diff options
Diffstat (limited to 'virt')
| -rw-r--r-- | virt/kvm/Kconfig | 3 | ||||
| -rw-r--r-- | virt/kvm/assigned-dev.c | 12 | ||||
| -rw-r--r-- | virt/kvm/coalesced_mmio.c | 43 | ||||
| -rw-r--r-- | virt/kvm/coalesced_mmio.h | 15 | ||||
| -rw-r--r-- | virt/kvm/eventfd.c | 39 | ||||
| -rw-r--r-- | virt/kvm/ioapic.c | 38 | ||||
| -rw-r--r-- | virt/kvm/ioapic.h | 2 | ||||
| -rw-r--r-- | virt/kvm/iommu.c | 36 | ||||
| -rw-r--r-- | virt/kvm/irq_comm.c | 6 | ||||
| -rw-r--r-- | virt/kvm/kvm_main.c | 392 |
10 files changed, 404 insertions, 182 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index daece36..7f1178f 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -12,3 +12,6 @@ config HAVE_KVM_EVENTFD config KVM_APIC_ARCHITECTURE bool + +config KVM_MMIO + bool diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index f73de63..057e2cc 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -504,12 +504,12 @@ out: static int kvm_vm_ioctl_assign_device(struct kvm *kvm, struct kvm_assigned_pci_dev *assigned_dev) { - int r = 0; + int r = 0, idx; struct kvm_assigned_dev_kernel *match; struct pci_dev *dev; mutex_lock(&kvm->lock); - down_read(&kvm->slots_lock); + idx = srcu_read_lock(&kvm->srcu); match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, assigned_dev->assigned_dev_id); @@ -526,7 +526,8 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, r = -ENOMEM; goto out; } - dev = pci_get_bus_and_slot(assigned_dev->busnr, + dev = pci_get_domain_bus_and_slot(assigned_dev->segnr, + assigned_dev->busnr, assigned_dev->devfn); if (!dev) { printk(KERN_INFO "%s: host device not found\n", __func__); @@ -548,6 +549,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, pci_reset_function(dev); match->assigned_dev_id = assigned_dev->assigned_dev_id; + match->host_segnr = assigned_dev->segnr; match->host_busnr = assigned_dev->busnr; match->host_devfn = assigned_dev->devfn; match->flags = assigned_dev->flags; @@ -573,7 +575,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, } out: - up_read(&kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, idx); mutex_unlock(&kvm->lock); return r; out_list_del: @@ -585,7 +587,7 @@ out_put: pci_dev_put(dev); out_free: kfree(match); - up_read(&kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, idx); mutex_unlock(&kvm->lock); return r; } diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 04d69cd..5169736 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -92,41 +92,64 @@ static const struct kvm_io_device_ops coalesced_mmio_ops = { int kvm_coalesced_mmio_init(struct kvm *kvm) { struct kvm_coalesced_mmio_dev *dev; + struct page *page; int ret; + ret = -ENOMEM; + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + goto out_err; + kvm->coalesced_mmio_ring = page_address(page); + + ret = -ENOMEM; dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL); if (!dev) - return -ENOMEM; + goto out_free_page; spin_lock_init(&dev->lock); kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops); dev->kvm = kvm; kvm->coalesced_mmio_dev = dev; - ret = kvm_io_bus_register_dev(kvm, &kvm->mmio_bus, &dev->dev); + mutex_lock(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, &dev->dev); + mutex_unlock(&kvm->slots_lock); if (ret < 0) - kfree(dev); + goto out_free_dev; + + return ret; +out_free_dev: + kfree(dev); +out_free_page: + __free_page(page); +out_err: return ret; } +void kvm_coalesced_mmio_free(struct kvm *kvm) +{ + if (kvm->coalesced_mmio_ring) + free_page((unsigned long)kvm->coalesced_mmio_ring); +} + int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, - struct kvm_coalesced_mmio_zone *zone) + struct kvm_coalesced_mmio_zone *zone) { struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev; if (dev == NULL) return -EINVAL; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) { - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return -ENOBUFS; } dev->zone[dev->nb_zones] = *zone; dev->nb_zones++; - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return 0; } @@ -140,10 +163,10 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, if (dev == NULL) return -EINVAL; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); i = dev->nb_zones; - while(i) { + while (i) { z = &dev->zone[i - 1]; /* unregister all zones @@ -158,7 +181,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, i--; } - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return 0; } diff --git a/virt/kvm/coalesced_mmio.h b/virt/kvm/coalesced_mmio.h index 4b49f27..8a5959e 100644 --- a/virt/kvm/coalesced_mmio.h +++ b/virt/kvm/coalesced_mmio.h @@ -1,3 +1,6 @@ +#ifndef __KVM_COALESCED_MMIO_H__ +#define __KVM_COALESCED_MMIO_H__ + /* * KVM coalesced MMIO * @@ -7,6 +10,8 @@ * */ +#ifdef CONFIG_KVM_MMIO + #define KVM_COALESCED_MMIO_ZONE_MAX 100 struct kvm_coalesced_mmio_dev { @@ -18,7 +23,17 @@ struct kvm_coalesced_mmio_dev { }; int kvm_coalesced_mmio_init(struct kvm *kvm); +void kvm_coalesced_mmio_free(struct kvm *kvm); int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone); int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone); + +#else + +static inline int kvm_coalesced_mmio_init(struct kvm *kvm) { return 0; } +static inline void kvm_coalesced_mmio_free(struct kvm *kvm) { } + +#endif + +#endif diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 30f70fd..7016319 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -47,7 +47,6 @@ struct _irqfd { int gsi; struct list_head list; poll_table pt; - wait_queue_head_t *wqh; wait_queue_t wait; struct work_struct inject; struct work_struct shutdown; @@ -72,12 +71,13 @@ static void irqfd_shutdown(struct work_struct *work) { struct _irqfd *irqfd = container_of(work, struct _irqfd, shutdown); + u64 cnt; /* * Synchronize with the wait-queue and unhook ourselves to prevent * further events. */ - remove_wait_queue(irqfd->wqh, &irqfd->wait); + eventfd_ctx_remove_wait_queue(irqfd->eventfd, &irqfd->wait, &cnt); /* * We know no new events will be scheduled at this point, so block @@ -158,15 +158,13 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh, poll_table *pt) { struct _irqfd *irqfd = container_of(pt, struct _irqfd, pt); - - irqfd->wqh = wqh; add_wait_queue(wqh, &irqfd->wait); } static int kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi) { - struct _irqfd *irqfd; + struct _irqfd *irqfd, *tmp; struct file *file = NULL; struct eventfd_ctx *eventfd = NULL; int ret; @@ -203,9 +201,20 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi) 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; + } + events = file->f_op->poll(file, &irqfd->pt); - spin_lock_irq(&kvm->irqfds.lock); list_add_tail(&irqfd->list, &kvm->irqfds.items); spin_unlock_irq(&kvm->irqfds.lock); @@ -451,7 +460,7 @@ static int kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { int pio = args->flags & KVM_IOEVENTFD_FLAG_PIO; - struct kvm_io_bus *bus = pio ? &kvm->pio_bus : &kvm->mmio_bus; + enum kvm_bus bus_idx = pio ? KVM_PIO_BUS : KVM_MMIO_BUS; struct _ioeventfd *p; struct eventfd_ctx *eventfd; int ret; @@ -496,7 +505,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) else p->wildcard = true; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); /* Verify that there isnt a match already */ if (ioeventfd_check_collision(kvm, p)) { @@ -506,18 +515,18 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) kvm_iodevice_init(&p->dev, &ioeventfd_ops); - ret = __kvm_io_bus_register_dev(bus, &p->dev); + ret = kvm_io_bus_register_dev(kvm, bus_idx, &p->dev); if (ret < 0) goto unlock_fail; list_add_tail(&p->list, &kvm->ioeventfds); - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return 0; unlock_fail: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); fail: kfree(p); @@ -530,7 +539,7 @@ static int kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { int pio = args->flags & KVM_IOEVENTFD_FLAG_PIO; - struct kvm_io_bus *bus = pio ? &kvm->pio_bus : &kvm->mmio_bus; + enum kvm_bus bus_idx = pio ? KVM_PIO_BUS : KVM_MMIO_BUS; struct _ioeventfd *p, *tmp; struct eventfd_ctx *eventfd; int ret = -ENOENT; @@ -539,7 +548,7 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) if (IS_ERR(eventfd)) return PTR_ERR(eventfd); - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) { bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH); @@ -553,13 +562,13 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) if (!p->wildcard && p->datamatch != args->datamatch) continue; - __kvm_io_bus_unregister_dev(bus, &p->dev); + kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); ioeventfd_release(p); ret = 0; break; } - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); eventfd_ctx_put(eventfd); diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 38a2d20..3db15a8 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -100,6 +100,19 @@ static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx) return injected; } +static void update_handled_vectors(struct kvm_ioapic *ioapic) +{ + DECLARE_BITMAP(handled_vectors, 256); + int i; + + memset(handled_vectors, 0, sizeof(handled_vectors)); + for (i = 0; i < IOAPIC_NUM_PINS; ++i) + __set_bit(ioapic->redirtbl[i].fields.vector, handled_vectors); + memcpy(ioapic->handled_vectors, handled_vectors, + sizeof(handled_vectors)); + smp_wmb(); +} + static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) { unsigned index; @@ -134,6 +147,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) e->bits |= (u32) val; e->fields.remote_irr = 0; } + update_handled_vectors(ioapic); mask_after = e->fields.mask; if (mask_before != mask_after) kvm_fire_mask_notifiers(ioapic->kvm, index, mask_after); @@ -241,6 +255,9 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; + smp_rmb(); + if (!test_bit(vector, ioapic->handled_vectors)) + return; mutex_lock(&ioapic->lock); __kvm_ioapic_update_eoi(ioapic, vector, trigger_mode); mutex_unlock(&ioapic->lock); @@ -352,6 +369,7 @@ void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->ioregsel = 0; ioapic->irr = 0; ioapic->id = 0; + update_handled_vectors(ioapic); } static const struct kvm_io_device_ops ioapic_mmio_ops = { @@ -372,13 +390,28 @@ int kvm_ioapic_init(struct kvm *kvm) kvm_ioapic_reset(ioapic); kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops); ioapic->kvm = kvm; - ret = kvm_io_bus_register_dev(kvm, &kvm->mmio_bus, &ioapic->dev); - if (ret < 0) + mutex_lock(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); + mutex_unlock(&kvm->slots_lock); + if (ret < 0) { + kvm->arch.vioapic = NULL; kfree(ioapic); + } return ret; } +void kvm_ioapic_destroy(struct kvm *kvm) +{ + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + + if (ioapic) { + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); + kvm->arch.vioapic = NULL; + kfree(ioapic); + } +} + int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) { struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); @@ -399,6 +432,7 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) mutex_lock(&ioapic->lock); memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); + update_handled_vectors(ioapic); mutex_unlock(&ioapic->lock); return 0; } diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index 419c43b..8a751b7 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -46,6 +46,7 @@ struct kvm_ioapic { struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); struct mutex lock; + DECLARE_BITMAP(handled_vectors, 256); }; #ifdef DEBUG @@ -71,6 +72,7 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); +void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 1514758..80fd3ad 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -32,10 +32,10 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm); static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); -int kvm_iommu_map_pages(struct kvm *kvm, - gfn_t base_gfn, unsigned long npages) +int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { - gfn_t gfn = base_gfn; + gfn_t gfn = slot->base_gfn; + unsigned long npages = slot->npages; pfn_t pfn; int i, r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; @@ -54,7 +54,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) continue; - pfn = gfn_to_pfn(kvm, gfn); + pfn = gfn_to_pfn_memslot(kvm, slot, gfn); r = iommu_map_range(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn), @@ -69,17 +69,19 @@ int kvm_iommu_map_pages(struct kvm *kvm, return 0; unmap_pages: - kvm_iommu_put_pages(kvm, base_gfn, i); + kvm_iommu_put_pages(kvm, slot->base_gfn, i); return r; } static int kvm_iommu_map_memslots(struct kvm *kvm) { int i, r = 0; + struct kvm_memslots *slots; + + slots = rcu_dereference(kvm->memslots); - for (i = 0; i < kvm->nmemslots; i++) { - r = kvm_iommu_map_pages(kvm, kvm->memslots[i].base_gfn, - kvm->memslots[i].npages); + for (i = 0; i < slots->nmemslots; i++) { + r = kvm_iommu_map_pages(kvm, &slots->memslots[i]); if (r) break; } @@ -104,7 +106,8 @@ int kvm_assign_device(struct kvm *kvm, r = iommu_attach_device(domain, &pdev->dev); if (r) { - printk(KERN_ERR "assign device %x:%x.