接前一篇文章:
本文内容参考:
《 QEMU /KVM》 源码 解析与应用 —— 李强,机械工业出版社
《深度探索 Linux 系统 虚拟化 原理与实现》—— 王柏生 谢广军, 机械工业出版社
特此致谢!
三、KVM模块初始化介绍
2. KVM模块初始化
上一回开始对于kvm_init函数进行解析。讲解了第1个函数kvm_arch_init。本回继续往下进行讲解。为了便于理解和回顾,再次贴出kvm_init的源码,在Linux内核源码根目录/virt/kvm/kvm_main.c中,代码如下:
- int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
- struct module *module)
- {
- struct kvm_cpu_compat_check c;
- int r;
- int cpu;
-
- r = kvm_arch_init(opaque);
- if (r)
- goto out_fail;
-
- /*
- * kvm_arch_init makes sure there's at most one caller
- * for architectures that support multiple implementations,
- * like intel and amd on x86.
- * kvm_arch_init must be called before kvm_irqfd_init to avoid creating
- * conflicts in case kvm is already setup for another implementation.
- */
- r = kvm_irqfd_init();
- if (r)
- goto out_irqfd;
-
- if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
- r = -ENOMEM;
- goto out_free_0;
- }
-
- r = kvm_arch_hardware_setup(opaque);
- if (r < 0)
- goto out_free_1;
-
- c.ret = &r;
- c.opaque = opaque;
- for_each_online_cpu(cpu) {
- smp_call_function_single(cpu, check_processor_compat, &c, 1);
- if (r < 0)
- goto out_free_2;
- }
-
- r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting",
- kvm_starting_cpu, kvm_dying_cpu);
- if (r)
- goto out_free_2;
- register_reboot_notifier(&kvm_reboot_notifier);
-
- /* A kmem cache lets us meet the alignment requirements of fx_save. */
- if (!vcpu_align)
- vcpu_align = __alignof__(struct kvm_vcpu);
- kvm_vcpu_cache =
- kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align,
- SLAB_ACCOUNT,
- offsetof(struct kvm_vcpu, arch),
- offsetofend(struct kvm_vcpu, stats_id)
- - offsetof(struct kvm_vcpu, arch),
- NULL);
- if (!kvm_vcpu_cache) {
- r = -ENOMEM;
- goto out_free_3;
- }
-
- for_each_possible_cpu(cpu) {
- if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu),
- GFP_KERNEL, cpu_to_node(cpu))) {
- r = -ENOMEM;
- goto out_free_4;
- }
- }
-
- r = kvm_async_pf_init();
- if (r)
- goto out_free_4;
-
- kvm_chardev_ops.owner = module;
-
- r = misc_register(&kvm_dev);
- if (r) {
- pr_err("kvm: misc device register failed\n");
- goto out_unreg;
- }
-
- register_syscore_ops(&kvm_syscore_ops);
-
- kvm_preempt_ops.sched_in = kvm_sched_in;
- kvm_preempt_ops.sched_out = kvm_sched_out;
-
- kvm_init_debug();
-
- r = kvm_vfio_ops_init();
- WARN_ON(r);
-
- return 0;
-
- out_unreg:
- kvm_async_pf_deinit();
- out_free_4:
- for_each_possible_cpu(cpu)
- free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
- kmem_cache_destroy(kvm_vcpu_cache);
- out_free_3:
- unregister_reboot_notifier(&kvm_reboot_notifier);
- cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
- out_free_2:
- kvm_arch_hardware_unsetup();
- out_free_1:
- free_cpumask_var(cpus_hardware_enabled);
- out_free_0:
- kvm_irqfd_exit();
- out_irqfd:
- kvm_arch_exit();
- out_fail:
- return r;
- }
- EXPORT_SYMBOL_GPL(kvm_init);
kvm_init函数总体调用的函数如下图所示:
(2)kvm_irqfd_init函数
代码片段如下:
- /*
- * kvm_arch_init makes sure there's at most one caller
- * for architectures that support multiple implementations,
- * like intel and amd on x86.
