diff options
Diffstat (limited to 'include/linux/kvm_host.h')
| -rw-r--r-- | include/linux/kvm_host.h | 1225 |
1 files changed, 1047 insertions, 178 deletions
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bcb9b2ac0791..18592bdf4c1b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -10,7 +10,9 @@ #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> @@ -23,9 +25,16 @@ #include <linux/irqflags.h> #include <linux/context_tracking.h> #include <linux/irqbypass.h> -#include <linux/swait.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> @@ -34,9 +43,10 @@ #include <linux/kvm_types.h> #include <asm/kvm_host.h> +#include <linux/kvm_dirty_ring.h> -#ifndef KVM_MAX_VCPU_ID -#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS +#ifndef KVM_MAX_VCPU_IDS +#define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif /* @@ -138,22 +148,40 @@ static inline bool is_error_page(struct page *page) #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) +#define KVM_REQUEST_NO_ACTION BIT(10) /* * Architecture-independent vcpu->requests bit members - * Bits 4-7 are reserved for more arch-independent bits. + * Bits 3-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_PENDING_TIMER 2 -#define KVM_REQ_UNHALT 3 +#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_UNBLOCK 2 #define KVM_REQUEST_ARCH_BASE 8 +/* + * 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 (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) + #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) +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); +bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap); + #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -190,8 +218,8 @@ 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); -void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, - 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); @@ -206,15 +234,30 @@ struct kvm_async_pf { unsigned long addr; struct kvm_arch_async_pf arch; bool wakeup_all; + bool notpresent_injected; }; void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); -int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - unsigned long hva, struct kvm_arch_async_pf *arch); +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 KVM_ARCH_WANT_MMU_NOTIFIER +struct kvm_gfn_range { + struct kvm_memory_slot *slot; + gfn_t start; + gfn_t end; + pte_t pte; + bool may_block; +}; +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 { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, @@ -248,6 +291,11 @@ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) return !!map->hva; } +static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) +{ + return single_task_running() && !need_resched() && ktime_before(cur, stop); +} + /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. @@ -266,22 +314,23 @@ struct kvm_vcpu { int cpu; int vcpu_id; /* id given by userspace at creation */ int vcpu_idx; /* index in kvm->vcpus array */ - int srcu_idx; + int ____srcu_idx; /* Don't use this directly. You've been warned. */ +#ifdef CONFIG_PROVE_RCU + int srcu_depth; +#endif int mode; u64 requests; unsigned long guest_debug; - int pre_pcpu; - struct list_head blocked_vcpu_list; - struct mutex mutex; struct kvm_run *run; - struct swait_queue_head wq; +#ifndef __KVM_HAVE_ARCH_WQP + struct rcuwait wait; +#endif struct pid __rcu *pid; int sigset_active; sigset_t sigset; - struct kvm_vcpu_stat stat; unsigned int halt_poll_ns; bool valid_wakeup; @@ -318,9 +367,169 @@ struct kvm_vcpu { bool preempted; bool ready; struct kvm_vcpu_arch arch; - struct dentry *debugfs_dentry; + struct kvm_vcpu_stat stat; + char stats_id[KVM_STATS_NAME_SIZE]; + struct kvm_dirty_ring dirty_ring; + + /* + * The most recently used memslot by this vCPU and the slots generation + * for which it is valid. + * No wraparound protection is needed since generations won't overflow in + * thousands of years, even assuming 1M memslot operations per second. + */ + struct kvm_memory_slot *last_used_slot; + u64 last_used_slot_gen; }; +/* + * Start accounting time towards a guest. + * Must be called before entering guest context. + */ +static __always_inline void guest_timing_enter_irqoff(void) +{ + /* + * This is running in ioctl context so its safe to assume that it's the + * stime pending cputime to flush. + */ + instrumentation_begin(); + vtime_account_guest_enter(); + instrumentation_end(); +} + +/* + * 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) +{ + /* + * KVM does not hold any references to rcu protected data when it + * switches CPU into a guest mode. In fact switching to a guest mode + * is very similar to exiting to userspace from rcu point of view. In + * addition CPU may stay in a guest mode for quite a long time (up to + * one time slice). Lets treat guest mode as quiescent state, just like + * we do with user-mode execution. + */ + if (!context_tracking_guest_enter()) { + instrumentation_begin(); + rcu_virt_note_context_switch(smp_processor_id()); + instrumentation_end(); + } +} + +/* + * Deprecated. Architectures should move to guest_timing_enter_irqoff() and + * guest_state_enter_irqoff(). + */ +static __always_inline void guest_enter_irqoff(void) +{ + guest_timing_enter_irqoff(); + guest_context_enter_irqoff(); +} + +/** + * 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) +{ + instrumentation_begin(); + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(); + instrumentation_end(); + + guest_context_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +/* + * 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) +{ + context_tracking_guest_exit(); +} + +/* + * Stop accounting time towards a guest. + * Must be called after exiting guest context. + */ +static __always_inline void guest_timing_exit_irqoff(void) +{ + instrumentation_begin(); + /* Flush the guest cputime we spent on the guest */ + vtime_account_guest_exit(); + instrumentation_end(); +} + +/* + * Deprecated. Architectures should move to guest_state_exit_irqoff() and + * guest_timing_exit_irqoff(). + */ +static __always_inline void guest_exit_irqoff(void) +{ + guest_context_exit_irqoff(); + guest_timing_exit_irqoff(); +} + +static inline void guest_exit(void) +{ + unsigned long flags; + + local_irq_save(flags); + guest_exit_irqoff(); + local_irq_restore(flags); +} + +/** + * 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) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + guest_context_exit_irqoff(); + + instrumentation_begin(); + trace_hardirqs_off_finish(); + instrumentation_end(); +} + static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* @@ -338,7 +547,26 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) +/* + * 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 { + struct hlist_node id_node[2]; + struct interval_tree_node hva_node[2]; + struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; @@ -346,8 +574,14 @@ struct kvm_memory_slot { unsigned long userspace_addr; u32 flags; short id; + u16 as_id; }; +static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) +{ + return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; +} + static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) { return ALIGN(memslot->npages, BITS_PER_LONG) / 8; @@ -360,6 +594,10 @@ static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *mem return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap); } +#ifndef KVM_DIRTY_LOG_MANUAL_CAPS +#define KVM_DIRTY_LOG_MANUAL_CAPS KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE +#endif + struct kvm_s390_adapter_int { u64 ind_addr; u64 summary_addr; @@ -373,6 +611,13 @@ struct kvm_hv_sint { u32 sint; }; +struct kvm_xen_evtchn { + u32 port; + u32 vcpu_id; + int vcpu_idx; + u32 priority; +}; + struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; @@ -393,6 +638,7 @@ struct kvm_kernel_irq_routing_entry { } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; + struct kvm_xen_evtchn xen_evtchn; }; struct hlist_node link; }; @@ -405,17 +651,16 @@ struct kvm_irq_routing_table { * Array indexed by gsi. Each entry contains list of irq chips * the gsi is connected to. */ - struct hlist_head map[0]; + struct hlist_head map[]; }; #endif -#ifndef KVM_PRIVATE_MEM_SLOTS -#define KVM_PRIVATE_MEM_SLOTS 0 +#ifndef KVM_INTERNAL_MEM_SLOTS +#define KVM_INTERNAL_MEM_SLOTS 0 #endif -#ifndef KVM_MEM_SLOTS_NUM -#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) -#endif +#define KVM_MEM_SLOTS_NUM SHRT_MAX +#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS) #ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) @@ -424,26 +669,56 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) } #endif -/* - * Note: - * memslots are not sorted by id anymore, please use id_to_memslot() - * to get the memslot by its id. - */ struct kvm_memslots { u64 generation; - struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM]; - /* The mapping table from slot id to the index in memslots[]. */ - short id_to_index[KVM_MEM_SLOTS_NUM]; - atomic_t lru_slot; - int used_slots; + atomic_long_t last_used_slot; + struct rb_root_cached hva_tree; + struct rb_root gfn_tree; + /* + * The mapping table from slot id to memslot. + * + * 7-bit bucket count matches the size of the old id to index array for + * 512 slots, while giving good performance with this slot count. + * Higher bucket counts bring only small performance improvements but + * always result in higher memory usage (even for lower memslot counts). + */ + DECLARE_HASHTABLE(id_hash, 7); + int node_idx; }; struct kvm { +#ifdef KVM_HAVE_MMU_RWLOCK + rwlock_t mmu_lock; +#else spinlock_t mmu_lock; +#endif /* KVM_HAVE_MMU_RWLOCK */ + struct mutex slots_lock; + + /* + * Protects the arch-specific fields of struct kvm_memory_slots in + * use by the VM. To be used under the slots_lock (above) or in a + * kvm->srcu critical section where acquiring the slots_lock would + * lead to deadlock with the synchronize_srcu in + * install_new_memslots. + */ + struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ + unsigned long nr_memslot_pages; + /* The two memslot sets - active and inactive (per address space) */ + struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2]; + /* The current active memslot set for each address space */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; - struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct xarray vcpu_array; + + /* Used to wait for completion of MMU notifiers. */ + spinlock_t mn_invalidate_lock; + unsigned long mn_active_invalidate_count; + struct rcuwait mn_memslots_update_rcuwait; + + /* For management / invalidation of gfn_to_pfn_caches */ + spinlock_t gpc_lock; + struct list_head gpc_list; /* * created_vcpus is protected by kvm->lock, and is incremented @@ -452,6 +727,7 @@ struct kvm { * and is accessed atomically. */ atomic_t online_vcpus; + int max_vcpus; int created_vcpus; int last_boosted_vcpu; struct list_head vm_list; @@ -488,17 +764,27 @@ struct kvm { #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) struct mmu_notifier mmu_notifier; - unsigned long mmu_notifier_seq; - long mmu_notifier_count; + unsigned long mmu_invalidate_seq; + long mmu_invalidate_in_progress; + unsigned long mmu_invalidate_range_start; + unsigned long mmu_invalidate_range_end; #endif - long tlbs_dirty; struct list_head devices; - bool manual_dirty_log_protect; + u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; struct kvm_stat_data **debugfs_stat_data; struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; + unsigned int max_halt_poll_ns; + u32 dirty_ring_size; + bool vm_bugged; + bool vm_dead; + +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER + struct notifier_block pm_notifier; +#endif + char stats_id[KVM_STATS_NAME_SIZE]; }; #define kvm_err(fmt, ...) \ @@ -527,6 +813,61 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline void kvm_vm_dead(struct kvm *kvm) +{ + kvm->vm_dead = true; + kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD); +} + +static inline void kvm_vm_bugged(struct kvm *kvm) +{ + kvm->vm_bugged = true; + kvm_vm_dead(kvm); +} + + +#define KVM_BUG(cond, kvm, fmt...) \ +({ \ + int __ret = (cond); \ + \ + if (WARN_ONCE(__ret && !(kvm)->vm_bugged, fmt)) \ + kvm_vm_bugged(kvm); \ + unlikely(__ret); \ +}) + +#define KVM_BUG_ON(cond, kvm) \ +({ \ + int __ret = (cond); \ + \ + if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ + kvm_vm_bugged(kvm); \ + unlikely(__ret); \ +}) + +static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(vcpu->srcu_depth++, + "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); +#endif + vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) +{ + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); + +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(--vcpu->srcu_depth, + "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); +#endif +} + +static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) +{ + return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); +} + static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) { return srcu_dereference_check(kvm->buses[idx], &kvm->srcu, @@ -541,19 +882,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); - return kvm->vcpus[i]; + return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - for (idx = 0; \ - idx < atomic_read(&kvm->online_vcpus) && \ - (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ - idx++) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + 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) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (id < 0) return NULL; @@ -567,17 +906,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) -{ - return vcpu->vcpu_idx; -} - -#define kvm_for_each_memslot(memslot, slots) \ - for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\ - memslot++) - -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); +void kvm_destroy_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); @@ -612,7 +941,9 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, 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) @@ -635,18 +966,124 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) return __kvm_memslots(vcpu->kvm, as_id); } -static inline struct kvm_memory_slot * -id_to_memslot(struct kvm_memslots *slots, int id) +static inline bool kvm_memslots_empty(struct kvm_memslots *slots) +{ + return RB_EMPTY_ROOT(&slots->gfn_tree); +} + +#define kvm_for_each_memslot(memslot, bkt, slots) \ + hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ + if (WARN_ON_ONCE(!memslot->npages)) { \ + } else + +static inline +struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { - int index = slots->id_to_index[id]; struct kvm_memory_slot *slot; + int idx = slots->node_idx; - slot = &slots->memslots[index]; + hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { + if (slot->id == id) + return slot; + } - WARN_ON(slot->id != id); - return slot; + return NULL; } +/* Iterator used for walking memslots that overlap a gfn range. */ +struct kvm_memslot_iter { + struct kvm_memslots *slots; + struct rb_node *node; + struct kvm_memory_slot *slot; +}; + +static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) +{ + iter->node = rb_next(iter->node); + if (!iter->node) + return; + + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); +} + +static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, + struct kvm_memslots *slots, + gfn_t start) +{ + int idx = slots->node_idx; + struct rb_node *tmp; + struct kvm_memory_slot *slot; + + iter->slots = slots; + + /* + * Find the so called "upper bound" of a key - the first node that has + * its key strictly greater than the searched one (the start gfn in our case). + */ + iter->node = NULL; + for (tmp = slots->gfn_tree.rb_node; tmp; ) { + slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); + if (start < slot->base_gfn) { + iter->node = tmp; + tmp = tmp->rb_left; + } else { + tmp = tmp->rb_right; + } + } + + /* + * Find the slot with the lowest gfn that can possibly intersect with + * the range, so we'll ideally have slot start <= range start + */ + if (iter->node) { + /* + * A NULL previous node means that the very first slot + * already