diff options
Diffstat (limited to 'virt/kvm/kvm_main.c')
| -rw-r--r-- | virt/kvm/kvm_main.c | 3001 |
1 files changed, 2213 insertions, 788 deletions
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 70f03ce0e5c1..25d7872b29c1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -51,19 +51,22 @@ #include <linux/io.h> #include <linux/lockdep.h> #include <linux/kthread.h> +#include <linux/suspend.h> #include <asm/processor.h> #include <asm/ioctl.h> #include <linux/uaccess.h> -#include <asm/pgtable.h> #include "coalesced_mmio.h" #include "async_pf.h" +#include "kvm_mm.h" #include "vfio.h" #define CREATE_TRACE_POINTS #include <trace/events/kvm.h> +#include <linux/kvm_dirty_ring.h> + /* Worst case buffer size needed for holding an integer. */ #define ITOA_MAX_LEN 12 @@ -112,9 +115,10 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu); struct dentry *kvm_debugfs_dir; EXPORT_SYMBOL_GPL(kvm_debugfs_dir); -static int kvm_debugfs_num_entries; static const struct file_operations stat_fops_per_vm; +static struct file_operations kvm_chardev_ops; + static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #ifdef CONFIG_KVM_COMPAT @@ -144,26 +148,27 @@ static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); -static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); - __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); -static bool largepages_enabled = true; - #define KVM_EVENT_CREATE_VM 0 #define KVM_EVENT_DESTROY_VM 1 static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); static unsigned long long kvm_createvm_count; static unsigned long long kvm_active_vms; -__weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end, bool blockable) +static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask); + +__weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end) +{ +} + +__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { - return 0; } -bool kvm_is_zone_device_pfn(kvm_pfn_t pfn) +bool kvm_is_zone_device_page(struct page *page) { /* * The metadata used by is_zone_device_page() to determine whether or @@ -171,35 +176,42 @@ bool kvm_is_zone_device_pfn(kvm_pfn_t pfn) * the device has been pinned, e.g. by get_user_pages(). WARN if the * page_count() is zero to help detect bad usage of this helper. */ - if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn)))) + if (WARN_ON_ONCE(!page_count(page))) return false; - return is_zone_device_page(pfn_to_page(pfn)); + return is_zone_device_page(page); } -bool kvm_is_reserved_pfn(kvm_pfn_t pfn) +/* + * Returns a 'struct page' if the pfn is "valid" and backed by a refcounted + * page, NULL otherwise. Note, the list of refcounted PG_reserved page types + * is likely incomplete, it has been compiled purely through people wanting to + * back guest with a certain type of memory and encountering issues. + */ +struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn) { + struct page *page; + + if (!pfn_valid(pfn)) + return NULL; + + page = pfn_to_page(pfn); + if (!PageReserved(page)) + return page; + + /* The ZERO_PAGE(s) is marked PG_reserved, but is refcounted. */ + if (is_zero_pfn(pfn)) + return page; + /* * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting * perspective they are "normal" pages, albeit with slightly different * usage rules. */ - if (pfn_valid(pfn)) - return PageReserved(pfn_to_page(pfn)) && - !is_zero_pfn(pfn) && - !kvm_is_zone_device_pfn(pfn); + if (kvm_is_zone_device_page(page)) + return page; - return true; -} - -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn) -{ - struct page *page = pfn_to_page(pfn); - - if (!PageTransCompoundMap(page)) - return false; - - return is_transparent_hugepage(compound_head(page)); + return NULL; } /* @@ -244,73 +256,109 @@ static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req) return mode == IN_GUEST_MODE; } -static void ack_flush(void *_completed) +static void ack_kick(void *_completed) { } -static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) +static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait) { - if (unlikely(!cpus)) - cpus = cpu_online_mask; - if (cpumask_empty(cpus)) return false; - smp_call_function_many(cpus, ack_flush, NULL, wait); + smp_call_function_many(cpus, ack_kick, NULL, wait); return true; } +static void kvm_make_vcpu_request(struct kvm_vcpu *vcpu, unsigned int req, + struct cpumask *tmp, int current_cpu) +{ + int cpu; + + if (likely(!(req & KVM_REQUEST_NO_ACTION))) + __kvm_make_request(req, vcpu); + + if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) + return; + + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_request_needs_ipi(), which could result in sending an IPI + * to the previous pCPU. But, that's OK because the purpose of the IPI + * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is + * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES + * after this point is also OK, as the requirement is only that KVM wait + * for vCPUs that were reading SPTEs _before_ any changes were + * finalized. See kvm_vcpu_kick() for more details on handling requests. + */ + if (kvm_request_needs_ipi(vcpu, req)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != -1 && cpu != current_cpu) + __cpumask_set_cpu(cpu, tmp); + } +} + bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - unsigned long *vcpu_bitmap, cpumask_var_t tmp) + unsigned long *vcpu_bitmap) { - int i, cpu, me; struct kvm_vcpu *vcpu; + struct cpumask *cpus; + int i, me; bool called; me = get_cpu(); - kvm_for_each_vcpu(i, vcpu, kvm) { - if (vcpu_bitmap && !test_bit(i, vcpu_bitmap)) - continue; - - kvm_make_request(req, vcpu); - cpu = vcpu->cpu; + cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); + cpumask_clear(cpus); - if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) + for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) { + vcpu = kvm_get_vcpu(kvm, i); + if (!vcpu) continue; - - if (tmp != NULL && cpu != -1 && cpu != me && - kvm_request_needs_ipi(vcpu, req)) - __cpumask_set_cpu(cpu, tmp); + kvm_make_vcpu_request(vcpu, req, cpus, me); } - called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT)); + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); return called; } -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) { - cpumask_var_t cpus; + struct kvm_vcpu *vcpu; + struct cpumask *cpus; + unsigned long i; bool called; + int me; + + me = get_cpu(); - zalloc_cpumask_var(&cpus, GFP_ATOMIC); + cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); + cpumask_clear(cpus); - called = kvm_make_vcpus_request_mask(kvm, req, NULL, cpus); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu == except) + continue; + kvm_make_vcpu_request(vcpu, req, cpus, me); + } + + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); + put_cpu(); - free_cpumask_var(cpus); return called; } +bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) +{ + return kvm_make_all_cpus_request_except(kvm, req, NULL); +} +EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); + #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) { - /* - * Read tlbs_dirty before setting KVM_REQ_TLB_FLUSH in - * kvm_make_all_cpus_request. - */ - long dirty_count = smp_load_acquire(&kvm->tlbs_dirty); + ++kvm->stat.generic.remote_tlb_flush_requests; /* * We want to publish modifications to the page tables before reading @@ -325,17 +373,99 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) */ if (!kvm_arch_flush_remote_tlb(kvm) || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) - ++kvm->stat.remote_tlb_flush; - cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); + ++kvm->stat.generic.remote_tlb_flush; } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); #endif -void kvm_reload_remote_mmus(struct kvm *kvm) +static void kvm_flush_shadow_all(struct kvm *kvm) { - kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD); + kvm_arch_flush_shadow_all(kvm); + kvm_arch_guest_memory_reclaimed(kvm); +} + +#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE +static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, + gfp_t gfp_flags) +{ + gfp_flags |= mc->gfp_zero; + + if (mc->kmem_cache) + return kmem_cache_alloc(mc->kmem_cache, gfp_flags); + else + return (void *)__get_free_page(gfp_flags); } +int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min) +{ + gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT; + void *obj; + + if (mc->nobjs >= min) + return 0; + + if (unlikely(!mc->objects)) { + if (WARN_ON_ONCE(!capacity)) + return -EIO; + + mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp); + if (!mc->objects) + return -ENOMEM; + + mc->capacity = capacity; + } + + /* It is illegal to request a different capacity across topups. */ + if (WARN_ON_ONCE(mc->capacity != capacity)) + return -EIO; + + while (mc->nobjs < mc->capacity) { + obj = mmu_memory_cache_alloc_obj(mc, gfp); + if (!obj) + return mc->nobjs >= min ? 0 : -ENOMEM; + mc->objects[mc->nobjs++] = obj; + } + return 0; +} + +int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min) +{ + return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min); +} + +int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc) +{ + return mc->nobjs; +} + +void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) +{ + while (mc->nobjs) { + if (mc->kmem_cache) + kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]); + else + free_page((unsigned long)mc->objects[--mc->nobjs]); + } + + kvfree(mc->objects); + + mc->objects = NULL; + mc->capacity = 0; +} + +void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) +{ + void *p; + + if (WARN_ON(!mc->nobjs)) + p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT); + else + p = mc->objects[--mc->nobjs]; + BUG_ON(!p); + return p; +} +#endif + static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { mutex_init(&vcpu->mutex); @@ -343,22 +473,27 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; - init_swait_queue_head(&vcpu->wq); +#ifndef __KVM_HAVE_ARCH_WQP + rcuwait_init(&vcpu->wait); +#endif kvm_async_pf_vcpu_init(vcpu); - vcpu->pre_pcpu = -1; - INIT_LIST_HEAD(&vcpu->blocked_vcpu_list); - kvm_vcpu_set_in_spin_loop(vcpu, false); kvm_vcpu_set_dy_eligible(vcpu, false); vcpu->preempted = false; vcpu->ready = false; preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); + vcpu->last_used_slot = NULL; + + /* Fill the stats id string for the vcpu */ + snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", + task_pid_nr(current), id); } -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) +static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { kvm_arch_vcpu_destroy(vcpu); + kvm_dirty_ring_free(&vcpu->dirty_ring); /* * No need for rcu_read_lock as VCPU_RUN is the only place that changes @@ -370,7 +505,20 @@ void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->run); kmem_cache_free(kvm_vcpu_cache, vcpu); } -EXPORT_SYMBOL_GPL(kvm_vcpu_destroy); + +void kvm_destroy_vcpus(struct kvm *kvm) +{ + unsigned long i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_vcpu_destroy(vcpu); + xa_erase(&kvm->vcpu_array, i); + } + + atomic_set(&kvm->online_vcpus, 0); +} +EXPORT_SYMBOL_GPL(kvm_destroy_vcpus); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) @@ -378,79 +526,320 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) return container_of(mn, struct kvm, mmu_notifier); } -static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address, - pte_t pte) +static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end) { struct kvm *kvm = mmu_notifier_to_kvm(mn); int idx; idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); - kvm->mmu_notifier_seq++; + kvm_arch_mmu_notifier_invalidate_range(kvm, start, end); + srcu_read_unlock(&kvm->srcu, idx); +} + +typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); + +typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start, + unsigned long end); + +typedef void (*on_unlock_fn_t)(struct kvm *kvm); + +struct kvm_hva_range { + unsigned long start; + unsigned long end; + pte_t pte; + hva_handler_t handler; + on_lock_fn_t on_lock; + on_unlock_fn_t on_unlock; + bool flush_on_ret; + bool may_block; +}; + +/* + * Use a dedicated stub instead of NULL to indicate that there is no callback + * function/handler. The compiler technically can't guarantee that a real + * function will have a non-zero address, and so it will generate code to + * check for !NULL, whereas comparing against a stub will be elided at compile + * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9). + */ +static void kvm_null_fn(void) +{ + +} +#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn) + +/* Iterate over each memslot intersecting [start, last] (inclusive) range */ +#define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \ + for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \ + node; \ + node = interval_tree_iter_next(node, start, last)) \ + +static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, + const struct kvm_hva_range *range) +{ + bool ret = false, locked = false; + struct kvm_gfn_range gfn_range; + struct kvm_memory_slot *slot; + struct kvm_memslots *slots; + int i, idx; + + if (WARN_ON_ONCE(range->end <= range->start)) + return 0; + + /* A null handler is allowed if and only if on_lock() is provided. */ + if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) && + IS_KVM_NULL_FN(range->handler))) + return 0; + + idx = srcu_read_lock(&kvm->srcu); + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct interval_tree_node *node; + + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot_in_hva_range(node, slots, + range->start, range->end - 1) { + unsigned long hva_start, hva_end; + + slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]); + hva_start = max(range->start, slot->userspace_addr); + hva_end = min(range->end, slot->userspace_addr + + (slot->npages << PAGE_SHIFT)); + + /* + * To optimize for the likely case where the address + * range is covered by zero or one memslots, don't + * bother making these conditional (to avoid writes on + * the second or later invocation of the handler). + */ + gfn_range.pte = range->pte; + gfn_range.may_block = range->may_block; + + /* + * {gfn(page) | page intersects with [hva_start, hva_end)} = + * {gfn_start, gfn_start+1, ..., gfn_end-1}. + */ + gfn_range.start = hva_to_gfn_memslot(hva_start, slot); + gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot); + gfn_range.slot = slot; + + if (!locked) { + locked = true; + KVM_MMU_LOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_lock)) + range->on_lock(kvm, range->start, range->end); + if (IS_KVM_NULL_FN(range->handler)) + break; + } + ret |= range->handler(kvm, &gfn_range); + } + } - if (kvm_set_spte_hva(kvm, address, pte)) + if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); - spin_unlock(&kvm->mmu_lock); + if (locked) { + KVM_MMU_UNLOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_unlock)) + range->on_unlock(kvm); + } + srcu_read_unlock(&kvm->srcu, idx); + + /* The notifiers are averse to booleans. :-( */ + return (int)ret; } -static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, - const struct mmu_notifier_range *range) +static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn, + unsigned long start, + unsigned long end, + pte_t pte, + hva_handler_t handler) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush = 0, idx; - int ret; + const struct kvm_hva_range range = { + .start = start, + .end = end, + .pte = pte, + .handler = handler, + .