- * kvm_arch_init must be called before kvm_irqfd_init to avoid creating
- * conflicts in case kvm is already setup for another implementation.
- */
- r = kvm_irqfd_init();
- if (r)
- goto out_irqfd;
该函数相关的声明在Linux内核源码根目录/include/linux/kvm_host.h中,如下:
- #ifdef CONFIG_HAVE_KVM_IRQFD
- int kvm_irqfd_init(void);
- void kvm_irqfd_exit(void);
- #else
- static inline int kvm_irqfd_init(void)
- {
- return 0;
- }
-
- static inline void kvm_irqfd_exit(void)
- {
- }
- #endif
可以看到,这是一个可以配置的函数。只有当配置了CONFIG_HAVE_KVM_IRQFD时,该函数才有实际内容,否则就是一个空函数。
配置有效的kvm_irqfd_init函数在Linux内核源码根目录/virt/kvm/eventfd.c中,代码如下:
- /*
- * create a host-wide workqueue for issuing deferred shutdown requests
- * aggregated from all vm* instances. We need our own isolated
- * queue to ease flushing work items when a VM exits.
- */
- int kvm_irqfd_init(void)
- {
- irqfd_cleanup_wq = alloc_workqueue("kvm-irqfd-cleanup", 0, 0);
- if (!irqfd_cleanup_wq)
- return -ENOMEM;
-
- return 0;
- }
-
- void kvm_irqfd_exit(void)
- {
- destroy_workqueue(irqfd_cleanup_wq);
- }
这里要讲解一下QEMU/KVM的irqfd机制。参考以下博文:
https://www.cnblogs.com/haiyonghao/p/14440723.html
QEMU/KVM的irqfd机制
irqfd机制与ioeventfd机制类似,其基本原理都是基于eventfd。ioeventfd机制为Guest提供了向QEMU/KVM发送通知的快捷通道(Guest -> QEMU/KVM);对应地,irqfd机制提供了QEMU/KVM向Guest发送通知的快捷通道(QEMU/KVM -> Guest)。
irqfd机制将一个eventfd与一个全局中断号联系起来,当向这个eventfd发送信号时,就会导致对应的中断注入到 虚拟机 中。
QEMU注册irqfd
与ioeventfd类似,irqfd在使用前必须先初始化一个EventNotifier对象(利用event_notifier_init函数初始化),初始化EventNotifier对象完成之后获得了一个eventfd。
向kvm发送注册中断irqfd请求
获得一个eventfd之后,QEMU通过kvm_irqchip_add_irqfd_notifier_gsi=>kvm_irqchip_assign_irqfd构造kvm_irqchip结构,并向kvm发送ioctl(KVM_IRQFD)。
- static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int rfd, int virq,
- bool assign)
- {
- struct kvm_irqfd irqfd = {
- .fd = fd,
- .gsi = virq,
- .flags = assign ? 0 : KVM_IRQFD_FLAG_DEASSIGN,
- };
-
- if (rfd != -1) {
- irqfd.flags |= KVM_IRQFD_FLAG_RESAMPLE;
- irqfd.resamplefd = rfd;
- }
-
- if (!kvm_irqfds_enabled()) {
- return -ENOSYS;
- }
-
- return kvm_vm_ioctl(s, KVM_IRQFD, &irqfd);
- }
在kvm_irqchip_assign_irqfd函数中,首先构造了一个kvm_irqfd结构的变量irqfd,其中fd为之前初始化的eventfd,gsi是全局系统中断,flags中定义了是向kvm注册irqfd(flags=0)还是解除注册irqfd(KVM_IRQFD_FLAG_DEASSIGN)(也就是flags=1)。flags的bit1(KVM_IRQFD_FLAG_RESAMPLE)表明该中断是否为电平触发。
- KVM_IRQFD_FLAG_RESAMPLE相关信息
当中断处于沿触发模式时,irqfd->fd连接kvm中的中断芯片(irqchip)的gsi管脚,也由irqfd->fd负责中断的toggle,以及对用户空间的handler的触发。
当中断处于电平触发模式时,同样irqfd->fd连接kvm中的中断芯片的gsi管脚,当中断芯片收到一个EOI(end of interrupt)重采样信号时,gsi进行电平翻转,对用户空间的通知由irqfd->resample_fd完成(resample_fd也是一个eventfd)。
kvm_irqchip_assign_irqfd最后调用kvm_vm_ioctl(s, KVM_IRQFD, &irqfd),向kvm请求注册包含上面构造的kvm_irqfd信息的irqfd。
