diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-04 09:30:33 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-04 09:30:33 -0700 |
commit | ecefbd94b834fa32559d854646d777c56749ef1c (patch) | |
tree | ca8958900ad9e208a8e5fb7704f1b66dc76131b4 /virt/kvm | |
parent | ce57e981f2b996aaca2031003b3f866368307766 (diff) | |
parent | 3d11df7abbff013b811d5615320580cd5d9d7d31 (diff) |
Merge tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Avi Kivity:
"Highlights of the changes for this release include support for vfio
level triggered interrupts, improved big real mode support on older
Intels, a streamlines guest page table walker, guest APIC speedups,
PIO optimizations, better overcommit handling, and read-only memory."
* tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits)
KVM: s390: Fix vcpu_load handling in interrupt code
KVM: x86: Fix guest debug across vcpu INIT reset
KVM: Add resampling irqfds for level triggered interrupts
KVM: optimize apic interrupt delivery
KVM: MMU: Eliminate pointless temporary 'ac'
KVM: MMU: Avoid access/dirty update loop if all is well
KVM: MMU: Eliminate eperm temporary
KVM: MMU: Optimize is_last_gpte()
KVM: MMU: Simplify walk_addr_generic() loop
KVM: MMU: Optimize pte permission checks
KVM: MMU: Update accessed and dirty bits after guest pagetable walk
KVM: MMU: Move gpte_access() out of paging_tmpl.h
KVM: MMU: Optimize gpte_access() slightly
KVM: MMU: Push clean gpte write protection out of gpte_access()
KVM: clarify kvmclock documentation
KVM: make processes waiting on vcpu mutex killable
KVM: SVM: Make use of asm.h
KVM: VMX: Make use of asm.h
KVM: VMX: Make lto-friendly
KVM: x86: lapic: Clean up find_highest_vector() and count_vectors()
...
Conflicts:
arch/s390/include/asm/processor.h
arch/x86/kvm/i8259.c
Diffstat (limited to 'virt/kvm')
-rw-r--r-- | virt/kvm/Kconfig | 3 | ||||
-rw-r--r-- | virt/kvm/async_pf.c | 11 | ||||
-rw-r--r-- | virt/kvm/eventfd.c | 150 | ||||
-rw-r--r-- | virt/kvm/ioapic.c | 37 | ||||
-rw-r--r-- | virt/kvm/iommu.c | 16 | ||||
-rw-r--r-- | virt/kvm/irq_comm.c | 17 | ||||
-rw-r--r-- | virt/kvm/kvm_main.c | 541 |
7 files changed, 525 insertions, 250 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 28694f4a9139..d01b24b72c61 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -21,3 +21,6 @@ config KVM_ASYNC_PF config HAVE_KVM_MSI bool + +config HAVE_KVM_CPU_RELAX_INTERCEPT + bool diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 74268b4c2ee1..ea475cd03511 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -111,8 +111,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) list_entry(vcpu->async_pf.done.next, typeof(*work), link); list_del(&work->link); - if (work->page) - put_page(work->page); + if (!is_error_page(work->page)) + kvm_release_page_clean(work->page); kmem_cache_free(async_pf_cache, work); } spin_unlock(&vcpu->async_pf.lock); @@ -138,8 +138,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) list_del(&work->queue); vcpu->async_pf.queued--; - if (work->page) - put_page(work->page); + if (!is_error_page(work->page)) + kvm_release_page_clean(work->page); kmem_cache_free(async_pf_cache, work); } } @@ -203,8 +203,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu) if (!work) return -ENOMEM; - work->page = bad_page; - get_page(bad_page); + work->page = KVM_ERR_PTR_BAD_PAGE; INIT_LIST_HEAD(&work->queue); /* for list_del to work */ spin_lock(&vcpu->async_pf.lock); diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 67a35e90384c..9718e98d6d2a 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -43,6 +43,31 @@ * -------------------------------------------------------------------- */ +/* + * Resampling irqfds are a special variety of irqfds used to emulate + * level triggered interrupts. The interrupt is asserted on eventfd + * trigger. On acknowledgement through the irq ack notifier, the + * interrupt is de-asserted and userspace is notified through the + * resamplefd. All resamplers on the same gsi are de-asserted + * together, so we don't