + +static inline void print_cp_instr(const struct coproc_params *p) +{ + /* Look, we even formatted it for you to paste into the table! */ + if (p->is_64bit) { + kvm_pr_unimpl(" { CRm64(%2lu), Op1(%2lu), is64, func_%s },\n", + p->CRn, p->Op1, p->is_write ? "write" : "read"); + } else { + kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32," + " func_%s },\n", + p->CRn, p->CRm, p->Op1, p->Op2, + p->is_write ? "write" : "read"); + } +} + +static inline bool ignore_write(struct kvm_vcpu *vcpu, + const struct coproc_params *p) +{ + return true; +} + +static inline bool read_zero(struct kvm_vcpu *vcpu, + const struct coproc_params *p) +{ + *vcpu_reg(vcpu, p->Rt1) = 0; + return true; +} + +static inline bool write_to_read_only(struct kvm_vcpu *vcpu, + const struct coproc_params *params) +{ + kvm_debug("CP15 write to read-only register at: %08lx\n", + *vcpu_pc(vcpu)); + print_cp_instr(params); + return false; +} + +static inline bool read_from_write_only(struct kvm_vcpu *vcpu, + const struct coproc_params *params) +{ + kvm_debug("CP15 read to write-only register at: %08lx\n", + *vcpu_pc(vcpu)); + print_cp_instr(params); + return false; +} + +/* Reset functions */ +static inline void reset_unknown(struct kvm_vcpu *vcpu, + const struct coproc_reg *r) +{ + BUG_ON(!r->reg); + BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.cp15)); + vcpu->arch.cp15[r->reg] = 0xdecafbad; +} + +static inline void reset_val(struct kvm_vcpu *vcpu, const struct coproc_reg *r) +{ + BUG_ON(!r->reg); + BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.cp15)); + vcpu->arch.cp15[r->reg] = r->val; +} + +static inline void reset_unknown64(struct kvm_vcpu *vcpu, + const struct coproc_reg *r) +{ + BUG_ON(!r->reg); + BUG_ON(r->reg + 1 >= ARRAY_SIZE(vcpu->arch.cp15)); + + vcpu->arch.cp15[r->reg] = 0xdecafbad; + vcpu->arch.cp15[r->reg+1] = 0xd0c0ffee; +} + +static inline int cmp_reg(const struct coproc_reg *i1, + const struct coproc_reg *i2) +{ + BUG_ON(i1 == i2); + if (!i1) + return 1; + else if (!i2) + return -1; + if (i1->CRn != i2->CRn) + return i1->CRn - i2->CRn; + if (i1->CRm != i2->CRm) + return i1->CRm - i2->CRm; + if (i1->Op1 != i2->Op1) + return i1->Op1 - i2->Op1; + if (i1->Op2 != i2->Op2) + return i1->Op2 - i2->Op2; + return i2->is_64 - i1->is_64; +} + + +#define CRn(_x) .CRn = _x +#define CRm(_x) .CRm = _x +#define CRm64(_x) .CRn = _x, .CRm = 0 +#define Op1(_x) .Op1 = _x +#define Op2(_x) .Op2 = _x +#define is64 .is_64 = true +#define is32 .is_64 = false + +bool access_vm_reg(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r); + +#endif /* __ARM_KVM_COPROC_LOCAL_H__ */ diff --git a/kernel/arch/arm/kvm/coproc_a15.c b/kernel/arch/arm/kvm/coproc_a15.c new file mode 100644 index 000000000..a7136757d --- /dev/null +++ b/kernel/arch/arm/kvm/coproc_a15.c @@ -0,0 +1,51 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Authors: Rusty Russell + * Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#include +#include +#include +#include + +#include "coproc.h" + +/* + * A15-specific CP15 registers. + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. + */ +static const struct coproc_reg a15_regs[] = { + /* SCTLR: swapped by interrupt.S. */ + { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_val, c1_SCTLR, 0x00C50078 }, +}; + +static struct kvm_coproc_target_table a15_target_table = { + .target = KVM_ARM_TARGET_CORTEX_A15, + .table = a15_regs, + .num = ARRAY_SIZE(a15_regs), +}; + +static int __init coproc_a15_init(void) +{ + kvm_register_target_coproc_table(&a15_target_table); + return 0; +} +late_initcall(coproc_a15_init); diff --git a/kernel/arch/arm/kvm/coproc_a7.c b/kernel/arch/arm/kvm/coproc_a7.c new file mode 100644 index 000000000..b19e46d1b --- /dev/null +++ b/kernel/arch/arm/kvm/coproc_a7.c @@ -0,0 +1,54 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Copyright (C) 2013 - ARM Ltd + * + * Authors: Rusty Russell + * Christoffer Dall + * Jonathan Austin + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#include +#include +#include +#include + +#include "coproc.h" + +/* + * Cortex-A7 specific CP15 registers. + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. + */ +static const struct coproc_reg a7_regs[] = { + /* SCTLR: swapped by interrupt.S. */ + { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_val, c1_SCTLR, 0x00C50878 }, +}; + +static struct kvm_coproc_target_table a7_target_table = { + .target = KVM_ARM_TARGET_CORTEX_A7, + .table = a7_regs, + .num = ARRAY_SIZE(a7_regs), +}; + +static int __init coproc_a7_init(void) +{ + kvm_register_target_coproc_table(&a7_target_table); + return 0; +} +late_initcall(coproc_a7_init); diff --git a/kernel/arch/arm/kvm/emulate.c b/kernel/arch/arm/kvm/emulate.c new file mode 100644 index 000000000..d6c005283 --- /dev/null +++ b/kernel/arch/arm/kvm/emulate.c @@ -0,0 +1,402 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include +#include +#include +#include +#include +#include + +#include "trace.h" + +#define VCPU_NR_MODES 6 +#define VCPU_REG_OFFSET_USR 0 +#define VCPU_REG_OFFSET_FIQ 1 +#define VCPU_REG_OFFSET_IRQ 2 +#define VCPU_REG_OFFSET_SVC 3 +#define VCPU_REG_OFFSET_ABT 4 +#define VCPU_REG_OFFSET_UND 5 +#define REG_OFFSET(_reg) \ + (offsetof(struct kvm_regs, _reg) / sizeof(u32)) + +#define USR_REG_OFFSET(_num) REG_OFFSET(usr_regs.uregs[_num]) + +static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][15] = { + /* USR/SYS Registers */ + [VCPU_REG_OFFSET_USR] = { + USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), + USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), + USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), + USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), + USR_REG_OFFSET(12), USR_REG_OFFSET(13), USR_REG_OFFSET(14), + }, + + /* FIQ Registers */ + [VCPU_REG_OFFSET_FIQ] = { + USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), + USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), + USR_REG_OFFSET(6), USR_REG_OFFSET(7), + REG_OFFSET(fiq_regs[0]), /* r8 */ + REG_OFFSET(fiq_regs[1]), /* r9 */ + REG_OFFSET(fiq_regs[2]), /* r10 */ + REG_OFFSET(fiq_regs[3]), /* r11 */ + REG_OFFSET(fiq_regs[4]), /* r12 */ + REG_OFFSET(fiq_regs[5]), /* r13 */ + REG_OFFSET(fiq_regs[6]), /* r14 */ + }, + + /* IRQ Registers */ + [VCPU_REG_OFFSET_IRQ] = { + USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), + USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), + USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), + USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), + USR_REG_OFFSET(12), + REG_OFFSET(irq_regs[0]), /* r13 */ + REG_OFFSET(irq_regs[1]), /* r14 */ + }, + + /* SVC Registers */ + [VCPU_REG_OFFSET_SVC] = { + USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), + USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), + USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), + USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), + USR_REG_OFFSET(12), + REG_OFFSET(svc_regs[0]), /* r13 */ + REG_OFFSET(svc_regs[1]), /* r14 */ + }, + + /* ABT Registers */ + [VCPU_REG_OFFSET_ABT] = { + USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), + USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), + USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), + USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), + USR_REG_OFFSET(12), + REG_OFFSET(abt_regs[0]), /* r13 */ + REG_OFFSET(abt_regs[1]), /* r14 */ + }, + + /* UND Registers */ + [VCPU_REG_OFFSET_UND] = { + USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), + USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), + USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), + USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), + USR_REG_OFFSET(12), + REG_OFFSET(und_regs[0]), /* r13 */ + REG_OFFSET(und_regs[1]), /* r14 */ + }, +}; + +/* + * Return a pointer to the register number valid in the current mode of + * the virtual CPU. + */ +unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num) +{ + unsigned long *reg_array = (unsigned long *)&vcpu->arch.regs; + unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; + + switch (mode) { + case USR_MODE...SVC_MODE: + mode &= ~MODE32_BIT; /* 0 ... 3 */ + break; + + case ABT_MODE: + mode = VCPU_REG_OFFSET_ABT; + break; + + case UND_MODE: + mode = VCPU_REG_OFFSET_UND; + break; + + case SYSTEM_MODE: + mode = VCPU_REG_OFFSET_USR; + break; + + default: + BUG(); + } + + return reg_array + vcpu_reg_offsets[mode][reg_num]; +} + +/* + * Return the SPSR for the current mode of the virtual CPU. + */ +unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu) +{ + unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; + switch (mode) { + case SVC_MODE: + return &vcpu->arch.regs.KVM_ARM_SVC_spsr; + case ABT_MODE: + return &vcpu->arch.regs.KVM_ARM_ABT_spsr; + case UND_MODE: + return &vcpu->arch.regs.KVM_ARM_UND_spsr; + case IRQ_MODE: + return &vcpu->arch.regs.KVM_ARM_IRQ_spsr; + case FIQ_MODE: + return &vcpu->arch.regs.KVM_ARM_FIQ_spsr; + default: + BUG(); + } +} + +/* + * A conditional instruction is allowed to trap, even though it + * wouldn't be executed. So let's re-implement the hardware, in + * software! + */ +bool kvm_condition_valid(struct kvm_vcpu *vcpu) +{ + unsigned long cpsr, cond, insn; + + /* + * Exception Code 0 can only happen if we set HCR.TGE to 1, to + * catch undefined instructions, and then we won't get past + * the arm_exit_handlers test anyway. + */ + BUG_ON(!kvm_vcpu_trap_get_class(vcpu)); + + /* Top two bits non-zero? Unconditional. */ + if (kvm_vcpu_get_hsr(vcpu) >> 30) + return true; + + cpsr = *vcpu_cpsr(vcpu); + + /* Is condition field valid? */ + if ((kvm_vcpu_get_hsr(vcpu) & HSR_CV) >> HSR_CV_SHIFT) + cond = (kvm_vcpu_get_hsr(vcpu) & HSR_COND) >> HSR_COND_SHIFT; + else { + /* This can happen in Thumb mode: examine IT state. */ + unsigned long it; + + it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); + + /* it == 0 => unconditional. */ + if (it == 0) + return true; + + /* The cond for this insn works out as the top 4 bits. */ + cond = (it >> 4); + } + + /* Shift makes it look like an ARM-mode instruction */ + insn = cond << 28; + return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL; +} + +/** + * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block + * @vcpu: The VCPU pointer + * + * When exceptions occur while instructions are executed in Thumb IF-THEN + * blocks, the ITSTATE field of the CPSR is not advanved (updated), so we have + * to do this little bit of work manually. The fields map like this: + * + * IT[7:0] -> CPSR[26:25],CPSR[15:10] + */ +static void kvm_adjust_itstate(struct kvm_vcpu *vcpu) +{ + unsigned long itbits, cond; + unsigned long cpsr = *vcpu_cpsr(vcpu); + bool is_arm = !(cpsr & PSR_T_BIT); + + BUG_ON(is_arm && (cpsr & PSR_IT_MASK)); + + if (!(cpsr & PSR_IT_MASK)) + return; + + cond = (cpsr & 0xe000) >> 13; + itbits = (cpsr & 0x1c00) >> (10 - 2); + itbits |= (cpsr & (0x3 << 25)) >> 25; + + /* Perform ITAdvance (see page A-52 in ARM DDI 0406C) */ + if ((itbits & 0x7) == 0) + itbits = cond = 0; + else + itbits = (itbits << 1) & 0x1f; + + cpsr &= ~PSR_IT_MASK; + cpsr |= cond << 13; + cpsr |= (itbits & 0x1c) << (10 - 2); + cpsr |= (itbits & 0x3) << 25; + *vcpu_cpsr(vcpu) = cpsr; +} + +/** + * kvm_skip_instr - skip a trapped instruction and proceed to the next + * @vcpu: The vcpu pointer + */ +void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) +{ + bool is_thumb; + + is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_T_BIT); + if (is_thumb && !is_wide_instr) + *vcpu_pc(vcpu) += 2; + else + *vcpu_pc(vcpu) += 4; + kvm_adjust_itstate(vcpu); +} + + +/****************************************************************************** + * Inject exceptions into the guest + */ + +static u32 exc_vector_base(struct kvm_vcpu *vcpu) +{ + u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; + u32 vbar = vcpu->arch.cp15[c12_VBAR]; + + if (sctlr & SCTLR_V) + return 0xffff0000; + else /* always have security exceptions */ + return vbar; +} + +/** + * kvm_inject_undefined - inject an undefined exception into the guest + * @vcpu: The VCPU to receive the undefined exception + * + * It is assumed that this code is called from the VCPU thread and that the + * VCPU therefore is not currently executing guest code. + * + * Modelled after TakeUndefInstrException() pseudocode. + */ +void kvm_inject_undefined(struct kvm_vcpu *vcpu) +{ + unsigned long new_lr_value; + unsigned long new_spsr_value; + unsigned long cpsr = *vcpu_cpsr(vcpu); + u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; + bool is_thumb = (cpsr & PSR_T_BIT); + u32 vect_offset = 4; + u32 return_offset = (is_thumb) ? 2 : 4; + + new_spsr_value = cpsr; + new_lr_value = *vcpu_pc(vcpu) - return_offset; + + *vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | UND_MODE; + *vcpu_cpsr(vcpu) |= PSR_I_BIT; + *vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT); + + if (sctlr & SCTLR_TE) + *vcpu_cpsr(vcpu) |= PSR_T_BIT; + if (sctlr & SCTLR_EE) + *vcpu_cpsr(vcpu) |= PSR_E_BIT; + + /* Note: These now point to UND banked copies */ + *vcpu_spsr(vcpu) = cpsr; + *vcpu_reg(vcpu, 14) = new_lr_value; + + /* Branch to exception vector */ + *vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset; +} + +/* + * Modelled after TakeDataAbortException() and TakePrefetchAbortException + * pseudocode. + */ +static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr) +{ + unsigned long new_lr_value; + unsigned long new_spsr_value; + unsigned long cpsr = *vcpu_cpsr(vcpu); + u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; + bool is_thumb = (cpsr & PSR_T_BIT); + u32 vect_offset; + u32 return_offset = (is_thumb) ? 4 : 0; + bool is_lpae; + + new_spsr_value = cpsr; + new_lr_value = *vcpu_pc(vcpu) + return_offset; + + *vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | ABT_MODE; + *vcpu_cpsr(vcpu) |= PSR_I_BIT | PSR_A_BIT; + *vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT); + + if (sctlr & SCTLR_TE) + *vcpu_cpsr(vcpu) |= PSR_T_BIT; + if (sctlr & SCTLR_EE) + *vcpu_cpsr(vcpu) |= PSR_E_BIT; + + /* Note: These now point to ABT banked copies */ + *vcpu_spsr(vcpu) = cpsr; + *vcpu_reg(vcpu, 14) = new_lr_value; + + if (is_pabt) + vect_offset = 12; + else + vect_offset = 16; + + /* Branch to exception vector */ + *vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset; + + if (is_pabt) { + /* Set IFAR and IFSR */ + vcpu->arch.cp15[c6_IFAR] = addr; + is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31); + /* Always give debug fault for now - should give guest a clue */ + if (is_lpae) + vcpu->arch.cp15[c5_IFSR] = 1 << 9 | 0x22; + else + vcpu->arch.cp15[c5_IFSR] = 2; + } else { /* !iabt */ + /* Set DFAR and DFSR */ + vcpu->arch.cp15[c6_DFAR] = addr; + is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31); + /* Always give debug fault for now - should give guest a clue */ + if (is_lpae) + vcpu->arch.cp15[c5_DFSR] = 1 << 9 | 0x22; + else + vcpu->arch.cp15[c5_DFSR] = 2; + } + +} + +/** + * kvm_inject_dabt - inject a data abort into the guest + * @vcpu: The VCPU to receive the undefined exception + * @addr: The address to report in the DFAR + * + * It is assumed that this code is called from the VCPU thread and that the + * VCPU therefore is not currently executing guest code. + */ +void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) +{ + inject_abt(vcpu, false, addr); +} + +/** + * kvm_inject_pabt - inject a prefetch abort into the guest + * @vcpu: The VCPU to receive the undefined exception + * @addr: The address to report in the DFAR + * + * It is assumed that this code is called from the VCPU thread and that the + * VCPU therefore is not currently executing guest code. + */ +void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) +{ + inject_abt(vcpu, true, addr); +} diff --git a/kernel/arch/arm/kvm/guest.c b/kernel/arch/arm/kvm/guest.c new file mode 100644 index 000000000..d503fbb78 --- /dev/null +++ b/kernel/arch/arm/kvm/guest.c @@ -0,0 +1,292 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define VM_STAT(x) { #x, offsetof(struct kvm, stat.x), KVM_STAT_VM } +#define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU } + +struct kvm_stats_debugfs_item debugfs_entries[] = { + { NULL } +}; + +int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) +{ + return 0; +} + +static u64 core_reg_offset_from_id(u64 id) +{ + return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); +} + +static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + u32 __user *uaddr = (u32 __user *)(long)reg->addr; + struct kvm_regs *regs = &vcpu->arch.regs; + u64 off; + + if (KVM_REG_SIZE(reg->id) != 4) + return -ENOENT; + + /* Our ID is an index into the kvm_regs struct. */ + off = core_reg_offset_from_id(reg->id); + if (off >= sizeof(*regs) / KVM_REG_SIZE(reg->id)) + return -ENOENT; + + return put_user(((u32 *)regs)[off], uaddr); +} + +static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + u32 __user *uaddr = (u32 __user *)(long)reg->addr; + struct kvm_regs *regs = &vcpu->arch.regs; + u64 off, val; + + if (KVM_REG_SIZE(reg->id) != 4) + return -ENOENT; + + /* Our ID is an index into the kvm_regs struct. */ + off = core_reg_offset_from_id(reg->id); + if (off >= sizeof(*regs) / KVM_REG_SIZE(reg->id)) + return -ENOENT; + + if (get_user(val, uaddr) != 0) + return -EFAULT; + + if (off == KVM_REG_ARM_CORE_REG(usr_regs.ARM_cpsr)) { + unsigned long mode = val & MODE_MASK; + switch (mode) { + case USR_MODE: + case FIQ_MODE: + case IRQ_MODE: + case SVC_MODE: + case ABT_MODE: + case UND_MODE: + break; + default: + return -EINVAL; + } + } + + ((u32 *)regs)[off] = val; + return 0; +} + +int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + return -EINVAL; +} + +#define NUM_TIMER_REGS 3 + +static bool is_timer_reg(u64 index) +{ + switch (index) { + case KVM_REG_ARM_TIMER_CTL: + case KVM_REG_ARM_TIMER_CNT: + case KVM_REG_ARM_TIMER_CVAL: + return true; + } + return false; +} + +static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + if (put_user(KVM_REG_ARM_TIMER_CTL, uindices)) + return -EFAULT; + uindices++; + if (put_user(KVM_REG_ARM_TIMER_CNT, uindices)) + return -EFAULT; + uindices++; + if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices)) + return -EFAULT; + + return 0; +} + +static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + int ret; + + ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)); + if (ret != 0) + return -EFAULT; + + return kvm_arm_timer_set_reg(vcpu, reg->id, val); +} + +static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + + val = kvm_arm_timer_get_reg(vcpu, reg->id); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); +} + +static unsigned long num_core_regs(void) +{ + return sizeof(struct kvm_regs) / sizeof(u32); +} + +/** + * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG + * + * This is for all registers. + */ +unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu) +{ + return num_core_regs() + kvm_arm_num_coproc_regs(vcpu) + + NUM_TIMER_REGS; +} + +/** + * kvm_arm_copy_reg_indices - get indices of all registers. + * + * We do core registers right here, then we apppend coproc regs. + */ +int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + unsigned int i; + const u64 core_reg = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE; + int ret; + + for (i = 0; i < sizeof(struct kvm_regs)/sizeof(u32); i++) { + if (put_user(core_reg | i, uindices)) + return -EFAULT; + uindices++; + } + + ret = copy_timer_indices(vcpu, uindices); + if (ret) + return ret; + uindices += NUM_TIMER_REGS; + + return kvm_arm_copy_coproc_indices(vcpu, uindices); +} + +int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + /* We currently use nothing arch-specific in upper 32 bits */ + if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM >> 32) + return -EINVAL; + + /* Register group 16 means we want a core register. */ + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) + return get_core_reg(vcpu, reg); + + if (is_timer_reg(reg->id)) + return get_timer_reg(vcpu, reg); + + return kvm_arm_coproc_get_reg(vcpu, reg); +} + +int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + /* We currently use nothing arch-specific in upper 32 bits */ + if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM >> 32) + return -EINVAL; + + /* Register group 16 means we set a core register. */ + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) + return set_core_reg(vcpu, reg); + + if (is_timer_reg(reg->id)) + return set_timer_reg(vcpu, reg); + + return kvm_arm_coproc_set_reg(vcpu, reg); +} + +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + return -EINVAL; +} + +int __attribute_const__ kvm_target_cpu(void) +{ + switch (read_cpuid_part()) { + case ARM_CPU_PART_CORTEX_A7: + return KVM_ARM_TARGET_CORTEX_A7; + case ARM_CPU_PART_CORTEX_A15: + return KVM_ARM_TARGET_CORTEX_A15; + default: + return -EINVAL; + } +} + +int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) +{ + int target = kvm_target_cpu(); + + if (target < 0) + return -ENODEV; + + memset(init, 0, sizeof(*init)); + + /* + * For now, we don't return any features. + * In future, we might use features to return target + * specific features available for the preferred + * target type. + */ + init->target = (__u32)target; + + return 0; +} + +int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, + struct kvm_translation *tr) +{ + return -EINVAL; +} diff --git a/kernel/arch/arm/kvm/handle_exit.c b/kernel/arch/arm/kvm/handle_exit.c new file mode 100644 index 000000000..95f12b2cc --- /dev/null +++ b/kernel/arch/arm/kvm/handle_exit.c @@ -0,0 +1,173 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" + +typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *); + +static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* SVC called from Hyp mode should never get here */ + kvm_debug("SVC called from Hyp mode shouldn't go here\n"); + BUG(); + return -EINVAL; /* Squash warning */ +} + +static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + int ret; + + trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), + kvm_vcpu_hvc_get_imm(vcpu)); + + ret = kvm_psci_call(vcpu); + if (ret < 0) { + kvm_inject_undefined(vcpu); + return 1; + } + + return ret; +} + +static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + kvm_inject_undefined(vcpu); + return 1; +} + +static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* The hypervisor should never cause aborts */ + kvm_err("Prefetch Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n", + kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu)); + return -EFAULT; +} + +static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* This is either an error in the ws. code or an external abort */ + kvm_err("Data Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n", + kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu)); + return -EFAULT; +} + +/** + * kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests + * @vcpu: the vcpu pointer + * @run: the kvm_run structure pointer + * + * WFE: Yield the CPU and come back to this vcpu when the scheduler + * decides to. + * WFI: Simply call kvm_vcpu_block(), which will halt execution of + * world-switches and schedule other host processes until there is an + * incoming IRQ or FIQ to the VM. + */ +static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) { + trace_kvm_wfx(*vcpu_pc(vcpu), true); + kvm_vcpu_on_spin(vcpu); + } else { + trace_kvm_wfx(*vcpu_pc(vcpu), false); + kvm_vcpu_block(vcpu); + } + + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + + return 1; +} + +static exit_handle_fn arm_exit_handlers[] = { + [HSR_EC_WFI] = kvm_handle_wfx, + [HSR_EC_CP15_32] = kvm_handle_cp15_32, + [HSR_EC_CP15_64] = kvm_handle_cp15_64, + [HSR_EC_CP14_MR] = kvm_handle_cp14_access, + [HSR_EC_CP14_LS] = kvm_handle_cp14_load_store, + [HSR_EC_CP14_64] = kvm_handle_cp14_access, + [HSR_EC_CP_0_13] = kvm_handle_cp_0_13_access, + [HSR_EC_CP10_ID] = kvm_handle_cp10_id, + [HSR_EC_SVC_HYP] = handle_svc_hyp, + [HSR_EC_HVC] = handle_hvc, + [HSR_EC_SMC] = handle_smc, + [HSR_EC_IABT] = kvm_handle_guest_abort, + [HSR_EC_IABT_HYP] = handle_pabt_hyp, + [HSR_EC_DABT] = kvm_handle_guest_abort, + [HSR_EC_DABT_HYP] = handle_dabt_hyp, +}; + +static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) +{ + u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); + + if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) || + !arm_exit_handlers[hsr_ec]) { + kvm_err("Unknown exception class: hsr: %#08x\n", + (unsigned int)kvm_vcpu_get_hsr(vcpu)); + BUG(); + } + + return arm_exit_handlers[hsr_ec]; +} + +/* + * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on + * proper exit to userspace. + */ +int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, + int exception_index) +{ + exit_handle_fn exit_handler; + + switch (exception_index) { + case ARM_EXCEPTION_IRQ: + return 1; + case ARM_EXCEPTION_UNDEFINED: + kvm_err("Undefined exception in Hyp mode at: %#08lx\n", + kvm_vcpu_get_hyp_pc(vcpu)); + BUG(); + panic("KVM: Hypervisor undefined exception!\n"); + case ARM_EXCEPTION_DATA_ABORT: + case ARM_EXCEPTION_PREF_ABORT: + case ARM_EXCEPTION_HVC: + /* + * See ARM ARM B1.14.1: "Hyp traps on instructions + * that fail their condition code check" + */ + if (!kvm_condition_valid(vcpu)) { + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; + } + + exit_handler = kvm_get_exit_handler(vcpu); + + return exit_handler(vcpu, run); + default: + kvm_pr_unimpl("Unsupported exception type: %d", + exception_index); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return 0; + } +} diff --git a/kernel/arch/arm/kvm/init.S b/kernel/arch/arm/kvm/init.S new file mode 100644 index 000000000..3988e72d1 --- /dev/null +++ b/kernel/arch/arm/kvm/init.S @@ -0,0 +1,159 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include +#include +#include +#include +#include +#include +#include + +/******************************************************************** + * Hypervisor initialization + * - should be called with: + * r0 = top of Hyp stack (kernel VA) + * r1 = pointer to hyp vectors + * r2,r3 = Hypervisor pgd pointer + * + * The init scenario is: + * - We jump in HYP with four parameters: boot HYP pgd, runtime HYP pgd, + * runtime stack, runtime vectors + * - Enable the MMU with the boot pgd + * - Jump to a target into the trampoline page (remember, this is the same + * physical page!) + * - Now switch to the runtime pgd (same VA, and still the same physical + * page!) + * - Invalidate TLBs + * - Set stack and vectors + * - Profit! (or eret, if you only care about the code). + * + * As we only have four registers available to pass parameters (and we + * need six), we split the init in two phases: + * - Phase 1: r0 = 0, r1 = 0, r2,r3 contain the boot PGD. + * Provides the basic HYP init, and enable the MMU. + * - Phase 2: r0 = ToS, r1 = vectors, r2,r3 contain the runtime PGD. + * Switches to the runtime PGD, set stack and vectors. + */ + + .text + .pushsection .hyp.idmap.text,"ax" + .align 5 +__kvm_hyp_init: + .globl __kvm_hyp_init + + @ Hyp-mode exception vector + W(b) . + W(b) . + W(b) . + W(b) . + W(b) . + W(b) __do_hyp_init + W(b) . + W(b) . + +__do_hyp_init: + cmp r0, #0 @ We have a SP? + bne phase2 @ Yes, second stage init + + @ Set the HTTBR to point to the hypervisor PGD pointer passed + mcrr p15, 4, rr_lo_hi(r2, r3), c2 + + @ Set the HTCR and VTCR to the same shareability and cacheability + @ settings as the non-secure TTBCR and with T0SZ == 0. + mrc p15, 4, r0, c2, c0, 2 @ HTCR + ldr r2, =HTCR_MASK + bic r0, r0, r2 + mrc p15, 0, r1, c2, c0, 2 @ TTBCR + and r1, r1, #(HTCR_MASK & ~TTBCR_T0SZ) + orr r0, r0, r1 + mcr p15, 4, r0, c2, c0, 2 @ HTCR + + mrc p15, 4, r1, c2, c1, 2 @ VTCR + ldr r2, =VTCR_MASK + bic r1, r1, r2 + bic r0, r0, #(~VTCR_HTCR_SH) @ clear non-reusable HTCR bits + orr r1, r0, r1 + orr r1, r1, #(KVM_VTCR_SL0 | KVM_VTCR_T0SZ | KVM_VTCR_S) + mcr p15, 4, r1, c2, c1, 2 @ VTCR + + @ Use the same memory attributes for hyp. accesses as the kernel + @ (copy MAIRx ro HMAIRx). + mrc p15, 0, r0, c10, c2, 0 + mcr p15, 4, r0, c10, c2, 0 + mrc p15, 0, r0, c10, c2, 1 + mcr p15, 4, r0, c10, c2, 1 + + @ Invalidate the stale TLBs from Bootloader + mcr p15, 4, r0, c8, c7, 0 @ TLBIALLH + dsb ish + + @ Set the HSCTLR to: + @ - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel) + @ - Endianness: Kernel config + @ - Fast Interrupt Features: Kernel config + @ - Write permission implies XN: disabled + @ - Instruction cache: enabled + @ - Data/Unified cache: enabled + @ - Memory alignment checks: enabled + @ - MMU: enabled (this code must be run from an identity mapping) + mrc p15, 4, r0, c1, c0, 0 @ HSCR + ldr r2, =HSCTLR_MASK + bic r0, r0, r2 + mrc p15, 0, r1, c1, c0, 0 @ SCTLR + ldr r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C) + and r1, r1, r2 + ARM( ldr r2, =(HSCTLR_M | HSCTLR_A) ) + THUMB( ldr r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE) ) + orr r1, r1, r2 + orr r0, r0, r1 + isb + mcr p15, 4, r0, c1, c0, 0 @ HSCR + + @ End of init phase-1 + eret + +phase2: + @ Set stack pointer + mov sp, r0 + + @ Set HVBAR to point to the HYP vectors + mcr p15, 4, r1, c12, c0, 0 @ HVBAR + + @ Jump to the trampoline page + ldr r0, =TRAMPOLINE_VA + adr r1, target + bfi r0, r1, #0, #PAGE_SHIFT + ret r0 + +target: @ We're now in the trampoline code, switch page tables + mcrr p15, 4, rr_lo_hi(r2, r3), c2 + isb + + @ Invalidate the old TLBs + mcr p15, 4, r0, c8, c7, 0 @ TLBIALLH + dsb ish + + eret + + .ltorg + + .globl __kvm_hyp_init_end +__kvm_hyp_init_end: + + .popsection diff --git a/kernel/arch/arm/kvm/interrupts.S b/kernel/arch/arm/kvm/interrupts.S new file mode 100644 index 000000000..f7db3a5d8 --- /dev/null +++ b/kernel/arch/arm/kvm/interrupts.S @@ -0,0 +1,524 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "interrupts_head.S" + + .text + +__kvm_hyp_code_start: + .globl __kvm_hyp_code_start + +/******************************************************************** + * Flush per-VMID TLBs + * + * void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); + * + * We rely on the hardware to broadcast the TLB invalidation to all CPUs + * inside the inner-shareable domain (which is the case for all v7 + * implementations). If we come across a non-IS SMP implementation, we'll + * have to use an IPI based mechanism. Until then, we stick to the simple + * hardware assisted version. + * + * As v7 does not support flushing per IPA, just nuke the whole TLB + * instead, ignoring the ipa value. + */ +ENTRY(__kvm_tlb_flush_vmid_ipa) + push {r2, r3} + + dsb ishst + add r0, r0, #KVM_VTTBR + ldrd r2, r3, [r0] + mcrr p15, 6, rr_lo_hi(r2, r3), c2 @ Write VTTBR + isb + mcr p15, 0, r0, c8, c3, 0 @ TLBIALLIS (rt ignored) + dsb ish + isb + mov r2, #0 + mov r3, #0 + mcrr p15, 6, r2, r3, c2 @ Back to VMID #0 + isb @ Not necessary if followed by eret + + pop {r2, r3} + bx lr +ENDPROC(__kvm_tlb_flush_vmid_ipa) + +/** + * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs + * + * Reuses __kvm_tlb_flush_vmid_ipa() for ARMv7, without passing address + * parameter + */ + +ENTRY(__kvm_tlb_flush_vmid) + b __kvm_tlb_flush_vmid_ipa +ENDPROC(__kvm_tlb_flush_vmid) + +/******************************************************************** + * Flush TLBs and instruction caches of all CPUs inside the inner-shareable + * domain, for all VMIDs + * + * void __kvm_flush_vm_context(void); + */ +ENTRY(__kvm_flush_vm_context) + mov r0, #0 @ rn parameter for c15 flushes is SBZ + + /* Invalidate NS Non-Hyp TLB Inner Shareable (TLBIALLNSNHIS) */ + mcr p15, 4, r0, c8, c3, 4 + /* Invalidate instruction caches Inner Shareable (ICIALLUIS) */ + mcr p15, 0, r0, c7, c1, 0 + dsb ish + isb @ Not necessary if followed by eret + + bx lr +ENDPROC(__kvm_flush_vm_context) + + +/******************************************************************** + * Hypervisor world-switch code + * + * + * int __kvm_vcpu_run(struct kvm_vcpu *vcpu) + */ +ENTRY(__kvm_vcpu_run) + @ Save the vcpu pointer + mcr p15, 4, vcpu, c13, c0, 2 @ HTPIDR + + save_host_regs + + restore_vgic_state + restore_timer_state + + @ Store hardware CP15 state and load guest state + read_cp15_state store_to_vcpu = 0 + write_cp15_state read_from_vcpu = 1 + + @ If the host kernel has not been configured with VFPv3 support, + @ then it is safer if we deny guests from using it as well. +#ifdef CONFIG_VFPv3 + @ Set FPEXC_EN so the guest doesn't trap floating point instructions + VFPFMRX r2, FPEXC @ VMRS + push {r2} + orr r2, r2, #FPEXC_EN + VFPFMXR FPEXC, r2 @ VMSR +#endif + + @ Configure Hyp-role + configure_hyp_role vmentry + + @ Trap coprocessor CRx accesses + set_hstr vmentry + set_hcptr vmentry, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hdcr vmentry + + @ Write configured ID register into MIDR alias + ldr r1, [vcpu, #VCPU_MIDR] + mcr p15, 4, r1, c0, c0, 0 + + @ Write guest view of MPIDR into VMPIDR + ldr r1, [vcpu, #CP15_OFFSET(c0_MPIDR)] + mcr p15, 4, r1, c0, c0, 5 + + @ Set up guest memory translation + ldr r1, [vcpu, #VCPU_KVM] + add r1, r1, #KVM_VTTBR + ldrd r2, r3, [r1] + mcrr p15, 6, rr_lo_hi(r2, r3), c2 @ Write VTTBR + + @ We're all done, just restore the GPRs and go to the guest + restore_guest_regs + clrex @ Clear exclusive monitor + eret + +__kvm_vcpu_return: + /* + * return convention: + * guest r0, r1, r2 saved on the stack + * r0: vcpu pointer + * r1: exception code + */ + save_guest_regs + + @ Set VMID == 0 + mov r2, #0 + mov r3, #0 + mcrr p15, 6, r2, r3, c2 @ Write VTTBR + + @ Don't trap coprocessor accesses for host kernel + set_hstr vmexit + set_hdcr vmexit + set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore + +#ifdef CONFIG_VFPv3 + @ Switch VFP/NEON hardware state to the host's + add r7, vcpu, #VCPU_VFP_GUEST + store_vfp_state r7 + add r7, vcpu, #VCPU_VFP_HOST + ldr r7, [r7] + restore_vfp_state r7 + +after_vfp_restore: + @ Restore FPEXC_EN which we clobbered on entry + pop {r2} + VFPFMXR FPEXC, r2 +#else +after_vfp_restore: +#endif + + @ Reset Hyp-role + configure_hyp_role vmexit + + @ Let host read hardware MIDR + mrc p15, 0, r2, c0, c0, 0 + mcr p15, 4, r2, c0, c0, 0 + + @ Back to hardware MPIDR + mrc p15, 0, r2, c0, c0, 5 + mcr p15, 4, r2, c0, c0, 5 + + @ Store guest CP15 state and restore host state + read_cp15_state store_to_vcpu = 1 + write_cp15_state read_from_vcpu = 0 + + save_timer_state + save_vgic_state + + restore_host_regs + clrex @ Clear exclusive monitor +#ifndef CONFIG_CPU_ENDIAN_BE8 + mov r0, r1 @ Return the return code + mov r1, #0 @ Clear upper bits in return value +#else + @ r1 already has return code + mov r0, #0 @ Clear upper bits in return value +#endif /* CONFIG_CPU_ENDIAN_BE8 */ + bx lr @ return to IOCTL + +/******************************************************************** + * Call function in Hyp mode + * + * + * u64 kvm_call_hyp(void *hypfn, ...); + * + * This is not really a variadic function in the classic C-way and care must + * be taken when calling this to ensure parameters are passed in registers + * only, since the stack will change between the caller and the callee. + * + * Call the function with the first argument containing a pointer to the + * function you wish to call in Hyp mode, and subsequent arguments will be + * passed as r0, r1, and r2 (a maximum of 3 arguments in addition to the + * function pointer can be passed). The function being called must be mapped + * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are + * passed in r0 and r1. + * + * A function pointer with a value of 0xffffffff has a special meaning, + * and is used to implement __hyp_get_vectors in the same way as in + * arch/arm/kernel/hyp_stub.S. + * + * The calling convention follows the standard AAPCS: + * r0 - r3: caller save + * r12: caller save + * rest: callee save + */ +ENTRY(kvm_call_hyp) + hvc #0 + bx lr + +/******************************************************************** + * Hypervisor exception vector and handlers + * + * + * The KVM/ARM Hypervisor ABI is defined as follows: + * + * Entry to Hyp mode from the host kernel will happen _only_ when an HVC + * instruction is issued since all traps are disabled when running the host + * kernel as per the Hyp-mode initialization at boot time. + * + * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc + * below) when the HVC instruction is called from SVC mode (i.e. a guest or the + * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC + * instructions are called from within Hyp-mode. + * + * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode): + * Switching to Hyp mode is done through a simple HVC #0 instruction. The + * exception vector code will check that the HVC comes from VMID==0 and if + * so will push the necessary state (SPSR, lr_usr) on the Hyp stack. + * - r0 contains a pointer to a HYP function + * - r1, r2, and r3 contain arguments to the above function. + * - The HYP function will be called with its arguments in r0, r1 and r2. + * On HYP function return, we return directly to SVC. + * + * Note that the above is used to execute code in Hyp-mode from a host-kernel + * point of view, and is a different concept from performing a world-switch and + * executing guest code SVC mode (with a VMID != 0). + */ + +/* Handle undef, svc, pabt, or dabt by crashing with a user notice */ +.macro bad_exception exception_code, panic_str + push {r0-r2} + mrrc p15, 6, r0, r1, c2 @ Read VTTBR + lsr r1, r1, #16 + ands r1, r1, #0xff + beq 99f + + load_vcpu @ Load VCPU pointer + .if \exception_code == ARM_EXCEPTION_DATA_ABORT + mrc p15, 4, r2, c5, c2, 0 @ HSR + mrc p15, 4, r1, c6, c0, 0 @ HDFAR + str r2, [vcpu, #VCPU_HSR] + str r1, [vcpu, #VCPU_HxFAR] + .endif + .if \exception_code == ARM_EXCEPTION_PREF_ABORT + mrc p15, 4, r2, c5, c2, 0 @ HSR + mrc p15, 4, r1, c6, c0, 2 @ HIFAR + str r2, [vcpu, #VCPU_HSR] + str r1, [vcpu, #VCPU_HxFAR] + .endif + mov r1, #\exception_code + b __kvm_vcpu_return + + @ We were in the host already. Let's craft a panic-ing return to SVC. +99: mrs r2, cpsr + bic r2, r2, #MODE_MASK + orr r2, r2, #SVC_MODE +THUMB( orr r2, r2, #PSR_T_BIT ) + msr spsr_cxsf, r2 + mrs r1, ELR_hyp + ldr r2, =BSYM(panic) + msr ELR_hyp, r2 + ldr r0, =\panic_str + clrex @ Clear exclusive monitor + eret +.endm + + .text + + .align 5 +__kvm_hyp_vector: + .globl __kvm_hyp_vector + + @ Hyp-mode exception vector + W(b) hyp_reset + W(b) hyp_undef + W(b) hyp_svc + W(b) hyp_pabt + W(b) hyp_dabt + W(b) hyp_hvc + W(b) hyp_irq + W(b) hyp_fiq + + .align +hyp_reset: + b hyp_reset + + .align +hyp_undef: + bad_exception ARM_EXCEPTION_UNDEFINED, und_die_str + + .align +hyp_svc: + bad_exception ARM_EXCEPTION_HVC, svc_die_str + + .align +hyp_pabt: + bad_exception ARM_EXCEPTION_PREF_ABORT, pabt_die_str + + .align +hyp_dabt: + bad_exception ARM_EXCEPTION_DATA_ABORT, dabt_die_str + + .align +hyp_hvc: + /* + * Getting here is either becuase of a trap from a guest or from calling + * HVC from the host kernel, which means "switch to Hyp mode". + */ + push {r0, r1, r2} + + @ Check syndrome register + mrc p15, 4, r1, c5, c2, 0 @ HSR + lsr r0, r1, #HSR_EC_SHIFT +#ifdef CONFIG_VFPv3 + cmp r0, #HSR_EC_CP_0_13 + beq switch_to_guest_vfp +#endif + cmp r0, #HSR_EC_HVC + bne guest_trap @ Not HVC instr. + + /* + * Let's check if the HVC came from VMID 0 and allow simple + * switch to Hyp mode + */ + mrrc p15, 6, r0, r2, c2 + lsr r2, r2, #16 + and r2, r2, #0xff + cmp r2, #0 + bne guest_trap @ Guest called HVC + +host_switch_to_hyp: + pop {r0, r1, r2} + + /* Check for __hyp_get_vectors */ + cmp r0, #-1 + mrceq p15, 4, r0, c12, c0, 0 @ get HVBAR + beq 1f + + push {lr} + mrs lr, SPSR + push {lr} + + mov lr, r0 + mov r0, r1 + mov r1, r2 + mov r2, r3 + +THUMB( orr lr, #1) + blx lr @ Call the HYP function + + pop {lr} + msr SPSR_csxf, lr + pop {lr} +1: eret + +guest_trap: + load_vcpu @ Load VCPU pointer to r0 + str r1, [vcpu, #VCPU_HSR] + + @ Check if we need the fault information + lsr r1, r1, #HSR_EC_SHIFT + cmp r1, #HSR_EC_IABT + mrceq p15, 4, r2, c6, c0, 2 @ HIFAR + beq 2f + cmp r1, #HSR_EC_DABT + bne 1f + mrc p15, 4, r2, c6, c0, 0 @ HDFAR + +2: str r2, [vcpu, #VCPU_HxFAR] + + /* + * B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode: + * + * Abort on the stage 2 translation for a memory access from a + * Non-secure PL1 or PL0 mode: + * + * For any Access flag fault or Translation fault, and also for any + * Permission fault on the stage 2 translation of a memory access + * made as part of a translation table walk for a stage 1 translation, + * the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR + * is UNKNOWN. + */ + + /* Check for permission fault, and S1PTW */ + mrc p15, 4, r1, c5, c2, 0 @ HSR + and r0, r1, #HSR_FSC_TYPE + cmp r0, #FSC_PERM + tsteq r1, #(1 << 7) @ S1PTW + mrcne p15, 4, r2, c6, c0, 4 @ HPFAR + bne 3f + + /* Preserve PAR */ + mrrc p15, 0, r0, r1, c7 @ PAR + push {r0, r1} + + /* Resolve IPA using the xFAR */ + mcr p15, 0, r2, c7, c8, 0 @ ATS1CPR + isb + mrrc p15, 0, r0, r1, c7 @ PAR + tst r0, #1 + bne 4f @ Failed translation + ubfx r2, r0, #12, #20 + lsl r2, r2, #4 + orr r2, r2, r1, lsl #24 + + /* Restore PAR */ + pop {r0, r1} + mcrr p15, 0, r0, r1, c7 @ PAR + +3: load_vcpu @ Load VCPU pointer to r0 + str r2, [r0, #VCPU_HPFAR] + +1: mov r1, #ARM_EXCEPTION_HVC + b __kvm_vcpu_return + +4: pop {r0, r1} @ Failed translation, return to guest + mcrr p15, 0, r0, r1, c7 @ PAR + clrex + pop {r0, r1, r2} + eret + +/* + * If VFPv3 support is not available, then we will not switch the VFP + * registers; however cp10 and cp11 accesses will still trap and fallback + * to the regular coprocessor emulation code, which currently will + * inject an undefined exception to the guest. + */ +#ifdef CONFIG_VFPv3 +switch_to_guest_vfp: + load_vcpu @ Load VCPU pointer to r0 + push {r3-r7} + + @ NEON/VFP used. Turn on VFP access. + set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11)) + + @ Switch VFP/NEON hardware state to the guest's + add r7, r0, #VCPU_VFP_HOST + ldr r7, [r7] + store_vfp_state r7 + add r7, r0, #VCPU_VFP_GUEST + restore_vfp_state r7 + + pop {r3-r7} + pop {r0-r2} + clrex + eret +#endif + + .align +hyp_irq: + push {r0, r1, r2} + mov r1, #ARM_EXCEPTION_IRQ + load_vcpu @ Load VCPU pointer to r0 + b __kvm_vcpu_return + + .align +hyp_fiq: + b hyp_fiq + + .ltorg + +__kvm_hyp_code_end: + .globl __kvm_hyp_code_end + + .section ".rodata" + +und_die_str: + .ascii "unexpected undefined exception in Hyp mode at: %#08x\n" +pabt_die_str: + .ascii "unexpected prefetch abort in Hyp mode at: %#08x\n" +dabt_die_str: + .ascii "unexpected data abort in Hyp mode at: %#08x\n" +svc_die_str: + .ascii "unexpected HVC/SVC trap in Hyp mode at: %#08x\n" diff --git a/kernel/arch/arm/kvm/interrupts_head.S b/kernel/arch/arm/kvm/interrupts_head.S new file mode 100644 index 000000000..48efe2ee4 --- /dev/null +++ b/kernel/arch/arm/kvm/interrupts_head.S @@ -0,0 +1,649 @@ +#include +#include + +#define VCPU_USR_REG(_reg_nr) (VCPU_USR_REGS + (_reg_nr * 4)) +#define VCPU_USR_SP (VCPU_USR_REG(13)) +#define VCPU_USR_LR (VCPU_USR_REG(14)) +#define CP15_OFFSET(_cp15_reg_idx) (VCPU_CP15 + (_cp15_reg_idx * 4)) + +/* + * Many of these macros need to access the VCPU structure, which is always + * held in r0. These macros should never clobber r1, as it is used to hold the + * exception code on the return path (except of course the macro that switches + * all the registers before the final jump to the VM). + */ +vcpu .req r0 @ vcpu pointer always in r0 + +/* Clobbers {r2-r6} */ +.macro store_vfp_state vfp_base + @ The VFPFMRX and VFPFMXR macros are the VMRS and VMSR instructions + VFPFMRX r2, FPEXC + @ Make sure VFP is enabled so we can touch the registers. + orr r6, r2, #FPEXC_EN + VFPFMXR FPEXC, r6 + + VFPFMRX r3, FPSCR + tst r2, #FPEXC_EX @ Check for VFP Subarchitecture + beq 1f + @ If FPEXC_EX is 0, then FPINST/FPINST2 reads are upredictable, so + @ we only need to save them if FPEXC_EX is set. + VFPFMRX r4, FPINST + tst r2, #FPEXC_FP2V + VFPFMRX r5, FPINST2, ne @ vmrsne + bic r6, r2, #FPEXC_EX @ FPEXC_EX disable + VFPFMXR FPEXC, r6 +1: + VFPFSTMIA \vfp_base, r6 @ Save VFP registers + stm \vfp_base, {r2-r5} @ Save FPEXC, FPSCR, FPINST, FPINST2 +.endm + +/* Assume FPEXC_EN is on and FPEXC_EX is off, clobbers {r2-r6} */ +.macro restore_vfp_state vfp_base + VFPFLDMIA \vfp_base, r6 @ Load VFP registers + ldm \vfp_base, {r2-r5} @ Load FPEXC, FPSCR, FPINST, FPINST2 + + VFPFMXR FPSCR, r3 + tst r2, #FPEXC_EX @ Check for VFP Subarchitecture + beq 1f + VFPFMXR FPINST, r4 + tst r2, #FPEXC_FP2V + VFPFMXR FPINST2, r5, ne +1: + VFPFMXR FPEXC, r2 @ FPEXC (last, in case !EN) +.endm + +/* These are simply for the macros to work - value don't have meaning */ +.equ usr, 0 +.equ svc, 1 +.equ abt, 2 +.equ und, 3 +.equ irq, 4 +.equ fiq, 5 + +.macro push_host_regs_mode mode + mrs r2, SP_\mode + mrs r3, LR_\mode + mrs r4, SPSR_\mode + push {r2, r3, r4} +.endm + +/* + * Store all host persistent registers on the stack. + * Clobbers all registers, in all modes, except r0 and r1. + */ +.macro save_host_regs + /* Hyp regs. Only ELR_hyp (SPSR_hyp already saved) */ + mrs r2, ELR_hyp + push {r2} + + /* usr regs */ + push {r4-r12} @ r0-r3 are always clobbered + mrs r2, SP_usr + mov r3, lr + push {r2, r3} + + push_host_regs_mode svc + push_host_regs_mode abt + push_host_regs_mode und + push_host_regs_mode irq + + /* fiq regs */ + mrs r2, r8_fiq + mrs r3, r9_fiq + mrs r4, r10_fiq + mrs r5, r11_fiq + mrs r6, r12_fiq + mrs r7, SP_fiq + mrs r8, LR_fiq + mrs r9, SPSR_fiq + push {r2-r9} +.endm + +.macro pop_host_regs_mode mode + pop {r2, r3, r4} + msr SP_\mode, r2 + msr LR_\mode, r3 + msr SPSR_\mode, r4 +.endm + +/* + * Restore all host registers from the stack. + * Clobbers all registers, in all modes, except r0 and r1. + */ +.macro restore_host_regs + pop {r2-r9} + msr r8_fiq, r2 + msr r9_fiq, r3 + msr r10_fiq, r4 + msr r11_fiq, r5 + msr r12_fiq, r6 + msr SP_fiq, r7 + msr LR_fiq, r8 + msr SPSR_fiq, r9 + + pop_host_regs_mode irq + pop_host_regs_mode und + pop_host_regs_mode abt + pop_host_regs_mode svc + + pop {r2, r3} + msr SP_usr, r2 + mov lr, r3 + pop {r4-r12} + + pop {r2} + msr ELR_hyp, r2 +.endm + +/* + * Restore SP, LR and SPSR for a given mode. offset is the offset of + * this mode's registers from the VCPU base. + * + * Assumes vcpu pointer in vcpu reg + * + * Clobbers r1, r2, r3, r4. + */ +.macro restore_guest_regs_mode mode, offset + add r1, vcpu, \offset + ldm r1, {r2, r3, r4} + msr SP_\mode, r2 + msr LR_\mode, r3 + msr SPSR_\mode, r4 +.endm + +/* + * Restore all guest registers from the vcpu struct. + * + * Assumes vcpu pointer in vcpu reg + * + * Clobbers *all* registers. + */ +.macro restore_guest_regs + restore_guest_regs_mode svc, #VCPU_SVC_REGS + restore_guest_regs_mode abt, #VCPU_ABT_REGS + restore_guest_regs_mode und, #VCPU_UND_REGS + restore_guest_regs_mode irq, #VCPU_IRQ_REGS + + add r1, vcpu, #VCPU_FIQ_REGS + ldm r1, {r2-r9} + msr r8_fiq, r2 + msr r9_fiq, r3 + msr r10_fiq, r4 + msr r11_fiq, r5 + msr r12_fiq, r6 + msr SP_fiq, r7 + msr LR_fiq, r8 + msr SPSR_fiq, r9 + + @ Load return state + ldr r2, [vcpu, #VCPU_PC] + ldr r3, [vcpu, #VCPU_CPSR] + msr ELR_hyp, r2 + msr SPSR_cxsf, r3 + + @ Load user registers + ldr r2, [vcpu, #VCPU_USR_SP] + ldr r3, [vcpu, #VCPU_USR_LR] + msr SP_usr, r2 + mov lr, r3 + add vcpu, vcpu, #(VCPU_USR_REGS) + ldm vcpu, {r0-r12} +.endm + +/* + * Save SP, LR and SPSR for a given mode. offset is the offset of + * this mode's registers from the VCPU base. + * + * Assumes vcpu pointer in vcpu reg + * + * Clobbers r2, r3, r4, r5. + */ +.macro save_guest_regs_mode mode, offset + add r2, vcpu, \offset + mrs r3, SP_\mode + mrs r4, LR_\mode + mrs r5, SPSR_\mode + stm r2, {r3, r4, r5} +.endm + +/* + * Save all guest registers to the vcpu struct + * Expects guest's r0, r1, r2 on the stack. + * + * Assumes vcpu pointer in vcpu reg + * + * Clobbers r2, r3, r4, r5. + */ +.macro save_guest_regs + @ Store usr registers + add r2, vcpu, #VCPU_USR_REG(3) + stm r2, {r3-r12} + add r2, vcpu, #VCPU_USR_REG(0) + pop {r3, r4, r5} @ r0, r1, r2 + stm r2, {r3, r4, r5} + mrs r2, SP_usr + mov r3, lr + str r2, [vcpu, #VCPU_USR_SP] + str r3, [vcpu, #VCPU_USR_LR] + + @ Store return state + mrs r2, ELR_hyp + mrs r3, spsr + str r2, [vcpu, #VCPU_PC] + str r3, [vcpu, #VCPU_CPSR] + + @ Store other guest registers + save_guest_regs_mode svc, #VCPU_SVC_REGS + save_guest_regs_mode abt, #VCPU_ABT_REGS + save_guest_regs_mode und, #VCPU_UND_REGS + save_guest_regs_mode irq, #VCPU_IRQ_REGS +.endm + +/* Reads cp15 registers from hardware and stores them in memory + * @store_to_vcpu: If 0, registers are written in-order to the stack, + * otherwise to the VCPU struct pointed to by vcpup + * + * Assumes vcpu pointer in vcpu reg + * + * Clobbers r2 - r12 + */ +.macro read_cp15_state store_to_vcpu + mrc p15, 0, r2, c1, c0, 0 @ SCTLR + mrc p15, 0, r3, c1, c0, 2 @ CPACR + mrc p15, 0, r4, c2, c0, 2 @ TTBCR + mrc p15, 0, r5, c3, c0, 0 @ DACR + mrrc p15, 0, r6, r7, c2 @ TTBR 0 + mrrc p15, 1, r8, r9, c2 @ TTBR 1 + mrc p15, 0, r10, c10, c2, 0 @ PRRR + mrc p15, 0, r11, c10, c2, 1 @ NMRR + mrc p15, 2, r12, c0, c0, 0 @ CSSELR + + .if \store_to_vcpu == 0 + push {r2-r12} @ Push CP15 registers + .else + str r2, [vcpu, #CP15_OFFSET(c1_SCTLR)] + str r3, [vcpu, #CP15_OFFSET(c1_CPACR)] + str r4, [vcpu, #CP15_OFFSET(c2_TTBCR)] + str r5, [vcpu, #CP15_OFFSET(c3_DACR)] + add r2, vcpu, #CP15_OFFSET(c2_TTBR0) + strd r6, r7, [r2] + add r2, vcpu, #CP15_OFFSET(c2_TTBR1) + strd r8, r9, [r2] + str r10, [vcpu, #CP15_OFFSET(c10_PRRR)] + str r11, [vcpu, #CP15_OFFSET(c10_NMRR)] + str r12, [vcpu, #CP15_OFFSET(c0_CSSELR)] + .endif + + mrc p15, 0, r2, c13, c0, 1 @ CID + mrc p15, 0, r3, c13, c0, 2 @ TID_URW + mrc p15, 0, r4, c13, c0, 3 @ TID_URO + mrc p15, 0, r5, c13, c0, 4 @ TID_PRIV + mrc p15, 0, r6, c5, c0, 0 @ DFSR + mrc p15, 0, r7, c5, c0, 1 @ IFSR + mrc p15, 0, r8, c5, c1, 0 @ ADFSR + mrc p15, 0, r9, c5, c1, 1 @ AIFSR + mrc p15, 0, r10, c6, c0, 0 @ DFAR + mrc p15, 0, r11, c6, c0, 2 @ IFAR + mrc p15, 0, r12, c12, c0, 0 @ VBAR + + .if \store_to_vcpu == 0 + push {r2-r12} @ Push CP15 registers + .else + str r2, [vcpu, #CP15_OFFSET(c13_CID)] + str r3, [vcpu, #CP15_OFFSET(c13_TID_URW)] + str r4, [vcpu, #CP15_OFFSET(c13_TID_URO)] + str r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)] + str r6, [vcpu, #CP15_OFFSET(c5_DFSR)] + str r7, [vcpu, #CP15_OFFSET(c5_IFSR)] + str r8, [vcpu, #CP15_OFFSET(c5_ADFSR)] + str r9, [vcpu, #CP15_OFFSET(c5_AIFSR)] + str r10, [vcpu, #CP15_OFFSET(c6_DFAR)] + str r11, [vcpu, #CP15_OFFSET(c6_IFAR)] + str r12, [vcpu, #CP15_OFFSET(c12_VBAR)] + .endif + + mrc p15, 0, r2, c14, c1, 0 @ CNTKCTL + mrrc p15, 0, r4, r5, c7 @ PAR + mrc p15, 0, r6, c10, c3, 0 @ AMAIR0 + mrc p15, 0, r7, c10, c3, 1 @ AMAIR1 + + .if \store_to_vcpu == 0 + push {r2,r4-r7} + .else + str r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)] + add r12, vcpu, #CP15_OFFSET(c7_PAR) + strd r4, r5, [r12] + str r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)] + str r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)] + .endif +.endm + +/* + * Reads cp15 registers from memory and writes them to hardware + * @read_from_vcpu: If 0, registers are read in-order from the stack, + * otherwise from the VCPU struct pointed to by vcpup + * + * Assumes vcpu pointer in vcpu reg + */ +.macro write_cp15_state read_from_vcpu + .if \read_from_vcpu == 0 + pop {r2,r4-r7} + .else + ldr r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)] + add r12, vcpu, #CP15_OFFSET(c7_PAR) + ldrd r4, r5, [r12] + ldr r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)] + ldr r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)] + .endif + + mcr p15, 0, r2, c14, c1, 0 @ CNTKCTL + mcrr p15, 0, r4, r5, c7 @ PAR + mcr p15, 0, r6, c10, c3, 0 @ AMAIR0 + mcr p15, 0, r7, c10, c3, 1 @ AMAIR1 + + .if \read_from_vcpu == 0 + pop {r2-r12} + .else + ldr r2, [vcpu, #CP15_OFFSET(c13_CID)] + ldr r3, [vcpu, #CP15_OFFSET(c13_TID_URW)] + ldr r4, [vcpu, #CP15_OFFSET(c13_TID_URO)] + ldr r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)] + ldr r6, [vcpu, #CP15_OFFSET(c5_DFSR)] + ldr r7, [vcpu, #CP15_OFFSET(c5_IFSR)] + ldr r8, [vcpu, #CP15_OFFSET(c5_ADFSR)] + ldr r9, [vcpu, #CP15_OFFSET(c5_AIFSR)] + ldr r10, [vcpu, #CP15_OFFSET(c6_DFAR)] + ldr r11, [vcpu, #CP15_OFFSET(c6_IFAR)] + ldr r12, [vcpu, #CP15_OFFSET(c12_VBAR)] + .endif + + mcr p15, 0, r2, c13, c0, 1 @ CID + mcr p15, 0, r3, c13, c0, 2 @ TID_URW + mcr p15, 0, r4, c13, c0, 3 @ TID_URO + mcr p15, 0, r5, c13, c0, 4 @ TID_PRIV + mcr p15, 0, r6, c5, c0, 0 @ DFSR + mcr p15, 0, r7, c5, c0, 1 @ IFSR + mcr p15, 0, r8, c5, c1, 0 @ ADFSR + mcr p15, 0, r9, c5, c1, 1 @ AIFSR + mcr p15, 0, r10, c6, c0, 0 @ DFAR + mcr p15, 0, r11, c6, c0, 2 @ IFAR + mcr p15, 0, r12, c12, c0, 0 @ VBAR + + .if \read_from_vcpu == 0 + pop {r2-r12} + .else + ldr r2, [vcpu, #CP15_OFFSET(c1_SCTLR)] + ldr r3, [vcpu, #CP15_OFFSET(c1_CPACR)] + ldr r4, [vcpu, #CP15_OFFSET(c2_TTBCR)] + ldr r5, [vcpu, #CP15_OFFSET(c3_DACR)] + add r12, vcpu, #CP15_OFFSET(c2_TTBR0) + ldrd r6, r7, [r12] + add r12, vcpu, #CP15_OFFSET(c2_TTBR1) + ldrd r8, r9, [r12] + ldr r10, [vcpu, #CP15_OFFSET(c10_PRRR)] + ldr r11, [vcpu, #CP15_OFFSET(c10_NMRR)] + ldr r12, [vcpu, #CP15_OFFSET(c0_CSSELR)] + .endif + + mcr p15, 0, r2, c1, c0, 0 @ SCTLR + mcr p15, 0, r3, c1, c0, 2 @ CPACR + mcr p15, 0, r4, c2, c0, 2 @ TTBCR + mcr p15, 0, r5, c3, c0, 0 @ DACR + mcrr p15, 0, r6, r7, c2 @ TTBR 0 + mcrr p15, 1, r8, r9, c2 @ TTBR 1 + mcr p15, 0, r10, c10, c2, 0 @ PRRR + mcr p15, 0, r11, c10, c2, 1 @ NMRR + mcr p15, 2, r12, c0, c0, 0 @ CSSELR +.endm + +/* + * Save the VGIC CPU state into memory + * + * Assumes vcpu pointer in vcpu reg + */ +.macro save_vgic_state + /* Get VGIC VCTRL base into r2 */ + ldr r2, [vcpu, #VCPU_KVM] + ldr r2, [r2, #KVM_VGIC_VCTRL] + cmp r2, #0 + beq 2f + + /* Compute the address of struct vgic_cpu */ + add r11, vcpu, #VCPU_VGIC_CPU + + /* Save all interesting registers */ + ldr r3, [r2, #GICH_HCR] + ldr r4, [r2, #GICH_VMCR] + ldr r5, [r2, #GICH_MISR] + ldr r6, [r2, #GICH_EISR0] + ldr r7, [r2, #GICH_EISR1] + ldr r8, [r2, #GICH_ELRSR0] + ldr r9, [r2, #GICH_ELRSR1] + ldr r10, [r2, #GICH_APR] +ARM_BE8(rev r3, r3 ) +ARM_BE8(rev r4, r4 ) +ARM_BE8(rev r5, r5 ) +ARM_BE8(rev r6, r6 ) +ARM_BE8(rev r7, r7 ) +ARM_BE8(rev r8, r8 ) +ARM_BE8(rev r9, r9 ) +ARM_BE8(rev r10, r10 ) + + str r3, [r11, #VGIC_V2_CPU_HCR] + str r4, [r11, #VGIC_V2_CPU_VMCR] + str r5, [r11, #VGIC_V2_CPU_MISR] +#ifdef CONFIG_CPU_ENDIAN_BE8 + str r6, [r11, #(VGIC_V2_CPU_EISR + 4)] + str r7, [r11, #VGIC_V2_CPU_EISR] + str r8, [r11, #(VGIC_V2_CPU_ELRSR + 4)] + str r9, [r11, #VGIC_V2_CPU_ELRSR] +#else + str r6, [r11, #VGIC_V2_CPU_EISR] + str r7, [r11, #(VGIC_V2_CPU_EISR + 4)] + str r8, [r11, #VGIC_V2_CPU_ELRSR] + str r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)] +#endif + str r10, [r11, #VGIC_V2_CPU_APR] + + /* Clear GICH_HCR */ + mov r5, #0 + str r5, [r2, #GICH_HCR] + + /* Save list registers */ + add r2, r2, #GICH_LR0 + add r3, r11, #VGIC_V2_CPU_LR + ldr r4, [r11, #VGIC_CPU_NR_LR] +1: ldr r6, [r2], #4 +ARM_BE8(rev r6, r6 ) + str r6, [r3], #4 + subs r4, r4, #1 + bne 1b +2: +.endm + +/* + * Restore the VGIC CPU state from memory + * + * Assumes vcpu pointer in vcpu reg + */ +.macro restore_vgic_state + /* Get VGIC VCTRL base into r2 */ + ldr r2, [vcpu, #VCPU_KVM] + ldr r2, [r2, #KVM_VGIC_VCTRL] + cmp r2, #0 + beq 2f + + /* Compute the address of struct vgic_cpu */ + add r11, vcpu, #VCPU_VGIC_CPU + + /* We only restore a minimal set of registers */ + ldr r3, [r11, #VGIC_V2_CPU_HCR] + ldr r4, [r11, #VGIC_V2_CPU_VMCR] + ldr r8, [r11, #VGIC_V2_CPU_APR] +ARM_BE8(rev r3, r3 ) +ARM_BE8(rev r4, r4 ) +ARM_BE8(rev r8, r8 ) + + str r3, [r2, #GICH_HCR] + str r4, [r2, #GICH_VMCR] + str r8, [r2, #GICH_APR] + + /* Restore list registers */ + add r2, r2, #GICH_LR0 + add r3, r11, #VGIC_V2_CPU_LR + ldr r4, [r11, #VGIC_CPU_NR_LR] +1: ldr r6, [r3], #4 +ARM_BE8(rev r6, r6 ) + str r6, [r2], #4 + subs r4, r4, #1 + bne 1b +2: +.endm + +#define CNTHCTL_PL1PCTEN (1 << 0) +#define CNTHCTL_PL1PCEN (1 << 1) + +/* + * Save the timer state onto the VCPU and allow physical timer/counter access + * for the host. + * + * Assumes vcpu pointer in vcpu reg + * Clobbers r2-r5 + */ +.macro save_timer_state + ldr r4, [vcpu, #VCPU_KVM] + ldr r2, [r4, #KVM_TIMER_ENABLED] + cmp r2, #0 + beq 1f + + mrc p15, 0, r2, c14, c3, 1 @ CNTV_CTL + str r2, [vcpu, #VCPU_TIMER_CNTV_CTL] + bic r2, #1 @ Clear ENABLE + mcr p15, 0, r2, c14, c3, 1 @ CNTV_CTL + isb + + mrrc p15, 3, rr_lo_hi(r2, r3), c14 @ CNTV_CVAL + ldr r4, =VCPU_TIMER_CNTV_CVAL + add r5, vcpu, r4 + strd r2, r3, [r5] + + @ Ensure host CNTVCT == CNTPCT + mov r2, #0 + mcrr p15, 4, r2, r2, c14 @ CNTVOFF + +1: + @ Allow physical timer/counter access for the host + mrc p15, 4, r2, c14, c1, 0 @ CNTHCTL + orr r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN) + mcr p15, 4, r2, c14, c1, 0 @ CNTHCTL +.endm + +/* + * Load the timer state from the VCPU and deny physical timer/counter access + * for the host. + * + * Assumes vcpu pointer in vcpu reg + * Clobbers r2-r5 + */ +.macro restore_timer_state + @ Disallow physical timer access for the guest + @ Physical counter access is allowed + mrc p15, 4, r2, c14, c1, 0 @ CNTHCTL + orr r2, r2, #CNTHCTL_PL1PCTEN + bic r2, r2, #CNTHCTL_PL1PCEN + mcr p15, 4, r2, c14, c1, 0 @ CNTHCTL + + ldr r4, [vcpu, #VCPU_KVM] + ldr r2, [r4, #KVM_TIMER_ENABLED] + cmp r2, #0 + beq 1f + + ldr r2, [r4, #KVM_TIMER_CNTVOFF] + ldr r3, [r4, #(KVM_TIMER_CNTVOFF + 4)] + mcrr p15, 4, rr_lo_hi(r2, r3), c14 @ CNTVOFF + + ldr r4, =VCPU_TIMER_CNTV_CVAL + add r5, vcpu, r4 + ldrd r2, r3, [r5] + mcrr p15, 3, rr_lo_hi(r2, r3), c14 @ CNTV_CVAL + isb + + ldr r2, [vcpu, #VCPU_TIMER_CNTV_CTL] + and r2, r2, #3 + mcr p15, 0, r2, c14, c3, 1 @ CNTV_CTL +1: +.endm + +.equ vmentry, 0 +.equ vmexit, 1 + +/* Configures the HSTR (Hyp System Trap Register) on entry/return + * (hardware reset value is 0) */ +.macro set_hstr operation + mrc p15, 4, r2, c1, c1, 3 + ldr r3, =HSTR_T(15) + .if \operation == vmentry + orr r2, r2, r3 @ Trap CR{15} + .else + bic r2, r2, r3 @ Don't trap any CRx accesses + .endif + mcr p15, 4, r2, c1, c1, 3 +.endm + +/* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return + * (hardware reset value is 0). Keep previous value in r2. + * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if + * VFP wasn't already enabled (always executed on vmtrap). + * If a label is specified with vmexit, it is branched to if VFP wasn't + * enabled. + */ +.macro set_hcptr operation, mask, label = none + mrc p15, 4, r2, c1, c1, 2 + ldr r3, =\mask + .if \operation == vmentry + orr r3, r2, r3 @ Trap coproc-accesses defined in mask + .else + bic r3, r2, r3 @ Don't trap defined coproc-accesses + .endif + mcr p15, 4, r3, c1, c1, 2 + .if \operation != vmentry + .if \operation == vmexit + tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) + beq 1f + .endif + isb + .if \label != none + b \label + .endif +1: + .endif +.endm + +/* Configures the HDCR (Hyp Debug Configuration Register) on entry/return + * (hardware reset value is 0) */ +.macro set_hdcr operation + mrc p15, 4, r2, c1, c1, 1 + ldr r3, =(HDCR_TPM|HDCR_TPMCR) + .if \operation == vmentry + orr r2, r2, r3 @ Trap some perfmon accesses + .else + bic r2, r2, r3 @ Don't trap any perfmon accesses + .endif + mcr p15, 4, r2, c1, c1, 1 +.endm + +/* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */ +.macro configure_hyp_role operation + .if \operation == vmentry + ldr r2, [vcpu, #VCPU_HCR] + ldr r3, [vcpu, #VCPU_IRQ_LINES] + orr r2, r2, r3 + .else + mov r2, #0 + .endif + mcr p15, 4, r2, c1, c1, 0 @ HCR +.endm + +.macro load_vcpu + mrc p15, 4, vcpu, c13, c0, 2 @ HTPIDR +.endm diff --git a/kernel/arch/arm/kvm/mmio.c b/kernel/arch/arm/kvm/mmio.c new file mode 100644 index 000000000..974b1c606 --- /dev/null +++ b/kernel/arch/arm/kvm/mmio.c @@ -0,0 +1,218 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include +#include +#include +#include + +#include "trace.h" + +static void mmio_write_buf(char *buf, unsigned int len, unsigned long data) +{ + void *datap = NULL; + union { + u8 byte; + u16 hword; + u32 word; + u64 dword; + } tmp; + + switch (len) { + case 1: + tmp.byte = data; + datap = &tmp.byte; + break; + case 2: + tmp.hword = data; + datap = &tmp.hword; + break; + case 4: + tmp.word = data; + datap = &tmp.word; + break; + case 8: + tmp.dword = data; + datap = &tmp.dword; + break; + } + + memcpy(buf, datap, len); +} + +static unsigned long mmio_read_buf(char *buf, unsigned int len) +{ + unsigned long data = 0; + union { + u16 hword; + u32 word; + u64 dword; + } tmp; + + switch (len) { + case 1: + data = buf[0]; + break; + case 2: + memcpy(&tmp.hword, buf, len); + data = tmp.hword; + break; + case 4: + memcpy(&tmp.word, buf, len); + data = tmp.word; + break; + case 8: + memcpy(&tmp.dword, buf, len); + data = tmp.dword; + break; + } + + return data; +} + +/** + * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + * + * This should only be called after returning from userspace for MMIO load + * emulation. + */ +int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + unsigned long data; + unsigned int len; + int mask; + + if (!run->mmio.is_write) { + len = run->mmio.len; + if (len > sizeof(unsigned long)) + return -EINVAL; + + data = mmio_read_buf(run->mmio.data, len); + + if (vcpu->arch.mmio_decode.sign_extend && + len < sizeof(unsigned long)) { + mask = 1U << ((len * 8) - 1); + data = (data ^ mask) - mask; + } + + trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, + data); + data = vcpu_data_host_to_guest(vcpu, data, len); + *vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data; + } + + return 0; +} + +static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len) +{ + unsigned long rt; + int access_size; + bool sign_extend; + + if (kvm_vcpu_dabt_isextabt(vcpu)) { + /* cache operation on I/O addr, tell guest unsupported */ + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + return 1; + } + + if (kvm_vcpu_dabt_iss1tw(vcpu)) { + /* page table accesses IO mem: tell guest to fix its TTBR */ + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + return 1; + } + + access_size = kvm_vcpu_dabt_get_as(vcpu); + if (unlikely(access_size < 0)) + return access_size; + + *is_write = kvm_vcpu_dabt_iswrite(vcpu); + sign_extend = kvm_vcpu_dabt_issext(vcpu); + rt = kvm_vcpu_dabt_get_rd(vcpu); + + *len = access_size; + vcpu->arch.mmio_decode.sign_extend = sign_extend; + vcpu->arch.mmio_decode.rt = rt; + + /* + * The MMIO instruction is emulated and should not be re-executed + * in the guest. + */ + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 0; +} + +int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, + phys_addr_t fault_ipa) +{ + unsigned long data; + unsigned long rt; + int ret; + bool is_write; + int len; + u8 data_buf[8]; + + /* + * Prepare MMIO operation. First decode the syndrome data we get + * from the CPU. Then try if some in-kernel emulation feels + * responsible, otherwise let user space do its magic. + */ + if (kvm_vcpu_dabt_isvalid(vcpu)) { + ret = decode_hsr(vcpu, &is_write, &len); + if (ret) + return ret; + } else { + kvm_err("load/store instruction decoding not implemented\n"); + return -ENOSYS; + } + + rt = vcpu->arch.mmio_decode.rt; + + if (is_write) { + data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len); + + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); + mmio_write_buf(data_buf, len, data); + + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); + } else { + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, + fault_ipa, 0); + + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); + } + + /* Now prepare kvm_run for the potential return to userland. */ + run->mmio.is_write = is_write; + run->mmio.phys_addr = fault_ipa; + run->mmio.len = len; + memcpy(run->mmio.data, data_buf, len); + + if (!ret) { + /* We handled the access successfully in the kernel. */ + kvm_handle_mmio_return(vcpu, run); + return 1; + } + + run->exit_reason = KVM_EXIT_MMIO; + return 0; +} diff --git a/kernel/arch/arm/kvm/mmu.c b/kernel/arch/arm/kvm/mmu.c new file mode 100644 index 000000000..1d5accbd3 --- /dev/null +++ b/kernel/arch/arm/kvm/mmu.c @@ -0,0 +1,1926 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" + +extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; + +static pgd_t *boot_hyp_pgd; +static pgd_t *hyp_pgd; +static pgd_t *merged_hyp_pgd; +static DEFINE_MUTEX(kvm_hyp_pgd_mutex); + +static unsigned long hyp_idmap_start; +static unsigned long hyp_idmap_end; +static phys_addr_t hyp_idmap_vector; + +#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t)) + +#define kvm_pmd_huge(_x) (pmd_huge(_x) || pmd_trans_huge(_x)) +#define kvm_pud_huge(_x) pud_huge(_x) + +#define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0) +#define KVM_S2_FLAG_LOGGING_ACTIVE (1UL << 1) + +static bool memslot_is_logging(struct kvm_memory_slot *memslot) +{ + return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY); +} + +/** + * kvm_flush_remote_tlbs() - flush all VM TLB entries for v7/8 + * @kvm: pointer to kvm structure. + * + * Interface