/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_HOST_H #define __KVM_HOST_H #include <linux/types.h> #include <linux/hardirq.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/stat.h> #include <linux/bug.h> #include <linux/minmax.h> #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/preempt.h> #include <linux/msi.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/rcupdate.h> #include <linux/ratelimit.h> #include <linux/err.h> #include <linux/irqflags.h> #include <linux/context_tracking.h> #include <linux/irqbypass.h> #include <linux/rcuwait.h> #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> #include <linux/ftrace.h> #include <linux/hashtable.h> #include <linux/instrumentation.h> #include <linux/interval_tree.h> #include <linux/rbtree.h> #include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> #include <linux/kvm_para.h> #include <linux/kvm_types.h> #include <asm/kvm_host.h> #include <linux/kvm_dirty_ring.h> #ifndef KVM_MAX_VCPU_IDS #define KVM_MAX_VCPU_IDS … #endif /* * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally * used in kvm, other bits are visible for userspace which are defined in * include/linux/kvm_h. */ #define KVM_MEMSLOT_INVALID … /* * Bit 63 of the memslot generation number is an "update in-progress flag", * e.g. is temporarily set for the duration of kvm_swap_active_memslots(). * This flag effectively creates a unique generation number that is used to * mark cached memslot data, e.g. MMIO accesses, as potentially being stale, * i.e. may (or may not) have come from the previous memslots generation. * * This is necessary because the actual memslots update is not atomic with * respect to the generation number update. Updating the generation number * first would allow a vCPU to cache a spte from the old memslots using the * new generation number, and updating the generation number after switching * to the new memslots would allow cache hits using the old generation number * to reference the defunct memslots. * * This mechanism is used to prevent getting hits in KVM's caches while a * memslot update is in-progress, and to prevent cache hits *after* updating * the actual generation number against accesses that were inserted into the * cache *before* the memslots were updated. */ #define KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS … /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS … #ifndef KVM_MAX_NR_ADDRESS_SPACES #define KVM_MAX_NR_ADDRESS_SPACES … #endif /* * For the normal pfn, the highest 12 bits should be zero, * so we can mask bit 62 ~ bit 52 to indicate the error pfn, * mask bit 63 to indicate the noslot pfn. */ #define KVM_PFN_ERR_MASK … #define KVM_PFN_ERR_NOSLOT_MASK … #define KVM_PFN_NOSLOT … #define KVM_PFN_ERR_FAULT … #define KVM_PFN_ERR_HWPOISON … #define KVM_PFN_ERR_RO_FAULT … #define KVM_PFN_ERR_SIGPENDING … /* * error pfns indicate that the gfn is in slot but faild to * translate it to pfn on host. */ static inline bool is_error_pfn(kvm_pfn_t pfn) { … } /* * KVM_PFN_ERR_SIGPENDING indicates that fetching the PFN was interrupted * by a pending signal. Note, the signal may or may not be fatal. */ static inline bool is_sigpending_pfn(kvm_pfn_t pfn) { … } /* * error_noslot pfns indicate that the gfn can not be * translated to pfn - it is not in slot or failed to * translate it to pfn. */ static inline bool is_error_noslot_pfn(kvm_pfn_t pfn) { … } /* noslot pfn indicates that the gfn is not in slot. */ static inline bool is_noslot_pfn(kvm_pfn_t pfn) { … } /* * architectures with KVM_HVA_ERR_BAD other than PAGE_OFFSET (e.g. s390) * provide own defines and kvm_is_error_hva */ #ifndef KVM_HVA_ERR_BAD #define KVM_HVA_ERR_BAD … #define KVM_HVA_ERR_RO_BAD … static inline bool kvm_is_error_hva(unsigned long addr) { … } #endif static inline bool kvm_is_error_gpa(gpa_t gpa) { … } #define KVM_ERR_PTR_BAD_PAGE … static inline bool is_error_page(struct page *page) { … } #define KVM_REQUEST_MASK … #define KVM_REQUEST_NO_WAKEUP … #define KVM_REQUEST_WAIT … #define KVM_REQUEST_NO_ACTION … /* * Architecture-independent vcpu->requests bit members * Bits 3-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH … #define KVM_REQ_VM_DEAD … #define KVM_REQ_UNBLOCK … #define KVM_REQ_DIRTY_RING_SOFT_FULL … #define KVM_REQUEST_ARCH_BASE … /* * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to * OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick" * in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing * on. A kick only guarantees that the vCPU is on its way out, e.g. a previous * kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no * guarantee the vCPU received an IPI and has actually exited guest mode. */ #define KVM_REQ_OUTSIDE_GUEST_MODE … #define KVM_ARCH_REQ_FLAGS(nr, flags) … #define KVM_ARCH_REQ(nr) … 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); #define KVM_USERSPACE_IRQ_SOURCE_ID … #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID … extern struct mutex kvm_lock; extern struct list_head vm_list; struct kvm_io_range { … }; #define NR_IOBUS_DEVS … struct kvm_io_bus { … }; enum kvm_bus { … }; int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val); int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val, long cookie); int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev); struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr); #ifdef CONFIG_KVM_ASYNC_PF struct kvm_async_pf { … }; void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, unsigned