kvm注册irqfd
收到ioctl(KVM_IRQFD)之后,KVM首先获取传入的数据结构kvm_irqfd的信息,然后调用kvm_irqfd函数。
- case KVM_IRQFD: {
- struct kvm_irqfd data;
-
- r = -EFAULT;
- if (copy_from_user(&data, argp, sizeof(data)))
- goto out;
- r = kvm_irqfd(kvm, &data);
- break;
- }
在kvm_irqfd函数中,首先分辨传入的kvm_irqfd结构中的flags的bit0要求的是进行irqfd注册还是解除irqfd的注册。irqfd注册调用kvm_irqfd_assign函数;解除注册都调用kvm_irqfd_deasign函数。
- int
- kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
- {
- if (args->flags & ~(KVM_IRQFD_FLAG_DEASSIGN | KVM_IRQFD_FLAG_RESAMPLE))
- return -EINVAL;
-
- if (args->flags & KVM_IRQFD_FLAG_DEASSIGN)
- return kvm_irqfd_deassign(kvm, args);
-
- return kvm_irqfd_assign(kvm, args);
- }
kvm_irqfd_assign函数在同文件(Linux内核源码根目录/virt/kvm/eventfd.c)中,代码如下:
- static int
- kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
- {
- struct kvm_kernel_irqfd *irqfd, *tmp;
- struct fd f;
- struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
- int ret;
- __poll_t events;
- int idx;
-
- if (!kvm_arch_intc_initialized(kvm))
- return -EAGAIN;
-
- if (!kvm_arch_irqfd_allowed(kvm, args))
- return -EINVAL;
-
- irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL_ACCOUNT);
- if (!irqfd)
- return -ENOMEM;
-
- irqfd->kvm = kvm;
- irqfd->gsi = args->gsi;
- INIT_LIST_HEAD(&irqfd->list);
- INIT_WORK(&irqfd->inject, irqfd_inject);
- INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
- seqcount_spinlock_init(&irqfd->irq_entry_sc, &kvm->irqfds.lock);
-
- f = fdget(args->fd);
- if (!f.file) {
- ret = -EBADF;
- goto out;
- }
-
- eventfd = eventfd_ctx_fileget(f.file);
- if (IS_ERR(eventfd)) {
- ret = PTR_ERR(eventfd);
- goto fail;
- }
-
- irqfd->eventfd = eventfd;
-
- if (args->flags & KVM_IRQFD_FLAG_RESAMPLE) {
- struct kvm_kernel_irqfd_resampler *resampler;
-
- resamplefd = eventfd_ctx_fdget(args->resamplefd);
- if (IS_ERR(resamplefd)) {
- ret = PTR_ERR(resamplefd);
- goto fail;
- }
-
- irqfd->resamplefd = resamplefd;
- INIT_LIST_HEAD(&irqfd->resampler_link);
-
- mutex_lock(&kvm->irqfds.resampler_lock);
-
- list_for_each_entry(resampler,
- &kvm->irqfds.resampler_list, link) {
- if (resampler->notifier.gsi == irqfd->gsi) {
- irqfd->resampler = resampler;
- break;
- }
- }
-
- if (!irqfd->resampler) {
- resampler = kzalloc(sizeof(*resampler),
- GFP_KERNEL_ACCOUNT);
- if (!resampler) {
- ret = -ENOMEM;
- mutex_unlock(&kvm->irqfds.resampler_lock);
- goto fail;
- }
-
- resampler->kvm = kvm;
- INIT_LIST_HEAD(&resampler->list);
- resampler->notifier.gsi = irqfd->gsi;
- resampler->notifier.irq_acked = irqfd_resampler_ack;