has a higher start gfn. + * In this case slot start > range start. + */ + tmp = rb_prev(iter->node); + if (tmp) + iter->node = tmp; + } else { + /* a NULL node below means no slots */ + iter->node = rb_last(&slots->gfn_tree); + } + + if (iter->node) { + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); + + /* + * It is possible in the slot start < range start case that the + * found slot ends before or at range start (slot end <= range start) + * and so it does not overlap the requested range. + * + * In such non-overlapping case the next slot (if it exists) will + * already have slot start > range start, otherwise the logic above + * would have found it instead of the current slot. + */ + if (iter->slot->base_gfn + iter->slot->npages <= start) + kvm_memslot_iter_next(iter); + } +} + +static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) +{ + if (!iter->node) + return false; + + /* + * If this slot starts beyond or at the end of the range so does + * every next one + */ + return iter->slot->base_gfn < end; +} + +/* Iterate over each memslot at least partially intersecting [start, end) range */ +#define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ + for (kvm_memslot_iter_start(iter, slots, start); \ + kvm_memslot_iter_is_valid(iter, end); \ + kvm_memslot_iter_next(iter)) + /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot @@ -669,22 +1106,16 @@ int kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem); int __kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem); -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages); +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, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + 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, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); -bool kvm_largepages_enabled(void); -void kvm_disable_largepages(void); /* flush all memory translations */ void kvm_arch_flush_shadow_all(struct kvm *kvm); /* flush memory translations pointing to 'slot' */ @@ -702,30 +1133,30 @@ 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); -void kvm_set_page_accessed(struct page *page); -kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); 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(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, +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 *async, bool write_fault, - bool *writable); + 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_get_pfn(kvm_pfn_t pfn); -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); +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, @@ -738,32 +1169,54 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); -#define __kvm_put_guest(kvm, gfn, offset, value, type) \ +#define __kvm_get_guest(kvm, gfn, offset, v) \ +({ \ + unsigned long __addr = gfn_to_hva(kvm, gfn); \ + typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ + int __ret = -EFAULT; \ + \ + if (!kvm_is_error_hva(__addr)) \ + __ret = get_user(v, __uaddr); \ + __ret; \ +}) + +#define kvm_get_guest(kvm, gpa, v) \ +({ \ + gpa_t __gpa = gpa; \ + struct kvm *__kvm = kvm; \ + \ + __kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT, \ + offset_in_page(__gpa), v); \ +}) + +#define __kvm_put_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ - type __user *__uaddr = (type __user *)(__addr + offset); \ + typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ int __ret = -EFAULT; \ \ if (!kvm_is_error_hva(__addr)) \ - __ret = put_user(value, __uaddr); \ + __ret = put_user(v, __uaddr); \ if (!__ret) \ mark_page_dirty(kvm, gfn); \ __ret; \ }) -#define kvm_put_guest(kvm, gpa, value, type) \ +#define kvm_put_guest(kvm, gpa, v) \ ({ \ gpa_t __gpa = gpa; \ struct kvm *__kvm = kvm; \ + \ __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ - offset_in_page(__gpa), (value), type); \ + offset_in_page(__gpa), v); \ }) -int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); 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); @@ -771,12 +1224,7 @@ 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); -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic); -struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic); 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, @@ -791,10 +1239,116 @@ 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. + * + * This sets up a gfn_to_pfn_cache by initializing locks. Note, the cache must + * be zero-allocated (or zeroed by the caller before init). + */ +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc); + +/** + * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest + * physical address. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @vcpu: vCPU to be used for marking pages dirty and to be woken on + * invalidation. + * @usage: indicates if the resulting host physical PFN is used while + * the @vcpu is IN_GUEST_MODE (in which case invalidation of + * the cache from MMU notifiers---but not for KVM memslot + * changes!