long hva, struct kvm_arch_async_pf *arch); int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER kvm_mmu_notifier_arg; struct kvm_gfn_range { … }; 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); #endif enum { … }; #define KVM_UNMAPPED_PAGE … struct kvm_host_map { … }; /* * Used to check if the mapping is valid or not. Never use 'kvm_host_map' * directly to check for that. */ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) { … } static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) { … } /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. */ struct kvm_mmio_fragment { … }; struct kvm_vcpu { … }; /* * Start accounting time towards a guest. * Must be called before entering guest context. */ static __always_inline void guest_timing_enter_irqoff(void) { … } /* * Enter guest context and enter an RCU extended quiescent state. * * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is * unsafe to use any code which may directly or indirectly use RCU, tracing * (including IRQ flag tracing), or lockdep. All code in this period must be * non-instrumentable. */ static __always_inline void guest_context_enter_irqoff(void) { … } /* * Deprecated. Architectures should move to guest_timing_enter_irqoff() and * guest_state_enter_irqoff(). */ static __always_inline void guest_enter_irqoff(void) { … } /** * guest_state_enter_irqoff - Fixup state when entering a guest * * Entry to a guest will enable interrupts, but the kernel state is interrupts * disabled when this is invoked. Also tell RCU about it. * * 1) Trace interrupts on state * 2) Invoke context tracking if enabled to adjust RCU state * 3) Tell lockdep that interrupts are enabled * * Invoked from architecture specific code before entering a guest. * Must be called with interrupts disabled and the caller must be * non-instrumentable. * The caller has to invoke guest_timing_enter_irqoff() before this. * * Note: this is analogous to exit_to_user_mode(). */ static __always_inline void guest_state_enter_irqoff(void) { … } /* * Exit guest context and exit an RCU extended quiescent state. * * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is * unsafe to use any code which may directly or indirectly use RCU, tracing * (including IRQ flag tracing), or lockdep. All code in this period must be * non-instrumentable. */ static __always_inline void guest_context_exit_irqoff(void) { … } /* * Stop accounting time towards a guest. * Must be called after exiting guest context. */ static __always_inline void guest_timing_exit_irqoff(void) { … } /* * Deprecated. Architectures should move to guest_state_exit_irqoff() and * guest_timing_exit_irqoff(). */ static __always_inline void guest_exit_irqoff(void) { … } static inline void guest_exit(void) { … } /** * guest_state_exit_irqoff - Establish state when returning from guest mode * * Entry from a guest disables interrupts, but guest mode is traced as * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. * * 1) Tell lockdep that interrupts are disabled * 2) Invoke context tracking if enabled to reactivate RCU * 3) Trace interrupts off state * * Invoked from architecture specific code after exiting a guest. * Must be invoked with interrupts disabled and the caller must be * non-instrumentable. * The caller has to invoke guest_timing_exit_irqoff() after this. * * Note: this is analogous to enter_from_user_mode(). */ static __always_inline void guest_state_exit_irqoff(void) { … } static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { … } /* * Some of the bitops functions do not support too long bitmaps. * This number must be determined not to exceed such limits. */ #define KVM_MEM_MAX_NR_PAGES … /* * Since at idle each memslot belongs to two memslot sets it has to contain * two embedded nodes for each data structure that it forms a part of. * * Two memslot sets (one active and one inactive) are necessary so the VM * continues to run on one memslot set while the other is being modified. * * These two memslot sets normally point to the same set of memslots. * They can, however, be desynchronized when performing a memslot management * operation by replacing the memslot to be modified by its copy. * After the operation is complete, both memslot sets once again point to * the same, common set of memslot data. * * The memslots themselves are independent of each other so they can be * individually added or deleted. */ struct kvm_memory_slot { … }; static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot) { … } static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { … } static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) { … } static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *memslot) { … } #ifndef KVM_DIRTY_LOG_MANUAL_CAPS #define KVM_DIRTY_LOG_MANUAL_CAPS … #endif struct kvm_s390_adapter_int { … }; struct kvm_hv_sint { … }; struct kvm_xen_evtchn { … }; struct kvm_kernel_irq_routing_entry { … }; #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING struct kvm_irq_routing_table { … }; #endif bool kvm_arch_irqchip_in_kernel(struct kvm *kvm); #ifndef KVM_INTERNAL_MEM_SLOTS #define KVM_INTERNAL_MEM_SLOTS … #endif #define KVM_MEM_SLOTS_NUM … #define KVM_USER_MEM_SLOTS … #if KVM_MAX_NR_ADDRESS_SPACES == 1 static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm) { return KVM_MAX_NR_ADDRESS_SPACES; } static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) { return 0; } #endif /* * Arch code must define kvm_arch_has_private_mem if support for private memory * is enabled. */ #if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) static inline bool kvm_arch_has_private_mem(struct kvm *kvm) { return false; } #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 { … }; struct kvm { … }; #define kvm_err(fmt, ...) … #define kvm_info(fmt, ...) … #define kvm_debug(fmt, ...) … #define kvm_debug_ratelimited(fmt, ...) … #define kvm_pr_unimpl(fmt, ...) … /* The guest did something we don't support. */ #define vcpu_unimpl(vcpu, fmt, ...) … #define vcpu_debug(vcpu, fmt, ...) … #define vcpu_debug_ratelimited(vcpu, fmt, ...) … #define vcpu_err(vcpu, fmt, ...) … static inline void kvm_vm_dead(struct kvm *kvm) { … } static inline void kvm_vm_bugged(struct kvm *kvm) { … } #define KVM_BUG(cond, kvm, fmt...) … #define KVM_BUG_ON(cond, kvm) … /* * Note, "data corruption" refers to corruption of host kernel data structures, * not guest data. Guest data corruption, suspected or confirmed, that is tied * and contained to a single VM should *never* BUG() and potentially panic the * host, i.e. use this variant of KVM_BUG() if and only if a KVM data structure * is corrupted and that corruption can have a cascading effect to other parts * of the hosts and/or to other VMs. */ #define KVM_BUG_ON_DATA_CORRUPTION(cond, kvm) … static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) { … } static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) { … } static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { … } 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) { … } #define kvm_for_each_vcpu(idx, vcpup, kvm) … static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { … } void kvm_destroy_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); #ifdef __KVM_HAVE_IOAPIC void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm); void kvm_arch_post_irq_routing_update(struct kvm *kvm); #else static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm) { } static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm) { } #endif #ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd_init(void); void kvm_irqfd_exit(void); #else static inline int kvm_irqfd_init(void) { return 0; } static inline void kvm_irqfd_exit(void) { } #endif int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); bool kvm_get_kvm_safe(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); bool file_is_kvm(struct file *file); void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { … } static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) { … } static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) { … } static inline bool kvm_memslots_empty(struct kvm_memslots *slots) { … } bool kvm_are_all_memslots_empty(struct kvm *kvm); #define kvm_for_each_memslot(memslot, bkt, slots) … static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { … } /* Iterator used for walking memslots that overlap a gfn range. */ struct kvm_memslot_iter { … }; static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) { … } static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, struct kvm_memslots *slots, gfn_t start) { … } static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) { … } /* Iterate over each memslot at least partially intersecting [start, end) range */ #define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) … /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot * - delete an existing memory slot * - modify an existing memory slot * -- move it in the guest physical memory space * -- 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(): */ enum kvm_mr_change { … }; 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); 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, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); /* flush all memory translations */ void kvm_arch_flush_shadow_all(struct kvm *kvm); /* flush memory translations pointing to 'slot' */ 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); 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); 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); 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); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len); int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); #define __kvm_get_guest(kvm, gfn, offset, v) … #define kvm_get_guest(kvm, gpa, v) … #define __kvm_put_guest(kvm, gfn, offset, v) … #define kvm_put_guest(kvm, gpa, v) … 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); 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); 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, int len); int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len); int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len); int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, int offset, int len); int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); /** * kvm_gpc_init - initialize gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * @kvm: pointer to kvm instance. * * This sets up a gfn_to_pfn_cache by initializing locks and assigning the * immutable attributes. Note, the cache must be zero-allocated (or zeroed by * the caller before init). */ void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm); /** * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest * physical address. * * @gpc: struct gfn_to_pfn_cache object. * @gpa: guest physical address to map. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * This primes a gfn_to_pfn_cache and links it into the @gpc->kvm's list for * invalidations to be processed. Callers are required to use kvm_gpc_check() * to ensure that the cache is valid before accessing the target page. */ int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len); /** * kvm_gpc_activate_hva - prepare a cached kernel mapping and HPA for a given HVA. * * @gpc: struct gfn_to_pfn_cache object. * @hva: userspace virtual address to map. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * The semantics of this function are the same as those of kvm_gpc_activate(). It * merely bypasses a layer of address translation. */ int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long hva, unsigned long len); /** * kvm_gpc_check - check validity of a gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * @len: sanity check; the range being access must fit a single page. * * @return: %true if the cache is still valid and the address matches. * %false if the cache is not valid. * * Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock * while calling this function, and then continue to hold the lock until the * access is complete. * * Callers in IN_GUEST_MODE may do so without locking, although they should * still hold a read lock on kvm->scru for the memslot checks. */ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len); /** * kvm_gpc_refresh - update a previously initialized cache. * * @gpc: struct gfn_to_pfn_cache object. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * This will attempt to refresh a gfn_to_pfn_cache. Note that a successful * return from this function does not mean the page can be immediately * accessed because it may have raced with an invalidation. Callers must * still lock and check the cache status, as this function does not return * with the lock still held to permit access. */ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len); /** * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * * This removes a cache from the VM's list to be processed on MMU notifier * invocation. */ void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc); static inline bool kvm_gpc_is_gpa_active(struct gfn_to_pfn_cache *gpc) { … } static inline bool kvm_gpc_is_hva_active(struct gfn_to_pfn_cache *gpc) { … } void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); void kvm_vcpu_halt(struct kvm_vcpu *vcpu); bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot); #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min); int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min); int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc); void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); #endif void kvm_mmu_invalidate_begin(struct kvm *kvm); void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end); void kvm_mmu_invalidate_end(struct kvm *kvm); bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf); int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext); void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot); #ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty, struct kvm_memory_slot **memslot); #endif int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr); int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); 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_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); int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); #endif #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); #else static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING /* * 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); 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); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* * All architectures that want to use vzalloc currently also * need their own kvm_arch_alloc_vm implementation. */ static inline struct kvm *kvm_arch_alloc_vm(void) { return kzalloc(sizeof(struct kvm), GFP_KERNEL_ACCOUNT); } #endif static inline void __kvm_arch_free_vm(struct kvm *kvm) { … } #ifndef __KVM_HAVE_ARCH_VM_FREE static inline void kvm_arch_free_vm(struct kvm *kvm) { __kvm_arch_free_vm(kvm); } #endif #ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { return -ENOTSUPP; } #else int kvm_arch_flush_remote_tlbs(struct kvm *kvm); #endif #ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { return -EOPNOTSUPP; } #else int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); #endif #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA void kvm_arch_register_noncoherent_dma(struct kvm *kvm); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm); bool kvm_arch_has_noncoherent_dma(struct kvm *kvm); #else static inline void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { } static inline void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { } static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) { return false; } #endif #ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE void kvm_arch_start_assignment(struct kvm *kvm); void kvm_arch_end_assignment(struct kvm *kvm); bool kvm_arch_has_assigned_device(struct kvm *kvm); #else static inline void kvm_arch_start_assignment(struct kvm *kvm) { } static inline void kvm_arch_end_assignment(struct kvm *kvm) { } static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } #endif static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { … } /* * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns * true if the vCPU was blocking and was awakened, false otherwise. */ static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { … } static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) { … } #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and * ready to accept virtual IRQ. On some architectures the virtual interrupt * controller is dynamically instantiated and this is not always true. */ bool kvm_arch_intc_initialized(struct kvm *kvm); #else static inline bool kvm_arch_intc_initialized(struct kvm *kvm) { … } #endif #ifdef CONFIG_GUEST_PERF_EVENTS unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu); void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)); void kvm_unregister_perf_callbacks(void); #else static inline void kvm_register_perf_callbacks(void *ign) {} static inline void kvm_unregister_perf_callbacks(void) {} #endif /* CONFIG_GUEST_PERF_EVENTS */ 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 { … }; int kvm_irq_map_gsi(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *entries, int gsi); int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin); int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, int irq_source_id, int level, bool line_status); int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status); bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_notify_acked_gsi(struct kvm *kvm, int gsi); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); int kvm_request_irq_source_id(struct kvm *kvm); void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. */ static inline struct kvm_memory_slot * try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { … } /* * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * * With "approx" set returns the memslot also when the address falls * in a hole. In that case one of the memslots bordering the hole is * returned. */ static inline struct kvm_memory_slot * search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { … } static inline struct kvm_memory_slot * ____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { … } /* * __gfn_to_memslot() and its descendants are here to allow arch code to inline * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline * because that would bloat other code too much. */ static inline struct kvm_memory_slot * __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) { … } static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { … } static inline int memslot_id(struct kvm *kvm, gfn_t gfn) { … } static inline gfn_t hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot) { … } static inline gpa_t gfn_to_gpa(gfn_t gfn) { … } static inline gfn_t gpa_to_gfn(gpa_t gpa) { … } static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) { … } static inline bool kvm_is_gpa_in_memslot(struct kvm *kvm, gpa_t gpa) { … } static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc) { … } enum kvm_stat_kind { … }; struct kvm_stat_data { … }; struct _kvm_stats_desc { … }; #define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) … #define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) … #define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) … #define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) … #define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) … /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) … #define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) … #define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) … #define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) … #define STATS_DESC_LINEAR_HIST(SCOPE, name, unit, base, exponent, sz, bsz) … #define STATS_DESC_LOG_HIST(SCOPE, name, unit, base, exponent, sz) … /* Cumulative counter, read/write */ #define STATS_DESC_COUNTER(SCOPE, name) … /* Instantaneous counter, read only */ #define STATS_DESC_ICOUNTER(SCOPE, name) … /* Peak counter, read/write */ #define STATS_DESC_PCOUNTER(SCOPE, name) … /* Instantaneous boolean value, read only */ #define STATS_DESC_IBOOLEAN(SCOPE, name) … /* Peak (sticky) boolean value, read/write */ #define STATS_DESC_PBOOLEAN(SCOPE, name) … /* Cumulative time in nanosecond */ #define STATS_DESC_TIME_NSEC(SCOPE, name) … /* Linear histogram for time in nanosecond */ #define STATS_DESC_LINHIST_TIME_NSEC(SCOPE, name, sz, bsz) … /* Logarithmic histogram for time in nanosecond */ #define STATS_DESC_LOGHIST_TIME_NSEC(SCOPE, name, sz) … #define KVM_GENERIC_VM_STATS() … #define KVM_GENERIC_VCPU_STATS() … 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, char __user *user_buffer, size_t size, loff_t *offset); /** * kvm_stats_linear_hist_update() - Update bucket value for linear histogram * statistics data. * * @data: start address of the stats data * @size: the number of bucket of the stats data * @value: the new value used to update the linear histogram's bucket * @bucket_size: the size (width) of a bucket */ static inline void kvm_stats_linear_hist_update(u64 *data, size_t size, u64 value, size_t bucket_size) { … } /** * kvm_stats_log_hist_update() - Update bucket value for logarithmic histogram * statistics data. * * @data: start address of the stats data * @size: the number of bucket of the stats data * @value: the new value used to update the logarithmic histogram's bucket */ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) { … } #define KVM_STATS_LINEAR_HIST_UPDATE(array, value, bsize) … #define KVM_STATS_LOG_HIST_UPDATE(array, value) … extern const