need to track the state of each individual + * user. We can also therefore share the same irq source ID. + */ +struct _irqfd_resampler { + struct kvm *kvm; + /* + * List of resampling struct _irqfd objects sharing this gsi. + * RCU list modified under kvm->irqfds.resampler_lock + */ + struct list_head list; + struct kvm_irq_ack_notifier notifier; + /* + * Entry in list of kvm->irqfd.resampler_list. Use for sharing + * resamplers among irqfds on the same gsi. + * Accessed and modified under kvm->irqfds.resampler_lock + */ + struct list_head link; +}; + struct _irqfd { /* Used for MSI fast-path */ struct kvm *kvm; @@ -52,6 +77,12 @@ struct _irqfd { /* Used for level IRQ fast-path */ int gsi; struct work_struct inject; + /* The resampler used by this irqfd (resampler-only) */ + struct _irqfd_resampler *resampler; + /* Eventfd notified on resample (resampler-only) */ + struct eventfd_ctx *resamplefd; + /* Entry in list of irqfds for a resampler (resampler-only) */ + struct list_head resampler_link; /* Used for setup/shutdown */ struct eventfd_ctx *eventfd; struct list_head list; @@ -67,8 +98,58 @@ irqfd_inject(struct work_struct *work) struct _irqfd *irqfd = container_of(work, struct _irqfd, inject); struct kvm *kvm = irqfd->kvm; - kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1); - kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0); + if (!irqfd->resampler) { + kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1); + kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0); + } else + kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + irqfd->gsi, 1); +} + +/* + * Since resampler irqfds share an IRQ source ID, we de-assert once + * then notify all of the resampler irqfds using this GSI. We can't + * do multiple de-asserts or we risk racing with incoming re-asserts. + */ +static void +irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) +{ + struct _irqfd_resampler *resampler; + struct _irqfd *irqfd; + + resampler = container_of(kian, struct _irqfd_resampler, notifier); + + kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + resampler->notifier.gsi, 0); + + rcu_read_lock(); + + list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link) + eventfd_signal(irqfd->resamplefd, 1); + + rcu_read_unlock(); +} + +static void +irqfd_resampler_shutdown(struct _irqfd *irqfd) +{ + struct _irqfd_resampler *resampler = irqfd->resampler; + struct kvm *kvm = resampler->kvm; + + mutex_lock(&kvm->irqfds.resampler_lock); + + list_del_rcu(&irqfd->resampler_link); + synchronize_rcu(); + + if (list_empty(&resampler->list)) { + list_del(&resampler->link); + kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier); + kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + resampler->notifier.gsi, 0); + kfree(resampler); + } + + mutex_unlock(&kvm->irqfds.resampler_lock); } /* @@ -92,6 +173,11 @@ irqfd_shutdown(struct work_struct *work) */ flush_work(&irqfd->inject); + if (irqfd->resampler) { + irqfd_resampler_shutdown(irqfd); + eventfd_ctx_put(irqfd->resamplefd); + } + /* * It is now safe to release the object's resources */ @@ -203,7 +289,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) struct kvm_irq_routing_table *irq_rt; struct _irqfd *irqfd, *tmp; struct file *file = NULL; - struct eventfd_ctx *eventfd = NULL; + struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL; int ret; unsigned int events; @@ -231,6 +317,54 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) irqfd->eventfd = eventfd; + if (args->flags & KVM_IRQFD_FLAG_RESAMPLE) { + struct _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, list) { + if (resampler->notifier.gsi == irqfd->gsi) { + irqfd->resampler = resampler; + break; + } + } + + if (!irqfd->resampler) { + resampler = kzalloc(sizeof(*resampler), GFP_KERNEL); + 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_rcu(); + + 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 @@ -276,6 +410,12 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) 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); @@ -291,6 +431,8 @@ kvm_eventfd_init(struct kvm *kvm) { spin_lock_init(&kvm->irqfds.lock); INIT_LIST_HEAD(&kvm->irqfds.items); + INIT_LIST_HEAD(&kvm->irqfds.resampler_list); + mutex_init(&kvm->irqfds.resampler_lock); INIT_LIST_HEAD(&kvm->ioeventfds); } @@ -340,7 +482,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) { - if (args->flags & ~KVM_IRQFD_FLAG_DEASSIGN) + if (args->flags & ~(KVM_IRQFD_FLAG_DEASSIGN | KVM_IRQFD_FLAG_RESAMPLE)) return -EINVAL; if (args->flags & KVM_IRQFD_FLAG_DEASSIGN) diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index ef61d529a6c4..cfb7e4d52dc2 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -197,28 +197,29 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, u32 old_irr; u32 mask = 1 << irq; union kvm_ioapic_redirect_entry entry; - int ret = 1; + int ret, irq_level; + + BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS); spin_lock(&ioapic->lock); old_irr = ioapic->irr; - if (irq >= 0 && irq < IOAPIC_NUM_PINS) { - int irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq], - irq_source_id, level); - entry = ioapic->redirtbl[irq]; - irq_level ^= entry.fields.polarity; - if (!irq_level) - ioapic->irr &= ~mask; - else { - int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG); - ioapic->irr |= mask; - if ((edge && old_irr != ioapic->irr) || - (!edge && !entry.fields.remote_irr)) - ret = ioapic_service(ioapic, irq); - else - ret = 0; /* report coalesced interrupt */ - } - trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0); + irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq], + irq_source_id, level); + entry = ioapic->redirtbl[irq]; + irq_level ^= entry.fields.polarity; + if (!irq_level) { + ioapic->irr &= ~mask; + ret = 1; + } else { + int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG); + ioapic->irr |= mask; + if ((edge && old_irr != ioapic->irr) || + (!edge && !entry.fields.remote_irr)) + ret = ioapic_service(ioapic, irq); + else + ret = 0; /* report coalesced interrupt */ } + trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0); spin_unlock(&ioapic->lock); return ret; diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index e9fff9830bf0..037cb6730e68 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -42,13 +42,13 @@ 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); -static pfn_t kvm_pin_pages(struct kvm *kvm, struct kvm_memory_slot *slot, - gfn_t gfn, unsigned long size) +static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, + unsigned long size) { gfn_t end_gfn; pfn_t pfn; - pfn = gfn_to_pfn_memslot(kvm, slot, gfn); + pfn = gfn_to_pfn_memslot(slot, gfn); end_gfn = gfn + (size >> PAGE_SHIFT); gfn += 1; @@ -56,7 +56,7 @@ static pfn_t kvm_pin_pages(struct kvm *kvm, struct kvm_memory_slot *slot, return pfn; while (gfn < end_gfn) - gfn_to_pfn_memslot(kvm, slot, gfn++); + gfn_to_pfn_memslot(slot, gfn++); return pfn; } @@ -105,7 +105,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) * Pin all pages we are about to map in memory. This is * important because we unmap and unpin in 4kb steps later. */ - pfn = kvm_pin_pages(kvm, slot, gfn, page_size); + pfn = kvm_pin_pages(slot, gfn, page_size); if (is_error_pfn(pfn)) { gfn += 1; continue; @@ -300,6 +300,12 @@ static void kvm_iommu_put_pages(struct kvm *kvm, /* Get physical address */ phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn)); + + if (!phys) { + gfn++; + continue; + } + pfn = phys >> PAGE_SHIFT; /* Unmap address from IO address space */ diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 83402d74a767..2eb58af7ee99 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -68,8 +68,13 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_vcpu *vcpu, *lowest = NULL; if (irq->dest_mode == 0 && irq->dest_id == 0xff && - kvm_is_dm_lowest_prio(irq)) + kvm_is_dm_lowest_prio(irq)) { printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); + irq->delivery_mode = APIC_DM_FIXED; + } + + if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r)) + return r; kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_apic_present(vcpu)) @@ -223,6 +228,9 @@ int kvm_request_irq_source_id(struct kvm *kvm) } ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); +#ifdef CONFIG_X86 + ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID); +#endif set_bit(irq_source_id, bitmap); unlock: mutex_unlock(&kvm->irq_lock); @@ -233,6 +241,9 @@ unlock: void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) { ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); +#ifdef CONFIG_X86 + ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID); +#endif mutex_lock(&kvm->irq_lock); if (irq_source_id < 0 || @@ -321,11 +332,11 @@ 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; + max_pin = PIC_NUM_PINS; break; case KVM_IRQCHIP_PIC_SLAVE: e->set = kvm_set_pic_irq; - max_pin = 16; + max_pin = PIC_NUM_PINS; delta = 8; break; case KVM_IRQCHIP_IOAPIC: diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d617f69131d7..c353b4599cec 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -100,13 +100,7 @@ EXPORT_SYMBOL_GPL(kvm_rebooting); static bool largepages_enabled = true; -static struct page *hwpoison_page; -static pfn_t hwpoison_pfn; - -struct page *fault_page; -pfn_t fault_pfn; - -inline int kvm_is_mmio_pfn(pfn_t pfn) +bool kvm_is_mmio_pfn(pfn_t pfn) { if (pfn_valid(pfn)) { int reserved; @@ -137,11 +131,12 @@ inline int kvm_is_mmio_pfn(pfn_t pfn) /* * Switches to specified vcpu, until a matching vcpu_put() */ -void vcpu_load(struct kvm_vcpu *vcpu) +int vcpu_load(struct kvm_vcpu *vcpu) { int cpu; - mutex_lock(&vcpu->mutex); + if (mutex_lock_killable(&vcpu->mutex)) + return -EINTR; if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) { /* The thread running this VCPU changed. */ struct pid *oldpid = vcpu->pid; @@ -154,6 +149,7 @@ void vcpu_load(struct kvm_vcpu *vcpu) preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); + return 0; } void vcpu_put(struct kvm_vcpu *vcpu) @@ -236,6 +232,9 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) } vcpu->run = page_address(page); + kvm_vcpu_set_in_spin_loop(vcpu, false); + kvm_vcpu_set_dy_eligible(vcpu, false); + r = kvm_arch_vcpu_init(vcpu); if (r < 0) goto fail_free_run; @@ -332,8 +331,7 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; - for (; start < end; start += PAGE_SIZE) - need_tlb_flush |= kvm_unmap_hva(kvm, start); + need_tlb_flush = kvm_unmap_hva_range(kvm, start, end); need_tlb_flush |= kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) @@ -412,7 +410,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, int idx; idx = srcu_read_lock(&kvm->srcu); - kvm_arch_flush_shadow(kvm); + kvm_arch_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); } @@ -551,16 +549,12 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) static void kvm_free_physmem_slot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { - if (!dont || free->rmap != dont->rmap) - vfree(free->rmap); - if (!dont || free->dirty_bitmap != dont->dirty_bitmap) kvm_destroy_dirty_bitmap(free); kvm_arch_free_memslot(free, dont); free->npages = 0; - free->rmap = NULL; } void kvm_free_physmem(struct kvm *kvm) @@ -590,7 +584,7 @@ static void kvm_destroy_vm(struct kvm *kvm) #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); #else - kvm_arch_flush_shadow(kvm); + kvm_arch_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_free_physmem(kvm); @@ -686,6 +680,20 @@ void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new) slots->generation++; } +static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) +{ + u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; + +#ifdef KVM_CAP_READONLY_MEM + valid_flags |= KVM_MEM_READONLY; +#endif + + if (mem->flags & ~valid_flags) + return -EINVAL; + + return 0; +} + /* * Allocate some memory and give it an address in the guest physical address * space. @@ -706,6 +714,10 @@ int __kvm_set_memory_region(struct kvm *kvm, struct kvm_memory_slot old, new; struct kvm_memslots *slots, *old_memslots; + r = check_memory_region_flags(mem); + if (r) + goto out; + r = -EINVAL; /* General sanity checks */ if (mem->memory_size & (PAGE_SIZE - 1)) @@ -769,11 +781,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if (npages && !old.npages) { new.user_alloc = user_alloc; new.userspace_addr = mem->userspace_addr; -#ifndef CONFIG_S390 - new.rmap = vzalloc(npages * sizeof(*new.rmap)); - if (!new.rmap) - goto out_free; -#endif /* not defined CONFIG_S390 */ + if (kvm_arch_create_memslot(&new, npages)) goto out_free; } @@ -785,7 +793,7 @@ int __kvm_set_memory_region(struct kvm *kvm, /* destroy any largepage mappings for dirty tracking */ } - if (!npages) { + if (!npages || base_gfn != old.base_gfn) { struct kvm_memory_slot *slot; r = -ENOMEM; @@ -801,14 +809,14 @@ int __kvm_set_memory_region(struct kvm *kvm, 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. + /* From this point no new shadow pages pointing to a deleted, + * or moved, 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); + kvm_arch_flush_shadow_memslot(kvm, slot); kfree(old_memslots); } @@ -832,7 +840,6 @@ int __kvm_set_memory_region(struct kvm *kvm, /* actual memory is freed via old in kvm_free_physmem_slot below */ if (!npages) { - new.rmap = NULL; new.dirty_bitmap = NULL; memset(&new.arch, 0, sizeof(new.arch)); } @@ -844,13 +851,6 @@ int __kvm_set_memory_region(struct kvm *kvm, kvm_arch_commit_memory_region(kvm, mem, old, user_alloc); - /* - * If the new memory slot is created, we need to clear all - * mmio sptes. - */ - if (npages && old.base_gfn != mem->guest_phys_addr >> PAGE_SHIFT) - kvm_arch_flush_shadow(kvm); - kvm_free_physmem_slot(&old, &new); kfree(old_memslots); @@ -932,53 +932,6 @@ void kvm_disable_largepages(void) } EXPORT_SYMBOL_GPL(kvm_disable_largepages); -int is_error_page(struct page *page) -{ - return page == bad_page || page == hwpoison_page || page == fault_page; -} -EXPORT_SYMBOL_GPL(is_error_page); - -int is_error_pfn(pfn_t pfn) -{ - return pfn == bad_pfn || pfn == hwpoison_pfn || pfn == fault_pfn; -} -EXPORT_SYMBOL_GPL(is_error_pfn); - -int is_hwpoison_pfn(pfn_t pfn) -{ - return pfn == hwpoison_pfn; -} -EXPORT_SYMBOL_GPL(is_hwpoison_pfn); - -int is_fault_pfn(pfn_t pfn) -{ - return pfn == fault_pfn; -} -EXPORT_SYMBOL_GPL(is_fault_pfn); - -int is_noslot_pfn(pfn_t pfn) -{ - return pfn == bad_pfn; -} -EXPORT_SYMBOL_GPL(is_noslot_pfn); - -int is_invalid_pfn(pfn_t pfn) -{ - return pfn == hwpoison_pfn || pfn == fault_pfn; -} -EXPORT_SYMBOL_GPL(is_invalid_pfn); - -static inline unsigned long bad_hva(void) -{ - return PAGE_OFFSET; -} - -int kvm_is_error_hva(unsigned long addr) -{ - return addr == bad_hva(); -} -EXPORT_SYMBOL_GPL(kvm_is_error_hva); - struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { return __gfn_to_memslot(kvm_memslots(kvm), gfn); @@ -1021,28 +974,62 @@ out: return size; } -static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, - gfn_t *nr_pages) +static bool memslot_is_readonly(struct kvm_memory_slot *slot) +{ + return slot->flags & KVM_MEM_READONLY; +} + +static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, + gfn_t *nr_pages, bool write) { if (!slot || slot->flags & KVM_MEMSLOT_INVALID) - return bad_hva(); + return KVM_HVA_ERR_BAD; + + if (memslot_is_readonly(slot) && write) + return KVM_HVA_ERR_RO_BAD; if (nr_pages) *nr_pages = slot->npages - (gfn - slot->base_gfn); - return gfn_to_hva_memslot(slot, gfn); + return __gfn_to_hva_memslot(slot, gfn); } +static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, + gfn_t *nr_pages) +{ + return __gfn_to_hva_many(slot, gfn, nr_pages, true); +} + +unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, + gfn_t gfn) +{ + return gfn_to_hva_many(slot, gfn, NULL); +} +EXPORT_SYMBOL_GPL(gfn_to_hva_memslot); + unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL); } EXPORT_SYMBOL_GPL(gfn_to_hva); -static pfn_t get_fault_pfn(void) +/* + * The hva returned by this function is only allowed to be read. + * It should pair with kvm_read_hva() or kvm_read_hva_atomic(). + */ +static unsigned long