- INIT_LIST_HEAD(&resampler->link);
-
- list_add(&resampler->link, &kvm->irqfds.resampler_list);
- kvm_register_irq_ack_notifier(kvm,
- &resampler->notifier);
- irqfd->resampler = resampler;
- }
-
- list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
- synchronize_srcu(&kvm->irq_srcu);
-
- mutex_unlock(&kvm->irqfds.resampler_lock);
- }
-
- /*
- * Install our own custom wake-up handling so we are notified via
- * a callback whenever someone signals the underlying eventfd
- */
- init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup);
- init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc);
-
- spin_lock_irq(&kvm->irqfds.lock);
-
- ret = 0;
- list_for_each_entry(tmp, &kvm->irqfds.items, list) {
- if (irqfd->eventfd != tmp->eventfd)
- continue;
- /* This fd is used for another irq already. */
- ret = -EBUSY;
- spin_unlock_irq(&kvm->irqfds.lock);
- goto fail;
- }
-
- idx = srcu_read_lock(&kvm->irq_srcu);
- irqfd_update(kvm, irqfd);
-
- list_add_tail(&irqfd->list, &kvm->irqfds.items);
-
- spin_unlock_irq(&kvm->irqfds.lock);
-
- /*
- * Check if there was an event already pending on the eventfd
- * before we registered, and trigger it as if we didn't miss it.
- */
- events = vfs_poll(f.file, &irqfd->pt);
-
- if (events & EPOLLIN)
- schedule_work(&irqfd->inject);
-
- #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
- if (kvm_arch_has_irq_bypass()) {
- irqfd->consumer.token = (void *)irqfd->eventfd;
- irqfd->consumer.add_producer = kvm_arch_irq_bypass_add_producer;
- irqfd->consumer.del_producer = kvm_arch_irq_bypass_del_producer;
- irqfd->consumer.stop = kvm_arch_irq_bypass_stop;
- irqfd->consumer.start = kvm_arch_irq_bypass_start;
- ret = irq_bypass_register_consumer(&irqfd->consumer);
- if (ret)
- pr_info("irq bypass consumer (token %p) registration fails: %d\n",
- irqfd->consumer.token, ret);
- }
- #endif
-
- srcu_read_unlock(&kvm->irq_srcu, idx);
-
- /*
- * do not drop the file until the irqfd is fully initialized, otherwise
- * we might race against the EPOLLHUP
- */
- fdput(f);
- return 0;
-
- fail:
- if (irqfd->resampler)
- irqfd_resampler_shutdown(irqfd);
-
- if (resamplefd && !IS_ERR(resamplefd))
- eventfd_ctx_put(resamplefd);
-
- if (eventfd && !IS_ERR(eventfd))
- eventfd_ctx_put(eventfd);
-
- fdput(f);
-
- out:
- kfree(irqfd);
- return ret;
- }
在kvm_irqfd_assign函数中,首先申请了一个kvm_kernel_irqfd结构类型的变量irqfd,并为之分配空间,之后对irqfd的各子域进行赋值。代码片段如下:
- irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL_ACCOUNT);
- if (!irqfd)
- return -ENOMEM;
-
- irqfd->kvm = kvm;
- irqfd->gsi = args->gsi;