to HYP function to flush all VM TLB entries + */ +void kvm_flush_remote_tlbs(struct kvm *kvm) +{ + kvm_call_hyp(__kvm_tlb_flush_vmid, kvm); +} + +static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) +{ + /* + * This function also gets called when dealing with HYP page + * tables. As HYP doesn't have an associated struct kvm (and + * the HYP page tables are fairly static), we don't do + * anything there. + */ + if (kvm) + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa); +} + +/* + * D-Cache management functions. They take the page table entries by + * value, as they are flushing the cache using the kernel mapping (or + * kmap on 32bit). + */ +static void kvm_flush_dcache_pte(pte_t pte) +{ + __kvm_flush_dcache_pte(pte); +} + +static void kvm_flush_dcache_pmd(pmd_t pmd) +{ + __kvm_flush_dcache_pmd(pmd); +} + +static void kvm_flush_dcache_pud(pud_t pud) +{ + __kvm_flush_dcache_pud(pud); +} + +/** + * stage2_dissolve_pmd() - clear and flush huge PMD entry + * @kvm: pointer to kvm structure. + * @addr: IPA + * @pmd: pmd pointer for IPA + * + * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. Marks all + * pages in the range dirty. + */ +static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd) +{ + if (!kvm_pmd_huge(*pmd)) + return; + + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + put_page(virt_to_page(pmd)); +} + +static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, + int min, int max) +{ + void *page; + + BUG_ON(max > KVM_NR_MEM_OBJS); + if (cache->nobjs >= min) + return 0; + while (cache->nobjs < max) { + page = (void *)__get_free_page(PGALLOC_GFP); + if (!page) + return -ENOMEM; + cache->objects[cache->nobjs++] = page; + } + return 0; +} + +static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) +{ + while (mc->nobjs) + free_page((unsigned long)mc->objects[--mc->nobjs]); +} + +static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) +{ + void *p; + + BUG_ON(!mc || !mc->nobjs); + p = mc->objects[--mc->nobjs]; + return p; +} + +static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr) +{ + pud_t *pud_table __maybe_unused = pud_offset(pgd, 0); + pgd_clear(pgd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + pud_free(NULL, pud_table); + put_page(virt_to_page(pgd)); +} + +static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr) +{ + pmd_t *pmd_table = pmd_offset(pud, 0); + VM_BUG_ON(pud_huge(*pud)); + pud_clear(pud); + kvm_tlb_flush_vmid_ipa(kvm, addr); + pmd_free(NULL, pmd_table); + put_page(virt_to_page(pud)); +} + +static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) +{ + pte_t *pte_table = pte_offset_kernel(pmd, 0); + VM_BUG_ON(kvm_pmd_huge(*pmd)); + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + pte_free_kernel(NULL, pte_table); + put_page(virt_to_page(pmd)); +} + +/* + * Unmapping vs dcache management: + * + * If a guest maps certain memory pages as uncached, all writes will + * bypass the data cache and go directly to RAM. However, the CPUs + * can still speculate reads (not writes) and fill cache lines with + * data. + * + * Those cache lines will be *clean* cache lines though, so a + * clean+invalidate operation is equivalent to an invalidate + * operation, because no cache lines are marked dirty. + * + * Those clean cache lines could be filled prior to an uncached write + * by the guest, and the cache coherent IO subsystem would therefore + * end up writing old data to disk. + * + * This is why right after unmapping a page/section and invalidating + * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure + * the IO subsystem will never hit in the cache. + */ +static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, + phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t start_addr = addr; + pte_t *pte, *start_pte; + + start_pte = pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte)) { + pte_t old_pte = *pte; + + kvm_set_pte(pte, __pte(0)); + kvm_tlb_flush_vmid_ipa(kvm, addr); + + /* No need to invalidate the cache for device mappings */ + if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(old_pte); + + put_page(virt_to_page(pte)); + } + } while (pte++, addr += PAGE_SIZE, addr != end); + + if (kvm_pte_table_empty(kvm, start_pte)) + clear_pmd_entry(kvm, pmd, start_addr); +} + +static void unmap_pmds(struct kvm *kvm, pud_t *pud, + phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t next, start_addr = addr; + pmd_t *pmd, *start_pmd; + + start_pmd = pmd = pmd_offset(pud, addr); + do { + next = kvm_pmd_addr_end(addr, end); + if (!pmd_none(*pmd)) { + if (kvm_pmd_huge(*pmd)) { + pmd_t old_pmd = *pmd; + + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pmd(old_pmd); + + put_page(virt_to_page(pmd)); + } else { + unmap_ptes(kvm, pmd, addr, next); + } + } + } while (pmd++, addr = next, addr != end); + + if (kvm_pmd_table_empty(kvm, start_pmd)) + clear_pud_entry(kvm, pud, start_addr); +} + +static void unmap_puds(struct kvm *kvm, pgd_t *pgd, + phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t next, start_addr = addr; + pud_t *pud, *start_pud; + + start_pud = pud = pud_offset(pgd, addr); + do { + next = kvm_pud_addr_end(addr, end); + if (!pud_none(*pud)) { + if (pud_huge(*pud)) { + pud_t old_pud = *pud; + + pud_clear(pud); + kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pud(old_pud); + + put_page(virt_to_page(pud)); + } else { + unmap_pmds(kvm, pud, addr, next); + } + } + } while (pud++, addr = next, addr != end); + + if (kvm_pud_table_empty(kvm, start_pud)) + clear_pgd_entry(kvm, pgd, start_addr); +} + + +static void unmap_range(struct kvm *kvm, pgd_t *pgdp, + phys_addr_t start, u64 size) +{ + pgd_t *pgd; + phys_addr_t addr = start, end = start + size; + phys_addr_t next; + + pgd = pgdp + kvm_pgd_index(addr); + do { + next = kvm_pgd_addr_end(addr, end); + if (!pgd_none(*pgd)) + unmap_puds(kvm, pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, + phys_addr_t addr, phys_addr_t end) +{ + pte_t *pte; + + pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte) && + (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(*pte); + } while (pte++, addr += PAGE_SIZE, addr != end); +} + +static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, + phys_addr_t addr, phys_addr_t end) +{ + pmd_t *pmd; + phys_addr_t next; + + pmd = pmd_offset(pud, addr); + do { + next = kvm_pmd_addr_end(addr, end); + if (!pmd_none(*pmd)) { + if (kvm_pmd_huge(*pmd)) + kvm_flush_dcache_pmd(*pmd); + else + stage2_flush_ptes(kvm, pmd, addr, next); + } + } while (pmd++, addr = next, addr != end); +} + +static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd, + phys_addr_t addr, phys_addr_t end) +{ + pud_t *pud; + phys_addr_t next; + + pud = pud_offset(pgd, addr); + do { + next = kvm_pud_addr_end(addr, end); + if (!pud_none(*pud)) { + if (pud_huge(*pud)) + kvm_flush_dcache_pud(*pud); + else + stage2_flush_pmds(kvm, pud, addr, next); + } + } while (pud++, addr = next, addr != end); +} + +static void stage2_flush_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t end = addr + PAGE_SIZE * memslot->npages; + phys_addr_t next; + pgd_t *pgd; + + pgd = kvm->arch.pgd + kvm_pgd_index(addr); + do { + next = kvm_pgd_addr_end(addr, end); + stage2_flush_puds(kvm, pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +/** + * stage2_flush_vm - Invalidate cache for pages mapped in stage 2 + * @kvm: The struct kvm pointer + * + * Go through the stage 2 page tables and invalidate any cache lines + * backing memory already mapped to the VM. + */ +static void stage2_flush_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_flush_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); +} + +/** + * free_boot_hyp_pgd - free HYP boot page tables + * + * Free the HYP boot page tables. The bounce page is also freed. + */ +void free_boot_hyp_pgd(void) +{ + mutex_lock(&kvm_hyp_pgd_mutex); + + if (boot_hyp_pgd) { + unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE); + unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE); + free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order); + boot_hyp_pgd = NULL; + } + + if (hyp_pgd) + unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE); + + mutex_unlock(&kvm_hyp_pgd_mutex); +} + +/** + * free_hyp_pgds - free Hyp-mode page tables + * + * Assumes hyp_pgd is a page table used strictly in Hyp-mode and + * therefore contains either mappings in the kernel memory area (above + * PAGE_OFFSET), or device mappings in the vmalloc range (from + * VMALLOC_START to VMALLOC_END). + * + * boot_hyp_pgd should only map two pages for the init code. + */ +void free_hyp_pgds(void) +{ + unsigned long addr; + + free_boot_hyp_pgd(); + + mutex_lock(&kvm_hyp_pgd_mutex); + + if (hyp_pgd) { + for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE) + unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE); + for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE) + unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE); + + free_pages((unsigned long)hyp_pgd, hyp_pgd_order); + hyp_pgd = NULL; + } + if (merged_hyp_pgd) { + clear_page(merged_hyp_pgd); + free_page((unsigned long)merged_hyp_pgd); + merged_hyp_pgd = NULL; + } + + mutex_unlock(&kvm_hyp_pgd_mutex); +} + +static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start, + unsigned long end, unsigned long pfn, + pgprot_t prot) +{ + pte_t *pte; + unsigned long addr; + + addr = start; + do { + pte = pte_offset_kernel(pmd, addr); + kvm_set_pte(pte, pfn_pte(pfn, prot)); + get_page(virt_to_page(pte)); + kvm_flush_dcache_to_poc(pte, sizeof(*pte)); + pfn++; + } while (addr += PAGE_SIZE, addr != end); +} + +static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start, + unsigned long end, unsigned long pfn, + pgprot_t prot) +{ + pmd_t *pmd; + pte_t *pte; + unsigned long addr, next; + + addr = start; + do { + pmd = pmd_offset(pud, addr); + + BUG_ON(pmd_sect(*pmd)); + + if (pmd_none(*pmd)) { + pte = pte_alloc_one_kernel(NULL, addr); + if (!pte) { + kvm_err("Cannot allocate Hyp pte\n"); + return -ENOMEM; + } + pmd_populate_kernel(NULL, pmd, pte); + get_page(virt_to_page(pmd)); + kvm_flush_dcache_to_poc(pmd, sizeof(*pmd)); + } + + next = pmd_addr_end(addr, end); + + create_hyp_pte_mappings(pmd, addr, next, pfn, prot); + pfn += (next - addr) >> PAGE_SHIFT; + } while (addr = next, addr != end); + + return 0; +} + +static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start, + unsigned long end, unsigned long pfn, + pgprot_t prot) +{ + pud_t *pud; + pmd_t *pmd; + unsigned long addr, next; + int ret; + + addr = start; + do { + pud = pud_offset(pgd, addr); + + if (pud_none_or_clear_bad(pud)) { + pmd = pmd_alloc_one(NULL, addr); + if (!pmd) { + kvm_err("Cannot allocate Hyp pmd\n"); + return -ENOMEM; + } + pud_populate(NULL, pud, pmd); + get_page(virt_to_page(pud)); + kvm_flush_dcache_to_poc(pud, sizeof(*pud)); + } + + next = pud_addr_end(addr, end); + ret = create_hyp_pmd_mappings(pud, addr, next, pfn, prot); + if (ret) + return ret; + pfn += (next - addr) >> PAGE_SHIFT; + } while (addr = next, addr != end); + + return 0; +} + +static int __create_hyp_mappings(pgd_t *pgdp, + unsigned long start, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + pgd_t *pgd; + pud_t *pud; + unsigned long addr, next; + int err = 0; + + mutex_lock(&kvm_hyp_pgd_mutex); + addr = start & PAGE_MASK; + end = PAGE_ALIGN(end); + do { + pgd = pgdp + pgd_index(addr); + + if (pgd_none(*pgd)) { + pud = pud_alloc_one(NULL, addr); + if (!pud) { + kvm_err("Cannot allocate Hyp pud\n"); + err = -ENOMEM; + goto out; + } + pgd_populate(NULL, pgd, pud); + get_page(virt_to_page(pgd)); + kvm_flush_dcache_to_poc(pgd, sizeof(*pgd)); + } + + next = pgd_addr_end(addr, end); + err = create_hyp_pud_mappings(pgd, addr, next, pfn, prot); + if (err) + goto out; + pfn += (next - addr) >> PAGE_SHIFT; + } while (addr = next, addr != end); +out: + mutex_unlock(&kvm_hyp_pgd_mutex); + return err; +} + +static phys_addr_t kvm_kaddr_to_phys(void *kaddr) +{ + if (!is_vmalloc_addr(kaddr)) { + BUG_ON(!virt_addr_valid(kaddr)); + return __pa(kaddr); + } else { + return page_to_phys(vmalloc_to_page(kaddr)) + + offset_in_page(kaddr); + } +} + +/** + * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode + * @from: The virtual kernel start address of the range + * @to: The virtual kernel end address of the range (exclusive) + * + * The same virtual address as the kernel virtual address is also used + * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying + * physical pages. + */ +int create_hyp_mappings(void *from, void *to) +{ + phys_addr_t phys_addr; + unsigned long virt_addr; + unsigned long start = KERN_TO_HYP((unsigned long)from); + unsigned long end = KERN_TO_HYP((unsigned long)to); + + start = start & PAGE_MASK; + end = PAGE_ALIGN(end); + + for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) { + int err; + + phys_addr = kvm_kaddr_to_phys(from + virt_addr - start); + err = __create_hyp_mappings(hyp_pgd, virt_addr, + virt_addr + PAGE_SIZE, + __phys_to_pfn(phys_addr), + PAGE_HYP); + if (err) + return err; + } + + return 0; +} + +/** + * create_hyp_io_mappings - duplicate a kernel IO mapping into Hyp mode + * @from: The kernel start VA of the range + * @to: The kernel end VA of the range (exclusive) + * @phys_addr: The physical start address which gets mapped + * + * The resulting HYP VA is the same as the kernel VA, modulo + * HYP_PAGE_OFFSET. + */ +int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr) +{ + unsigned long start = KERN_TO_HYP((unsigned long)from); + unsigned long end = KERN_TO_HYP((unsigned long)to); + + /* Check for a valid kernel IO mapping */ + if (!is_vmalloc_addr(from) || !is_vmalloc_addr(to - 1)) + return -EINVAL; + + return __create_hyp_mappings(hyp_pgd, start, end, + __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE); +} + +/* Free the HW pgd, one page at a time */ +static void kvm_free_hwpgd(void *hwpgd) +{ + free_pages_exact(hwpgd, kvm_get_hwpgd_size()); +} + +/* Allocate the HW PGD, making sure that each page gets its own refcount */ +static void *kvm_alloc_hwpgd(void) +{ + unsigned int size = kvm_get_hwpgd_size(); + + return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); +} + +/** + * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation. + * @kvm: The KVM struct pointer for the VM. + * + * Allocates the 1st level table only of size defined by S2_PGD_ORDER (can + * support either full 40-bit input addresses or limited to 32-bit input + * addresses). Clears the allocated pages. + * + * Note we don't need locking here as this is only called when the VM is + * created, which can only be done once. + */ +int kvm_alloc_stage2_pgd(struct kvm *kvm) +{ + pgd_t *pgd; + void *hwpgd; + + if (kvm->arch.pgd != NULL) { + kvm_err("kvm_arch already initialized?