---will also force @vcpu to exit the guest and + * refresh the cache); and/or if the PFN used directly + * by KVM (and thus needs a kernel virtual mapping). + * @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 @kvm's list for + * invalidations to be processed. Callers are required to use + * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before + * accessing the target page. + */ +int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, + gpa_t gpa, unsigned long len); + +/** + * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @gpa: current guest physical address to map. + * @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_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len); + +/** + * kvm_gfn_to_pfn_cache_refresh - update a previously initialized cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @gpa: updated 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 will attempt to refresh a gfn_to_pfn_cache. Note that a successful + * returm 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_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len); + +/** + * kvm_gfn_to_pfn_cache_unmap - temporarily unmap a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * + * This unmaps the referenced page. The cache is left in the invalid state + * but at least the mapping from GPA to userspace HVA will remain cached + * and can be reused on a subsequent refresh. + */ +void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); + +/** + * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * + * This removes a cache from the @kvm's list to be processed on MMU notifier + * invocation. + */ +void kvm_gpc_deactivate(struct kvm *kvm, 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_block(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); @@ -803,13 +1357,19 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); void kvm_flush_remote_tlbs(struct kvm *kvm); -void kvm_reload_remote_mmus(struct kvm *kvm); -bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - unsigned long *vcpu_bitmap, cpumask_var_t tmp); -bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); -bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, - unsigned long *vcpu_bitmap); +#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, unsigned long start, + unsigned long end); +void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start, + unsigned long end); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -819,23 +1379,20 @@ 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); -int kvm_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log, int *is_dirty); - -int kvm_get_dirty_log_protect(struct kvm *kvm, - struct kvm_dirty_log *log, bool *flush); -int kvm_clear_dirty_log_protect(struct kvm *kvm, - struct kvm_clear_dirty_log *log, bool *flush); - void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); - -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log); -int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, - struct kvm_clear_dirty_log *log); +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot); + +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, + const struct kvm_memory_slot *memslot); +#else /* !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); @@ -843,6 +1400,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); long 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); @@ -862,7 +1421,7 @@ 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, struct kvm_run *kvm_run); +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); int kvm_arch_init(void *opaque); void kvm_arch_exit(void); @@ -876,21 +1435,29 @@ 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); +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 int kvm_arch_hardware_enable(void); void kvm_arch_hardware_disable(void); -int kvm_arch_hardware_setup(void); +int kvm_arch_hardware_setup(void *opaque); void kvm_arch_hardware_unsetup(void); -int kvm_arch_check_processor_compat(void); +int kvm_arch_check_processor_compat(void *opaque); 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); int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); +int kvm_arch_create_vm_debugfs(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* @@ -901,10 +1468,17 @@ static inline struct kvm *kvm_arch_alloc_vm(void) { return kzalloc(sizeof(struct kvm), GFP_KERNEL); } +#endif + +static inline void __kvm_arch_free_vm(struct kvm *kvm) +{ + kvfree(kvm); +} +#ifndef __KVM_HAVE_ARCH_VM_FREE static inline void kvm_arch_free_vm(struct kvm *kvm) { - kfree(kvm); + __kvm_arch_free_vm(kvm); } #endif @@ -946,21 +1520,35 @@ static inline void kvm_arch_end_assignment(struct kvm *kvm) { } -static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } #endif -static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) +static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP - return vcpu->arch.wqp; + return vcpu->arch.waitp; #else - return &vcpu->wq; + return &vcpu->wait; #endif } +/* + * 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) +{ + return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); +} + +static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) +{ + return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); +} + #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and @@ -975,15 +1563,24 @@ 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); -bool kvm_is_reserved_pfn(kvm_pfn_t pfn); -bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn); +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; @@ -1014,50 +1611,91 @@ 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); /* - * search_memslots() and __gfn_to_memslot() are here because they are - * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c. - * gfn_to_memslot() itself isn't here