%x failed", + printk(KERN_ERR "assign device %x:%x:%x.%x failed", + pci_domain_nr(pdev->bus), pdev->bus->number, PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn)); @@ -125,7 +128,8 @@ int kvm_assign_device(struct kvm *kvm, goto out_unmap; } - printk(KERN_DEBUG "assign device: host bdf = %x:%x:%x\n", + printk(KERN_DEBUG "assign device %x:%x:%x.%x\n", + assigned_dev->host_segnr, assigned_dev->host_busnr, PCI_SLOT(assigned_dev->host_devfn), PCI_FUNC(assigned_dev->host_devfn)); @@ -152,7 +156,8 @@ int kvm_deassign_device(struct kvm *kvm, iommu_detach_device(domain, &pdev->dev); - printk(KERN_DEBUG "deassign device: host bdf = %x:%x:%x\n", + printk(KERN_DEBUG "deassign device %x:%x:%x.%x\n", + assigned_dev->host_segnr, assigned_dev->host_busnr, PCI_SLOT(assigned_dev->host_devfn), PCI_FUNC(assigned_dev->host_devfn)); @@ -210,10 +215,13 @@ static void kvm_iommu_put_pages(struct kvm *kvm, static int kvm_iommu_unmap_memslots(struct kvm *kvm) { int i; + struct kvm_memslots *slots; + + slots = rcu_dereference(kvm->memslots); - for (i = 0; i < kvm->nmemslots; i++) { - kvm_iommu_put_pages(kvm, kvm->memslots[i].base_gfn, - kvm->memslots[i].npages); + for (i = 0; i < slots->nmemslots; i++) { + kvm_iommu_put_pages(kvm, slots->memslots[i].base_gfn, + slots->memslots[i].npages); } return 0; diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 9b07734..9fd5b3e 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -302,6 +302,7 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt, { int r = -EINVAL; int delta; + unsigned max_pin; struct kvm_kernel_irq_routing_entry *ei; struct hlist_node *n; @@ -322,12 +323,15 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt, switch (ue->u.irqchip.irqchip) { case KVM_IRQCHIP_PIC_MASTER: e->set = kvm_set_pic_irq; + max_pin = 16; break; case KVM_IRQCHIP_PIC_SLAVE: e->set = kvm_set_pic_irq; + max_pin = 16; delta = 8; break; case KVM_IRQCHIP_IOAPIC: + max_pin = KVM_IOAPIC_NUM_PINS; e->set = kvm_set_ioapic_irq; break; default: @@ -335,7 +339,7 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt, } e->irqchip.irqchip = ue->u.irqchip.irqchip; e->irqchip.pin = ue->u.irqchip.pin + delta; - if (e->irqchip.pin >= KVM_IOAPIC_NUM_PINS) + if (e->irqchip.pin >= max_pin) goto out; rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi; break; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a944be3..548f925 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -44,6 +44,8 @@ #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/compat.h> +#include <linux/srcu.h> +#include <linux/hugetlb.h> #include <asm/processor.h> #include <asm/io.h> @@ -51,9 +53,7 @@ #include <asm/pgtable.h> #include <asm-generic/bitops/le.h> -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET #include "coalesced_mmio.h" -#endif #define CREATE_TRACE_POINTS #include <trace/events/kvm.h> @@ -86,6 +86,8 @@ static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, static int hardware_enable_all(void); static void hardware_disable_all(void); +static void kvm_io_bus_destroy(struct kvm_io_bus *bus); + static bool kvm_rebooting; static bool largepages_enabled = true; @@ -136,7 +138,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) zalloc_cpumask_var(&cpus, GFP_ATOMIC); - spin_lock(&kvm->requests_lock); + raw_spin_lock(&kvm->requests_lock); me = smp_processor_id(); kvm_for_each_vcpu(i, vcpu, kvm) { if (test_and_set_bit(req, &vcpu->requests)) @@ -151,7 +153,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) smp_call_function_many(cpus, ack_flush, NULL, 1); else called = false; - spin_unlock(&kvm->requests_lock); + raw_spin_unlock(&kvm->requests_lock); free_cpumask_var(cpus); return called; } @@ -215,7 +217,7 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, unsigned long address) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush; + int need_tlb_flush, idx; /* * When ->invalidate_page runs, the linux pte has been zapped @@ -235,10 +237,12 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, * pte after kvm_unmap_hva returned, without noticing the page * is going to be freed. */ + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); kvm->mmu_notifier_seq++; need_tlb_flush = kvm_unmap_hva(kvm, address); spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) @@ -252,11 +256,14 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, pte_t pte) { struct kvm *kvm = mmu_notifier_to_kvm(mn); + int idx; + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); kvm->mmu_notifier_seq++; kvm_set_spte_hva(kvm, address, pte); spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); } static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, @@ -265,8 +272,9 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, unsigned long end) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush = 0; + int need_tlb_flush = 0, idx; + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); /* * The count increase must become visible at unlock time as no @@ -277,6 +285,7 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, for (; start < end; start += PAGE_SIZE) need_tlb_flush |= kvm_unmap_hva(kvm, start); spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) @@ -314,11 +323,13 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, unsigned long address) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int young; + int young, idx; + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); young = kvm_age_hva(kvm, address); spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); if (young) kvm_flush_remote_tlbs(kvm); @@ -341,15 +352,26 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { .change_pte = kvm_mmu_notifier_change_pte, .release = kvm_mmu_notifier_release, }; + +static int kvm_init_mmu_notifier(struct kvm *kvm) +{ + kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; + return mmu_notifier_register(&kvm->mmu_notifier, current->mm); +} + +#else /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */ + +static int kvm_init_mmu_notifier(struct kvm *kvm) +{ + return 0; +} + #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ static struct kvm *kvm_create_vm(void) { - int r = 0; + int r = 0, i; struct kvm *kvm = kvm_arch_create_vm(); -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - struct page *page; -#endif if (IS_ERR(kvm)) goto out; @@ -363,39 +385,35 @@ static struct kvm *kvm_create_vm(void) INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; + r = -ENOMEM; + kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + if (!kvm->memslots) goto out_err; - } - kvm->coalesced_mmio_ring = - (struct kvm_coalesced_mmio_ring *)page_address(page); -#endif - -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) - { - kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; - r = mmu_notifier_register(&kvm->mmu_notifier, current->mm); - if (r) { -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - put_page(page); -#endif + if (init_srcu_struct(&kvm->srcu)) + goto out_err; + for (i = 0; i < KVM_NR_BUSES; i++) { + kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), + GFP_KERNEL); + if (!kvm->buses[i]) { + cleanup_srcu_struct(&kvm->srcu); goto out_err; } } -#endif + + r = kvm_init_mmu_notifier(kvm); + if (r) { + cleanup_srcu_struct(&kvm->srcu); + goto out_err; + } kvm->mm = current->mm; atomic_inc(&kvm->mm->mm_count); spin_lock_init(&kvm->mmu_lock); - spin_lock_init(&kvm->requests_lock); - kvm_io_bus_init(&kvm->pio_bus); + raw_spin_lock_init(&kvm->requests_lock); kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); - kvm_io_bus_init(&kvm->mmio_bus); - init_rwsem(&kvm->slots_lock); + mutex_init(&kvm->slots_lock); atomic_set(&kvm->users_count, 1); spin_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); @@ -406,12 +424,12 @@ static struct kvm *kvm_create_vm(void) out: return kvm; -#if defined(KVM_COALESCED_MMIO_PAGE_OFFSET) || \ - (defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)) out_err: hardware_disable_all(); -#endif out_err_nodisable: + for (i = 0; i < KVM_NR_BUSES; i++) + kfree(kvm->buses[i]); + kfree(kvm->memslots); kfree(kvm); return ERR_PTR(r); } @@ -446,13 +464,17 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free, void kvm_free_physmem(struct kvm *kvm) { int i; + struct kvm_memslots *slots = kvm->memslots; + + for (i = 0; i < slots->nmemslots; ++i) + kvm_free_physmem_slot(&slots->memslots[i], NULL); - for (i = 0; i < kvm->nmemslots; ++i) - kvm_free_physmem_slot(&kvm->memslots[i], NULL); + kfree(kvm->memslots); } static void kvm_destroy_vm(struct kvm *kvm) { + int i; struct mm_struct *mm = kvm->mm; kvm_arch_sync_events(kvm); @@ -460,12 +482,9 @@ static void kvm_destroy_vm(struct kvm *kvm) list_del(&kvm->vm_list); spin_unlock(&kvm_lock); kvm_free_irq_routing(kvm); - kvm_io_bus_destroy(&kvm->pio_bus); - kvm_io_bus_destroy(&kvm->mmio_bus); -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - if (kvm->coalesced_mmio_ring != NULL) - free_page((unsigned long)kvm->coalesced_mmio_ring); -#endif + for (i = 0; i < KVM_NR_BUSES; i++) + kvm_io_bus_destroy(kvm->buses[i]); + kvm_coalesced_mmio_free(kvm); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); #else @@ -512,12 +531,13 @@ int __kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, int user_alloc) { - int r; + int r, flush_shadow = 0; gfn_t base_gfn; unsigned long npages; unsigned long i; struct kvm_memory_slot *memslot; struct kvm_memory_slot old, new; + struct kvm_memslots *slots, *old_memslots; r = -EINVAL; /* General sanity checks */ @@ -532,7 +552,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; - memslot = &kvm->memslots[mem->slot]; + memslot = &kvm->memslots->memslots[mem->slot]; base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; @@ -553,7 +573,7 @@ int __kvm_set_memory_region(struct kvm *kvm, /* Check for overlaps */ r = -EEXIST; for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { - struct kvm_memory_slot *s = &kvm->memslots[i]; + struct kvm_memory_slot *s = &kvm->memslots->memslots[i]; if (s == memslot || !s->npages) continue; @@ -579,15 +599,7 @@ int __kvm_set_memory_region(struct kvm *kvm, memset(new.rmap, 0, npages * sizeof(*new.rmap)); new.user_alloc = user_alloc; - /* - * hva_to_rmmap() serialzies with the mmu_lock and to be - * safe it has to ignore memslots with !user_alloc && - * !userspace_addr. - */ - if (user_alloc) - new.userspace_addr = mem->userspace_addr; - else - new.userspace_addr = 0; + new.userspace_addr = mem->userspace_addr; } if (!npages) goto skip_lpage; @@ -642,8 +654,9 @@ skip_lpage: if (!new.dirty_bitmap) goto out_free; memset(new.dirty_bitmap, 0, dirty_bytes); + /* destroy any largepage mappings for dirty tracking */ if (old.npages) - kvm_arch_flush_shadow(kvm); + flush_shadow = 1; } #else /* not defined CONFIG_S390 */ new.user_alloc = user_alloc; @@ -651,36 +664,72 @@ skip_lpage: new.userspace_addr = mem->userspace_addr; #endif /* not defined CONFIG_S390 */ - if (!npages) + if (!npages) { + r = -ENOMEM; + slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + if (!slots) + goto out_free; + memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); + if (mem->slot >= slots->nmemslots) + slots->nmemslots = mem->slot + 1; + slots->memslots[mem->slot].flags |= KVM_MEMSLOT_INVALID; + + old_memslots = kvm->memslots; + rcu_assign_pointer(kvm->memslots, slots); + synchronize_srcu_expedited(&kvm->srcu); + /* From this point no new shadow pages pointing to a deleted + * memslot will be created. + * + * validation of sp->gfn happens in: + * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) + * - kvm_is_visible_gfn (mmu_check_roots) + */ kvm_arch_flush_shadow(kvm); + kfree(old_memslots); + } - spin_lock(&kvm->mmu_lock); - if (mem->slot >= kvm->nmemslots) - kvm->nmemslots = mem->slot + 1; - - *memslot = new; - spin_unlock(&kvm->mmu_lock); - - r = kvm_arch_set_memory_region(kvm, mem, old, user_alloc); - if (r) { - spin_lock(&kvm->mmu_lock); - *memslot = old; - spin_unlock(&kvm->mmu_lock); + r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc); + if (r) goto out_free; - } - kvm_free_physmem_slot(&old, npages ? &new : NULL); - /* Slot deletion case: we have to update the current slot */ - spin_lock(&kvm->mmu_lock); - if (!npages) - *memslot = old; - spin_unlock(&kvm->mmu_lock); #ifdef CONFIG_DMAR /* map the pages in iommu page table */ - r = kvm_iommu_map_pages(kvm, base_gfn, npages); - if (r) - goto out; + if (npages) { + r = kvm_iommu_map_pages(kvm, &new); + if (r) + goto out_free; + } #endif + + r = -ENOMEM; + slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + if (!slots) + goto out_free; + memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); + if (mem->slot >= slots->nmemslots) + slots->nmemslots = mem->slot + 1; + + /* actual memory is freed via old in kvm_free_physmem_slot below */ + if (!npages) { + new.rmap = NULL; + new.dirty_bitmap = NULL; + for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) + new.lpage_info[i] = NULL; + } + + slots->memslots[mem->slot] = new; + old_memslots = kvm->memslots; + rcu_assign_pointer(kvm->memslots, slots); + synchronize_srcu_expedited(&kvm->srcu); + + kvm_arch_commit_memory_region(kvm, mem, old, user_alloc); + + kvm_free_physmem_slot(&old, &new); + kfree(old_memslots); + + if (flush_shadow) + kvm_arch_flush_shadow(kvm); + return 0; out_free: @@ -697,9 +746,9 @@ int kvm_set_memory_region(struct kvm *kvm, { int r; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); r = __kvm_set_memory_region(kvm, mem, user_alloc); - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return r; } EXPORT_SYMBOL_GPL(kvm_set_memory_region); @@ -726,7 +775,7 @@ int kvm_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_MEMORY_SLOTS) goto out; - memslot = &kvm->memslots[log->slot]; + memslot = &kvm->memslots->memslots[log->slot]; r = -ENOENT; if (!memslot->dirty_bitmap) goto out; @@ -780,9 +829,10 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva); struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn) { int i; + struct kvm_memslots *slots = rcu_dereference(kvm->memslots); - for (i = 0; i < kvm->nmemslots; ++i) { - struct kvm_memory_slot *memslot = &kvm->memslots[i]; + for (i = 0; i < slots->nmemslots; ++i) { + struct kvm_memory_slot *memslot = &slots->memslots[i]; if (gfn >= memslot->base_gfn && gfn < memslot->base_gfn + memslot->npages) @@ -801,10 +851,14 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { int i; + struct kvm_memslots *slots = rcu_dereference(kvm->memslots); - gfn = unalias_gfn(kvm, gfn); + gfn = unalias_gfn_instantiation(kvm, gfn); for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { - struct kvm_memory_slot *memslot = &kvm->memslots[i]; + struct kvm_memory_slot *memslot = &slots->memslots[i]; + + if (memslot->flags & KVM_MEMSLOT_INVALID) + continue; if (gfn >= memslot->base_gfn && gfn < memslot->base_gfn + memslot->npages) @@ -814,33 +868,68 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); +unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn) +{ + struct vm_area_struct *vma; + unsigned long addr, size; + + size = PAGE_SIZE; + + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return PAGE_SIZE; + + down_read(¤t->mm->mmap_sem); + vma = find_vma(current->mm, addr); + if (!vma) + goto out; + + size = vma_kernel_pagesize(vma); + +out: + up_read(¤t->mm->mmap_sem); + + return size; +} + +int memslot_id(struct kvm *kvm, gfn_t gfn) +{ + int i; + struct kvm_memslots *slots = rcu_dereference(kvm->memslots); + struct kvm_memory_slot *memslot = NULL; + + gfn = unalias_gfn(kvm, gfn); + for (i = 0; i < slots->nmemslots; ++i) { + memslot = &slots->memslots[i]; + + if (gfn >= memslot->base_gfn + && gfn < memslot->base_gfn + memslot->npages) + break; + } + + return memslot - slots->memslots; +} + unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *slot; - gfn = unalias_gfn(kvm, gfn); + gfn = unalias_gfn_instantiation(kvm, gfn); slot = gfn_to_memslot_unaliased(kvm, gfn); - if (!slot) + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return bad_hva(); return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); } EXPORT_SYMBOL_GPL(gfn_to_hva); -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr) { struct page *page[1]; - unsigned long addr; int npages; pfn_t pfn; might_sleep(); - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) { - get_page(bad_page); - return page_to_pfn(bad_page); - } - npages = get_user_pages_fast(addr, 1, 1, page); if (unlikely(npages != 1)) { @@ -865,8 +954,32 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) return pfn; } +pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +{ + unsigned long addr; + + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) { + get_page(bad_page); + return page_to_pfn(bad_page); + } + + return hva_to_pfn(kvm, addr); +} EXPORT_SYMBOL_GPL(gfn_to_pfn); +static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +{ + return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); +} + +pfn_t gfn_to_pfn_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn) +{ + unsigned long addr = gfn_to_hva_memslot(slot, gfn); + return hva_to_pfn(kvm, addr); +} + struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { pfn_t pfn; @@ -1854,12 +1967,7 @@ static struct notifier_block kvm_reboot_notifier = { .priority = 0, }; -void kvm_io_bus_init(struct kvm_io_bus *bus) -{ - memset(bus, 0, sizeof(*bus)); -} - -void kvm_io_bus_destroy(struct kvm_io_bus *bus) +static void kvm_io_bus_destroy(struct kvm_io_bus *bus) { int i; @@ -1868,13 +1976,15 @@ void kvm_io_bus_destroy(struct kvm_io_bus *bus) kvm_iodevice_destructor(pos); } + kfree(bus); } /* kvm_io_bus_write - called under kvm->slots_lock */ -int kvm_io_bus_write(struct kvm_io_bus *bus, gpa_t addr, +int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { int i; + struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]); for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_write(bus->devs[i], addr, len, val)) return 0; @@ -1882,59 +1992,71 @@ int kvm_io_bus_write(struct kvm_io_bus *bus, gpa_t addr, } /* kvm_io_bus_read - called under kvm->slots_lock */ -int kvm_io_bus_read(struct kvm_io_bus *bus, gpa_t addr, int len, void *val) +int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, + int len, void *val) { int i; + struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]); + for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_read(bus->devs[i], addr, len, val)) return 0; return -EOPNOTSUPP; } -int kvm_io_bus_register_dev(struct kvm *kvm, struct kvm_io_bus *bus, - struct kvm_io_device *dev) +/* Caller must hold slots_lock. */ +int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev) { - int ret; - - down_write(&kvm->slots_lock); - ret = __kvm_io_bus_register_dev(bus, dev); - up_write(&kvm->slots_lock); + struct kvm_io_bus *new_bus, *bus; - return ret; -} - -/* An unlocked version. Caller must have write lock on slots_lock. */ -int __kvm_io_bus_register_dev(struct kvm_io_bus *bus, - struct kvm_io_device *dev) -{ + bus = kvm->buses[bus_idx]; if (bus->dev_count > NR_IOBUS_DEVS-1) return -ENOSPC; - bus->devs[bus->dev_count++] = dev; + new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); + if (!new_bus) + return -ENOMEM; + memcpy(new_bus, bus, sizeof(struct kvm_io_bus)); + new_bus->devs[new_bus->dev_count++] = dev; + rcu_assign_pointer(kvm->buses[bus_idx], new_bus); + synchronize_srcu_expedited(&kvm->srcu); + kfree(bus); return 0; } -void kvm_io_bus_unregister_dev(struct kvm *kvm, - struct kvm_io_bus *bus, - struct kvm_io_device *dev) +/* Caller must hold slots_lock. */ +int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev) { - down_write(&kvm->slots_lock); - __kvm_io_bus_unregister_dev(bus, dev); - up_write(&kvm->slots_lock); -} + int i, r; + struct kvm_io_bus *new_bus, *bus; -/* An unlocked version. Caller must have write lock on slots_lock. */ -void __kvm_io_bus_unregister_dev(struct kvm_io_bus *bus, - struct kvm_io_device *dev) -{ - int i; + new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); + if (!new_bus) + return -ENOMEM; - for (i = 0; i < bus->dev_count; i++) - if (bus->devs[i] == dev) { - bus->devs[i] = bus->devs[--bus->dev_count]; + bus = kvm->buses[bus_idx]; + memcpy(new_bus, bus, sizeof(struct kvm_io_bus)); + + r = -ENOENT; + for (i = 0; i < new_bus->dev_count; i++) + if (new_bus->devs[i] == dev) { + r = 0; + new_bus->devs[i] = new_bus->devs[--new_bus->dev_count]; break; } + + if (r) { + kfree(new_bus); + return r; + } + + rcu_assign_pointer(kvm->buses[bus_idx], new_bus); + synchronize_srcu_expedited(&kvm->srcu); + kfree(bus); + return r; } static struct notifier_block kvm_cpu_notifier = { |