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, + .flush_on_ret = true, + .may_block = false, + }; + + return __kvm_handle_hva_range(kvm, &range); +} + +static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn, + unsigned long start, + unsigned long end, + hva_handler_t handler) +{ + struct kvm *kvm = mmu_notifier_to_kvm(mn); + const struct kvm_hva_range range = { + .start = start, + .end = end, + .pte = __pte(0), + .handler = handler, + .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, + .flush_on_ret = false, + .may_block = false, + }; + + return __kvm_handle_hva_range(kvm, &range); +} +static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address, + pte_t pte) +{ + struct kvm *kvm = mmu_notifier_to_kvm(mn); + + trace_kvm_set_spte_hva(address); - idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); + /* + * .change_pte() must be surrounded by .invalidate_range_{start,end}(). + * If mmu_invalidate_in_progress is zero, then no in-progress + * invalidations, including this one, found a relevant memslot at + * start(); rechecking memslots here is unnecessary. Note, a false + * positive (count elevated by a different invalidation) is sub-optimal + * but functionally ok. + */ + WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count)); + if (!READ_ONCE(kvm->mmu_invalidate_in_progress)) + return; + + kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn); +} + +void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start, + unsigned long end) +{ /* * The count increase must become visible at unlock time as no * spte can be established without taking the mmu_lock and * count is also read inside the mmu_lock critical section. */ - kvm->mmu_notifier_count++; - need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end); - need_tlb_flush |= kvm->tlbs_dirty; - /* we've to flush the tlb before the pages can be freed */ - if (need_tlb_flush) - kvm_flush_remote_tlbs(kvm); + kvm->mmu_invalidate_in_progress++; + if (likely(kvm->mmu_invalidate_in_progress == 1)) { + kvm->mmu_invalidate_range_start = start; + kvm->mmu_invalidate_range_end = end; + } else { + /* + * Fully tracking multiple concurrent ranges has diminishing + * returns. Keep things simple and just find the minimal range + * which includes the current and new ranges. As there won't be + * enough information to subtract a range after its invalidate + * completes, any ranges invalidated concurrently will + * accumulate and persist until all outstanding invalidates + * complete. + */ + kvm->mmu_invalidate_range_start = + min(kvm->mmu_invalidate_range_start, start); + kvm->mmu_invalidate_range_end = + max(kvm->mmu_invalidate_range_end, end); + } +} - spin_unlock(&kvm->mmu_lock); +static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, + const struct mmu_notifier_range *range) +{ + struct kvm *kvm = mmu_notifier_to_kvm(mn); + const struct kvm_hva_range hva_range = { + .start = range->start, + .end = range->end, + .pte = __pte(0), + .handler = kvm_unmap_gfn_range, + .on_lock = kvm_mmu_invalidate_begin, + .on_unlock = kvm_arch_guest_memory_reclaimed, + .flush_on_ret = true, + .may_block = mmu_notifier_range_blockable(range), + }; - ret = kvm_arch_mmu_notifier_invalidate_range(kvm, range->start, - range->end, - mmu_notifier_range_blockable(range)); + trace_kvm_unmap_hva_range(range->start, range->end); - srcu_read_unlock(&kvm->srcu, idx); + /* + * Prevent memslot modification between range_start() and range_end() + * so that conditionally locking provides the same result in both + * functions. Without that guarantee, the mmu_invalidate_in_progress + * adjustments will be imbalanced. + * + * Pairs with the decrement in range_end(). + */ + spin_lock(&kvm->mn_invalidate_lock); + kvm->mn_active_invalidate_count++; + spin_unlock(&kvm->mn_invalidate_lock); - return ret; + /* + * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e. + * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring + * each cache's lock. There are relatively few caches in existence at + * any given time, and the caches themselves can check for hva overlap, + * i.e. don't need to rely on memslot overlap checks for performance. + * Because this runs without holding mmu_lock, the pfn caches must use + * mn_active_invalidate_count (see above) instead of + * mmu_invalidate_in_progress. + */ + gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end, + hva_range.may_block); + + __kvm_handle_hva_range(kvm, &hva_range); + + return 0; } -static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, - const struct mmu_notifier_range *range) +void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start, + unsigned long end) { - struct kvm *kvm = mmu_notifier_to_kvm(mn); - - spin_lock(&kvm->mmu_lock); /* * This sequence increase will notify the kvm page fault that * the page that is going to be mapped in the spte could have * been freed. */ - kvm->mmu_notifier_seq++; + kvm->mmu_invalidate_seq++; smp_wmb(); /* * The above sequence increase must be visible before the * below count decrease, which is ensured by the smp_wmb above - * in conjunction with the smp_rmb in mmu_notifier_retry(). + * in conjunction with the smp_rmb in mmu_invalidate_retry(). */ - kvm->mmu_notifier_count--; - spin_unlock(&kvm->mmu_lock); + kvm->mmu_invalidate_in_progress--; +} + +static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, + const struct mmu_notifier_range *range) +{ + struct kvm *kvm = mmu_notifier_to_kvm(mn); + const struct kvm_hva_range hva_range = { + .start = range->start, + .end = range->end, + .pte = __pte(0), + .handler = (void *)kvm_null_fn, + .on_lock = kvm_mmu_invalidate_end, + .on_unlock = (void *)kvm_null_fn, + .flush_on_ret = false, + .may_block = mmu_notifier_range_blockable(range), + }; + bool wake; + + __kvm_handle_hva_range(kvm, &hva_range); + + /* Pairs with the increment in range_start(). */ + spin_lock(&kvm->mn_invalidate_lock); + wake = (--kvm->mn_active_invalidate_count == 0); + spin_unlock(&kvm->mn_invalidate_lock); - BUG_ON(kvm->mmu_notifier_count < 0); + /* + * There can only be one waiter, since the wait happens under + * slots_lock. + */ + if (wake) + rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait); + + BUG_ON(kvm->mmu_invalidate_in_progress < 0); } static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, @@ -458,20 +847,9 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, unsigned long start, unsigned long end) { - struct kvm *kvm = mmu_notifier_to_kvm(mn); - int young, idx; - - idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); - - young = kvm_age_hva(kvm, start, end); - if (young) - kvm_flush_remote_tlbs(kvm); + trace_kvm_age_hva(start, end); - spin_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); - - return young; + return kvm_handle_hva_range(mn, start, end, __pte(0), kvm_age_gfn); } static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn, @@ -479,11 +857,8 @@ static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn, unsigned long start, unsigned long end) { - struct kvm *kvm = mmu_notifier_to_kvm(mn); - int young, idx; + trace_kvm_age_hva(start, end); - idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); /* * Even though we do not flush TLB, this will still adversely * affect performance on pre-Haswell Intel EPT, where there is @@ -497,27 +872,17 @@ static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn, * cadence. If we find this inaccurate, we might come up with a * more sophisticated heuristic later. */ - young = kvm_age_hva(kvm, start, end); - spin_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); - - return young; + return kvm_handle_hva_range_no_flush(mn, start, end, kvm_age_gfn); } static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address) { - struct kvm *kvm = mmu_notifier_to_kvm(mn); - int young, idx; - - idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); - young = kvm_test_age_hva(kvm, address); - spin_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); + trace_kvm_test_age_hva(address); - return young; + return kvm_handle_hva_range_no_flush(mn, address, address + 1, + kvm_test_age_gfn); } static void kvm_mmu_notifier_release(struct mmu_notifier *mn, @@ -527,11 +892,12 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, int idx; idx = srcu_read_lock(&kvm->srcu); - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { + .invalidate_range = kvm_mmu_notifier_invalidate_range, .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start, .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end, .clear_flush_young = kvm_mmu_notifier_clear_flush_young, @@ -556,20 +922,37 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ -static struct kvm_memslots *kvm_alloc_memslots(void) +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +static int kvm_pm_notifier_call(struct notifier_block *bl, + unsigned long state, + void *unused) { - int i; - struct kvm_memslots *slots; + struct kvm *kvm = container_of(bl, struct kvm, pm_notifier); - slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT); - if (!slots) - return NULL; + return kvm_arch_pm_notifier(kvm, state); +} - for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) - slots->id_to_index[i] = slots->memslots[i].id = i; +static void kvm_init_pm_notifier(struct kvm *kvm) +{ + kvm->pm_notifier.notifier_call = kvm_pm_notifier_call; + /* Suspend KVM before we suspend ftrace, RCU, etc. */ + kvm->pm_notifier.priority = INT_MAX; + register_pm_notifier(&kvm->pm_notifier); +} - return slots; +static void kvm_destroy_pm_notifier(struct kvm *kvm) +{ + unregister_pm_notifier(&kvm->pm_notifier); +} +#else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */ +static void kvm_init_pm_notifier(struct kvm *kvm) +{ +} + +static void kvm_destroy_pm_notifier(struct kvm *kvm) +{ } +#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) { @@ -580,38 +963,55 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) memslot->dirty_bitmap = NULL; } -/* - * Free any memory in @free but not in @dont. - */ -static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +/* This does not remove the slot from struct kvm_memslots data structures */ +static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - if (!dont || free->dirty_bitmap != dont->dirty_bitmap) - kvm_destroy_dirty_bitmap(free); + kvm_destroy_dirty_bitmap(slot); - kvm_arch_free_memslot(kvm, free, dont); + kvm_arch_free_memslot(kvm, slot); - free->npages = 0; + kfree(slot); } static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) { + struct hlist_node *idnode; struct kvm_memory_slot *memslot; + int bkt; - if (!slots) + /* + * The same memslot objects live in both active and inactive sets, + * arbitrarily free using index '1' so the second invocation of this + * function isn't operating over a structure with dangling pointers + * (even though this function isn't actually touching them). + */ + if (!slots->node_idx) return; - kvm_for_each_memslot(memslot, slots) - kvm_free_memslot(kvm, memslot, NULL); + hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1]) + kvm_free_memslot(kvm, memslot); +} - kvfree(slots); +static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) +{ + switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) { + case KVM_STATS_TYPE_INSTANT: + return 0444; + case KVM_STATS_TYPE_CUMULATIVE: + case KVM_STATS_TYPE_PEAK: + default: + return 0644; + } } + static void kvm_destroy_vm_debugfs(struct kvm *kvm) { int i; + int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + + kvm_vcpu_stats_header.num_desc; - if (!kvm->debugfs_dentry) + if (IS_ERR(kvm->debugfs_dentry)) return; debugfs_remove_recursive(kvm->debugfs_dentry); @@ -623,37 +1023,79 @@ static void kvm_destroy_vm_debugfs(struct kvm *kvm) } } -static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) +static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname) { + static DEFINE_MUTEX(kvm_debugfs_lock); + struct dentry *dent; char dir_name[ITOA_MAX_LEN * 2]; struct kvm_stat_data *stat_data; - struct kvm_stats_debugfs_item *p; + const struct _kvm_stats_desc *pdesc; + int i, ret = -ENOMEM; + int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + + kvm_vcpu_stats_header.num_desc; if (!debugfs_initialized()) return 0; - snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd); - kvm->debugfs_dentry = debugfs_create_dir(dir_name, kvm_debugfs_dir); + snprintf(dir_name, sizeof(dir_name), "%d-%s", task_pid_nr(current), fdname); + mutex_lock(&kvm_debugfs_lock); + dent = debugfs_lookup(dir_name, kvm_debugfs_dir); + if (dent) { + pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name); + dput(dent); + mutex_unlock(&kvm_debugfs_lock); + return 0; + } + dent = debugfs_create_dir(dir_name, kvm_debugfs_dir); + mutex_unlock(&kvm_debugfs_lock); + if (IS_ERR(dent)) + return 0; + kvm->debugfs_dentry = dent; kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries, sizeof(*kvm->debugfs_stat_data), GFP_KERNEL_ACCOUNT); if (!kvm->debugfs_stat_data) - return -ENOMEM; + goto out_err; - for (p = debugfs_entries; p->name; p++) { + for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { + pdesc = &kvm_vm_stats_desc[i]; stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); if (!stat_data) - return -ENOMEM; + goto out_err; stat_data->kvm = kvm; - stat_data->dbgfs_item = p; - kvm->debugfs_stat_data[p - debugfs_entries] = stat_data; - debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p), + stat_data->desc = pdesc; + stat_data->kind = KVM_STAT_VM; + kvm->debugfs_stat_data[i] = stat_data; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); } + + for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { + pdesc = &kvm_vcpu_stats_desc[i]; + stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); + if (!stat_data) + goto out_err; + + stat_data->kvm = kvm; + stat_data->desc = pdesc; + stat_data->kind = KVM_STAT_VCPU; + kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm->debugfs_dentry, stat_data, + &stat_fops_per_vm); + } + + ret = kvm_arch_create_vm_debugfs(kvm); + if (ret) + goto out_err; + return 0; +out_err: + kvm_destroy_vm_debugfs(kvm); + return ret; } /* @@ -673,26 +1115,59 @@ void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm) { } -static struct kvm *kvm_create_vm(unsigned long type) +/* + * Called after per-vm debugfs created. When called kvm->debugfs_dentry should + * be setup already, so we can create arch-specific debugfs entries under it. + * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so + * a per-arch destroy interface is not needed. + */ +int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) +{ + return 0; +} + +static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) { struct kvm *kvm = kvm_arch_alloc_vm(); + struct kvm_memslots *slots; int r = -ENOMEM; - int i; + int i, j; if (!kvm) return ERR_PTR(-ENOMEM); - spin_lock_init(&kvm->mmu_lock); + /* KVM is pinned via open("/dev/kvm"), the fd passed to this ioctl(). */ + __module_get(kvm_chardev_ops.owner); + + KVM_MMU_LOCK_INIT(kvm); mmgrab(current->mm); kvm->mm = current->mm; kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); + mutex_init(&kvm->slots_arch_lock); + spin_lock_init(&kvm->mn_invalidate_lock); + rcuwait_init(&kvm->mn_memslots_update_rcuwait); + xa_init(&kvm->vcpu_array); + + INIT_LIST_HEAD(&kvm->gpc_list); + spin_lock_init(&kvm->gpc_lock); + INIT_LIST_HEAD(&kvm->devices); + kvm->max_vcpus = KVM_MAX_VCPUS; BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); + /* + * Force subsequent debugfs file creations to fail if the VM directory + * is not created (by kvm_create_vm_debugfs()). + */ + kvm->debugfs_dentry = ERR_PTR(-ENOENT); + + snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d", + task_pid_nr(current)); + if (init_srcu_struct(&kvm->srcu)) goto out_err_no_srcu; if (init_srcu_struct(&kvm->irq_srcu)) @@ -700,13 +1175,20 @@ static struct kvm *kvm_create_vm(unsigned long type) refcount_set(&kvm->users_count, 1); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_memslots *slots = kvm_alloc_memslots(); + for (j = 0; j < 2; j++) { + slots = &kvm->__memslots[i][j]; - if (!slots) - goto out_err_no_arch_destroy_vm; - /* Generations must be different for each address space. */ - slots->generation = i; - rcu_assign_pointer(kvm->memslots[i], slots); + atomic_long_set(&slots->last_used_slot, (unsigned long)NULL); + slots->hva_tree = RB_ROOT_CACHED; + slots->gfn_tree = RB_ROOT; + hash_init(slots->id_hash); + slots->node_idx = j; + + /* Generations must be different for each address space. */ + slots->generation = i; + } + + rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]); } for (i = 0; i < KVM_NR_BUSES; i++) { @@ -716,6 +1198,8 @@ static struct kvm *kvm_create_vm(unsigned long type) goto out_err_no_arch_destroy_vm; } + kvm->max_halt_poll_ns = halt_poll_ns; + r = kvm_arch_init_vm(kvm, type); if (r) goto out_err_no_arch_destroy_vm; @@ -732,6 +1216,14 @@ static struct kvm *kvm_create_vm(unsigned long type) if (r) goto out_err_no_mmu_notifier; + r = kvm_coalesced_mmio_init(kvm); + if (r < 0) + goto out_no_coalesced_mmio; + + r = kvm_create_vm_debugfs(kvm, fdname); + if (r) + goto out_err_no_debugfs; + r = kvm_arch_post_init_vm(kvm); if (r) goto out_err; @@ -741,10 +1233,15 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_unlock(&kvm_lock); preempt_notifier_inc(); + kvm_init_pm_notifier(kvm); return kvm; out_err: + kvm_destroy_vm_debugfs(kvm); +out_err_no_debugfs: + kvm_coalesced_mmio_free(kvm); +out_no_coalesced_mmio: #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) if (kvm->mmu_notifier.ops) mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); @@ -757,14 +1254,13 @@ out_err_no_arch_destroy_vm: WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm_get_bus(kvm, i)); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); cleanup_srcu_struct(&kvm->irq_srcu); out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); out_err_no_srcu: kvm_arch_free_vm(kvm); mmdrop(current->mm); + module_put(kvm_chardev_ops.owner); return ERR_PTR(r); } @@ -788,6 +1284,7 @@ static void kvm_destroy_vm(struct kvm *kvm) int i; struct mm_struct *mm = kvm->mm; + kvm_destroy_pm_notifier(kvm); kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm); kvm_destroy_vm_debugfs(kvm); kvm_arch_sync_events(kvm); @@ -807,19 +1304,32 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_coalesced_mmio_free(kvm); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); + /* + * At this point, pending calls to invalidate_range_start() + * have completed but no more MMU notifiers will run, so + * mn_active_invalidate_count may remain unbalanced. + * No threads can be waiting in install_new_memslots as the + * last reference on KVM has been dropped, but freeing + * memslots would deadlock without this manual intervention. + */ + WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); + kvm->mn_active_invalidate_count = 0; #else - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + kvm_free_memslots(kvm, &kvm->__memslots[i][0]); + kvm_free_memslots(kvm, &kvm->__memslots[i][1]); + } cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); preempt_notifier_dec(); hardware_disable_all(); mmdrop(mm); + module_put(kvm_chardev_ops.owner); } void kvm_get_kvm(struct kvm *kvm) @@ -828,6 +1338,16 @@ void kvm_get_kvm(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_get_kvm); +/* + * Make sure the vm is not during destruction, which is a safe version of + * kvm_get_kvm(). Return true if kvm referenced successfully, false otherwise. + */ +bool kvm_get_kvm_safe(struct kvm *kvm) +{ + return refcount_inc_not_zero(&kvm->users_count); +} +EXPORT_SYMBOL_GPL(kvm_get_kvm_safe); + void kvm_put_kvm(struct kvm *kvm) { if (refcount_dec_and_test(&kvm->users_count)) @@ -860,77 +1380,150 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) /* * Allocation size is twice as large as the actual dirty bitmap size. - * See x86's kvm_vm_ioctl_get_dirty_log() why this is needed. + * See kvm_vm_ioctl_get_dirty_log() why this is needed. */ -static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) +static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) { - unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot); + unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(memslot); - memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL_ACCOUNT); + memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT); if (!memslot->dirty_bitmap) return -ENOMEM; return 0; } +static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id) +{ + struct kvm_memslots *active = __kvm_memslots(kvm, as_id); + int node_idx_inactive = active->node_idx ^ 1; + + return &kvm->__memslots[as_id][node_idx_inactive]; +} + /* - * Insert memslot and re-sort memslots based on their GFN, - * so binary search could be used to lookup GFN. - * Sorting algorithm takes advantage of having initially - * sorted array and known changed memslot position. + * Helper to get the address space ID when one of memslot pointers may be NULL. + * This also serves as a sanity that at least one of the pointers is non-NULL, + * and that their address space IDs don't diverge. */ -static void update_memslots(struct kvm_memslots *slots, - struct kvm_memory_slot *new, - enum kvm_mr_change change) +static int kvm_memslots_get_as_id(struct kvm_memory_slot *a, + struct kvm_memory_slot *b) { - int id = new->id; - int i = slots->id_to_index[id]; - struct kvm_memory_slot *mslots = slots->memslots; + if (WARN_ON_ONCE(!a && !b)) + return 0; - WARN_ON(mslots[i].id != id); - switch (change) { - case KVM_MR_CREATE: - slots->used_slots++; - WARN_ON(mslots[i].npages || !new->npages); - break; - case KVM_MR_DELETE: - slots->used_slots--; - WARN_ON(new->npages || !mslots[i].npages); - break; - default: - break; + if (!a) + return b->as_id; + if (!b) + return a->as_id; + + WARN_ON_ONCE(a->as_id != b->as_id); + return a->as_id; +} + +static void kvm_insert_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) +{ + struct rb_root *gfn_tree = &slots->gfn_tree; + struct rb_node **node, *parent; + int idx = slots->node_idx; + + parent = NULL; + for (node = &gfn_tree->rb_node; *node; ) { + struct kvm_memory_slot *tmp; + + tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]); + parent = *node; + if (slot->base_gfn < tmp->base_gfn) + node = &(*node)->rb_left; + else if (slot->base_gfn > tmp->base_gfn) + node = &(*node)->rb_right; + else + BUG(); } - while (i < KVM_MEM_SLOTS_NUM - 1 && - new->base_gfn <= mslots[i + 1].base_gfn) { - if (!mslots[i + 1].npages) - break; - mslots[i] = mslots[i + 1]; - slots->id_to_index[mslots[i].id] = i; - i++; + rb_link_node(&slot->gfn_node[idx], parent, node); + rb_insert_color(&slot->gfn_node[idx], gfn_tree); +} + +static void kvm_erase_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) +{ + rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree); +} + +static void kvm_replace_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + int idx = slots->node_idx; + + WARN_ON_ONCE(old->base_gfn != new->base_gfn); + + rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx], + &slots->gfn_tree); +} + +/* + * Replace @old with @new in the inactive memslots. + * + * With NULL @old this simply adds @new. + * With NULL @new this simply removes @old. + * + * If @new is non-NULL its hva_node[slots_idx] range has to be set + * appropriately. + */ +static void kvm_replace_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + int as_id = kvm_memslots_get_as_id(old, new); + struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); + int idx = slots->node_idx; + + if (old) { + hash_del(&old->id_node[idx]); + interval_tree_remove(&old->hva_node[idx], &slots->hva_tree); + + if ((long)old == atomic_long_read(&slots->last_used_slot)) + atomic_long_set(&slots->last_used_slot, (long)new); + + if (!new) { + kvm_erase_gfn_node(slots, old); + return; + } } /* - * The ">=" is needed when creating a slot with base_gfn == 0, - * so that it moves before all those with base_gfn == npages == 0. - * - * On the other hand, if new->npages is zero, the above loop has - * already left i pointing to the beginning of the empty part of - * mslots, and the ">=" would move the hole backwards in this - * case---which is wrong. So skip the loop when deleting a slot. + * Initialize @new's hva range. Do this even when replacing an @old + * slot, kvm_copy_memslot() deliberately does not touch node data. */ - if (new->npages) { - while (i > 0 && - new->base_gfn >= mslots[i - 1].base_gfn) { - mslots[i] = mslots[i - 1]; - slots->id_to_index[mslots[i].id] = i; - i--; - } - } else - WARN_ON_ONCE(i != slots->used_slots); + new->hva_node[idx].start = new->userspace_addr; + new->hva_node[idx].last = new->userspace_addr + + (new->npages << PAGE_SHIFT) - 1; + + /* + * (Re)Add the new memslot. There is no O(1) interval_tree_replace(), + * hva_node needs to be swapped with remove+insert even though hva can't + * change when replacing an existing slot. + */ + hash_add(slots->id_hash, &new->id_node[idx], new->id); + interval_tree_insert(&new->hva_node[idx], &slots->hva_tree); - mslots[i] = *new; - slots->id_to_index[mslots[i].id] = i; + /* + * If the memslot gfn is unchanged, rb_replace_node() can be used to + * switch the node in the gfn tree instead of removing the old and + * inserting the new as two separate operations. Replacement is a + * single O(1) operation versus two O(log(n)) operations for + * remove+insert. + */ + if (old && old->base_gfn == new->base_gfn) { + kvm_replace_gfn_node(slots, old, new); + } else { + if (old) + kvm_erase_gfn_node(slots, old); + kvm_insert_gfn_node(slots, new); + } } static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem) @@ -947,16 +1540,40 @@ static int check_memory_region_flags(const struct kvm_userspace_memory_region *m return 0; } -static struct kvm_memslots *install_new_memslots(struct kvm *kvm, - int as_id, struct kvm_memslots *slots) +static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) { - struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id); - u64 gen = old_memslots->generation; + struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); + + /* Grab the generation from the activate memslots. */ + u64 gen = __kvm_memslots(kvm, as_id)->generation; WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; + /* + * Do not store the new memslots while there are invalidations in + * progress, otherwise the locking in invalidate_range_start and + * invalidate_range_end will be unbalanced. + */ + spin_lock(&kvm->mn_invalidate_lock); + prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait); + while (kvm->mn_active_invalidate_count) { + set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock(&kvm->mn_invalidate_lock); + schedule(); + spin_lock(&kvm->mn_invalidate_lock); + } + finish_rcuwait(&kvm->mn_memslots_update_rcuwait); rcu_assign_pointer(kvm->memslots[as_id], slots); + spin_unlock(&kvm->mn_invalidate_lock); + + /* + * Acquired in kvm_set_memslot. Must be released before synchronize + * SRCU below in order to avoid deadlock with another thread + * acquiring the slots_arch_lock in an srcu critical section. + */ + mutex_unlock(&kvm->slots_arch_lock); + synchronize_srcu_expedited(&kvm->srcu); /* @@ -979,8 +1596,319 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, kvm_arch_memslots_updated(kvm, gen); slots->generation = gen; +} + +static int kvm_prepare_memory_region(struct kvm *kvm, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + int r; + + /* + * If dirty logging is disabled, nullify the bitmap; the old bitmap + * will be freed on "commit". If logging is enabled in both old and + * new, reuse the existing bitmap. If logging is enabled only in the + * new and KVM isn't using a ring buffer, allocate and initialize a + * new bitmap. + */ + if (change != KVM_MR_DELETE) { + if (!