diff options
Diffstat (limited to 'virt/kvm')
| -rw-r--r-- | virt/kvm/Kconfig | 15 | ||||
| -rw-r--r-- | virt/kvm/Makefile.kvm | 2 | ||||
| -rw-r--r-- | virt/kvm/async_pf.c | 2 | ||||
| -rw-r--r-- | virt/kvm/guest_memfd.c | 81 | ||||
| -rw-r--r-- | virt/kvm/kvm_main.c | 55 | ||||
| -rw-r--r-- | virt/kvm/kvm_mm.h | 4 |
6 files changed, 132 insertions, 27 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 727b542074e7..1b7d5be0b6c4 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -112,19 +112,18 @@ config KVM_GENERIC_MEMORY_ATTRIBUTES depends on KVM_GENERIC_MMU_NOTIFIER bool -config KVM_PRIVATE_MEM +config KVM_GUEST_MEMFD select XARRAY_MULTI bool -config KVM_GENERIC_PRIVATE_MEM - select KVM_GENERIC_MEMORY_ATTRIBUTES - select KVM_PRIVATE_MEM - bool - config HAVE_KVM_ARCH_GMEM_PREPARE bool - depends on KVM_PRIVATE_MEM + depends on KVM_GUEST_MEMFD config HAVE_KVM_ARCH_GMEM_INVALIDATE bool - depends on KVM_PRIVATE_MEM + depends on KVM_GUEST_MEMFD + +config HAVE_KVM_ARCH_GMEM_POPULATE + bool + depends on KVM_GUEST_MEMFD diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm index 724c89af78af..d047d4cf58c9 100644 --- a/virt/kvm/Makefile.kvm +++ b/virt/kvm/Makefile.kvm @@ -12,4 +12,4 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o -kvm-$(CONFIG_KVM_PRIVATE_MEM) += $(KVM)/guest_memfd.o +kvm-$(CONFIG_KVM_GUEST_MEMFD) += $(KVM)/guest_memfd.o diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 0ee4816b079a..b8aaa96b799b 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -192,7 +192,7 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * do alloc nowait since if we are going to sleep anyway we * may as well sleep faulting in page */ - work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN); + work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT); if (!work) return false; diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 7d85cc33c0bb..08a6bc7d25b6 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -312,7 +312,74 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn) return gfn - slot->base_gfn + slot->gmem.pgoff; } +static bool kvm_gmem_supports_mmap(struct inode *inode) +{ + const u64 flags = (u64)inode->i_private; + + return flags & GUEST_MEMFD_FLAG_MMAP; +} + +static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vmf->vma->vm_file); + struct folio *folio; + vm_fault_t ret = VM_FAULT_LOCKED; + + if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode)) + return VM_FAULT_SIGBUS; + + folio = kvm_gmem_get_folio(inode, vmf->pgoff); + if (IS_ERR(folio)) { + int err = PTR_ERR(folio); + + if (err == -EAGAIN) + return VM_FAULT_RETRY; + + return vmf_error(err); + } + + if (WARN_ON_ONCE(folio_test_large(folio))) { + ret = VM_FAULT_SIGBUS; + goto out_folio; + } + + if (!folio_test_uptodate(folio)) { + clear_highpage(folio_page(folio, 0)); + kvm_gmem_mark_prepared(folio); + } + + vmf->page = folio_file_page(folio, vmf->pgoff); + +out_folio: + if (ret != VM_FAULT_LOCKED) { + folio_unlock(folio); + folio_put(folio); + } + + return ret; +} + +static const struct vm_operations_struct kvm_gmem_vm_ops = { + .fault = kvm_gmem_fault_user_mapping, +}; + +static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (!kvm_gmem_supports_mmap(file_inode(file))) + return -ENODEV; + + if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) != + (VM_SHARED | VM_MAYSHARE)) { + return -EINVAL; + } + + vma->vm_ops = &kvm_gmem_vm_ops; + + return 0; +} + static struct file_operations kvm_gmem_fops = { + .mmap = kvm_gmem_mmap, .open = generic_file_open, .release = kvm_gmem_release, .fallocate = kvm_gmem_fallocate, @@ -391,6 +458,11 @@ static const struct inode_operations kvm_gmem_iops = { .setattr = kvm_gmem_setattr, }; +bool __weak kvm_arch_supports_gmem_mmap(struct kvm *kvm) +{ + return true; +} + static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) { const char *anon_name = "[kvm-gmem]"; @@ -452,6 +524,9 @@ int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args) u64 flags = args->flags; u64 valid_flags = 0; + if (kvm_arch_supports_gmem_mmap(kvm)) + valid_flags |= GUEST_MEMFD_FLAG_MMAP; + if (flags & ~valid_flags) return -EINVAL; @@ -508,6 +583,8 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, */ WRITE_ONCE(slot->gmem.file, file); slot->gmem.pgoff = start; + if (kvm_gmem_supports_mmap(inode)) + slot->flags |= KVM_MEMSLOT_GMEM_ONLY; xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL); filemap_invalidate_unlock(inode->i_mapping); @@ -627,7 +704,7 @@ out: } EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn); -#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque) { @@ -643,7 +720,7 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long return -EINVAL; slot = gfn_to_memslot(kvm, start_gfn); - if (!kvm_slot_can_be_private(slot)) + if (!kvm_slot_has_gmem(slot)) return -EINVAL; file = kvm_gmem_get_file(slot); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6c07dd423458..f2e77ebee0ff 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -331,7 +331,7 @@ void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, * All current use cases for flushing the TLBs for a specific memslot * are related to dirty logging, and many do the TLB flush out of * mmu_lock. The interaction between the various operations on memslot - * must be serialized by slots_locks to ensure