as an inline because that would - * bloat other code too much. + * Returns a pointer to the memslot if it contains gfn. + * Otherwise returns NULL. */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn) +try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->lru_slot); - struct kvm_memory_slot *memslots = slots->memslots; - - if (gfn >= memslots[slot].base_gfn && - gfn < memslots[slot].base_gfn + memslots[slot].npages) - return &memslots[slot]; + if (!slot) + return NULL; - while (start < end) { - slot = start + (end - start) / 2; + if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) + return slot; + else + return NULL; +} - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; +/* + * 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) +{ + struct kvm_memory_slot *slot; + struct rb_node *node; + int idx = slots->node_idx; + + slot = NULL; + for (node = slots->gfn_tree.rb_node; node; ) { + slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); + if (gfn >= slot->base_gfn) { + if (gfn < slot->base_gfn + slot->npages) + return slot; + node = node->rb_right; + } else + node = node->rb_left; } - if (gfn >= memslots[start].base_gfn && - gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->lru_slot, start); - return &memslots[start]; + return approx ? slot : NULL; +} + +static inline struct kvm_memory_slot * +____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) +{ + struct kvm_memory_slot *slot; + + slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); + slot = try_get_memslot(slot, gfn); + if (slot) + return slot; + + slot = search_memslots(slots, gfn, approx); + if (slot) { + atomic_long_set(&slots->last_used_slot, (unsigned long)slot); + return slot; } return NULL; } +/* + * __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) { - return search_memslots(slots, gfn); + return ____gfn_to_memslot(slots, gfn, false); } static inline unsigned long -__gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +__gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { - return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE; + /* + * The index was checked originally in search_memslots. To avoid + * that a malicious guest builds a Spectre gadget out of e.g. page + * table walks, do not let the processor speculate loads outside + * the guest's registered memslots. + */ + unsigned long offset = gfn - slot->base_gfn; + offset = array_index_nospec(offset, slot->npages); + return slot->userspace_addr + offset * PAGE_SIZE; } static inline int memslot_id(struct kvm *kvm, gfn_t gfn) @@ -1088,12 +1726,6 @@ static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) return (hpa_t)pfn << PAGE_SHIFT; } -static inline struct page *kvm_vcpu_gpa_to_page(struct kvm_vcpu *vcpu, - gpa_t gpa) -{ - return kvm_vcpu_gfn_to_page(vcpu, gpa_to_gfn(gpa)); -} - static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa) { unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); @@ -1108,39 +1740,222 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - struct kvm_stats_debugfs_item *dbgfs_item; + const struct _kvm_stats_desc *desc; + enum kvm_stat_kind kind; }; -struct kvm_stats_debugfs_item { - const char *name; - int offset; - enum kvm_stat_kind kind; - int mode; +struct _kvm_stats_desc { + struct kvm_stats_desc desc; + char name[KVM_STATS_NAME_SIZE]; }; -#define KVM_DBGFS_GET_MODE(dbgfs_item) \ - ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) +#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = sz, \ + .bucket_size = bsz + +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, stat) \ + }, \ + .name = #stat, \ + } +/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ +#define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ + SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) + +#define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, \ + unit, base, exponent, 1, 0) +#define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, \ + unit, base, exponent, 1, 0) +#define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, \ + unit, base, exponent, 1, 0) +#define STATS_DESC_LINEAR_HIST(SCOPE, name, unit, base, exponent, sz, bsz) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LINEAR_HIST, \ + unit, base, exponent, sz, bsz) +#define STATS_DESC_LOG_HIST(SCOPE, name, unit, base, exponent, sz) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LOG_HIST, \ + unit, base, exponent, sz, 0) + +/* Cumulative counter, read/write */ +#define STATS_DESC_COUNTER(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Instantaneous counter, read only */ +#define STATS_DESC_ICOUNTER(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Peak counter, read/write */ +#define STATS_DESC_PCOUNTER(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) + +/* Instantaneous boolean value, read only */ +#define STATS_DESC_IBOOLEAN(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) +/* Peak (sticky) boolean value, read/write */ +#define STATS_DESC_PBOOLEAN(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) + +/* Cumulative time in nanosecond */ +#define STATS_DESC_TIME_NSEC(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9) +/* Linear histogram for time in nanosecond */ +#define STATS_DESC_LINHIST_TIME_NSEC(SCOPE, name, sz, bsz) \ + STATS_DESC_LINEAR_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9, sz, bsz) +/* Logarithmic histogram for time