(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) + new->dirty_bitmap = NULL; + else if (old && old->dirty_bitmap) + new->dirty_bitmap = old->dirty_bitmap; + else if (!kvm->dirty_ring_size) { + r = kvm_alloc_dirty_bitmap(new); + if (r) + return r; + + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + bitmap_set(new->dirty_bitmap, 0, new->npages); + } + } - return old_memslots; + r = kvm_arch_prepare_memory_region(kvm, old, new, change); + + /* Free the bitmap on failure if it was allocated above. */ + if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap)) + kvm_destroy_dirty_bitmap(new); + + return r; +} + +static void kvm_commit_memory_region(struct kvm *kvm, + struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + /* + * Update the total number of memslot pages before calling the arch + * hook so that architectures can consume the result directly. + */ + if (change == KVM_MR_DELETE) + kvm->nr_memslot_pages -= old->npages; + else if (change == KVM_MR_CREATE) + kvm->nr_memslot_pages += new->npages; + + kvm_arch_commit_memory_region(kvm, old, new, change); + + switch (change) { + case KVM_MR_CREATE: + /* Nothing more to do. */ + break; + case KVM_MR_DELETE: + /* Free the old memslot and all its metadata. */ + kvm_free_memslot(kvm, old); + break; + case KVM_MR_MOVE: + case KVM_MR_FLAGS_ONLY: + /* + * Free the dirty bitmap as needed; the below check encompasses + * both the flags and whether a ring buffer is being used) + */ + if (old->dirty_bitmap && !new->dirty_bitmap) + kvm_destroy_dirty_bitmap(old); + + /* + * The final quirk. Free the detached, old slot, but only its + * memory, not any metadata. Metadata, including arch specific + * data, may be reused by @new. + */ + kfree(old); + break; + default: + BUG(); + } +} + +/* + * Activate @new, which must be installed in the inactive slots by the caller, + * by swapping the active slots and then propagating @new to @old once @old is + * unreachable and can be safely modified. + * + * With NULL @old this simply adds @new to @active (while swapping the sets). + * With NULL @new this simply removes @old from @active and frees it + * (while also swapping the sets). + */ +static void kvm_activate_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + int as_id = kvm_memslots_get_as_id(old, new); + + kvm_swap_active_memslots(kvm, as_id); + + /* Propagate the new memslot to the now inactive memslots. */ + kvm_replace_memslot(kvm, old, new); +} + +static void kvm_copy_memslot(struct kvm_memory_slot *dest, + const struct kvm_memory_slot *src) +{ + dest->base_gfn = src->base_gfn; + dest->npages = src->npages; + dest->dirty_bitmap = src->dirty_bitmap; + dest->arch = src->arch; + dest->userspace_addr = src->userspace_addr; + dest->flags = src->flags; + dest->id = src->id; + dest->as_id = src->as_id; +} + +static void kvm_invalidate_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Mark the current slot INVALID. As with all memslot modifications, + * this must be done on an unreachable slot to avoid modifying the + * current slot in the active tree. + */ + kvm_copy_memslot(invalid_slot, old); + invalid_slot->flags |= KVM_MEMSLOT_INVALID; + kvm_replace_memslot(kvm, old, invalid_slot); + + /* + * Activate the slot that is now marked INVALID, but don't propagate + * the slot to the now inactive slots. The slot is either going to be + * deleted or recreated as a new slot. + */ + kvm_swap_active_memslots(kvm, old->as_id); + + /* + * From this point no new shadow pages pointing to a deleted, or moved, + * memslot will be created. Validation of sp->gfn happens in: + * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) + * - kvm_is_visible_gfn (mmu_check_root) + */ + kvm_arch_flush_shadow_memslot(kvm, old); + kvm_arch_guest_memory_reclaimed(kvm); + + /* Was released by kvm_swap_active_memslots, reacquire. */ + mutex_lock(&kvm->slots_arch_lock); + + /* + * Copy the arch-specific field of the newly-installed slot back to the + * old slot as the arch data could have changed between releasing + * slots_arch_lock in install_new_memslots() and re-acquiring the lock + * above. Writers are required to retrieve memslots *after* acquiring + * slots_arch_lock, thus the active slot's data is guaranteed to be fresh. + */ + old->arch = invalid_slot->arch; +} + +static void kvm_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *new) +{ + /* Add the new memslot to the inactive set and activate. */ + kvm_replace_memslot(kvm, NULL, new); + kvm_activate_memslot(kvm, NULL, new); +} + +static void kvm_delete_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Remove the old memslot (in the inactive memslots) by passing NULL as + * the "new" slot, and for the invalid version in the active slots. + */ + kvm_replace_memslot(kvm, old, NULL); + kvm_activate_memslot(kvm, invalid_slot, NULL); +} + +static void kvm_move_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Replace the old memslot in the inactive slots, and then swap slots + * and replace the current INVALID with the new as well. + */ + kvm_replace_memslot(kvm, old, new); + kvm_activate_memslot(kvm, invalid_slot, new); +} + +static void kvm_update_flags_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + /* + * Similar to the MOVE case, but the slot doesn't need to be zapped as + * an intermediate step. Instead, the old memslot is simply replaced + * with a new, updated copy in both memslot sets. + */ + kvm_replace_memslot(kvm, old, new); + kvm_activate_memslot(kvm, old, new); +} + +static int kvm_set_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + struct kvm_memory_slot *invalid_slot; + int r; + + /* + * Released in kvm_swap_active_memslots. + * + * Must be held from before the current memslots are copied until + * after the new memslots are installed with rcu_assign_pointer, + * then released before the synchronize srcu in kvm_swap_active_memslots. + * + * When modifying memslots outside of the slots_lock, must be held + * before reading the pointer to the current memslots until after all + * changes to those memslots are complete. + * + * These rules ensure that installing new memslots does not lose + * changes made to the previous memslots. + */ + mutex_lock(&kvm->slots_arch_lock); + + /* + * Invalidate the old slot if it's being deleted or moved. This is + * done prior to actually deleting/moving the memslot to allow vCPUs to + * continue running by ensuring there are no mappings or shadow pages + * for the memslot when it is deleted/moved. Without pre-invalidation + * (and without a lock), a window would exist between effecting the + * delete/move and committing the changes in arch code where KVM or a + * guest could access a non-existent memslot. + * + * Modifications are done on a temporary, unreachable slot. The old + * slot needs to be preserved in case a later step fails and the + * invalidation needs to be reverted. + */ + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { + invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT); + if (!invalid_slot) { + mutex_unlock(&kvm->slots_arch_lock); + return -ENOMEM; + } + kvm_invalidate_memslot(kvm, old, invalid_slot); + } + + r = kvm_prepare_memory_region(kvm, old, new, change); + if (r) { + /* + * For DELETE/MOVE, revert the above INVALID change. No + * modifications required since the original slot was preserved + * in the inactive slots. Changing the active memslots also + * release slots_arch_lock. + */ + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { + kvm_activate_memslot(kvm, invalid_slot, old); + kfree(invalid_slot); + } else { + mutex_unlock(&kvm->slots_arch_lock); + } + return r; + } + + /* + * For DELETE and MOVE, the working slot is now active as the INVALID + * version of the old slot. MOVE is particularly special as it reuses + * the old slot and returns a copy of the old slot (in working_slot). + * For CREATE, there is no old slot. For DELETE and FLAGS_ONLY, the + * old slot is detached but otherwise preserved. + */ + if (change == KVM_MR_CREATE) + kvm_create_memslot(kvm, new); + else if (change == KVM_MR_DELETE) + kvm_delete_memslot(kvm, old, invalid_slot); + else if (change == KVM_MR_MOVE) + kvm_move_memslot(kvm, old, new, invalid_slot); + else if (change == KVM_MR_FLAGS_ONLY) + kvm_update_flags_memslot(kvm, old, new); + else + BUG(); + + /* Free the temporary INVALID slot used for DELETE and MOVE. */ + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + kfree(invalid_slot); + + /* + * No need to refresh new->arch, changes after dropping slots_arch_lock + * will directly hit the final, active memslot. Architectures are + * responsible for knowing that new->arch may be stale. + */ + kvm_commit_memory_region(kvm, old, new, change); + + return 0; +} + +static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, + gfn_t start, gfn_t end) +{ + struct kvm_memslot_iter iter; + + kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) { + if (iter.slot->id != id) + return true; + } + + return false; } /* @@ -994,162 +1922,103 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, int __kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem) { - int r; - gfn_t base_gfn; + struct kvm_memory_slot *old, *new; + struct kvm_memslots *slots; + enum kvm_mr_change change; unsigned long npages; - struct kvm_memory_slot *slot; - struct kvm_memory_slot old, new; - struct kvm_memslots *slots = NULL, *old_memslots; + gfn_t base_gfn; int as_id, id; - enum kvm_mr_change change; + int r; r = check_memory_region_flags(mem); if (r) - goto out; + return r; - r = -EINVAL; as_id = mem->slot >> 16; id = (u16)mem->slot; /* General sanity checks */ - if (mem->memory_size & (PAGE_SIZE - 1)) - goto out; + if ((mem->memory_size & (PAGE_SIZE - 1)) || + (mem->memory_size != (unsigned long)mem->memory_size)) + return -EINVAL; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) - goto out; + return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ - if ((id < KVM_USER_MEM_SLOTS) && - ((mem->userspace_addr & (PAGE_SIZE - 1)) || + if ((mem->userspace_addr & (PAGE_SIZE - 1)) || + (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, - mem->memory_size))) - goto out; + mem->memory_size)) + return -EINVAL; if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM) - goto out; + return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) - goto out; - - slot = id_to_memslot(__kvm_memslots(kvm, as_id), id); - base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; - npages = mem->memory_size >> PAGE_SHIFT; - - if (npages > KVM_MEM_MAX_NR_PAGES) - goto out; - - new = old = *slot; - - new.id = id; - new.base_gfn = base_gfn; - new.npages = npages; - new.flags = mem->flags; - - if (npages) { - if (!old.npages) - change = KVM_MR_CREATE; - else { /* Modify an existing slot. */ - if ((mem->userspace_addr != old.userspace_addr) || - (npages != old.npages) || - ((new.flags ^ old.flags) & KVM_MEM_READONLY)) - goto out; - - if (base_gfn != old.base_gfn) - change = KVM_MR_MOVE; - else if (new.flags != old.flags) - change = KVM_MR_FLAGS_ONLY; - else { /* Nothing to change. */ - r = 0; - goto out; - } - } - } else { - if (!old.npages) - goto out; - - change = KVM_MR_DELETE; - new.base_gfn = 0; - new.flags = 0; - } + return -EINVAL; + if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES) + return -EINVAL; - if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { - /* Check for overlaps */ - r = -EEXIST; - kvm_for_each_memslot(slot, __kvm_memslots(kvm, as_id)) { - if (slot->id == id) - continue; - if (!