- INIT_LIST_HEAD(&irqfd->list);
- INIT_WORK(&irqfd->inject, irqfd_inject);
- INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
- seqcount_spinlock_init(&irqfd->irq_entry_sc, &kvm->irqfds.lock);
kvm_kernel_irqfd结构中有2个work_struct,inject和shutdown,分别负责触发中断和关闭中断,这两个work_struct各自对应的操作函数分别为irqfd_inject和irqfd_shutdown。
kvm_irq_assign调用init_waitqueue_func_entry函数将 irqfd_wakeup 函数注册为irqfd中 等待队列entry 激活时的处理函数。 这样任何写入该irqfd对应的eventfd的行为都将导致触发这个函数。
然后,kvm_irq_assign函数利用init_poll_funcptr将irqfd_ptable_queue_proc函数注册为irqfd中的poll table的处理函数。 irqfd_ptable_queue_proc会将poll table中对应的wait queue entry加入到waitqueue中去 。代码片段如下:
- /*
- * Install our own custom wake-up handling so we are notified via
- * a callback whenever someone signals the underlying eventfd
- */
- init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup);
- init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc);
kvm_irq_assign接着判断该eventfd是否已经被其它中断使用。代码片段如下:
- ret = 0;
- list_for_each_entry(tmp, &kvm->irqfds.items, list) {
- if (irqfd->eventfd != tmp->eventfd)
- continue;
- /* This fd is used for another irq already. */
- ret = -EBUSY;
- spin_unlock_irq(&kvm->irqfds.lock);
- goto fail;
- }
kvm_irq_assign函数以irqfd->pt为参数,调用eventfd的poll函数,也就是eventfd_poll,后者会调用poll_wait函数,也就是之前为poll table注册的irqfd_ptable_queue_proc函数。irqfd_ptable_queue_proc将irqfd->wait加入到了eventfd的wqh等待队列中。这样,当有其它进程或者内核对eventfd进行write时,就会导致eventfd的wqh等待队列上的对象函数得到执行,也就是irqfd_wakeup函数。
这里只讨论有数据,即flgas中的EPOLLIN置位时,会调用kvm_arch_set_irq_inatomic进行中断注入。
kvm_arch_set_irq_inatomic =>
kvm_set_msi_irq =>
kvm_irq_delivery_to_apic_fast
如果kvm_arch_set_irq_inatomic无法注入中断(即非MSI中断或非HV_SINT中断),那么就调用irqfd->inject,即调用irqfd_inject函数。
- static void irqfd_inject(struct work_struct *work)
- {
- struct kvm_kernel_irqfd *irqfd =
- container_of(work, struct kvm_kernel_irqfd, inject);
- struct kvm *kvm = irqfd->kvm;
-
- if (!irqfd->resampler) {
- kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1,
- false);
- kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0,
- false);
- } else
- kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
- irqfd->gsi, 1, false);
- }
在irqfd_inject函数中,如果该irqfd配置的中断为边沿触发,则调用两次kvm_set_irq,形成一个中断脉冲,以便KVM中的中断芯片(irqchip)能够感知到这个中断。如果该irqfd配置的中断为电平触发,则调用一次kvm_set_irq,将中断拉至高电平,使irqchip感知到,电平触发的中断信号拉低动作会由后续的irqchip的EOI触发。
总结
irqfd基于eventfd机制,qemu中将一个gsi(全局系统中断号)与eventfd捆绑后,向KVM发送注册irqfd请求。KVM收到请求后将带有gsi信息的eventfd加入到与irqfd有关的等待队列中,一旦有进程向该eventfd写入,等待队列中的元素就会唤醒,并调用相应唤醒函数(irqfd_wakeup)向Guest注入中断,而 注入中断 这一步骤相关知识与特定的中断芯片如PIC、APIC有关。
至此,kvm_arch_init函数的第2个函数kvm_irqfd_init函数就解析完了。下一回继续往下解析kvm_arch_init函数。