diff options
Diffstat (limited to 'include/linux/kvm_host.h')
| -rw-r--r-- | include/linux/kvm_host.h | 728 |
1 files changed, 579 insertions, 149 deletions
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c310648cc8f1..18592bdf4c1b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,6 +29,12 @@ #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> @@ -142,17 +148,26 @@ 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_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 -#define KVM_REQ_UNHALT 3 -#define KVM_REQ_VM_DEAD (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #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)); \ @@ -299,18 +314,20 @@ 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; +#ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; +#endif struct pid __rcu *pid; int sigset_active; sigset_t sigset; @@ -355,15 +372,20 @@ struct kvm_vcpu { 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. + * 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. */ - int last_used_slot; + struct kvm_memory_slot *last_used_slot; + u64 last_used_slot_gen; }; -/* must be called with irqs disabled */ -static __always_inline void guest_enter_irqoff(void) +/* + * 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 @@ -372,7 +394,18 @@ static __always_inline void guest_enter_irqoff(void) 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 @@ -388,16 +421,79 @@ static __always_inline void guest_enter_irqoff(void) } } -static __always_inline void guest_exit_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_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; @@ -407,6 +503,33 @@ static inline void guest_exit(void) 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) { /* @@ -424,7 +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; @@ -435,7 +577,7 @@ struct kvm_memory_slot { u16 as_id; }; -static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot) +static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; } @@ -469,6 +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; @@ -489,6 +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; }; @@ -505,12 +655,12 @@ struct kvm_irq_routing_table { }; #endif -#ifndef KVM_PRIVATE_MEM_SLOTS -#define KVM_PRIVATE_MEM_SLOTS 0 +#ifndef KVM_INTERNAL_MEM_SLOTS +#define KVM_INTERNAL_MEM_SLOTS 0 #endif #define KVM_MEM_SLOTS_NUM SHRT_MAX -#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS) +#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) @@ -519,18 +669,21 @@ 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; - /* The mapping table from slot id to the index in memslots[]. */ - short id_to_index[KVM_MEM_SLOTS_NUM]; - atomic_t last_used_slot; - int used_slots; - struct kvm_memory_slot memslots[]; + 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 { @@ -551,14 +704,22 @@ struct kvm { */ 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 * at the beginning of KVM_CREATE_VCPU. online_vcpus is only @@ -566,6 +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; @@ -602,10 +764,10 @@ 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_notifier_range_start; - unsigned long mmu_notifier_range_end; + unsigned long mmu_invalidate_seq; + long mmu_invalidate_in_progress; + unsigned long mmu_invalidate_range_start; + unsigned long mmu_invalidate_range_end; #endif struct list_head devices; u64 manual_dirty_log_protect; @@ -682,6 +844,25 @@ static inline void kvm_vm_bugged(struct kvm *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); @@ -701,19 +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; @@ -727,13 +906,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -#define kvm_for_each_memslot(memslot, slots) \ - for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + slots->used_slots; memslot++) \ - if (WARN_ON_ONCE(!memslot->npages)) { \ - } else - -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); @@ -793,21 +966,124 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) return __kvm_memslots(vcpu->kvm, as_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; - if (index < 0) - return NULL; + hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { + if (slot->id == id) + return slot; + } - slot = &slots->memslots[index]; + 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; - WARN_ON(slot->id != id); - return slot; + 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 @@ -833,11 +1109,10 @@ int __kvm_set_memory_region(struct kvm *kvm, 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, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); @@ -858,14 +1133,13 @@ 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(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, hva_t *hva); @@ -942,7 +1216,7 @@ 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, struct kvm_memory_slot *memslot, 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); @@ -950,7 +1224,6 @@ 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); -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); 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); @@ -966,10 +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); @@ -978,19 +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); #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_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); +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); @@ -1021,6 +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); @@ -1060,6 +1441,8 @@ int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); #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 int kvm_arch_hardware_enable(void); @@ -1137,7 +1520,7 @@ 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; } @@ -1152,6 +1535,20 @@ static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) #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 @@ -1166,15 +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; @@ -1205,25 +1611,15 @@ 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 at slot_index if it contains gfn. + * Returns a pointer to the memslot 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) +try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - struct kvm_memory_slot *slot; - - if (slot_index < 0 || slot_index >= slots->used_slots) + if (!slot) 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 @@ -1231,63 +1627,63 @@ try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) } /* - * Returns a pointer to the memslot that contains gfn and records the index of - * the slot in index. Otherwise returns NULL. + * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! + * 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, int *index) +search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { - int start = 0, end = slots->used_slots; - struct kvm_memory_slot *memslots = slots->memslots; struct kvm_memory_slot *slot; - - if (unlikely(!slots->used_slots)) - return NULL; - - while (start < end) { - int slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - slot = try_get_memslot(slots, start, gfn); - if (slot) { - *index = start; - return 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; } - return NULL; + return approx ? slot : 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) +____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; - int slot_index = atomic_read(&slots->last_used_slot); - slot = try_get_memslot(slots, slot_index, gfn); + 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, &slot_index); + slot = search_memslots(slots, gfn, approx); if (slot) { - atomic_set(&slots->last_used_slot, slot_index); + 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 ____gfn_to_memslot(slots, gfn, false); +} + static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { @@ -1330,12 +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)); @@ -1433,6 +1823,15 @@ struct _kvm_stats_desc { 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, \ @@ -1463,7 +1862,8 @@ struct _kvm_stats_desc { 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) + HALT_POLL_HIST_COUNT), \ + STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) extern struct dentry *kvm_debugfs_dir; @@ -1518,42 +1918,44 @@ 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_notifier_retry_hva(struct kvm *kvm, - unsigned long mmu_seq, - unsigned long hva) +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_notifier_count 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 + * 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_notifier_count) && - hva >= kvm->mmu_notifier_range_start && - hva < kvm->mmu_notifier_range_end) + if (unlikely(kvm->mmu_invalidate_in_progress) && + hva >= kvm->mmu_invalidate_range_start && + hva < kvm->mmu_invalidate_range_end) return 1; - if (kvm->mmu_notifier_seq != mmu_seq) + if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } @@ -1625,7 +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 @@ -1635,6 +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); @@ -1818,6 +2233,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, 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); #else @@ -1842,6 +2259,19 @@ 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) +{ + 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. |