diff options
Diffstat (limited to 'include/linux/kvm_host.h')
| -rw-r--r-- | include/linux/kvm_host.h | 268 |
1 files changed, 197 insertions, 71 deletions
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 48f31dcd318a..5438a1b446a6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -97,6 +97,7 @@ #define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1) #define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2) #define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3) +#define KVM_PFN_ERR_NEEDS_IO (KVM_PFN_ERR_MASK + 4) /* * error pfns indicate that the gfn is in slot but faild to @@ -153,13 +154,6 @@ static inline bool kvm_is_error_gpa(gpa_t gpa) return gpa == INVALID_GPA; } -#define KVM_ERR_PTR_BAD_PAGE (ERR_PTR(-ENOENT)) - -static inline bool is_error_page(struct page *page) -{ - return IS_ERR(page); -} - #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) @@ -193,8 +187,6 @@ static inline bool is_error_page(struct page *page) bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); -bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except); #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -221,6 +213,7 @@ enum kvm_bus { KVM_PIO_BUS, KVM_VIRTIO_CCW_NOTIFY_BUS, KVM_FAST_MMIO_BUS, + KVM_IOCSR_BUS, KVM_NR_BUSES }; @@ -259,21 +252,26 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { - pte_t pte; unsigned long attributes; }; +enum kvm_gfn_range_filter { + KVM_FILTER_SHARED = BIT(0), + KVM_FILTER_PRIVATE = BIT(1), +}; + struct kvm_gfn_range { struct kvm_memory_slot *slot; gfn_t start; gfn_t end; union kvm_mmu_notifier_arg arg; + enum kvm_gfn_range_filter attr_filter; bool may_block; + bool lockless; }; bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); -bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range); #endif enum { @@ -283,21 +281,19 @@ enum { READING_SHADOW_PAGE_TABLES, }; -#define KVM_UNMAPPED_PAGE ((void *) 0x500 + POISON_POINTER_DELTA) - struct kvm_host_map { /* * Only valid if the 'pfn' is managed by the host kernel (i.e. There is * a 'struct page' for it. When using mem= kernel parameter some memory * can be used as guest memory but they are not managed by host * kernel). - * If 'pfn' is not managed by the host kernel, this field is - * initialized to KVM_UNMAPPED_PAGE. */ + struct page *pinned_page; struct page *page; void *hva; kvm_pfn_t pfn; kvm_pfn_t gfn; + bool writable; }; /* @@ -346,7 +342,8 @@ struct kvm_vcpu { #ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; #endif - struct pid __rcu *pid; + struct pid *pid; + rwlock_t pid_lock; int sigset_active; sigset_t sigset; unsigned int halt_poll_ns; @@ -382,8 +379,10 @@ struct kvm_vcpu { bool dy_eligible; } spin_loop; #endif + bool wants_to_run; bool preempted; bool ready; + bool scheduled_out; struct kvm_vcpu_arch arch; struct kvm_vcpu_stat stat; char stats_id[KVM_STATS_NAME_SIZE]; @@ -487,7 +486,15 @@ static __always_inline void guest_state_enter_irqoff(void) */ static __always_inline void guest_context_exit_irqoff(void) { - context_tracking_guest_exit(); + /* + * Guest mode is treated as a quiescent state, see + * guest_context_enter_irqoff() for more details. + */ + if (!context_tracking_guest_exit()) { + instrumentation_begin(); + rcu_virt_note_context_switch(); + instrumentation_end(); + } } /* @@ -596,7 +603,12 @@ struct kvm_memory_slot { #ifdef CONFIG_KVM_PRIVATE_MEM struct { - struct file __rcu *file; + /* + * Writes protected by kvm->slots_lock. Acquiring a + * reference via kvm_gmem_get_file() is protected by + * either kvm->slots_lock or kvm->srcu. + */ + struct file *file; pgoff_t pgoff; } gmem; #endif @@ -717,6 +729,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm) } #endif +#ifndef kvm_arch_has_readonly_mem +static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; @@ -956,6 +975,15 @@ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { int num_vcpus = atomic_read(&kvm->online_vcpus); + + /* + * Explicitly verify the target vCPU is online, as the anti-speculation + * logic only limits the CPU's ability to speculate, e.g. given a "bad" + * index, clamping the index to 0 would return vCPU0, not NULL. + */ + if (i >= num_vcpus) + return NULL; + i = array_index_nospec(i, num_vcpus); /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ @@ -963,9 +991,10 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ - (atomic_read(&kvm->online_vcpus) - 1)) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + if (atomic_read(&kvm->online_vcpus)) \ + xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ + (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { @@ -1163,6 +1192,10 @@ static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_ kvm_memslot_iter_is_valid(iter, end); \ kvm_memslot_iter_next(iter)) +struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); +struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); +struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); + /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot @@ -1172,7 +1205,7 @@ static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_ * -- just change its flags * * Since flags can be changed by some of these operations, the following - * differentiation is the best we can do for __kvm_set_memory_region(): + * differentiation is the best we can do for kvm_set_memory_region(): */ enum kvm_mr_change { KVM_MR_CREATE, @@ -1181,10 +1214,8 @@ enum kvm_mr_change { KVM_MR_FLAGS_ONLY, }; -int kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region2 *mem); -int __kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region2 *mem); +int kvm_set_internal_memslot(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -1201,33 +1232,70 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm); void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); -int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, - struct page **pages, int nr_pages); +int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn, + struct page **pages, int nr_pages); + +struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write); +static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) +{ + return __gfn_to_page(kvm, gfn, true); +} -struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable); unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn); unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable); + +static inline void kvm_release_page_unused(struct page *page) +{ + if (!page) + return; + + put_page(page); +} + void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); -kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, - bool *writable); -kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, - bool atomic, bool interruptible, bool *async, - bool write_fault, bool *writable, hva_t *hva); - -void kvm_release_pfn_clean(kvm_pfn_t pfn); -void kvm_release_pfn_dirty(kvm_pfn_t pfn); -void kvm_set_pfn_dirty(kvm_pfn_t pfn); -void kvm_set_pfn_accessed(kvm_pfn_t pfn); - -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty); +static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page, + bool unused, bool dirty) +{ + lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused); + + if (!page) + return; + + /* + * If the page that KVM got from the *primary MMU* is writable, and KVM + * installed or reused a SPTE, mark the page/folio dirty. Note, this + * may mark a folio dirty even if KVM created a read-only SPTE, e.g. if + * the GFN is write-protected. Folios can't be safely marked dirty + * outside of mmu_lock as doing so could race with writeback on the + * folio. As a result, KVM can't mark folios dirty in the fast page + * fault handler, and so KVM must (somewhat) speculatively mark the + * folio dirty if KVM could locklessly make the SPTE writable. + */ + if (unused) + kvm_release_page_unused(page); + else if (dirty) + kvm_release_page_dirty(page); + else + kvm_release_page_clean(page); +} + +kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn, + unsigned int foll, bool *writable, + struct page **refcounted_page); + +static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, + bool write, bool *writable, + struct page **refcounted_page) +{ + return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, + write ? FOLL_WRITE : 0, writable, refcounted_page); +} + int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); @@ -1291,19 +1359,28 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, }) int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); -struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); -struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); -struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); -int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); -void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); +int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map, + bool writable); +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map); + +static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, + struct kvm_host_map *map) +{ + return __kvm_vcpu_map(vcpu, gpa, map, true); +} + +static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa, + struct kvm_host_map *map) +{ + return __kvm_vcpu_map(vcpu, gpa, map, false); +} + unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, @@ -1498,8 +1575,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); -void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); @@ -1518,8 +1593,22 @@ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING -int kvm_arch_hardware_enable(void); -void kvm_arch_hardware_disable(void); +/* + * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under + * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of + * kvm_usage_count, i.e. at the beginning of the generic hardware enabling + * sequence, and at the end of the generic hardware disabling sequence. + */ +void kvm_arch_enable_virtualization(void); +void kvm_arch_disable_virtualization(void); +/* + * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to + * do the actual twiddling of hardware bits. The hooks are called on all + * online CPUs when KVM enables/disabled virtualization, and on a single CPU + * when that CPU is onlined/offlined (including for Resume/Suspend). + */ +int kvm_arch_enable_virtualization_cpu(void); +void kvm_arch_disable_virtualization_cpu(void); #endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); @@ -1527,7 +1616,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu); -int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); void kvm_arch_create_vm_debugfs(struct kvm *kvm); @@ -1659,13 +1747,9 @@ static inline void kvm_unregister_perf_callbacks(void) {} int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); -void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); -struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn); -bool kvm_is_zone_device_page(struct page *page); - struct kvm_irq_ack_notifier { struct hlist_node link; unsigned gsi; @@ -1959,8 +2043,6 @@ struct _kvm_stats_desc { HALT_POLL_HIST_COUNT), \ STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) -extern struct dentry *kvm_debugfs_dir; - ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, const struct _kvm_stats_desc *desc, void *stats, size_t size_stats, @@ -2100,6 +2182,7 @@ int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); +int kvm_init_irq_routing(struct kvm *kvm); int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); @@ -2109,6 +2192,11 @@ void kvm_free_irq_routing(struct kvm *kvm); static inline void kvm_free_irq_routing(struct kvm *kvm) {} +static inline int kvm_init_irq_routing(struct kvm *kvm) +{ + return 0; +} + #endif int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); @@ -2355,12 +2443,6 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ -typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data); - -int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, - uintptr_t data, const char *name, - struct task_struct **thread_ptr); - #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) { @@ -2414,7 +2496,7 @@ static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn } bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, - unsigned long attrs); + unsigned long mask, unsigned long attrs); bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, @@ -2434,15 +2516,59 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) #ifdef CONFIG_KVM_PRIVATE_MEM int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, - gfn_t gfn, kvm_pfn_t *pfn, int *max_order); + gfn_t gfn, kvm_pfn_t *pfn, struct page **page, + int *max_order); #else static inline int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, - kvm_pfn_t *pfn, int *max_order) + kvm_pfn_t *pfn, struct page **page, + int *max_order) { KVM_BUG_ON(1, kvm); return -EIO; } #endif /* CONFIG_KVM_PRIVATE_MEM */ +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE +int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM +/** + * kvm_gmem_populate() - Populate/prepare a GPA range with guest data + * + * @kvm: KVM instance + * @gfn: starting GFN to be populated + * @src: userspace-provided buffer containing data to copy into GFN range + * (passed to @post_populate, and incremented on each iteration + * if not NULL) + * @npages: number of pages to copy from userspace-buffer + * @post_populate: callback to issue for each gmem page that backs the GPA + * range + * @opaque: opaque data to pass to @post_populate callback + * + * This is primarily intended for cases where a gmem-backed GPA range needs + * to be initialized with userspace-provided data prior to being mapped into + * the guest as a private page. This should be called with the slots->lock + * held so that caller-enforced invariants regarding the expected memory + * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES. + * + * Returns the number of pages that were populated. + */ +typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + void __user *src, int order, void *opaque); + +long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, + kvm_gmem_populate_cb post_populate, void *opaque); +#endif + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range); +#endif + #endif |