\n"); + return -EINVAL; + } + + hwpgd = kvm_alloc_hwpgd(); + if (!hwpgd) + return -ENOMEM; + + /* When the kernel uses more levels of page tables than the + * guest, we allocate a fake PGD and pre-populate it to point + * to the next-level page table, which will be the real + * initial page table pointed to by the VTTBR. + * + * When KVM_PREALLOC_LEVEL==2, we allocate a single page for + * the PMD and the kernel will use folded pud. + * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD + * pages. + */ + if (KVM_PREALLOC_LEVEL > 0) { + int i; + + /* + * Allocate fake pgd for the page table manipulation macros to + * work. This is not used by the hardware and we have no + * alignment requirement for this allocation. + */ + pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), + GFP_KERNEL | __GFP_ZERO); + + if (!pgd) { + kvm_free_hwpgd(hwpgd); + return -ENOMEM; + } + + /* Plug the HW PGD into the fake one. */ + for (i = 0; i < PTRS_PER_S2_PGD; i++) { + if (KVM_PREALLOC_LEVEL == 1) + pgd_populate(NULL, pgd + i, + (pud_t *)hwpgd + i * PTRS_PER_PUD); + else if (KVM_PREALLOC_LEVEL == 2) + pud_populate(NULL, pud_offset(pgd, 0) + i, + (pmd_t *)hwpgd + i * PTRS_PER_PMD); + } + } else { + /* + * Allocate actual first-level Stage-2 page table used by the + * hardware for Stage-2 page table walks. + */ + pgd = (pgd_t *)hwpgd; + } + + kvm_clean_pgd(pgd); + kvm->arch.pgd = pgd; + return 0; +} + +/** + * unmap_stage2_range -- Clear stage2 page table entries to unmap a range + * @kvm: The VM pointer + * @start: The intermediate physical base address of the range to unmap + * @size: The size of the area to unmap + * + * Clear a range of stage-2 mappings, lowering the various ref-counts. Must + * be called while holding mmu_lock (unless for freeing the stage2 pgd before + * destroying the VM), otherwise another faulting VCPU may come in and mess + * with things behind our backs. + */ +static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) +{ + unmap_range(kvm, kvm->arch.pgd, start, size); +} + +static void stage2_unmap_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + hva_t hva = memslot->userspace_addr; + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t size = PAGE_SIZE * memslot->npages; + hva_t reg_end = hva + size; + + /* + * A memory region could potentially cover multiple VMAs, and any holes + * between them, so iterate over all of them to find out if we should + * unmap any of them. + * + * +--------------------------------------------+ + * +---------------+----------------+ +----------------+ + * | : VMA 1 | VMA 2 | | VMA 3 : | + * +---------------+----------------+ +----------------+ + * | memory region | + * +--------------------------------------------+ + */ + do { + struct vm_area_struct *vma = find_vma(current->mm, hva); + hva_t vm_start, vm_end; + + if (!vma || vma->vm_start >= reg_end) + break; + + /* + * Take the intersection of this VMA with the memory region + */ + vm_start = max(hva, vma->vm_start); + vm_end = min(reg_end, vma->vm_end); + + if (!(vma->vm_flags & VM_PFNMAP)) { + gpa_t gpa = addr + (vm_start - memslot->userspace_addr); + unmap_stage2_range(kvm, gpa, vm_end - vm_start); + } + hva = vm_end; + } while (hva < reg_end); +} + +/** + * stage2_unmap_vm - Unmap Stage-2 RAM mappings + * @kvm: The struct kvm pointer + * + * Go through the memregions and unmap any reguler RAM + * backing memory already mapped to the VM. + */ +void stage2_unmap_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_unmap_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); +} + +/** + * kvm_free_stage2_pgd - free all stage-2 tables + * @kvm: The KVM struct pointer for the VM. + * + * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all + * underlying level-2 and level-3 tables before freeing the actual level-1 table + * and setting the struct pointer to NULL. + * + * Note we don't need locking here as this is only called when the VM is + * destroyed, which can only be done once. + */ +void kvm_free_stage2_pgd(struct kvm *kvm) +{ + if (kvm->arch.pgd == NULL) + return; + + unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); + kvm_free_hwpgd(kvm_get_hwpgd(kvm)); + if (KVM_PREALLOC_LEVEL > 0) + kfree(kvm->arch.pgd); + + kvm->arch.pgd = NULL; +} + +static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr) +{ + pgd_t *pgd; + pud_t *pud; + + pgd = kvm->arch.pgd + kvm_pgd_index(addr); + if (WARN_ON(pgd_none(*pgd))) { + if (!cache) + return NULL; + pud = mmu_memory_cache_alloc(cache); + pgd_populate(NULL, pgd, pud); + get_page(virt_to_page(pgd)); + } + + return pud_offset(pgd, addr); +} + +static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr) +{ + pud_t *pud; + pmd_t *pmd; + + pud = stage2_get_pud(kvm, cache, addr); + if (pud_none(*pud)) { + if (!cache) + return NULL; + pmd = mmu_memory_cache_alloc(cache); + pud_populate(NULL, pud, pmd); + get_page(virt_to_page(pud)); + } + + return pmd_offset(pud, addr); +} + +static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache + *cache, phys_addr_t addr, const pmd_t *new_pmd) +{ + pmd_t *pmd, old_pmd; + + pmd = stage2_get_pmd(kvm, cache, addr); + VM_BUG_ON(!pmd); + + /* + * Mapping in huge pages should only happen through a fault. If a + * page is merged into a transparent huge page, the individual + * subpages of that huge page should be unmapped through MMU + * notifiers before we get here. + * + * Merging of CompoundPages is not supported; they should become + * splitting first, unmapped, merged, and mapped back in on-demand. + */ + VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd)); + + old_pmd = *pmd; + kvm_set_pmd(pmd, *new_pmd); + if (pmd_present(old_pmd)) + kvm_tlb_flush_vmid_ipa(kvm, addr); + else + get_page(virt_to_page(pmd)); + return 0; +} + +static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr, const pte_t *new_pte, + unsigned long flags) +{ + pmd_t *pmd; + pte_t *pte, old_pte; + bool iomap = flags & KVM_S2PTE_FLAG_IS_IOMAP; + bool logging_active = flags & KVM_S2_FLAG_LOGGING_ACTIVE; + + VM_BUG_ON(logging_active && !cache); + + /* Create stage-2 page table mapping - Levels 0 and 1 */ + pmd = stage2_get_pmd(kvm, cache, addr); + if (!pmd) { + /* + * Ignore calls from kvm_set_spte_hva for unallocated + * address ranges. + */ + return 0; + } + + /* + * While dirty page logging - dissolve huge PMD, then continue on to + * allocate page. + */ + if (logging_active) + stage2_dissolve_pmd(kvm, addr, pmd); + + /* Create stage-2 page mappings - Level 2 */ + if (pmd_none(*pmd)) { + if (!cache) + return 0; /* ignore calls from kvm_set_spte_hva */ + pte = mmu_memory_cache_alloc(cache); + kvm_clean_pte(pte); + pmd_populate_kernel(NULL, pmd, pte); + get_page(virt_to_page(pmd)); + } + + pte = pte_offset_kernel(pmd, addr); + + if (iomap && pte_present(*pte)) + return -EFAULT; + + /* Create 2nd stage page table mapping - Level 3 */ + old_pte = *pte; + kvm_set_pte(pte, *new_pte); + if (pte_present(old_pte)) + kvm_tlb_flush_vmid_ipa(kvm, addr); + else + get_page(virt_to_page(pte)); + + return 0; +} + +/** + * kvm_phys_addr_ioremap - map a device range to guest IPA + * + * @kvm: The KVM pointer + * @guest_ipa: The IPA at which to insert the mapping + * @pa: The physical address of the device + * @size: The size of the mapping + */ +int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, + phys_addr_t pa, unsigned long size, bool writable) +{ + phys_addr_t addr, end; + int ret = 0; + unsigned long pfn; + struct kvm_mmu_memory_cache cache = { 0, }; + + end = (guest_ipa + size + PAGE_SIZE - 1) & PAGE_MASK; + pfn = __phys_to_pfn(pa); + + for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) { + pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE); + + if (writable) + kvm_set_s2pte_writable(&pte); + + ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES, + KVM_NR_MEM_OBJS); + if (ret) + goto out; + spin_lock(&kvm->mmu_lock); + ret = stage2_set_pte(kvm, &cache, addr, &pte, + KVM_S2PTE_FLAG_IS_IOMAP); + spin_unlock(&kvm->mmu_lock); + if (ret) + goto out; + + pfn++; + } + +out: + mmu_free_memory_cache(&cache); + return ret; +} + +static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap) +{ + pfn_t pfn = *pfnp; + gfn_t gfn = *ipap >> PAGE_SHIFT; + + if (PageTransCompound(pfn_to_page(pfn))) { + unsigned long mask; + /* + * The address we faulted on is backed by a transparent huge + * page. However, because we map the compound huge page and + * not the individual tail page, we need to transfer the + * refcount to the head page. We have to be careful that the + * THP doesn't start to split while we are adjusting the + * refcounts. + * + * We are sure this doesn't happen, because mmu_notifier_retry + * was successful and we are holding the mmu_lock, so if this + * THP is trying to split, it will be blocked in the mmu + * notifier before touching any of the pages, specifically + * before being able to call __split_huge_page_refcount(). + * + * We can therefore safely transfer the refcount from PG_tail + * to PG_head and switch the pfn from a tail page to the head + * page accordingly. + */ + mask = PTRS_PER_PMD - 1; + VM_BUG_ON((gfn & mask) != (pfn & mask)); + if (pfn & mask) { + *ipap &= PMD_MASK; + kvm_release_pfn_clean(pfn); + pfn &= ~mask; + kvm_get_pfn(pfn); + *pfnp = pfn; + } + + return true; + } + + return false; +} + +static bool kvm_is_write_fault(struct kvm_vcpu *vcpu) +{ + if (kvm_vcpu_trap_is_iabt(vcpu)) + return false; + + return kvm_vcpu_dabt_iswrite(vcpu); +} + +static bool kvm_is_device_pfn(unsigned long pfn) +{ + return !pfn_valid(pfn); +} + +/** + * stage2_wp_ptes - write protect PMD range + * @pmd: pointer to pmd entry + * @addr: range start address + * @end: range end address + */ +static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end) +{ + pte_t *pte; + + pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte)) { + if (!kvm_s2pte_readonly(pte)) + kvm_set_s2pte_readonly(pte); + } + } while (pte++, addr += PAGE_SIZE, addr != end); +} + +/** + * stage2_wp_pmds - write protect PUD range + * @pud: pointer to pud entry + * @addr: range start address + * @end: range end address + */ +static void stage2_wp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end) +{ + pmd_t *pmd; + phys_addr_t next; + + pmd = pmd_offset(pud, addr); + + do { + next = kvm_pmd_addr_end(addr, end); + if (!pmd_none(*pmd)) { + if (kvm_pmd_huge(*pmd)) { + if (!kvm_s2pmd_readonly(pmd)) + kvm_set_s2pmd_readonly(pmd); + } else { + stage2_wp_ptes(pmd, addr, next); + } + } + } while (pmd++, addr = next, addr != end); +} + +/** + * stage2_wp_puds - write protect PGD range + * @pgd: pointer to pgd entry + * @addr: range start address + * @end: range end address + * + * Process PUD entries, for a huge PUD we cause a panic. + */ +static void stage2_wp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end) +{ + pud_t *pud; + phys_addr_t next; + + pud = pud_offset(pgd, addr); + do { + next = kvm_pud_addr_end(addr, end); + if (!pud_none(*pud)) { + /* TODO:PUD not supported, revisit later if supported */ + BUG_ON(kvm_pud_huge(*pud)); + stage2_wp_pmds(pud, addr, next); + } + } while (pud++, addr = next, addr != end); +} + +/** + * stage2_wp_range() - write protect stage2 memory region range + * @kvm: The KVM pointer + * @addr: Start address of range + * @end: End address of range + */ +static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) +{ + pgd_t *pgd; + phys_addr_t next; + + pgd = kvm->arch.pgd + kvm_pgd_index(addr); + do { + /* + * Release kvm_mmu_lock periodically if the memory region is + * large. Otherwise, we may see kernel panics with + * CONFIG_DETECT_HUNG_TASK, CONFIG_LOCKUP_DETECTOR, + * CONFIG_LOCKDEP. Additionally, holding the lock too long + * will also starve other vCPUs. + */ + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) + cond_resched_lock(&kvm->mmu_lock); + + next = kvm_pgd_addr_end(addr, end); + if (pgd_present(*pgd)) + stage2_wp_puds(pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +/** + * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot + * @kvm: The KVM pointer + * @slot: The memory slot to write protect + * + * Called to start logging dirty pages after memory region + * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns + * all present PMD and PTEs are write protected in the memory region. + * Afterwards read of dirty page log can be called. + * + * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired, + * serializing operations for VM memory regions. + */ +void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot) +{ + struct kvm_memory_slot *memslot = id_to_memslot(kvm->memslots, slot); + phys_addr_t start = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; + + spin_lock(&kvm->mmu_lock); + stage2_wp_range(kvm, start, end); + spin_unlock(&kvm->mmu_lock); + kvm_flush_remote_tlbs(kvm); +} + +/** + * kvm_mmu_write_protect_pt_masked() - write protect dirty pages + * @kvm: The KVM pointer + * @slot: The memory slot associated with mask + * @gfn_offset: The gfn offset in memory slot + * @mask: The mask of dirty pages at offset 'gfn_offset' in this memory + * slot to be write protected + * + * Walks bits set in mask write protects the associated pte's. Caller must + * acquire kvm_mmu_lock. + */ +static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, unsigned long mask) +{ + phys_addr_t base_gfn = slot->base_gfn + gfn_offset; + phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; + phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; + + stage2_wp_range(kvm, start, end); +} + +/* + * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected + * dirty pages. + * + * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to + * enable dirty logging for them. + */ +void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, unsigned long mask) +{ + kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); +} + +static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, bool uncached) +{ + __coherent_cache_guest_page(vcpu, pfn, size, uncached); +} + +static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, + struct kvm_memory_slot *memslot, unsigned long hva, + unsigned long fault_status) +{ + int ret; + bool write_fault, writable, hugetlb = false, force_pte = false; + unsigned long mmu_seq; + gfn_t gfn = fault_ipa >> PAGE_SHIFT; + struct kvm *kvm = vcpu->kvm; + struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; + struct vm_area_struct *vma; + pfn_t pfn; + pgprot_t mem_type = PAGE_S2; + bool fault_ipa_uncached; + bool logging_active = memslot_is_logging(memslot); + unsigned long flags = 0; + + write_fault = kvm_is_write_fault(vcpu); + if (fault_status == FSC_PERM && !write_fault) { + kvm_err("Unexpected L2 read permission error\n"); + return -EFAULT; + } + + /* Let's check if we will get back a huge page backed by hugetlbfs */ + down_read(¤t->mm->mmap_sem); + vma = find_vma_intersection(current->mm, hva, hva + 1); + if (unlikely(!vma)) { + kvm_err("Failed to find VMA for hva 0x%lx\n", hva); + up_read(¤t->mm->mmap_sem); + return -EFAULT; + } + + if (is_vm_hugetlb_page(vma) && !logging_active) { + hugetlb = true; + gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT; + } else { + /* + * Pages belonging to memslots that don't have the same + * alignment for userspace and IPA cannot be mapped using + * block descriptors even if the pages belong to a THP for + * the process, because the stage-2 block descriptor will + * cover more than a single THP and we loose atomicity for + * unmapping, updates, and splits of the THP or other pages + * in the stage-2 block range. + */ + if ((memslot->userspace_addr & ~PMD_MASK) != + ((memslot->base_gfn << PAGE_SHIFT) & ~PMD_MASK)) + force_pte = true; + } + up_read(¤t->mm->mmap_sem); + + /* We need minimum second+third level pages */ + ret = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES, + KVM_NR_MEM_OBJS); + if (ret) + return ret; + + mmu_seq = vcpu->kvm->mmu_notifier_seq; + /* + * Ensure the read of mmu_notifier_seq happens before we call + * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk + * the page we just got a reference to gets unmapped before we have a + * chance to grab the mmu_lock, which ensure that if the page gets + * unmapped afterwards, the call to kvm_unmap_hva will take it away + * from us again properly. This smp_rmb() interacts with the smp_wmb() + * in kvm_mmu_notifier_invalidate_. + */ + smp_rmb(); + + pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable); + if (is_error_pfn(pfn)) + return -EFAULT; + + if (kvm_is_device_pfn(pfn)) { + mem_type = PAGE_S2_DEVICE; + flags |= KVM_S2PTE_FLAG_IS_IOMAP; + } else if (logging_active) { + /* + * Faults on pages in a memslot with logging enabled + * should not be mapped with huge pages (it introduces churn + * and performance degradation), so force a pte mapping. + */ + force_pte = true; + flags |= KVM_S2_FLAG_LOGGING_ACTIVE; + + /* + * Only actually map the page as writable if this was a write + * fault. + */ + if (!write_fault) + writable = false; + } + + spin_lock(&kvm->mmu_lock); + if (mmu_notifier_retry(kvm, mmu_seq)) + goto out_unlock; + + if (!hugetlb && !force_pte) + hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa); + + fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT; + + if (hugetlb) { + pmd_t new_pmd = pfn_pmd(pfn, mem_type); + new_pmd = pmd_mkhuge(new_pmd); + if (writable) { + kvm_set_s2pmd_writable(&new_pmd); + kvm_set_pfn_dirty(pfn); + } + coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached); + ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); + } else { + pte_t new_pte = pfn_pte(pfn, mem_type); + + if (writable) { + kvm_set_s2pte_writable(&new_pte); + kvm_set_pfn_dirty(pfn); + mark_page_dirty(kvm, gfn); + } + coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached); + ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags); + } + +out_unlock: + spin_unlock(&kvm->mmu_lock); + kvm_set_pfn_accessed(pfn); + kvm_release_pfn_clean(pfn); + return ret; +} + +/* + * Resolve the access fault by making the page young again. + * Note that because the faulting entry is guaranteed not to be + * cached in the TLB, we don't need to invalidate anything. + */ +static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) +{ + pmd_t *pmd; + pte_t *pte; + pfn_t pfn; + bool pfn_valid = false; + + trace_kvm_access_fault(fault_ipa); + + spin_lock(&vcpu->kvm->mmu_lock); + + pmd = stage2_get_pmd(vcpu->kvm, NULL, fault_ipa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + goto out; + + if (kvm_pmd_huge(*pmd)) { /* THP, HugeTLB */ + *pmd = pmd_mkyoung(*pmd); + pfn = pmd_pfn(*pmd); + pfn_valid = true; + goto out; + } + + pte = pte_offset_kernel(pmd, fault_ipa); + if (pte_none(*pte)) /* Nothing there either */ + goto out; + + *pte = pte_mkyoung(*pte); /* Just a page... */ + pfn = pte_pfn(*pte); + pfn_valid = true; +out: + spin_unlock(&vcpu->kvm->mmu_lock); + if (pfn_valid) + kvm_set_pfn_accessed(pfn); +} + +/** + * kvm_handle_guest_abort - handles all 2nd stage aborts + * @vcpu: the VCPU pointer + * @run: the kvm_run structure + * + * Any abort that gets to the host is almost guaranteed to be caused by a + * missing second stage translation table entry, which can mean that either the + * guest simply needs more memory and we must allocate an appropriate page or it + * can mean that the guest tried to access I/O memory, which is emulated by user + * space. The distinction is based on the IPA causing the fault and whether this + * memory region has been registered as standard RAM by user space. + */ +int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + unsigned long fault_status; + phys_addr_t fault_ipa; + struct kvm_memory_slot *memslot; + unsigned long hva; + bool is_iabt, write_fault, writable; + gfn_t gfn; + int ret, idx; + + is_iabt = kvm_vcpu_trap_is_iabt(vcpu); + fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); + + trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu), + kvm_vcpu_get_hfar(vcpu), fault_ipa); + + /* Check the stage-2 fault is trans. fault or write fault */ + fault_status = kvm_vcpu_trap_get_fault_type(vcpu); + if (fault_status != FSC_FAULT && fault_status != FSC_PERM && + fault_status != FSC_ACCESS) { + kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", + kvm_vcpu_trap_get_class(vcpu), + (unsigned long)kvm_vcpu_trap_get_fault(vcpu), + (unsigned long)kvm_vcpu_get_hsr(vcpu)); + return -EFAULT; + } + + idx = srcu_read_lock(&vcpu->kvm->srcu); + + gfn = fault_ipa >> PAGE_SHIFT; + memslot = gfn_to_memslot(vcpu->kvm, gfn); + hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable); + write_fault = kvm_is_write_fault(vcpu); + if (kvm_is_error_hva(hva) || (write_fault && !writable)) { + if (is_iabt) { + /* Prefetch Abort on I/O address */ + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + ret = 1; + goto out_unlock; + } + + /* + * The IPA is reported as [MAX:12], so we need to + * complement it with the bottom 12 bits from the + * faulting VA. This is always 12 bits, irrespective + * of the page size. + */ + fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1); + ret = io_mem_abort(vcpu, run, fault_ipa); + goto out_unlock; + } + + /* Userspace should not be able to register out-of-bounds IPAs */ + VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE); + + if (fault_status == FSC_ACCESS) { + handle_access_fault(vcpu, fault_ipa); + ret = 1; + goto out_unlock; + } + + ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); + if (ret == 0) + ret = 1; +out_unlock: + srcu_read_unlock(&vcpu->kvm->srcu, idx); + return ret; +} + +static int handle_hva_to_gpa(struct kvm *kvm, + unsigned long start, + unsigned long end, + int (*handler)(struct kvm *kvm, + gpa_t gpa, void *data), + void *data) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int ret = 0; + + slots = kvm_memslots(kvm); + + /* we only care about the pages that the guest sees */ + kvm_for_each_memslot(memslot, slots) { + unsigned long hva_start, hva_end; + gfn_t gfn, gfn_end; + + hva_start = max(start, memslot->userspace_addr); + hva_end = min(end, memslot->userspace_addr + + (memslot->npages << PAGE_SHIFT)); + if (hva_start >= hva_end) + continue; + + /* + * {gfn(page) | page intersects with [hva_start, hva_end)} = + * {gfn_start, gfn_start+1, ..., gfn_end-1}. + */ + gfn = hva_to_gfn_memslot(hva_start, memslot); + gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); + + for (; gfn < gfn_end; ++gfn) { + gpa_t gpa = gfn << PAGE_SHIFT; + ret |= handler(kvm, gpa, data); + } + } + + return ret; +} + +static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + unmap_stage2_range(kvm, gpa, PAGE_SIZE); + return 0; +} + +int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) +{ + unsigned long end = hva + PAGE_SIZE; + + if (!kvm->arch.pgd) + return 0; + + trace_kvm_unmap_hva(hva); + handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL); + return 0; +} + +int kvm_unmap_hva_range(struct kvm *kvm, + unsigned long start, unsigned long end) +{ + if (!kvm->arch.pgd) + return 0; + + trace_kvm_unmap_hva_range(start, end); + handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); + return 0; +} + +static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pte_t *pte = (pte_t *)data; + + /* + * We can always call stage2_set_pte with KVM_S2PTE_FLAG_LOGGING_ACTIVE + * flag clear because MMU notifiers will have unmapped a huge PMD before + * calling ->change_pte() (which in turn calls kvm_set_spte_hva()) and + * therefore stage2_set_pte() never needs to clear out a huge PMD + * through this calling path. + */ + stage2_set_pte(kvm, NULL, gpa, pte, 0); + return 0; +} + + +void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) +{ + unsigned long end = hva + PAGE_SIZE; + pte_t stage2_pte; + + if (!kvm->arch.pgd) + return; + + trace_kvm_set_spte_hva(hva); + stage2_pte = pfn_pte(pte_pfn(pte), PAGE_S2); + handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte); +} + +static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) { /* THP, HugeTLB */ + if (pmd_young(*pmd)) { + *pmd = pmd_mkold(*pmd); + return 1; + } + + return 0; + } + + pte = pte_offset_kernel(pmd, gpa); + if (pte_none(*pte)) + return 0; + + if (pte_young(*pte)) { + *pte = pte_mkold(*pte); /* Just a page... */ + return 1; + } + + return 0; +} + +static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) /* THP, HugeTLB */ + return pmd_young(*pmd); + + pte = pte_offset_kernel(pmd, gpa); + if (!pte_none(*pte)) /* Just a page... */ + return pte_young(*pte); + + return 0; +} + +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) +{ + trace_kvm_age_hva(start, end); + return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL); +} + +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + trace_kvm_test_age_hva(hva); + return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL); +} + +void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu) +{ + mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); +} + +phys_addr_t kvm_mmu_get_httbr(void) +{ + if (__kvm_cpu_uses_extended_idmap()) + return virt_to_phys(merged_hyp_pgd); + else + return virt_to_phys(hyp_pgd); +} + +phys_addr_t kvm_mmu_get_boot_httbr(void) +{ + if (__kvm_cpu_uses_extended_idmap()) + return virt_to_phys(merged_hyp_pgd); + else + return virt_to_phys(boot_hyp_pgd); +} + +phys_addr_t kvm_get_idmap_vector(void) +{ + return hyp_idmap_vector; +} + +int kvm_mmu_init(void) +{ + int err; + + hyp_idmap_start = kvm_virt_to_phys(__hyp_idmap_text_start); + hyp_idmap_end = kvm_virt_to_phys(__hyp_idmap_text_end); + hyp_idmap_vector = kvm_virt_to_phys(__kvm_hyp_init); + + /* + * We rely on the linker script to ensure at build time that the HYP + * init code does not cross a page boundary. + */ + BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); + + hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order); + boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order); + + if (!hyp_pgd || !boot_hyp_pgd) { + kvm_err("Hyp mode PGD not allocated\n"); + err = -ENOMEM; + goto out; + } + + /* Create the idmap in the boot page tables */ + err = __create_hyp_mappings(boot_hyp_pgd, + hyp_idmap_start, hyp_idmap_end, + __phys_to_pfn(hyp_idmap_start), + PAGE_HYP); + + if (err) { + kvm_err("Failed to idmap %lx-%lx\n", + hyp_idmap_start, hyp_idmap_end); + goto out; + } + + if (__kvm_cpu_uses_extended_idmap()) { + merged_hyp_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!merged_hyp_pgd) { + kvm_err("Failed to allocate extra HYP pgd\n"); + goto out; + } + __kvm_extend_hypmap(boot_hyp_pgd, hyp_pgd, merged_hyp_pgd, + hyp_idmap_start); + return 0; + } + + /* Map the very same page at the trampoline VA */ + err = __create_hyp_mappings(boot_hyp_pgd, + TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE, + __phys_to_pfn(hyp_idmap_start), + PAGE_HYP); + if (err) { + kvm_err("Failed to map trampoline @%lx into boot HYP pgd\n", + TRAMPOLINE_VA); + goto out; + } + + /* Map the same page again into the runtime page tables */ + err = __create_hyp_mappings(hyp_pgd, + TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE, + __phys_to_pfn(hyp_idmap_start), + PAGE_HYP); + if (err) { + kvm_err("Failed to map trampoline @%lx into runtime HYP pgd\n", + TRAMPOLINE_VA); + goto out; + } + + return 0; +out: + free_hyp_pgds(); + return err; +} + +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + enum kvm_mr_change change) +{ + /* + * At this point memslot has been committed and there is an + * allocated dirty_bitmap[], dirty pages will be be tracked while the + * memory slot is write protected. + */ + if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) + kvm_mmu_wp_memory_region(kvm, mem->slot); +} + +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) +{ + hva_t hva = mem->userspace_addr; + hva_t reg_end = hva + mem->memory_size; + bool writable = !(mem->flags & KVM_MEM_READONLY); + int ret = 0; + + if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && + change != KVM_MR_FLAGS_ONLY) + return 0; + + /* + * Prevent userspace from creating a memory region outside of the IPA + * space addressable by the KVM guest IPA space. + */ + if (memslot->base_gfn + memslot->npages >= + (KVM_PHYS_SIZE >> PAGE_SHIFT)) + return -EFAULT; + + /* + * A memory region could potentially cover multiple VMAs, and any holes + * between them, so iterate over all of them to find out if we can map + * any of them right now. + * + * +--------------------------------------------+ + * +---------------+----------------+ +----------------+ + * | : VMA 1 | VMA 2 | | VMA 3 : | + * +---------------+----------------+ +----------------+ + * | memory region | + * +--------------------------------------------+ + */ + do { + struct vm_area_struct *vma = find_vma(current->mm, hva); + hva_t vm_start, vm_end; + + if (!vma || vma->vm_start >= reg_end) + break; + + /* + * Mapping a read-only VMA is only allowed if the + * memory region is configured as read-only. + */ + if (writable && !(vma->vm_flags & VM_WRITE)) { + ret = -EPERM; + break; + } + + /* + * Take the intersection of this VMA with the memory region + */ + vm_start = max(hva, vma->vm_start); + vm_end = min(reg_end, vma->vm_end); + + if (vma->vm_flags & VM_PFNMAP) { + gpa_t gpa = mem->guest_phys_addr + + (vm_start - mem->userspace_addr); + phys_addr_t pa = (vma->vm_pgoff << PAGE_SHIFT) + + vm_start - vma->vm_start; + + /* IO region dirty page logging not allowed */ + if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) + return -EINVAL; + + ret = kvm_phys_addr_ioremap(kvm, gpa, pa, + vm_end - vm_start, + writable); + if (ret) + break; + } + hva = vm_end; + } while (hva < reg_end); + + if (change == KVM_MR_FLAGS_ONLY) + return ret; + + spin_lock(&kvm->mmu_lock); + if (ret) + unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size); + else + stage2_flush_memslot(kvm, memslot); + spin_unlock(&kvm->mmu_lock); + return ret; +} + +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ +} + +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) +{ + /* + * Readonly memslots are not incoherent with the caches by definition, + * but in practice, they are used mostly to emulate ROMs or NOR flashes + * that the guest may consider devices and hence map as uncached. + * To prevent incoherency issues in these cases, tag all readonly + * regions as incoherent. + */ + if (slot->flags & KVM_MEM_READONLY) + slot->flags |= KVM_MEMSLOT_INCOHERENT; + return 0; +} + +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + +void kvm_arch_flush_shadow_all(struct kvm *kvm) +{ +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + gpa_t gpa = slot->base_gfn << PAGE_SHIFT; + phys_addr_t size = slot->npages << PAGE_SHIFT; + + spin_lock(&kvm->mmu_lock); + unmap_stage2_range(kvm, gpa, size); + spin_unlock(&kvm->mmu_lock); +} + +/* + * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). + * + * Main problems: + * - S/W ops are local to a CPU (not broadcast) + * - We have line migration behind our back (speculation) + * - System caches don't support S/W at all (damn!) + * + * In the face of the above, the best we can do is to try and convert + * S/W ops to VA ops. Because the guest is not allowed to infer the + * S/W to PA mapping, it can only use S/W to nuke the whole cache, + * which is a rather good thing for us. + * + * Also, it is only used when turning caches on/off ("The expected + * usage of the cache maintenance instructions that operate by set/way + * is associated with the cache maintenance instructions associated + * with the powerdown and powerup of caches, if this is required by + * the implementation."). + * + * We use the following policy: + * + * - If we trap a S/W operation, we enable VM trapping to detect + * caches being turned on/off, and do a full clean. + * + * - We flush the caches on both caches being turned on and off. + * + * - Once the caches are enabled, we stop trapping VM ops. + */ +void kvm_set_way_flush(struct kvm_vcpu *vcpu) +{ + unsigned long hcr = vcpu_get_hcr(vcpu); + + /* + * If this is the first time we do a S/W operation + * (i.e. HCR_TVM not set) flush the whole memory, and set the + * VM trapping. + * + * Otherwise, rely on the VM trapping to wait for the MMU + + * Caches to be turned off. At that point, we'll be able to + * clean the caches again. + */ + if (!