((base_gfn + npages <= slot->base_gfn) || - (base_gfn >= slot->base_gfn + slot->npages))) - goto out; - } - } + slots = __kvm_memslots(kvm, as_id); - /* Free page dirty bitmap if unneeded */ - if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES)) - new.dirty_bitmap = NULL; + /* + * Note, the old memslot (and the pointer itself!) may be invalidated + * and/or destroyed by kvm_set_memslot(). + */ + old = id_to_memslot(slots, id); - r = -ENOMEM; - if (change == KVM_MR_CREATE) { - new.userspace_addr = mem->userspace_addr; + if (!mem->memory_size) { + if (!old || !old->npages) + return -EINVAL; - if (kvm_arch_create_memslot(kvm, &new, npages)) - goto out_free; - } + if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages)) + return -EIO; - /* Allocate page dirty bitmap if needed */ - if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) { - if (kvm_create_dirty_bitmap(&new) < 0) - goto out_free; + return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE); } - slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT); - if (!slots) - goto out_free; - memcpy(slots, __kvm_memslots(kvm, as_id), sizeof(struct kvm_memslots)); + base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT); + npages = (mem->memory_size >> PAGE_SHIFT); - if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { - slot = id_to_memslot(slots, id); - slot->flags |= KVM_MEMSLOT_INVALID; - - old_memslots = install_new_memslots(kvm, as_id, slots); - - /* From this point no new shadow pages pointing to a deleted, - * or moved, memslot will be created. - * - * validation of sp->gfn happens in: - * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) - * - kvm_is_visible_gfn (mmu_check_root) - */ - kvm_arch_flush_shadow_memslot(kvm, slot); + if (!old || !old->npages) { + change = KVM_MR_CREATE; /* - * We can re-use the old_memslots from above, the only difference - * from the currently installed memslots is the invalid flag. This - * will get overwritten by update_memslots anyway. + * To simplify KVM internals, the total number of pages across + * all memslots must fit in an unsigned long. */ - slots = old_memslots; - } - - r = kvm_arch_prepare_memory_region(kvm, &new, mem, change); - if (r) - goto out_slots; + if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) + return -EINVAL; + } else { /* Modify an existing slot. */ + if ((mem->userspace_addr != old->userspace_addr) || + (npages != old->npages) || + ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) + return -EINVAL; - /* actual memory is freed via old in kvm_free_memslot below */ - if (change == KVM_MR_DELETE) { - new.dirty_bitmap = NULL; - memset(&new.arch, 0, sizeof(new.arch)); + if (base_gfn != old->base_gfn) + change = KVM_MR_MOVE; + else if (mem->flags != old->flags) + change = KVM_MR_FLAGS_ONLY; + else /* Nothing to change. */ + return 0; } - update_memslots(slots, &new, change); - old_memslots = install_new_memslots(kvm, as_id, slots); + if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) && + kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages)) + return -EEXIST; - kvm_arch_commit_memory_region(kvm, mem, &old, &new, change); + /* Allocate a slot that will persist in the memslot. */ + new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); + if (!new) + return -ENOMEM; - kvm_free_memslot(kvm, &old, &new); - kvfree(old_memslots); - return 0; + new->as_id = as_id; + new->id = id; + new->base_gfn = base_gfn; + new->npages = npages; + new->flags = mem->flags; + new->userspace_addr = mem->userspace_addr; -out_slots: - kvfree(slots); -out_free: - kvm_free_memslot(kvm, &new, &old); -out: + r = kvm_set_memslot(kvm, old, new, change); + if (r) + kfree(new); return r; } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); @@ -1175,31 +2044,47 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, return kvm_set_memory_region(kvm, mem); } -int kvm_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log, int *is_dirty) +#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT +/** + * kvm_get_dirty_log - get a snapshot of dirty pages + * @kvm: pointer to kvm instance + * @log: slot id and address to which we copy the log + * @is_dirty: set to '1' if any dirty pages were found + * @memslot: set to the associated memslot, always valid on success + */ +int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, + int *is_dirty, struct kvm_memory_slot **memslot) { struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; int i, as_id, id; unsigned long n; unsigned long any = 0; + /* Dirty ring tracking is exclusive to dirty log tracking */ + if (kvm->dirty_ring_size) + return -ENXIO; + + *memslot = NULL; + *is_dirty = 0; + as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); - memslot = id_to_memslot(slots, id); - if (!memslot->dirty_bitmap) + *memslot = id_to_memslot(slots, id); + if (!(*memslot) || !(*memslot)->dirty_bitmap) return -ENOENT; - n = kvm_dirty_bitmap_bytes(memslot); + kvm_arch_sync_dirty_log(kvm, *memslot); + + n = kvm_dirty_bitmap_bytes(*memslot); for (i = 0; !any && i < n/sizeof(long); ++i) - any = memslot->dirty_bitmap[i]; + any = (*memslot)->dirty_bitmap[i]; - if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n)) + if (copy_to_user(log->dirty_bitmap, (*memslot)->dirty_bitmap, n)) return -EFAULT; if (any) @@ -1208,13 +2093,12 @@ int kvm_get_dirty_log(struct kvm *kvm, } EXPORT_SYMBOL_GPL(kvm_get_dirty_log); -#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT +#else /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ /** * kvm_get_dirty_log_protect - get a snapshot of dirty pages * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address to which we copy the log - * @flush: true if TLB flush is needed by caller * * We need to keep it in mind that VCPU threads can write to the bitmap * concurrently. So, to avoid losing track of dirty pages we keep the @@ -1231,8 +2115,7 @@ EXPORT_SYMBOL_GPL(kvm_get_dirty_log); * exiting to userspace will be logged for the next call. * */ -int kvm_get_dirty_log_protect(struct kvm *kvm, - struct kvm_dirty_log *log, bool *flush) +static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; @@ -1240,6 +2123,11 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, unsigned long n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; + bool flush; + + /* Dirty ring tracking is exclusive to dirty log tracking */ + if (kvm->dirty_ring_size) + return -ENXIO; as_id = log->slot >> 16; id = (u16)log->slot; @@ -1248,13 +2136,15 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); + if (!memslot || !memslot->dirty_bitmap) + return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; - if (!dirty_bitmap) - return -ENOENT; + + kvm_arch_sync_dirty_log(kvm, memslot); n = kvm_dirty_bitmap_bytes(memslot); - *flush = false; + flush = false; if (kvm->manual_dirty_log_protect) { /* * Unlike kvm_get_dirty_log, we always return false in *flush, @@ -1269,7 +2159,7 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); memset(dirty_bitmap_buffer, 0, n); - spin_lock(&kvm->mmu_lock); + KVM_MMU_LOCK(kvm); for (i = 0; i < n / sizeof(long); i++) { unsigned long mask; gfn_t offset; @@ -1277,7 +2167,7 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, if (!dirty_bitmap[i]) continue; - *flush = true; + flush = true; mask = xchg(&dirty_bitmap[i], 0); dirty_bitmap_buffer[i] = mask; @@ -1285,24 +2175,58 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } - spin_unlock(&kvm->mmu_lock); + KVM_MMU_UNLOCK(kvm); } + if (flush) + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); + if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(kvm_get_dirty_log_protect); + + +/** + * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot + * @kvm: kvm instance + * @log: slot id and address to which we copy the log + * + * Steps 1-4 below provide general overview of dirty page logging. See + * kvm_get_dirty_log_protect() function description for additional details. + * + * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we + * always flush the TLB (step 4) even if previous step failed and the dirty + * bitmap may be corrupt. Regardless of previous outcome the KVM logging API + * does not preclude user space subsequent dirty log read. Flushing TLB ensures + * writes will be marked dirty for next log read. + * + * 1. Take a snapshot of the bit and clear it if needed. + * 2. Write protect the corresponding page. + * 3. Copy the snapshot to the userspace. + * 4. Flush TLB's if needed. + */ +static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, + struct kvm_dirty_log *log) +{ + int r; + + mutex_lock(&kvm->slots_lock); + + r = kvm_get_dirty_log_protect(kvm, log); + + mutex_unlock(&kvm->slots_lock); + return r; +} /** * kvm_clear_dirty_log_protect - clear dirty bits in the bitmap * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address from which to fetch the bitmap of dirty pages - * @flush: true if TLB flush is needed by caller */ -int kvm_clear_dirty_log_protect(struct kvm *kvm, - struct kvm_clear_dirty_log *log, bool *flush) +static int kvm_clear_dirty_log_protect(struct kvm *kvm, + struct kvm_clear_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; @@ -1311,6 +2235,11 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, unsigned long i, n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; + bool flush; + + /* Dirty ring tracking is exclusive to dirty log tracking */ + if (kvm->dirty_ring_size) + return -ENXIO; as_id = log->slot >> 16; id = (u16)log->slot; @@ -1322,10 +2251,10 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); + if (!memslot || !memslot->dirty_bitmap) + return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; - if (!dirty_bitmap) - return -ENOENT; n = ALIGN(log->num_pages, BITS_PER_LONG) / 8; @@ -1334,12 +2263,14 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63))) return -EINVAL; - *flush = false; + kvm_arch_sync_dirty_log(kvm, memslot); + + flush = false; dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n)) return -EFAULT; - spin_lock(&kvm->mmu_lock); + KVM_MMU_LOCK(kvm); for (offset = log->first_page, i = offset / BITS_PER_LONG, n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--; i++, offset += BITS_PER_LONG) { @@ -1357,28 +2288,32 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, * a problem if userspace sets them in log->dirty_bitmap. */ if (mask) { - *flush = true; + flush = true; kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } } - spin_unlock(&kvm->mmu_lock); + KVM_MMU_UNLOCK(kvm); + + if (flush) + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); return 0; } -EXPORT_SYMBOL_GPL(kvm_clear_dirty_log_protect); -#endif -bool kvm_largepages_enabled(void) +static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, + struct kvm_clear_dirty_log *log) { - return largepages_enabled; -} + int r; -void kvm_disable_largepages(void) -{ - largepages_enabled = false; + mutex_lock(&kvm->slots_lock); + + r = kvm_clear_dirty_log_protect(kvm, log); + + mutex_unlock(&kvm->slots_lock); + return r; } -EXPORT_SYMBOL_GPL(kvm_disable_largepages); +#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { @@ -1388,21 +2323,53 @@ EXPORT_SYMBOL_GPL(gfn_to_memslot); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) { - return __gfn_to_memslot(kvm_vcpu_memslots(vcpu), gfn); + struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu); + u64 gen = slots->generation; + struct kvm_memory_slot *slot; + + /* + * This also protects against using a memslot from a different address space, + * since different address spaces have different generation numbers. + */ + if (unlikely(gen != vcpu->last_used_slot_gen)) { + vcpu->last_used_slot = NULL; + vcpu->last_used_slot_gen = gen; + } + + slot = try_get_memslot(vcpu->last_used_slot, gfn); + if (slot) + return slot; + + /* + * Fall back to searching all memslots. We purposely use + * search_memslots() instead of __gfn_to_memslot() to avoid + * thrashing the VM-wide last_used_slot in kvm_memslots. + */ + slot = search_memslots(slots, gfn, false); + if (slot) { + vcpu->last_used_slot = slot; + return slot; + } + + return NULL; } bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); - if (!memslot || memslot->id >= KVM_USER_MEM_SLOTS || - memslot->flags & KVM_MEMSLOT_INVALID) - return false; - - return true; + return kvm_is_visible_memslot(memslot); } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); +bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_memory_slot *memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return kvm_is_visible_memslot(memslot); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_is_visible_gfn); + unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn) { struct vm_area_struct *vma; @@ -1414,7 +2381,7 @@ unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn) if (kvm_is_error_hva(addr)) return PAGE_SIZE; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); vma = find_vma(current->mm, addr); if (!vma) goto out; @@ -1422,17 +2389,17 @@ unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn) size = vma_kernel_pagesize(vma); out: - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); return size; } -static bool memslot_is_readonly(struct kvm_memory_slot *slot) +static bool memslot_is_readonly(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_READONLY; } -static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, +static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages, bool write) { if (!slot || slot->flags & KVM_MEMSLOT_INVALID) @@ -1522,7 +2489,6 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault, bool *writable, kvm_pfn_t *pfn) { struct page *page[1]; - int npages; /* * Fast pin a writable pfn only if it is a write fault request @@ -1532,8 +2498,7 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault, if (!