the TLB flush from one + * must be serialized by slots_lock to ensure the TLB flush from one * operation is observed by any other operation on the same memslot. */ lockdep_assert_held(&kvm->slots_lock); @@ -1103,6 +1103,14 @@ void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) { } +/* Called only on cleanup and destruction paths when there are no users. */ +static inline struct kvm_io_bus *kvm_get_bus_for_destruction(struct kvm *kvm, + enum kvm_bus idx) +{ + return rcu_dereference_protected(kvm->buses[idx], + !refcount_read(&kvm->users_count)); +} + static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) { struct kvm *kvm = kvm_arch_alloc_vm(); @@ -1228,7 +1236,7 @@ out_err_no_disable: out_err_no_arch_destroy_vm: WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) - kfree(kvm_get_bus(kvm, i)); + kfree(kvm_get_bus_for_destruction(kvm, i)); kvm_free_irq_routing(kvm); out_err_no_irq_routing: cleanup_srcu_struct(&kvm->irq_srcu); @@ -1276,7 +1284,7 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) { - struct kvm_io_bus *bus = kvm_get_bus(kvm, i); + struct kvm_io_bus *bus = kvm_get_bus_for_destruction(kvm, i); if (bus) kvm_io_bus_destroy(bus); @@ -1312,6 +1320,7 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_free_memslots(kvm, &kvm->__memslots[i][1]); } cleanup_srcu_struct(&kvm->irq_srcu); + srcu_barrier(&kvm->srcu); cleanup_srcu_struct(&kvm->srcu); #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES xa_destroy(&kvm->mem_attr_array); @@ -1588,7 +1597,7 @@ static int check_memory_region_flags(struct kvm *kvm, { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; - if (kvm_arch_has_private_mem(kvm)) + if (IS_ENABLED(CONFIG_KVM_GUEST_MEMFD)) valid_flags |= KVM_MEM_GUEST_MEMFD; /* Dirty logging private memory is not currently supported. */ @@ -4915,9 +4924,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_MEMORY_ATTRIBUTES: return kvm_supported_mem_attributes(kvm); #endif -#ifdef CONFIG_KVM_PRIVATE_MEM +#ifdef CONFIG_KVM_GUEST_MEMFD case KVM_CAP_GUEST_MEMFD: - return !kvm || kvm_arch_has_private_mem(kvm); + return 1; + case KVM_CAP_GUEST_MEMFD_MMAP: + return !kvm || kvm_arch_supports_gmem_mmap(kvm); #endif default: break; @@ -5352,7 +5363,7 @@ static long kvm_vm_ioctl(struct file *filp, case KVM_GET_STATS_FD: r = kvm_vm_ioctl_get_stats_fd(kvm); break; -#ifdef CONFIG_KVM_PRIVATE_MEM +#ifdef CONFIG_KVM_GUEST_MEMFD case KVM_CREATE_GUEST_MEMFD: { struct kvm_create_guest_memfd guest_memfd; @@ -5843,6 +5854,18 @@ static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, return -EOPNOTSUPP; } +static struct kvm_io_bus *kvm_get_bus_srcu(struct kvm *kvm, enum kvm_bus idx) +{ + /* + * Ensure that any updates to kvm_buses[] observed by the previous vCPU + * machine instruction are also visible to the vCPU machine instruction + * that triggered this call. + */ + smp_mb__after_srcu_read_lock(); + + return srcu_dereference(kvm->buses[idx], &kvm->srcu); +} + int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { @@ -5855,7 +5878,7 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, .len = len, }; - bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + bus = kvm_get_bus_srcu(vcpu->kvm, bus_idx); if (!bus) return -ENOMEM; r = __kvm_io_bus_write(vcpu, bus, &range, val); @@ -5874,7 +5897,7 @@ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, .len = len, }; - bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + bus = kvm_get_bus_srcu(vcpu->kvm, bus_idx); if (!bus) return -ENOMEM; @@ -5924,7 +5947,7 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, .len = len, }; - bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + bus = kvm_get_bus_srcu(vcpu->kvm, bus_idx); if (!bus) return -ENOMEM; r = __kvm_io_bus_read(vcpu, bus, &range, val); @@ -5932,6 +5955,13 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, } EXPORT_SYMBOL_GPL(kvm_io_bus_read); +static void __free_bus(struct rcu_head *rcu) +{ + struct kvm_io_bus *bus = container_of(rcu, struct kvm_io_bus, rcu); + + kfree(bus); +} + int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev) { @@ -5970,8 +6000,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, memcpy(new_bus->range + i + 1, bus->range + i, (bus->dev_count - i) * sizeof(struct kvm_io_range)); rcu_assign_pointer(kvm->buses[bus_idx], new_bus); - synchronize_srcu_expedited(&kvm->srcu); - kfree(bus); + call_srcu(&kvm->srcu, &bus->rcu, __free_bus); return 0; } @@ -6033,7 +6062,7 @@ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, srcu_idx = srcu_read_lock(&kvm->srcu); - bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); + bus = kvm_get_bus_srcu(kvm, bus_idx); if (!bus) goto out_unlock; diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index acef3f5c582a..31defb08ccba 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -67,7 +67,7 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, } #endif /* HAVE_KVM_PFNCACHE */ -#ifdef CONFIG_KVM_PRIVATE_MEM +#ifdef CONFIG_KVM_GUEST_MEMFD void kvm_gmem_init(struct module *module); int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args); int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -91,6 +91,6 @@ static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot) { WARN_ON_ONCE(1); } -#endif /* CONFIG_KVM_PRIVATE_MEM */ +#endif /* CONFIG_KVM_GUEST_MEMFD */ #endif /* __KVM_MM_H__ */ |