(hcr & HCR_TVM)) { + trace_kvm_set_way_flush(*vcpu_pc(vcpu), + vcpu_has_cache_enabled(vcpu)); + stage2_flush_vm(vcpu->kvm); + vcpu_set_hcr(vcpu, hcr | HCR_TVM); + } +} + +void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled) +{ + bool now_enabled = vcpu_has_cache_enabled(vcpu); + + /* + * If switching the MMU+caches on, need to invalidate the caches. + * If switching it off, need to clean the caches. + * Clean + invalidate does the trick always. + */ + if (now_enabled != was_enabled) + stage2_flush_vm(vcpu->kvm); + + /* Caches are now on, stop trapping VM ops (until a S/W op) */ + if (now_enabled) + vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) & ~HCR_TVM); + + trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled); +} diff --git a/kernel/arch/arm/kvm/perf.c b/kernel/arch/arm/kvm/perf.c new file mode 100644 index 000000000..1a3849da0 --- /dev/null +++ b/kernel/arch/arm/kvm/perf.c @@ -0,0 +1,68 @@ +/* + * Based on the x86 implementation. + * + * Copyright (C) 2012 ARM Ltd. + * Author: Marc Zyngier + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include + +#include + +static int kvm_is_in_guest(void) +{ + return kvm_arm_get_running_vcpu() != NULL; +} + +static int kvm_is_user_mode(void) +{ + struct kvm_vcpu *vcpu; + + vcpu = kvm_arm_get_running_vcpu(); + + if (vcpu) + return !vcpu_mode_priv(vcpu); + + return 0; +} + +static unsigned long kvm_get_guest_ip(void) +{ + struct kvm_vcpu *vcpu; + + vcpu = kvm_arm_get_running_vcpu(); + + if (vcpu) + return *vcpu_pc(vcpu); + + return 0; +} + +static struct perf_guest_info_callbacks kvm_guest_cbs = { + .is_in_guest = kvm_is_in_guest, + .is_user_mode = kvm_is_user_mode, + .get_guest_ip = kvm_get_guest_ip, +}; + +int kvm_perf_init(void) +{ + return perf_register_guest_info_callbacks(&kvm_guest_cbs); +} + +int kvm_perf_teardown(void) +{ + return perf_unregister_guest_info_callbacks(&kvm_guest_cbs); +} diff --git a/kernel/arch/arm/kvm/psci.c b/kernel/arch/arm/kvm/psci.c new file mode 100644 index 000000000..e24f0461e --- /dev/null +++ b/kernel/arch/arm/kvm/psci.c @@ -0,0 +1,320 @@ +/* + * Copyright (C) 2012 - ARM Ltd + * Author: Marc Zyngier + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include +#include + +#include +#include +#include +#include + +/* + * This is an implementation of the Power State Coordination Interface + * as described in ARM document number ARM DEN 0022A. + */ + +#define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1) + +static unsigned long psci_affinity_mask(unsigned long affinity_level) +{ + if (affinity_level <= 3) + return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level); + + return 0; +} + +static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) +{ + /* + * NOTE: For simplicity, we make VCPU suspend emulation to be + * same-as WFI (Wait-for-interrupt) emulation. + * + * This means for KVM the wakeup events are interrupts and + * this is consistent with intended use of StateID as described + * in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A). + * + * Further, we also treat power-down request to be same as + * stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2 + * specification (ARM DEN 0022A). This means all suspend states + * for KVM will preserve the register state. + */ + kvm_vcpu_block(vcpu); + + return PSCI_RET_SUCCESS; +} + +static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pause = true; +} + +static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) +{ + struct kvm *kvm = source_vcpu->kvm; + struct kvm_vcpu *vcpu = NULL; + struct swait_head *wq; + unsigned long cpu_id; + unsigned long context_id; + phys_addr_t target_pc; + + cpu_id = *vcpu_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK; + if (vcpu_mode_is_32bit(source_vcpu)) + cpu_id &= ~((u32) 0); + + vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id); + + /* + * Make sure the caller requested a valid CPU and that the CPU is + * turned off. + */ + if (!vcpu) + return PSCI_RET_INVALID_PARAMS; + if (!vcpu->arch.pause) { + if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1) + return PSCI_RET_ALREADY_ON; + else + return PSCI_RET_INVALID_PARAMS; + } + + target_pc = *vcpu_reg(source_vcpu, 2); + context_id = *vcpu_reg(source_vcpu, 3); + + kvm_reset_vcpu(vcpu); + + /* Gracefully handle Thumb2 entry point */ + if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { + target_pc &= ~((phys_addr_t) 1); + vcpu_set_thumb(vcpu); + } + + /* Propagate caller endianness */ + if (kvm_vcpu_is_be(source_vcpu)) + kvm_vcpu_set_be(vcpu); + + *vcpu_pc(vcpu) = target_pc; + /* + * NOTE: We always update r0 (or x0) because for PSCI v0.1 + * the general puspose registers are undefined upon CPU_ON. + */ + *vcpu_reg(vcpu, 0) = context_id; + vcpu->arch.pause = false; + smp_mb(); /* Make sure the above is visible */ + + wq = kvm_arch_vcpu_wq(vcpu); + swait_wake_interruptible(wq); + + return PSCI_RET_SUCCESS; +} + +static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) +{ + int i; + unsigned long mpidr; + unsigned long target_affinity; + unsigned long target_affinity_mask; + unsigned long lowest_affinity_level; + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu *tmp; + + target_affinity = *vcpu_reg(vcpu, 1); + lowest_affinity_level = *vcpu_reg(vcpu, 2); + + /* Determine target affinity mask */ + target_affinity_mask = psci_affinity_mask(lowest_affinity_level); + if (!target_affinity_mask) + return PSCI_RET_INVALID_PARAMS; + + /* Ignore other bits of target affinity */ + target_affinity &= target_affinity_mask; + + /* + * If one or more VCPU matching target affinity are running + * then ON else OFF + */ + kvm_for_each_vcpu(i, tmp, kvm) { + mpidr = kvm_vcpu_get_mpidr_aff(tmp); + if (((mpidr & target_affinity_mask) == target_affinity) && + !tmp->arch.pause) { + return PSCI_0_2_AFFINITY_LEVEL_ON; + } + } + + return PSCI_0_2_AFFINITY_LEVEL_OFF; +} + +static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type) +{ + int i; + struct kvm_vcpu *tmp; + + /* + * The KVM ABI specifies that a system event exit may call KVM_RUN + * again and may perform shutdown/reboot at a later time that when the + * actual request is made. Since we are implementing PSCI and a + * caller of PSCI reboot and shutdown expects that the system shuts + * down or reboots immediately, let's make sure that VCPUs are not run + * after this call is handled and before the VCPUs have been + * re-initialized. + */ + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + tmp->arch.pause = true; + kvm_vcpu_kick(tmp); + } + + memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); + vcpu->run->system_event.type = type; + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + +static void kvm_psci_system_off(struct kvm_vcpu *vcpu) +{ + kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN); +} + +static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) +{ + kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET); +} + +int kvm_psci_version(struct kvm_vcpu *vcpu) +{ + if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) + return KVM_ARM_PSCI_0_2; + + return KVM_ARM_PSCI_0_1; +} + +static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) +{ + int ret = 1; + unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0); + unsigned long val; + + switch (psci_fn) { + case PSCI_0_2_FN_PSCI_VERSION: + /* + * Bits[31:16] = Major Version = 0 + * Bits[15:0] = Minor Version = 2 + */ + val = 2; + break; + case PSCI_0_2_FN_CPU_SUSPEND: + case PSCI_0_2_FN64_CPU_SUSPEND: + val = kvm_psci_vcpu_suspend(vcpu); + break; + case PSCI_0_2_FN_CPU_OFF: + kvm_psci_vcpu_off(vcpu); + val = PSCI_RET_SUCCESS; + break; + case PSCI_0_2_FN_CPU_ON: + case PSCI_0_2_FN64_CPU_ON: + val = kvm_psci_vcpu_on(vcpu); + break; + case PSCI_0_2_FN_AFFINITY_INFO: + case PSCI_0_2_FN64_AFFINITY_INFO: + val = kvm_psci_vcpu_affinity_info(vcpu); + break; + case PSCI_0_2_FN_MIGRATE_INFO_TYPE: + /* + * Trusted OS is MP hence does not require migration + * or + * Trusted OS is not present + */ + val = PSCI_0_2_TOS_MP; + break; + case PSCI_0_2_FN_SYSTEM_OFF: + kvm_psci_system_off(vcpu); + /* + * We should'nt be going back to guest VCPU after + * receiving SYSTEM_OFF request. + * + * If user space accidently/deliberately resumes + * guest VCPU after SYSTEM_OFF request then guest + * VCPU should see internal failure from PSCI return + * value. To achieve this, we preload r0 (or x0) with + * PSCI return value INTERNAL_FAILURE. + */ + val = PSCI_RET_INTERNAL_FAILURE; + ret = 0; + break; + case PSCI_0_2_FN_SYSTEM_RESET: + kvm_psci_system_reset(vcpu); + /* + * Same reason as SYSTEM_OFF for preloading r0 (or x0) + * with PSCI return value INTERNAL_FAILURE. + */ + val = PSCI_RET_INTERNAL_FAILURE; + ret = 0; + break; + default: + val = PSCI_RET_NOT_SUPPORTED; + break; + } + + *vcpu_reg(vcpu, 0) = val; + return ret; +} + +static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) +{ + unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0); + unsigned long val; + + switch (psci_fn) { + case KVM_PSCI_FN_CPU_OFF: + kvm_psci_vcpu_off(vcpu); + val = PSCI_RET_SUCCESS; + break; + case KVM_PSCI_FN_CPU_ON: + val = kvm_psci_vcpu_on(vcpu); + break; + default: + val = PSCI_RET_NOT_SUPPORTED; + break; + } + + *vcpu_reg(vcpu, 0) = val; + return 1; +} + +/** + * kvm_psci_call - handle PSCI call if r0 value is in range + * @vcpu: Pointer to the VCPU struct + * + * Handle PSCI calls from guests through traps from HVC instructions. + * The calling convention is similar to SMC calls to the secure world + * where the function number is placed in r0. + * + * This function returns: > 0 (success), 0 (success but exit to user + * space), and < 0 (errors) + * + * Errors: + * -EINVAL: Unrecognized PSCI function + */ +int kvm_psci_call(struct kvm_vcpu *vcpu) +{ + switch (kvm_psci_version(vcpu)) { + case KVM_ARM_PSCI_0_2: + return kvm_psci_0_2_call(vcpu); + case KVM_ARM_PSCI_0_1: + return kvm_psci_0_1_call(vcpu); + default: + return -EINVAL; + }; +} diff --git a/kernel/arch/arm/kvm/reset.c b/kernel/arch/arm/kvm/reset.c new file mode 100644 index 000000000..f558c073c --- /dev/null +++ b/kernel/arch/arm/kvm/reset.c @@ -0,0 +1,83 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include + +/****************************************************************************** + * Cortex-A15 and Cortex-A7 Reset Values + */ + +static struct kvm_regs cortexa_regs_reset = { + .usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT, +}; + +static const struct kvm_irq_level cortexa_vtimer_irq = { + { .irq = 27 }, + .level = 1, +}; + + +/******************************************************************************* + * Exported reset function + */ + +/** + * kvm_reset_vcpu - sets core registers and cp15 registers to reset value + * @vcpu: The VCPU pointer + * + * This function finds the right table above and sets the registers on the + * virtual CPU struct to their architectually defined reset values. + */ +int kvm_reset_vcpu(struct kvm_vcpu *vcpu) +{ + struct kvm_regs *reset_regs; + const struct kvm_irq_level *cpu_vtimer_irq; + + switch (vcpu->arch.target) { + case KVM_ARM_TARGET_CORTEX_A7: + case KVM_ARM_TARGET_CORTEX_A15: + reset_regs = &cortexa_regs_reset; + vcpu->arch.midr = read_cpuid_id(); + cpu_vtimer_irq = &cortexa_vtimer_irq; + break; + default: + return -ENODEV; + } + + /* Reset core registers */ + memcpy(&vcpu->arch.regs, reset_regs, sizeof(vcpu->arch.regs)); + + /* Reset CP15 registers */ + kvm_reset_coprocs(vcpu); + + /* Reset arch_timer context */ + kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq); + + return 0; +} diff --git a/kernel/arch/arm/kvm/trace.h b/kernel/arch/arm/kvm/trace.h new file mode 100644 index 000000000..0ec35392d --- /dev/null +++ b/kernel/arch/arm/kvm/trace.h @@ -0,0 +1,328 @@ +#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVM_H + +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm + +/* + * Tracepoints for entry/exit to guest + */ +TRACE_EVENT(kvm_entry, + TP_PROTO(unsigned long vcpu_pc), + TP_ARGS(vcpu_pc), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + ), + + TP_printk("PC: 0x%08lx", __entry->vcpu_pc) +); + +TRACE_EVENT(kvm_exit, + TP_PROTO(unsigned int exit_reason, unsigned long vcpu_pc), + TP_ARGS(exit_reason, vcpu_pc), + + TP_STRUCT__entry( + __field( unsigned int, exit_reason ) + __field( unsigned long, vcpu_pc ) + ), + + TP_fast_assign( + __entry->exit_reason = exit_reason; + __entry->vcpu_pc = vcpu_pc; + ), + + TP_printk("HSR_EC: 0x%04x, PC: 0x%08lx", + __entry->exit_reason, + __entry->vcpu_pc) +); + +TRACE_EVENT(kvm_guest_fault, + TP_PROTO(unsigned long vcpu_pc, unsigned long hsr, + unsigned long hxfar, + unsigned long long ipa), + TP_ARGS(vcpu_pc, hsr, hxfar, ipa), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( unsigned long, hsr ) + __field( unsigned long, hxfar ) + __field( unsigned long long, ipa ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->hsr = hsr; + __entry->hxfar = hxfar; + __entry->ipa = ipa; + ), + + TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx", + __entry->ipa, __entry->hsr, + __entry->hxfar, __entry->vcpu_pc) +); + +TRACE_EVENT(kvm_access_fault, + TP_PROTO(unsigned long ipa), + TP_ARGS(ipa), + + TP_STRUCT__entry( + __field( unsigned long, ipa ) + ), + + TP_fast_assign( + __entry->ipa = ipa; + ), + + TP_printk("IPA: %lx", __entry->ipa) +); + +TRACE_EVENT(kvm_irq_line, + TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level), + TP_ARGS(type, vcpu_idx, irq_num, level), + + TP_STRUCT__entry( + __field( unsigned int, type ) + __field( int, vcpu_idx ) + __field( int, irq_num ) + __field( int, level ) + ), + + TP_fast_assign( + __entry->type = type; + __entry->vcpu_idx = vcpu_idx; + __entry->irq_num = irq_num; + __entry->level = level; + ), + + TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d", + (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" : + (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" : + (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN", + __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level) +); + +TRACE_EVENT(kvm_mmio_emulate, + TP_PROTO(unsigned long vcpu_pc, unsigned long instr, + unsigned long cpsr), + TP_ARGS(vcpu_pc, instr, cpsr), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( unsigned long, instr ) + __field( unsigned long, cpsr ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->instr = instr; + __entry->cpsr = cpsr; + ), + + TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)", + __entry->vcpu_pc, __entry->instr, __entry->cpsr) +); + +/* Architecturally implementation defined CP15 register access */ +TRACE_EVENT(kvm_emulate_cp15_imp, + TP_PROTO(unsigned long Op1, unsigned long Rt1, unsigned long CRn, + unsigned long CRm, unsigned long Op2, bool is_write), + TP_ARGS(Op1, Rt1, CRn, CRm, Op2, is_write), + + TP_STRUCT__entry( + __field( unsigned int, Op1 ) + __field( unsigned int, Rt1 ) + __field( unsigned int, CRn ) + __field( unsigned int, CRm ) + __field( unsigned int, Op2 ) + __field( bool, is_write ) + ), + + TP_fast_assign( + __entry->is_write = is_write; + __entry->Op1 = Op1; + __entry->Rt1 = Rt1; + __entry->CRn = CRn; + __entry->CRm = CRm; + __entry->Op2 = Op2; + ), + + TP_printk("Implementation defined CP15: %s\tp15, %u, r%u, c%u, c%u, %u", + (__entry->is_write) ? "mcr" : "mrc", + __entry->Op1, __entry->Rt1, __entry->CRn, + __entry->CRm, __entry->Op2) +); + +TRACE_EVENT(kvm_wfx, + TP_PROTO(unsigned long vcpu_pc, bool is_wfe), + TP_ARGS(vcpu_pc, is_wfe), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( bool, is_wfe ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->is_wfe = is_wfe; + ), + + TP_printk("guest executed wf%c at: 0x%08lx", + __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc) +); + +TRACE_EVENT(kvm_unmap_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva) +); + +TRACE_EVENT(kvm_unmap_hva_range, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field( unsigned long, start ) + __field( unsigned long, end ) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("mmu notifier unmap range: %#08lx -- %#08lx", + __entry->start, __entry->end) +); + +TRACE_EVENT(kvm_set_spte_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva) +); + +TRACE_EVENT(kvm_age_hva, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field( unsigned long, start ) + __field( unsigned long, end ) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("mmu notifier age hva: %#08lx -- %#08lx", + __entry->start, __entry->end) +); + +TRACE_EVENT(kvm_test_age_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("mmu notifier test age hva: %#08lx", __entry->hva) +); + +TRACE_EVENT(kvm_hvc, + TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), + TP_ARGS(vcpu_pc, r0, imm), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( unsigned long, r0 ) + __field( unsigned long, imm ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->r0 = r0; + __entry->imm = imm; + ), + + TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx", + __entry->vcpu_pc, __entry->r0, __entry->imm) +); + +TRACE_EVENT(kvm_set_way_flush, + TP_PROTO(unsigned long vcpu_pc, bool cache), + TP_ARGS(vcpu_pc, cache), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( bool, cache ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->cache = cache; + ), + + TP_printk("S/W flush at 0x%016lx (cache %s)", + __entry->vcpu_pc, __entry->cache ? "on" : "off") +); + +TRACE_EVENT(kvm_toggle_cache, + TP_PROTO(unsigned long vcpu_pc, bool was, bool now), + TP_ARGS(vcpu_pc, was, now), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( bool, was ) + __field( bool, now ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->was = was; + __entry->now = now; + ), + + TP_printk("VM op at 0x%016lx (cache was %s, now %s)", + __entry->vcpu_pc, __entry->was ? "on" : "off", + __entry->now ? "on" : "off") +); + +#endif /* _TRACE_KVM_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH arch/arm/kvm +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* This part must be outside protection */ +#include -- cgit 1.2.3-korg