gfn_to_hva_read(struct kvm *kvm, gfn_t gfn) +{ + return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false); +} + +static int kvm_read_hva(void *data, void __user *hva, int len) { - get_page(fault_page); - return fault_pfn; + return __copy_from_user(data, hva, len); +} + +static int kvm_read_hva_atomic(void *data, void __user *hva, int len) +{ + return __copy_from_user_inatomic(data, hva, len); } int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, @@ -1065,108 +1052,186 @@ static inline int check_user_page_hwpoison(unsigned long addr) return rc == -EHWPOISON; } -static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic, - bool *async, bool write_fault, bool *writable) +/* + * The atomic path to get the writable pfn which will be stored in @pfn, + * true indicates success, otherwise false is returned. + */ +static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async, + bool write_fault, bool *writable, pfn_t *pfn) { struct page *page[1]; - int npages = 0; - pfn_t pfn; + int npages; - /* we can do it either atomically or asynchronously, not both */ - BUG_ON(atomic && async); + if (!(async || atomic)) + return false; - BUG_ON(!write_fault && !writable); + /* + * Fast pin a writable pfn only if it is a write fault request + * or the caller allows to map a writable pfn for a read fault + * request. + */ + if (!(write_fault || writable)) + return false; - if (writable) - *writable = true; + npages = __get_user_pages_fast(addr, 1, 1, page); + if (npages == 1) { + *pfn = page_to_pfn(page[0]); - if (atomic || async) - npages = __get_user_pages_fast(addr, 1, 1, page); + if (writable) + *writable = true; + return true; + } - if (unlikely(npages != 1) && !atomic) { - might_sleep(); + return false; +} - if (writable) - *writable = write_fault; +/* + * The slow path to get the pfn of the specified host virtual address, + * 1 indicates success, -errno is returned if error is detected. + */ +static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, + bool *writable, pfn_t *pfn) +{ + struct page *page[1]; + int npages = 0; - if (async) { - down_read(¤t->mm->mmap_sem); - npages = get_user_page_nowait(current, current->mm, - addr, write_fault, page); - up_read(¤t->mm->mmap_sem); - } else - npages = get_user_pages_fast(addr, 1, write_fault, - page); - - /* map read fault as writable if possible */ - if (unlikely(!write_fault) && npages == 1) { - struct page *wpage[1]; - - npages = __get_user_pages_fast(addr, 1, 1, wpage); - if (npages == 1) { - *writable = true; - put_page(page[0]); - page[0] = wpage[0]; - } - npages = 1; + might_sleep(); + + if (writable) + *writable = write_fault; + + if (async) { + down_read(¤t->mm->mmap_sem); + npages = get_user_page_nowait(current, current->mm, + addr, write_fault, page); + up_read(¤t->mm->mmap_sem); + } else + npages = get_user_pages_fast(addr, 1, write_fault, + page); + if (npages != 1) + return npages; + + /* map read fault as writable if possible */ + if (unlikely(!write_fault) && writable) { + struct page *wpage[1]; + + npages = __get_user_pages_fast(addr, 1, 1, wpage); + if (npages == 1) { + *writable = true; + put_page(page[0]); + page[0] = wpage[0]; } + + npages = 1; } + *pfn = page_to_pfn(page[0]); + return npages; +} - if (unlikely(npages != 1)) { - struct vm_area_struct *vma; +static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) +{ + if (unlikely(!(vma->vm_flags & VM_READ))) + return false; - if (atomic) - return get_fault_pfn(); + if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE)))) + return false; - down_read(¤t->mm->mmap_sem); - if (npages == -EHWPOISON || - (!async && check_user_page_hwpoison(addr))) { - up_read(¤t->mm->mmap_sem); - get_page(hwpoison_page); - return page_to_pfn(hwpoison_page); - } + return true; +} - vma = find_vma_intersection(current->mm, addr, addr+1); - - if (vma == NULL) - pfn = get_fault_pfn(); - else if ((vma->vm_flags & VM_PFNMAP)) { - pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + - vma->vm_pgoff; - BUG_ON(!kvm_is_mmio_pfn(pfn)); - } else { - if (async && (vma->vm_flags & VM_WRITE)) - *async = true; - pfn = get_fault_pfn(); - } - up_read(¤t->mm->mmap_sem); - } else - pfn = page_to_pfn(page[0]); +/* + * Pin guest page in memory and return its pfn. + * @addr: host virtual address which maps memory to the guest + * @atomic: whether this function can sleep + * @async: whether this function need to wait IO complete if the + * host page is not in the memory + * @write_fault: whether we should get a writable host page + * @writable: whether it allows to map a writable host page for !