diff options
Diffstat (limited to 'include/linux/kvm_host.h')
-rw-r--r-- | include/linux/kvm_host.h | 330 |
1 files changed, 289 insertions, 41 deletions
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8583ed3ff344..041ca7f15ea4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -28,6 +28,7 @@ #include <linux/rcuwait.h> #include <linux/refcount.h> #include <linux/nospec.h> +#include <linux/notifier.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -149,6 +150,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 +#define KVM_REQ_VM_BUGGED (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ @@ -157,6 +159,15 @@ static inline bool is_error_page(struct page *page) }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) +bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + struct kvm_vcpu *except, + unsigned long *vcpu_bitmap, cpumask_var_t tmp); +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 @@ -304,7 +315,6 @@ struct kvm_vcpu { struct pid __rcu *pid; int sigset_active; sigset_t sigset; - struct kvm_vcpu_stat stat; unsigned int halt_poll_ns; bool valid_wakeup; @@ -341,7 +351,16 @@ struct kvm_vcpu { bool preempted; bool ready; struct kvm_vcpu_arch arch; + struct kvm_vcpu_stat stat; + char stats_id[KVM_STATS_NAME_SIZE]; struct kvm_dirty_ring dirty_ring; + + /* + * The index of the most recently used memslot by this vCPU. It's ok + * if this becomes stale due to memslot changes since we always check + * it is a valid slot. + */ + int last_used_slot; }; /* must be called with irqs disabled */ @@ -510,7 +529,7 @@ struct kvm_memslots { u64 generation; /* The mapping table from slot id to the index in memslots[]. */ short id_to_index[KVM_MEM_SLOTS_NUM]; - atomic_t lru_slot; + atomic_t last_used_slot; int used_slots; struct kvm_memory_slot memslots[]; }; @@ -523,10 +542,24 @@ struct kvm { #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 */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + /* 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; + /* * created_vcpus is protected by kvm->lock, and is incremented * at the beginning of KVM_CREATE_VCPU. online_vcpus is only @@ -585,6 +618,12 @@ struct kvm { pid_t userspace_pid; unsigned int max_halt_poll_ns; u32 dirty_ring_size; + bool vm_bugged; + +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER + struct notifier_block pm_notifier; +#endif + char stats_id[KVM_STATS_NAME_SIZE]; }; #define kvm_err(fmt, ...) \ @@ -613,6 +652,30 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline void kvm_vm_bugged(struct kvm *kvm) +{ + kvm->vm_bugged = true; + kvm_make_all_cpus_request(kvm, KVM_REQ_VM_BUGGED); +} + +#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 bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); @@ -704,6 +767,7 @@ 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); @@ -808,7 +872,6 @@ 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); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, @@ -927,14 +990,10 @@ 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 -bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except, - unsigned long *vcpu_bitmap, cpumask_var_t tmp); -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); +void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start, + unsigned long end); +void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start, + unsigned long end); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -998,6 +1057,10 @@ 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); #endif @@ -1014,6 +1077,7 @@ 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 /* @@ -1137,29 +1201,49 @@ 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 at slot_index if it contains gfn. + * Otherwise returns NULL. + */ +static inline struct kvm_memory_slot * +try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) +{ + struct kvm_memory_slot *slot; + + if (slot_index < 0 || slot_index >= slots->used_slots) + return NULL; + + /* + * slot_index can come from vcpu->last_used_slot which is not kept + * in sync with userspace-controllable memslot deletion. So use nospec + * to prevent the CPU from speculating past the end of memslots[]. + */ + slot_index = array_index_nospec(slot_index, slots->used_slots); + slot = &slots->memslots[slot_index]; + + if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) + return slot; + else + return NULL; +} + +/* + * Returns a pointer to the memslot that contains gfn and records the index of + * the slot in index. Otherwise returns NULL. * * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn) +search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index) { int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->lru_slot); struct kvm_memory_slot *memslots = slots->memslots; + struct kvm_memory_slot *slot; if (unlikely(!slots->used_slots)) return NULL; - if (gfn >= memslots[slot].base_gfn && - gfn < memslots[slot].base_gfn + memslots[slot].npages) - return &memslots[slot]; - while (start < end) { - slot = start + (end - start) / 2; + int slot = start + (end - start) / 2; if (gfn >= memslots[slot].base_gfn) end = slot; @@ -1167,19 +1251,37 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn) start = slot + 1; } - if (start < slots->used_slots && gfn >= memslots[start].base_gfn && - gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->lru_slot, start); - return &memslots[start]; + slot = try_get_memslot(slots, start, gfn); + if (slot) { + *index = start; + return slot; } return NULL; } +/* + * __gfn_to_memslot() and its descendants are here because it is called from + * non-modular code in arch/powerpc/kvm/book3s_64_vio{,_hv}.c. 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); + struct kvm_memory_slot *slot; + int slot_index = atomic_read(&slots->last_used_slot); + + slot = try_get_memslot(slots, slot_index, gfn); + if (slot) + return slot; + + slot = search_memslots(slots, gfn, &slot_index); + if (slot) { + atomic_set(&slots->last_used_slot, slot_index); + return slot; + } + + return NULL; } static inline unsigned long @@ -1244,27 +1346,173 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - struct kvm_stats_debugfs_item *dbgfs_item; -}; - -struct kvm_stats_debugfs_item { - const char *name; - int offset; + const struct _kvm_stats_desc *desc; enum kvm_stat_kind kind; - int mode; }; -#define KVM_DBGFS_GET_MODE(dbgfs_item) \ - ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) +struct _kvm_stats_desc { + struct kvm_stats_desc desc; + char name[KVM_STATS_NAME_SIZE]; +}; -#define VM_STAT(n, x, ...) \ - { n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ } -#define VCPU_STAT(n, x, ...) \ - { n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ } +#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) + +/* 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) -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) { |