(write_fault || writable)) return false; - npages = __get_user_pages_fast(addr, 1, 1, page); - if (npages == 1) { + if (get_user_page_fast_only(addr, FOLL_WRITE, page)) { *pfn = page_to_pfn(page[0]); if (writable) @@ -1553,7 +2518,7 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, { unsigned int flags = FOLL_HWPOISON; struct page *page; - int npages = 0; + int npages; might_sleep(); @@ -1573,7 +2538,7 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, if (unlikely(!write_fault) && writable) { struct page *wpage; - if (__get_user_pages_fast(addr, 1, 1, &wpage) == 1) { + if (get_user_page_fast_only(addr, FOLL_WRITE, &wpage)) { *writable = true; put_page(page); page = wpage; @@ -1594,22 +2559,33 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) return true; } +static int kvm_try_get_pfn(kvm_pfn_t pfn) +{ + struct page *page = kvm_pfn_to_refcounted_page(pfn); + + if (!page) + return 1; + + return get_page_unless_zero(page); +} + static int hva_to_pfn_remapped(struct vm_area_struct *vma, - unsigned long addr, bool *async, - bool write_fault, bool *writable, - kvm_pfn_t *p_pfn) + unsigned long addr, bool write_fault, + bool *writable, kvm_pfn_t *p_pfn) { - unsigned long pfn; + kvm_pfn_t pfn; + pte_t *ptep; + spinlock_t *ptl; int r; - r = follow_pfn(vma, addr, &pfn); + r = follow_pte(vma->vm_mm, addr, &ptep, &ptl); if (r) { /* * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does * not call the fault handler, so do it here. */ bool unlocked = false; - r = fixup_user_fault(current, current->mm, addr, + r = fixup_user_fault(current->mm, addr, (write_fault ? FAULT_FLAG_WRITE : 0), &unlocked); if (unlocked) @@ -1617,30 +2593,45 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, if (r) return r; - r = follow_pfn(vma, addr, &pfn); + r = follow_pte(vma->vm_mm, addr, &ptep, &ptl); if (r) return r; + } + if (write_fault && !pte_write(*ptep)) { + pfn = KVM_PFN_ERR_RO_FAULT; + goto out; } if (writable) - *writable = true; + *writable = pte_write(*ptep); + pfn = pte_pfn(*ptep); /* * Get a reference here because callers of *hva_to_pfn* and * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the * returned pfn. This is only needed if the VMA has VM_MIXEDMAP - * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will + * set, but the kvm_try_get_pfn/kvm_release_pfn_clean pair will * simply do nothing for reserved pfns. * * Whoever called remap_pfn_range is also going to call e.g. * unmap_mapping_range before the underlying pages are freed, * causing a call to our MMU notifier. + * + * Certain IO or PFNMAP mappings can be backed with valid + * struct pages, but be allocated without refcounting e.g., + * tail pages of non-compound higher order allocations, which + * would then underflow the refcount when the caller does the + * required put_page. Don't allow those pages here. */ - kvm_get_pfn(pfn); + if (!kvm_try_get_pfn(pfn)) + r = -EFAULT; +out: + pte_unmap_unlock(ptep, ptl); *p_pfn = pfn; - return 0; + + return r; } /* @@ -1657,11 +2648,11 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, * 2): @write_fault = false && @writable, @writable will tell the caller * whether the mapping is writable. */ -static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, - bool write_fault, bool *writable) +kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, + bool write_fault, bool *writable) { struct vm_area_struct *vma; - kvm_pfn_t pfn = 0; + kvm_pfn_t pfn; int npages, r; /* we can do it either atomically or asynchronously, not both */ @@ -1677,7 +2668,7 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, if (npages == 1) return pfn; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); if (npages == -EHWPOISON || (!async && check_user_page_hwpoison(addr))) { pfn = KVM_PFN_ERR_HWPOISON; @@ -1685,12 +2676,12 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, } retry: - vma = find_vma_intersection(current->mm, addr, addr + 1); + vma = vma_lookup(current->mm, addr); if (vma == NULL) pfn = KVM_PFN_ERR_FAULT; else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) { - r = hva_to_pfn_remapped(vma, addr, async, write_fault, writable, &pfn); + r = hva_to_pfn_remapped(vma, addr, write_fault, writable, &pfn); if (r == -EAGAIN) goto retry; if (r < 0) @@ -1701,16 +2692,19 @@ retry: pfn = KVM_PFN_ERR_FAULT; } exit: - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); return pfn; } -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, bool atomic, bool *async, bool write_fault, - bool *writable) + bool *writable, hva_t *hva) { unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); + if (hva) + *hva = addr; + if (addr == KVM_HVA_ERR_RO_BAD) { if (writable) *writable = false; @@ -1738,28 +2732,22 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable) { return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL, - write_fault, writable); + write_fault, writable, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); -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) { - return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); + return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); -kvm_pfn_t gfn_to_pfn_memslot_atomic(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) { - return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); + return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); -kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) -{ - return gfn_to_pfn_memslot_atomic(gfn_to_memslot(kvm, gfn), gfn); -} -EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); - kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); @@ -1791,99 +2779,61 @@ int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, if (entry < nr_pages) return 0; - return __get_user_pages_fast(addr, nr_pages, 1, pages); + return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages); } EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic); -static struct page *kvm_pfn_to_page(kvm_pfn_t pfn) -{ - if (is_error_noslot_pfn(pfn)) - return KVM_ERR_PTR_BAD_PAGE; - - if (kvm_is_reserved_pfn(pfn)) { - WARN_ON(1); - return KVM_ERR_PTR_BAD_PAGE; - } - - return pfn_to_page(pfn); -} - +/* + * Do not use this helper unless you are absolutely certain the gfn _must_ be + * backed by 'struct page'. A valid example is if the backing memslot is + * controlled by KVM. Note, if the returned page is valid, it's refcount has + * been elevated by gfn_to_pfn(). + */ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { + struct page *page; kvm_pfn_t pfn; pfn = gfn_to_pfn(kvm, gfn); - return kvm_pfn_to_page(pfn); + if (is_error_noslot_pfn(pfn)) + return KVM_ERR_PTR_BAD_PAGE; + + page = kvm_pfn_to_refcounted_page(pfn); + if (!page) + return KVM_ERR_PTR_BAD_PAGE; + + return page; } EXPORT_SYMBOL_GPL(gfn_to_page); -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) { - if (pfn == 0) - return; - - if (cache) - cache->pfn = cache->gfn = 0; - if (dirty) kvm_release_pfn_dirty(pfn); else kvm_release_pfn_clean(pfn); } -static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn, - struct gfn_to_pfn_cache *cache, u64 gen) -{ - kvm_release_pfn(cache->pfn, cache->dirty, cache); - - cache->pfn = gfn_to_pfn_memslot(slot, gfn); - cache->gfn = gfn; - cache->dirty = false; - cache->generation = gen; -} - -static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn, - struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, - bool atomic) +int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) { kvm_pfn_t pfn; void *hva = NULL; struct page *page = KVM_UNMAPPED_PAGE; - struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn); - u64 gen = slots->generation; if (!map) return -EINVAL; - if (cache) { - if (!cache->pfn || cache->gfn != gfn || - cache->generation != gen) { - if (atomic) - return -EAGAIN; - kvm_cache_gfn_to_pfn(slot, gfn, cache, gen); - } - pfn = cache->pfn; - } else { - if (atomic) - return -EAGAIN; - pfn = gfn_to_pfn_memslot(slot, gfn); - } + pfn = gfn_to_pfn(vcpu->kvm, gfn); if (is_error_noslot_pfn(pfn)) return -EINVAL; if (pfn_valid(pfn)) { page = pfn_to_page(pfn); - if (atomic) - hva = kmap_atomic(page); - else - hva = kmap(page); + hva = kmap(page); #ifdef CONFIG_HAS_IOMEM - } else if (!atomic) { - hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); } else { - return -EINVAL; + hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); #endif } @@ -1897,26 +2847,9 @@ static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn, return 0; } - -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic) -{ - return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map, - cache, atomic); -} -EXPORT_SYMBOL_GPL(kvm_map_gfn); - -int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) -{ - return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map, - NULL, false); -} EXPORT_SYMBOL_GPL(kvm_vcpu_map); -static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot, - struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, - bool dirty, bool atomic) +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) { if (!map) return; @@ -1924,69 +2857,65 @@ static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot, if (!map->hva) return; - if (map->page != KVM_UNMAPPED_PAGE) { - if (atomic) - kunmap_atomic(map->hva); - else - kunmap(map->page); - } + if (map->page != KVM_UNMAPPED_PAGE) + kunmap(map->page); #ifdef CONFIG_HAS_IOMEM - else if (!atomic) - memunmap(map->hva); else - WARN_ONCE(1, "Unexpected unmapping in atomic context"); + memunmap(map->hva); #endif if (dirty) - mark_page_dirty_in_slot(memslot, map->gfn); + kvm_vcpu_mark_page_dirty(vcpu, map->gfn); - if (cache) - cache->dirty |= dirty; - else - kvm_release_pfn(map->pfn, dirty, NULL); + kvm_release_pfn(map->pfn, dirty); map->hva = NULL; map->page = NULL; } +EXPORT_SYMBOL_GPL(kvm_vcpu_unmap); -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic) +static bool kvm_is_ad_tracked_page(struct page *page) { - __kvm_unmap_gfn(gfn_to_memslot(vcpu->kvm, map->gfn), map, - cache, dirty, atomic); - return 0; + /* + * Per page-flags.h, pages tagged PG_reserved "should in general not be + * touched (e.g. set dirty) except by its owner". + */ + return !PageReserved(page); } -EXPORT_SYMBOL_GPL(kvm_unmap_gfn); -void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) +static void kvm_set_page_dirty(struct page *page) { - __kvm_unmap_gfn(kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), map, NULL, - dirty, false); + if (kvm_is_ad_tracked_page(page)) + SetPageDirty(page); } -EXPORT_SYMBOL_GPL(kvm_vcpu_unmap); -struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn) +static void kvm_set_page_accessed(struct page *page) { - kvm_pfn_t pfn; - - pfn = kvm_vcpu_gfn_to_pfn(vcpu, gfn); - - return kvm_pfn_to_page(pfn); + if (kvm_is_ad_tracked_page(page)) + mark_page_accessed(page); } -EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_page); void kvm_release_page_clean(struct page *page) { WARN_ON(is_error_page(page)); - kvm_release_pfn_clean(page_to_pfn(page)); + kvm_set_page_accessed(page); + put_page(page); } EXPORT_SYMBOL_GPL(kvm_release_page_clean); void kvm_release_pfn_clean(kvm_pfn_t pfn) { - if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn)) - put_page(pfn_to_page(pfn)); + struct page *page; + + if (is_error_noslot_pfn(pfn)) + return; + + page = kvm_pfn_to_refcounted_page(pfn); + if (!page) + return; + + kvm_release_page_clean(page); } EXPORT_SYMBOL_GPL(kvm_release_pfn_clean); @@ -1994,37 +2923,50 @@ void kvm_release_page_dirty(struct page *page) { WARN_ON(is_error_page(page)); - kvm_release_pfn_dirty(page_to_pfn(page)); + kvm_set_page_dirty(page); + kvm_release_page_clean(page); } EXPORT_SYMBOL_GPL(kvm_release_page_dirty); void kvm_release_pfn_dirty(kvm_pfn_t pfn) { - kvm_set_pfn_dirty(pfn); - kvm_release_pfn_clean(pfn); + struct page *page; + + if (is_error_noslot_pfn(pfn)) + return; + + page = kvm_pfn_to_refcounted_page(pfn); + if (!page) + return; + + kvm_release_page_dirty(page); } EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty); +/* + * Note, checking for an error/noslot pfn is the caller's responsibility when + * directly marking a page dirty/accessed. Unlike the "release" helpers, the + * "set" helpers are not to be used when the pfn might point at garbage. + */ void kvm_set_pfn_dirty(kvm_pfn_t pfn) { - if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) - SetPageDirty(pfn_to_page(pfn)); + if (WARN_ON(is_error_noslot_pfn(pfn))) + return; + + if (pfn_valid(pfn)) + kvm_set_page_dirty(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); void kvm_set_pfn_accessed(kvm_pfn_t pfn) { - if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) - mark_page_accessed(pfn_to_page(pfn)); -} -EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); + if (WARN_ON(is_error_noslot_pfn(pfn))) + return; -void kvm_get_pfn(kvm_pfn_t pfn) -{ - if (!kvm_is_reserved_pfn(pfn)) - get_page(pfn_to_page(pfn)); + if (pfn_valid(pfn)) + kvm_set_page_accessed(pfn_to_page(pfn)); } -EXPORT_SYMBOL_GPL(kvm_get_pfn); +EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); static int next_segment(unsigned long len, int offset) { @@ -2135,7 +3077,8 @@ int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic); -static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn, +static int __kvm_write_guest_page(struct kvm *kvm, + struct kvm_memory_slot *memslot, gfn_t gfn, const void *data, int offset, int len) { int r; @@ -2147,7 +3090,7 @@ static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn, r = __copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; - mark_page_dirty_in_slot(memslot, gfn); + mark_page_dirty_in_slot(kvm, memslot, gfn); return 0; } @@ -2156,7 +3099,7 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); - return __kvm_write_guest_page(slot, gfn, data, offset, len); + return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_write_guest_page); @@ -2165,7 +3108,7 @@ int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - return __kvm_write_guest_page(slot, gfn, data, offset, len); + return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page); @@ -2268,7 +3211,8 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int r; gpa_t gpa = ghc->gpa + offset; - BUG_ON(len + offset > ghc->len); + if (WARN_ON_ONCE(len + offset > ghc->len)) + return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) @@ -2284,7 +3228,7 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, r = __copy_to_user((void __user *)ghc->hva + offset, data, len); if (r) return -EFAULT; - mark_page_dirty_in_slot(ghc->memslot, gpa >> PAGE_SHIFT); + mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT); return 0; } @@ -2297,13 +3241,16 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, } EXPORT_SYMBOL_GPL(kvm_write_guest_cached); -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) { struct kvm_memslots *slots = kvm_memslots(kvm); int r; + gpa_t gpa = ghc->gpa + offset; - BUG_ON(len > ghc->len); + if (WARN_ON_ONCE(len + offset > ghc->len)) + return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) @@ -2314,33 +3261,33 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, return -EFAULT; if (unlikely(!ghc->memslot)) - return kvm_read_guest(kvm, ghc->gpa, data, len); + return kvm_read_guest(kvm, gpa, data, len); - r = __copy_from_user(data, (void __user *)ghc->hva, len); + r = __copy_from_user(data, (void __user *)ghc->hva + offset, len); if (r) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(kvm_read_guest_cached); +EXPORT_SYMBOL_GPL(kvm_read_guest_offset_cached); -int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len) +int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned long len) { - const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); - - return kvm_write_guest_page(kvm, gfn, zero_page, offset, len); + return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len); } -EXPORT_SYMBOL_GPL(kvm_clear_guest_page); +EXPORT_SYMBOL_GPL(kvm_read_guest_cached); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) { + const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { - ret = kvm_clear_guest_page(kvm, gfn, offset, seg); + ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, len); if (ret < 0) return ret; offset = 0; @@ -2351,22 +3298,36 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) } EXPORT_SYMBOL_GPL(kvm_clear_guest); -static void mark_page_dirty_in_slot(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) { - if (memslot && memslot->dirty_bitmap) { + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + +#ifdef CONFIG_HAVE_KVM_DIRTY_RING + if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm)) + return; +#endif + + if (memslot && kvm_slot_dirty_track_enabled(memslot)) { unsigned long rel_gfn = gfn - memslot->base_gfn; + u32 slot = (memslot->as_id << 16) | memslot->id; - set_bit_le(rel_gfn, memslot->dirty_bitmap); + if (kvm->dirty_ring_size) + kvm_dirty_ring_push(&vcpu->dirty_ring, + slot, rel_gfn); + else + set_bit_le(rel_gfn, memslot->dirty_bitmap); } } +EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot); void mark_page_dirty(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot; memslot = gfn_to_memslot(kvm, gfn); - mark_page_dirty_in_slot(memslot, gfn); + mark_page_dirty_in_slot(kvm, memslot, gfn); } EXPORT_SYMBOL_GPL(mark_page_dirty); @@ -2375,7 +3336,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn) struct kvm_memory_slot *memslot; memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - mark_page_dirty_in_slot(memslot, gfn); + mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty); @@ -2416,8 +3377,8 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) if (val < grow_start) val = grow_start; - if (val > halt_poll_ns) - val = halt_poll_ns; + if (val > vcpu->kvm->max_halt_poll_ns) + val = vcpu->kvm->max_halt_poll_ns; vcpu->halt_poll_ns = val; out: @@ -2426,15 +3387,19 @@ out: static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) { - unsigned int old, val, shrink; + unsigned int old, val, shrink, grow_start; old = val = vcpu->halt_poll_ns; shrink = READ_ONCE(halt_poll_ns_shrink); + grow_start = READ_ONCE(halt_poll_ns_grow_start); if (shrink == 0) val = 0; else val /= shrink; + if (val < grow_start) + val = 0; + vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); } @@ -2444,14 +3409,14 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) int ret = -EINTR; int idx = srcu_read_lock(&vcpu->kvm->srcu); - if (kvm_arch_vcpu_runnable(vcpu)) { - kvm_make_request(KVM_REQ_UNHALT, vcpu); + if (kvm_arch_vcpu_runnable(vcpu)) goto out; - } if (kvm_cpu_has_pending_timer(vcpu)) goto out; if (signal_pending(current)) goto out; + if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) + goto out; ret = 0; out: @@ -2460,85 +3425,143 @@ out: } /* - * The vCPU has executed a HLT instruction with in-kernel mode enabled. + * Block the vCPU until the vCPU is runnable, an event arrives, or a signal is + * pending. This is mostly used when halting a vCPU, but may also be used + * directly for other vCPU non-runnable states, e.g. x86's Wait-For-SIPI. */ -void kvm_vcpu_block(struct kvm_vcpu *vcpu) +bool kvm_vcpu_block(struct kvm_vcpu *vcpu) { - ktime_t start, cur; - DECLARE_SWAITQUEUE(wait); + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); bool waited = false; - u64 block_ns; + vcpu->stat.generic.blocking = 1; + + preempt_disable(); kvm_arch_vcpu_blocking(vcpu); + prepare_to_rcuwait(wait); + preempt_enable(); + + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + if (kvm_vcpu_check_block(vcpu) < 0) + break; + + waited = true; + schedule(); + } + + preempt_disable(); + finish_rcuwait(wait); + kvm_arch_vcpu_unblocking(vcpu); + preempt_enable(); + + vcpu->stat.generic.blocking = 0; + + return waited; +} + +static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, + ktime_t end, bool success) +{ + struct kvm_vcpu_stat_generic *stats = &vcpu->stat.generic; + u64 poll_ns = ktime_to_ns(ktime_sub(end, start)); - start = cur = ktime_get(); - if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) { - ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns); + ++vcpu->stat.generic.halt_attempted_poll; + + if (success) { + ++vcpu->stat.generic.halt_successful_poll; + + if (!vcpu_valid_wakeup(vcpu)) + ++vcpu->stat.generic.halt_poll_invalid; + + stats->halt_poll_success_ns += poll_ns; + KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_success_hist, poll_ns); + } else { + stats->halt_poll_fail_ns += poll_ns; + KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_fail_hist, poll_ns); + } +} + +/* + * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt + * polling is enabled, busy wait for a short time before blocking to avoid the + * expensive block+unblock sequence if a wake event arrives soon after the vCPU + * is halted. + */ +void kvm_vcpu_halt(struct kvm_vcpu *vcpu) +{ + bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); + bool do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; + ktime_t start, cur, poll_end; + bool waited = false; + u64 halt_ns; + + start = cur = poll_end = ktime_get(); + if (do_halt_poll) { + ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns); - ++vcpu->stat.halt_attempted_poll; do { /* * This sets KVM_REQ_UNHALT if an interrupt * arrives. */ - if (kvm_vcpu_check_block(vcpu) < 0) { - ++vcpu->stat.halt_successful_poll; - if (!vcpu_valid_wakeup(vcpu)) - ++vcpu->stat.halt_poll_invalid; + if (kvm_vcpu_check_block(vcpu) < 0) goto out; - } - cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + cpu_relax(); + poll_end = cur = ktime_get(); + } while (kvm_vcpu_can_poll(cur, stop)); } - for (;;) { - prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); - - if (kvm_vcpu_check_block(vcpu) < 0) - break; + waited = kvm_vcpu_block(vcpu); - waited = true; - schedule(); - } - - finish_swait(&vcpu->wq, &wait); cur = ktime_get(); + if (waited) { + vcpu->stat.generic.halt_wait_ns += + ktime_to_ns(cur) - ktime_to_ns(poll_end); + KVM_STATS_LOG_HIST_UPDATE(vcpu->stat.generic.halt_wait_hist, + ktime_to_ns(cur) - ktime_to_ns(poll_end)); + } out: - kvm_arch_vcpu_unblocking(vcpu); - block_ns = ktime_to_ns(cur) - ktime_to_ns(start); + /* The total time the vCPU was "halted", including polling time. */ + halt_ns = ktime_to_ns(cur) - ktime_to_ns(start); + + /* + * Note, halt-polling is considered successful so long as the vCPU was + * never actually scheduled out, i.e. even if the wake event arrived + * after of the halt-polling loop itself, but before the full wait. + */ + if (do_halt_poll) + update_halt_poll_stats(vcpu, start, poll_end, !waited); - if (!kvm_arch_no_poll(vcpu)) { + if (halt_poll_allowed) { if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); - } else if (halt_poll_ns) { - if (block_ns <= vcpu->halt_poll_ns) + } else if (vcpu->kvm->max_halt_poll_ns) { + if (halt_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ - else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns) + else if (vcpu->halt_poll_ns && + halt_ns > vcpu->kvm->max_halt_poll_ns) shrink_halt_poll_ns(vcpu); /* we had a short halt and our poll time is too small */ - else if (vcpu->halt_poll_ns < halt_poll_ns && - block_ns < halt_poll_ns) + else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns && + halt_ns < vcpu->kvm->max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; } } - trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu)); - kvm_arch_vcpu_block_finish(vcpu); + trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu)); } -EXPORT_SYMBOL_GPL(kvm_vcpu_block); +EXPORT_SYMBOL_GPL(kvm_vcpu_halt); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { - struct swait_queue_head *wqp; - - wqp = kvm_arch_vcpu_wq(vcpu); - if (swq_has_sleeper(wqp)) { - swake_up_one(wqp); + if (__kvm_vcpu_wake_up(vcpu)) { WRITE_ONCE(vcpu->ready, true); - ++vcpu->stat.halt_wakeup; + ++vcpu->stat.generic.halt_wakeup; return true; } @@ -2552,16 +3575,37 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up); */ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { - int me; - int cpu = vcpu->cpu; + int me, cpu; if (kvm_vcpu_wake_up(vcpu)) return; me = get_cpu(); - if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - if (kvm_arch_vcpu_should_kick(vcpu)) + /* + * The only state change done outside the vcpu mutex is IN_GUEST_MODE + * to EXITING_GUEST_MODE. Therefore the moderately expensive "should + * kick" check does not need atomic operations if kvm_vcpu_kick is used + * within the vCPU thread itself. + */ + if (vcpu == __this_cpu_read(kvm_running_vcpu)) { + if (vcpu->mode == IN_GUEST_MODE) + WRITE_ONCE(vcpu->mode, EXITING_GUEST_MODE); + goto out; + } + + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_arch_vcpu_should_kick(), which could result in sending an + * IPI to the previous pCPU. But, that's ok because the purpose of the + * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the + * vCPU also requires it to leave IN_GUEST_MODE. + */ + if (kvm_arch_vcpu_should_kick(vcpu)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); + } +out: put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick); @@ -2593,7 +3637,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); * * (a) VCPU which has not done pl-exit or cpu relax intercepted recently * (preempted lock holder), indicated by @in_spin_loop. - * Set at the beiginning and cleared at the end of interception/PLE handler. + * Set at the beginning and cleared at the end of interception/PLE handler. * * (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get * chance last time (mostly it has become eligible now since we have probably @@ -2649,15 +3693,20 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) return false; } +bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return false; +} + void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + unsigned long i; int yielded = 0; int try = 3; int pass; - int i; kvm_vcpu_set_in_spin_loop(me, true); /* @@ -2678,10 +3727,11 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; if (vcpu == me) continue; - if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu)) + if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu)) continue; if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && - !kvm_arch_vcpu_in_kernel(vcpu)) + !kvm_arch_dy_has_pending_interrupt(vcpu) && + !kvm_arch_vcpu_in_kernel(vcpu)) continue; if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) continue; @@ -2704,6 +3754,17 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) } EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); +static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff) +{ +#ifdef CONFIG_HAVE_KVM_DIRTY_RING + return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) && + (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET + + kvm->dirty_ring_size / PAGE_SIZE); +#else + return false; +#endif +} + static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data; @@ -2719,6 +3780,10 @@ static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf) else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET) page = virt_to_page(vcpu->kvm->coalesced_mmio_ring); #endif + else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff)) + page = kvm_dirty_ring_get_page( + &vcpu->dirty_ring, + vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET); else return kvm_arch_vcpu_fault(vcpu, vmf); get_page(page); @@ -2732,6 +3797,14 @@ static const struct vm_operations_struct kvm_vcpu_vm_ops = { static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) { + struct kvm_vcpu *vcpu = file->private_data; + unsigned long pages = vma_pages(vma); + + if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) || + kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) && + ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED))) + return -EINVAL; + vma->vm_ops = &kvm_vcpu_vm_ops; return 0; } @@ -2740,12 +3813,11 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp) { struct kvm_vcpu *vcpu = filp->private_data; - debugfs_remove_recursive(vcpu->debugfs_dentry); kvm_put_kvm(vcpu->kvm); return 0; } -static struct file_operations kvm_vcpu_fops = { +static const struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, .mmap = kvm_vcpu_mmap, @@ -2764,21 +3836,33 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu) return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } +#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS +static int vcpu_get_pid(void *data, u64 *val) +{ + struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data; + *val = pid_nr(rcu_access_pointer(vcpu->pid)); + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(vcpu_get_pid_fops, vcpu_get_pid, NULL, "%llu\n"); + static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) { -#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS + struct dentry *debugfs_dentry; char dir_name[ITOA_MAX_LEN * 2]; if (!debugfs_initialized()) return; snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id); - vcpu->debugfs_dentry = debugfs_create_dir(dir_name, - vcpu->kvm->debugfs_dentry); + debugfs_dentry = debugfs_create_dir(dir_name, + vcpu->kvm->debugfs_dentry); + debugfs_create_file("pid", 0444, debugfs_dentry, vcpu, + &vcpu_get_pid_fops); - kvm_arch_create_vcpu_debugfs(vcpu); -#endif + kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry); } +#endif /* * Creates some virtual cpus. Good luck creating more than one. @@ -2789,30 +3873,32 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) struct kvm_vcpu *vcpu; struct page *page; - if (id >= KVM_MAX_VCPU_ID) + if (id >= KVM_MAX_VCPU_IDS) return -EINVAL; mutex_lock(&kvm->lock); - if (kvm->created_vcpus == KVM_MAX_VCPUS) { + if (kvm->created_vcpus >= kvm->max_vcpus) { mutex_unlock(&kvm->lock); return -EINVAL; } + r = kvm_arch_vcpu_precreate(kvm, id); + if (r) { + mutex_unlock(&kvm->lock); + return r; + } + kvm->created_vcpus++; mutex_unlock(&kvm->lock); - r = kvm_arch_vcpu_precreate(kvm, id); - if (r) - goto vcpu_decrement; - - vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!vcpu) { r = -ENOMEM; goto