@write_fault + * + * The function will map a writable host page for these two cases: + * 1): @write_fault = true + * 2): @write_fault = false && @writable, @writable will tell the caller + * whether the mapping is writable. + */ +static pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, + bool write_fault, bool *writable) +{ + struct vm_area_struct *vma; + pfn_t pfn = 0; + int npages; + + /* we can do it either atomically or asynchronously, not both */ + BUG_ON(atomic && async); + if (hva_to_pfn_fast(addr, atomic, async, write_fault, writable, &pfn)) + return pfn; + + if (atomic) + return KVM_PFN_ERR_FAULT; + + npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn); + if (npages == 1) + return pfn; + + down_read(¤t->mm->mmap_sem); + if (npages == -EHWPOISON || + (!async && check_user_page_hwpoison(addr))) { + pfn = KVM_PFN_ERR_HWPOISON; + goto exit; + } + + vma = find_vma_intersection(current->mm, addr, addr + 1); + + if (vma == NULL) + pfn = KVM_PFN_ERR_FAULT; + else if ((vma->vm_flags & VM_PFNMAP)) { + pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + + vma->vm_pgoff; + BUG_ON(!kvm_is_mmio_pfn(pfn)); + } else { + if (async && vma_is_valid(vma, write_fault)) + *async = true; + pfn = KVM_PFN_ERR_FAULT; + } +exit: + up_read(¤t->mm->mmap_sem); return pfn; } -pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr) +static pfn_t +__gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, + bool *async, bool write_fault, bool *writable) { - return hva_to_pfn(kvm, addr, true, NULL, true, NULL); + unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); + + if (addr == KVM_HVA_ERR_RO_BAD) + return KVM_PFN_ERR_RO_FAULT; + + if (kvm_is_error_hva(addr)) + return KVM_PFN_ERR_BAD; + + /* Do not map writable pfn in the readonly memslot. */ + if (writable && memslot_is_readonly(slot)) { + *writable = false; + writable = NULL; + } + + return hva_to_pfn(addr, atomic, async, write_fault, + writable); } -EXPORT_SYMBOL_GPL(hva_to_pfn_atomic); static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async, bool write_fault, bool *writable) { - unsigned long addr; + struct kvm_memory_slot *slot; if (async) *async = false; - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) { - get_page(bad_page); - return page_to_pfn(bad_page); - } + slot = gfn_to_memslot(kvm, gfn); - return hva_to_pfn(kvm, addr, atomic, async, write_fault, writable); + return __gfn_to_pfn_memslot(slot, gfn, atomic, async, write_fault, + writable); } pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) @@ -1195,12 +1260,16 @@ pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); -pfn_t gfn_to_pfn_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn) +pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +{ + return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); +} + +pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) { - unsigned long addr = gfn_to_hva_memslot(slot, gfn); - return hva_to_pfn(kvm, addr, false, NULL, true, NULL); + return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); } +EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, int nr_pages) @@ -1219,30 +1288,42 @@ int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, } EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic); +static struct page *kvm_pfn_to_page(pfn_t pfn) +{ + if (is_error_pfn(pfn)) + return KVM_ERR_PTR_BAD_PAGE; + + if (kvm_is_mmio_pfn(pfn)) { + WARN_ON(1); + return KVM_ERR_PTR_BAD_PAGE; + } + |