in nanosecond */ +#define STATS_DESC_LOGHIST_TIME_NSEC(SCOPE, name, sz) \ + STATS_DESC_LOG_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9, sz) + +#define KVM_GENERIC_VM_STATS() \ + STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush), \ + STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush_requests) + +#define KVM_GENERIC_VCPU_STATS() \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns), \ + STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_success_hist, \ + HALT_POLL_HIST_COUNT), \ + STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ + HALT_POLL_HIST_COUNT), \ + STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ + HALT_POLL_HIST_COUNT), \ + STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) -extern struct kvm_stats_debugfs_item debugfs_entries[]; 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, + 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) +{ + size_t index = div64_u64(value, bucket_size); + + index = min(index, size - 1); + ++data[index]; +} + +/** + * 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) +{ + size_t index = fls64(value); + + index = min(index, size - 1); + ++data[index]; +} + +#define KVM_STATS_LINEAR_HIST_UPDATE(array, value, bsize) \ + kvm_stats_linear_hist_update(array, ARRAY_SIZE(array), value, bsize) +#define KVM_STATS_LOG_HIST_UPDATE(array, value) \ + kvm_stats_log_hist_update(array, ARRAY_SIZE(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[]; + #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) -static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) +static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { - if (unlikely(kvm->mmu_notifier_count)) + if (unlikely(kvm->mmu_invalidate_in_progress)) return 1; /* - * Ensure the read of mmu_notifier_count happens before the read - * of mmu_notifier_seq. This interacts with the smp_wmb() in - * mmu_notifier_invalidate_range_end to make sure that the caller - * either sees the old (non-zero) value of mmu_notifier_count or - * the new (incremented) value of mmu_notifier_seq. - * PowerPC Book3s HV KVM calls this under a per-page lock - * rather than under kvm->mmu_lock, for scalability, so - * can't rely on kvm->mmu_lock to keep things ordered. + * Ensure the read of mmu_invalidate_in_progress happens before + * the read of mmu_invalidate_seq. This interacts with the + * smp_wmb() in mmu_notifier_invalidate_range_end to make sure + * that the caller either sees the old (non-zero) value of + * mmu_invalidate_in_progress or the new (incremented) value of + * mmu_invalidate_seq. + * + * PowerPC Book3s HV KVM calls this under a per-page lock rather + * than under kvm->mmu_lock, for scalability, so can't rely on + * kvm->mmu_lock to keep things ordered. */ smp_rmb(); - if (kvm->mmu_notifier_seq != mmu_seq) + if (kvm->mmu_invalidate_seq != mmu_seq) + return 1; + return 0; +} + +static inline int mmu_invalidate_retry_hva(struct kvm *kvm, + unsigned long mmu_seq, + unsigned long hva) +{ + lockdep_assert_held(&kvm->mmu_lock); + /* + * If mmu_invalidate_in_progress is non-zero, then the range maintained + * by kvm_mmu_notifier_invalidate_range_start contains all addresses + * that might be being invalidated. Note that it may include some false + * positives, due to shortcuts when handing concurrent invalidations. + */ + if (unlikely(kvm->mmu_invalidate_in_progress) && + hva >= kvm->mmu_invalidate_range_start && + hva < kvm->mmu_invalidate_range_end) + return 1; + if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } @@ -1212,7 +2027,7 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) void kvm_arch_irq_routing_update(struct kvm *kvm); -static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Ensure the rest of the request is published to kvm_check_request's @@ -1222,6 +2037,19 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } +static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +{ + /* + * Request that don't require vCPU action should never be logged in + * vcpu->requests. The vCPU won't clear the request, so it will stay + * logged indefinitely and prevent the vCPU from entering the guest. + */ + BUILD_BUG_ON(!__builtin_constant_p(req) || + (req & KVM_REQUEST_NO_ACTION)); + + __kvm_make_request(req, vcpu); +} + static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->requests); @@ -1343,6 +2171,12 @@ 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) +{ + return (memslot && memslot->id < KVM_USER_MEM_SLOTS && + !(memslot->flags & KVM_MEMSLOT_INVALID)); +} + struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); @@ -1356,6 +2190,8 @@ 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 @@ -1394,8 +2230,10 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ -int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end, bool blockable); +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end); + +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); @@ -1412,4 +2250,35 @@ 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) +{ + vcpu->run->exit_reason = KVM_EXIT_INTR; + vcpu->stat.signal_exits++; +} +#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) +{ + mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, 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 64 + +/* Max number of entries allowed for each kvm dirty ring */ +#define KVM_DIRTY_RING_MAX_ENTRIES 65536 + #endif |