struct kvm_stats_header kvm_vm_stats_header; extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { … } static inline int mmu_invalidate_retry_gfn(struct kvm *kvm, unsigned long mmu_seq, gfn_t gfn) { … } /* * This lockless version of the range-based retry check *must* be paired with a * call to the locked version after acquiring mmu_lock, i.e. this is safe to * use only as a pre-check to avoid contending mmu_lock. This version *will* * get false negatives and false positives. */ static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, unsigned long mmu_seq, gfn_t gfn) { … } #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING #define KVM_MAX_IRQ_ROUTES … bool kvm_arch_can_set_irq_routing(struct kvm *kvm); 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); void kvm_free_irq_routing(struct kvm *kvm); #else 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); void kvm_eventfd_init(struct kvm *kvm); int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); bool kvm_notify_irqfd_resampler(struct kvm *kvm, unsigned int irqchip, unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) { return -EINVAL; } static inline void kvm_irqfd_release(struct kvm *kvm) {} static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, unsigned int irqchip, unsigned int pin) { return false; } #endif /* CONFIG_HAVE_KVM_IRQCHIP */ void kvm_arch_irq_routing_update(struct kvm *kvm); static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu) { … } static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) { … } static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { … } static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu) { … } static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu) { … } static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) { … } #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING extern bool kvm_rebooting; #endif extern unsigned int halt_poll_ns; extern unsigned int halt_poll_ns_grow; extern unsigned int halt_poll_ns_grow_start; extern unsigned int halt_poll_ns_shrink; struct kvm_device { … }; /* create, destroy, and name are mandatory */ struct kvm_device_ops { … }; struct kvm_device *kvm_device_from_filp(struct file *filp); int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; extern struct kvm_device_ops kvm_arm_vgic_v2_ops; extern struct kvm_device_ops kvm_arm_vgic_v3_ops; #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) { … } static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) { … } #else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) { } static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) { } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot) { … } struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS bool kvm_arch_has_irq_bypass(void); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *); void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *, struct kvm_kernel_irq_routing_entry *); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ #ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS /* If we wakeup during the poll time, was it a sucessful poll? */ static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { return vcpu->valid_wakeup; } #else static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { … } #endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */ #ifdef CONFIG_HAVE_KVM_NO_POLL /* Callback that tells if we must not poll */ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu); #else static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { return false; } #endif /* CONFIG_HAVE_KVM_NO_POLL */ #ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); #else static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { … } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) { … } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ kvm_vm_thread_fn_t; 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) { … } #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ /* * If more than one page is being (un)accounted, @virt must be the address of * the first page of a block of pages what were allocated together (i.e * accounted together). * * kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state() * is thread-safe. */ static inline void kvm_account_pgtable_pages(void *virt, int nr) { … } /* * This defines how many reserved entries we want to keep before we * kick the vcpu to the userspace to avoid dirty ring full. This * value can be tuned to higher if e.g. PML is enabled on the host. */ #define KVM_DIRTY_RING_RSVD_ENTRIES … /* Max number of entries allowed for each kvm dirty ring */ #define KVM_DIRTY_RING_MAX_ENTRIES … static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, gpa_t gpa, gpa_t size, bool is_write, bool is_exec, bool is_private) { … } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES 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 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, struct kvm_gfn_range *range); static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { … } #else static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return false; } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ #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); #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_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. */ kvm_gmem_populate_cb; 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
Codebase Browser
linux