vcpu_decrement; } BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE); - page = alloc_page(GFP_KERNEL | __GFP_ZERO); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) { r = -ENOMEM; goto vcpu_free; @@ -2825,7 +3911,12 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) if (r) goto vcpu_free_run_page; - kvm_create_vcpu_debugfs(vcpu); + if (kvm->dirty_ring_size) { + r = kvm_dirty_ring_alloc(&vcpu->dirty_ring, + id, kvm->dirty_ring_size); + if (r) + goto arch_vcpu_destroy; + } mutex_lock(&kvm->lock); if (kvm_get_vcpu_by_id(kvm, id)) { @@ -2834,32 +3925,36 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - BUG_ON(kvm->vcpus[vcpu->vcpu_idx]); + r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); + BUG_ON(r == -EBUSY); + if (r) + goto unlock_vcpu_destroy; /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { + xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); kvm_put_kvm_no_destroy(kvm); goto unlock_vcpu_destroy; } - kvm->vcpus[vcpu->vcpu_idx] = vcpu; - /* - * Pairs with smp_rmb() in kvm_get_vcpu. Write kvm->vcpus - * before kvm->online_vcpu's incremented value. + * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu + * pointer before kvm->online_vcpu's incremented value. */ smp_wmb(); atomic_inc(&kvm->online_vcpus); mutex_unlock(&kvm->lock); kvm_arch_vcpu_postcreate(vcpu); + kvm_create_vcpu_debugfs(vcpu); return r; unlock_vcpu_destroy: mutex_unlock(&kvm->lock); - debugfs_remove_recursive(vcpu->debugfs_dentry); + kvm_dirty_ring_free(&vcpu->dirty_ring); +arch_vcpu_destroy: kvm_arch_vcpu_destroy(vcpu); vcpu_free_run_page: free_page((unsigned long)vcpu->run); @@ -2883,6 +3978,44 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) return 0; } +static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer, + size_t size, loff_t *offset) +{ + struct kvm_vcpu *vcpu = file->private_data; + + return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header, + &kvm_vcpu_stats_desc[0], &vcpu->stat, + sizeof(vcpu->stat), user_buffer, size, offset); +} + +static const struct file_operations kvm_vcpu_stats_fops = { + .read = kvm_vcpu_stats_read, + .llseek = noop_llseek, +}; + +static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu) +{ + int fd; + struct file *file; + char name[15 + ITOA_MAX_LEN + 1]; + + snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id); + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + file = anon_inode_getfile(name, &kvm_vcpu_stats_fops, vcpu, O_RDONLY); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); + } + file->f_mode |= FMODE_PREAD; + fd_install(fd, file); + + return fd; +} + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2892,7 +4025,7 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; - if (vcpu->kvm->mm != current->mm) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) @@ -2929,7 +4062,7 @@ static long kvm_vcpu_ioctl(struct file *filp, synchronize_rcu(); put_pid(oldpid); } - r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run); + r = kvm_arch_vcpu_ioctl_run(vcpu); trace_kvm_userspace_exit(vcpu->run->exit_reason, r); break; } @@ -2954,7 +4087,6 @@ out_free1: case KVM_SET_REGS: { struct kvm_regs *kvm_regs; - r = -ENOMEM; kvm_regs = memdup_user(argp, sizeof(*kvm_regs)); if (IS_ERR(kvm_regs)) { r = PTR_ERR(kvm_regs); @@ -3081,6 +4213,10 @@ out_free1: r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu); break; } + case KVM_GET_STATS_FD: { + r = kvm_vcpu_ioctl_get_stats_fd(vcpu); + break; + } default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } @@ -3099,7 +4235,7 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, void __user *argp = compat_ptr(arg); int r; - if (vcpu->kvm->mm != current->mm) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; switch (ioctl) { @@ -3117,7 +4253,8 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, if (kvm_sigmask.len != sizeof(compat_sigset_t)) goto out; r = -EFAULT; - if (get_compat_sigset(&sigset, (void *)sigmask_arg->sigset)) + if (get_compat_sigset(&sigset, + (compat_sigset_t __user *)sigmask_arg->sigset)) goto out; r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); } else @@ -3164,7 +4301,7 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, { struct kvm_device *dev = filp->private_data; - if (dev->kvm->mm != current->mm) + if (dev->kvm->mm != current->mm || dev->kvm->vm_dead) return -EIO; switch (ioctl) { @@ -3241,7 +4378,7 @@ void kvm_unregister_device_ops(u32 type) static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_create_device *cd) { - const struct kvm_device_ops *ops = NULL; + const struct kvm_device_ops *ops; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; int type; @@ -3284,8 +4421,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm, kvm_put_kvm_no_destroy(kvm); mutex_lock(&kvm->lock); list_del(&dev->vm_node); + if (ops->release) + ops->release(dev); mutex_unlock(&kvm->lock); - ops->destroy(dev); + if (ops->destroy) + ops->destroy(dev); return ret; } @@ -3310,9 +4450,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: case KVM_CAP_ENABLE_CAP_VM: -#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT - case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: -#endif + case KVM_CAP_HALT_POLL: return 1; #ifdef CONFIG_KVM_MMIO case KVM_CAP_COALESCED_MMIO: @@ -3320,6 +4458,10 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_COALESCED_PIO: return 1; #endif +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: + return KVM_DIRTY_LOG_MANUAL_CAPS; +#endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; @@ -3330,12 +4472,87 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) #endif case KVM_CAP_NR_MEMSLOTS: return KVM_USER_MEM_SLOTS; + case KVM_CAP_DIRTY_LOG_RING: +#ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO + return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); +#else + return 0; +#endif + case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: +#ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL + return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); +#else + return 0; +#endif + case KVM_CAP_BINARY_STATS_FD: + case KVM_CAP_SYSTEM_EVENT_DATA: + return 1; default: break; } return kvm_vm_ioctl_check_extension(kvm, arg); } +static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size) +{ + int r; + + if (!KVM_DIRTY_LOG_PAGE_OFFSET) + return -EINVAL; + + /* the size should be power of 2 */ + if (!size || (size & (size - 1))) + return -EINVAL; + + /* Should be bigger to keep the reserved entries, or a page */ + if (size < kvm_dirty_ring_get_rsvd_entries() * + sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE) + return -EINVAL; + + if (size > KVM_DIRTY_RING_MAX_ENTRIES * + sizeof(struct kvm_dirty_gfn)) + return -E2BIG; + + /* We only allow it to set once */ + if (kvm->dirty_ring_size) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (kvm->created_vcpus) { + /* We don't allow to change this value after vcpu created */ + r = -EINVAL; + } else { + kvm->dirty_ring_size = size; + r = 0; + } + + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) +{ + unsigned long i; + struct kvm_vcpu *vcpu; + int cleared = 0; + + if (!kvm->dirty_ring_size) + return -EINVAL; + + mutex_lock(&kvm->slots_lock); + + kvm_for_each_vcpu(i, vcpu, kvm) + cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring); + + mutex_unlock(&kvm->slots_lock); + + if (cleared) + kvm_flush_remote_tlbs(kvm); + + return cleared; +} + int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -3347,17 +4564,72 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, { switch (cap->cap) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT - case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: - if (cap->flags || (cap->args[0] & ~1)) + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: { + u64 allowed_options = KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE; + + if (cap->args[0] & KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE) + allowed_options = KVM_DIRTY_LOG_MANUAL_CAPS; + + if (cap->flags || (cap->args[0] & ~allowed_options)) return -EINVAL; kvm->manual_dirty_log_protect = cap->args[0]; return 0; + } #endif + case KVM_CAP_HALT_POLL: { + if (cap->flags || cap->args[0] != (unsigned int)cap->args[0]) + return -EINVAL; + + kvm->max_halt_poll_ns = cap->args[0]; + return 0; + } + case KVM_CAP_DIRTY_LOG_RING: + case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: + if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap)) + return -EINVAL; + + return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); default: return kvm_vm_ioctl_enable_cap(kvm, cap); } } +static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer, + size_t size, loff_t *offset) +{ + struct kvm *kvm = file->private_data; + + return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header, + &kvm_vm_stats_desc[0], &kvm->stat, + sizeof(kvm->stat), user_buffer, size, offset); +} + +static const struct file_operations kvm_vm_stats_fops = { + .read = kvm_vm_stats_read, + .llseek = noop_llseek, +}; + +static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm) +{ + int fd; + struct file *file; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + file = anon_inode_getfile("kvm-vm-stats", + &kvm_vm_stats_fops, kvm, O_RDONLY); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); + } + file->f_mode |= FMODE_PREAD; + fd_install(fd, file); + + return fd; +} + static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -3365,7 +4637,7 @@ static long kvm_vm_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; - if (kvm->mm != current->mm) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: @@ -3501,21 +4773,18 @@ static long kvm_vm_ioctl(struct file *filp, if (routing.flags) goto out; if (routing.nr) { - r = -ENOMEM; - entries = vmalloc(array_size(sizeof(*entries), - routing.nr)); - if (!entries) - goto out; - r = -EFAULT; urouting = argp; - if (copy_from_user(entries, urouting->entries, - routing.nr * sizeof(*entries))) - goto out_free_irq_routing; + entries = vmemdup_user(urouting->entries, + array_size(sizeof(*entries), + routing.nr)); + if (IS_ERR(entries)) { + r = PTR_ERR(entries); + goto out; + } } r = kvm_set_irq_routing(kvm, entries, routing.nr, routing.flags); -out_free_irq_routing: - vfree(entries); + kvfree(entries); break; } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ @@ -3540,6 +4809,12 @@ out_free_irq_routing: case KVM_CHECK_EXTENSION: r = kvm_vm_ioctl_check_extension_generic(kvm, arg); break; + case KVM_RESET_DIRTY_RINGS: + r = kvm_vm_ioctl_reset_dirty_pages(kvm); + break; + case KVM_GET_STATS_FD: + r = kvm_vm_ioctl_get_stats_fd(kvm); + break; default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } @@ -3557,15 +4832,54 @@ struct compat_kvm_dirty_log { }; }; +struct compat_kvm_clear_dirty_log { + __u32 slot; + __u32 num_pages; + __u64 first_page; + union { + compat_uptr_t dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + +long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + return -ENOTTY; +} + static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; int r; - if (kvm->mm != current->mm) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; + + r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg); + if (r != -ENOTTY) + return r; + switch (ioctl) { +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CLEAR_DIRTY_LOG: { + struct compat_kvm_clear_dirty_log compat_log; + struct kvm_clear_dirty_log log; + + if (copy_from_user(&compat_log, (void __user *)arg, + sizeof(compat_log))) + return -EFAULT; + log.slot = compat_log.slot; + log.num_pages = compat_log.num_pages; + log.first_page = compat_log.first_page; + log.padding2 = compat_log.padding2; + log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); + + r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); + break; + } +#endif case KVM_GET_DIRTY_LOG: { struct compat_kvm_dirty_log compat_log; struct kvm_dirty_log log; @@ -3588,34 +4902,40 @@ static long kvm_vm_compat_ioctl(struct file *filp, } #endif -static struct file_operations kvm_vm_fops = { +static const struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, .llseek = noop_llseek, KVM_COMPAT(kvm_vm_compat_ioctl), }; +bool file_is_kvm(struct file *file) +{ + return file && file->f_op == &kvm_vm_fops; +} +EXPORT_SYMBOL_GPL(file_is_kvm); + static int kvm_dev_ioctl_create_vm(unsigned long type) { - int r; + char fdname[ITOA_MAX_LEN + 1]; + int r, fd; struct kvm *kvm; struct file *file; - kvm = kvm_create_vm(type); - if (IS_ERR(kvm)) - return PTR_ERR(kvm); -#ifdef CONFIG_KVM_MMIO - r = kvm_coalesced_mmio_init(kvm); - if (r < 0) - goto put_kvm; -#endif - r = get_unused_fd_flags(O_CLOEXEC); - if (r < 0) - goto put_kvm; + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + snprintf(fdname, sizeof(fdname), "%d", fd); + + kvm = kvm_create_vm(type, fdname); + if (IS_ERR(kvm)) { + r = PTR_ERR(kvm); + goto put_fd; + } file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (IS_ERR(file)) { - put_unused_fd(r); r = PTR_ERR(file); goto put_kvm; } @@ -3626,18 +4946,15 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) * cases it will be called by the final fput(file) and will take * care of doing kvm_put_kvm(kvm). */ - if (kvm_create_vm_debugfs(kvm, r) < 0) { - put_unused_fd(r); - fput(file); - return -ENOMEM; - } kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm); - fd_install(r, file); - return r; + fd_install(fd, file); + return fd; put_kvm: kvm_put_kvm(kvm); +put_fd: + put_unused_fd(fd); return r; } @@ -4018,42 +5335,51 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, return 0; } -/* Caller must hold slots_lock. */ -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) { - int i; + int i, j; struct kvm_io_bus *new_bus, *bus; + lockdep_assert_held(&kvm->slots_lock); + bus = kvm_get_bus(kvm, bus_idx); if (!bus) - return; + return 0; - for (i = 0; i < bus->dev_count; i++) + for (i = 0; i < bus->dev_count; i++) { if (bus->range[i].dev == dev) { break; } + } if (i == bus->dev_count) - return; + return 0; new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1), GFP_KERNEL_ACCOUNT); - if (!new_bus) { - pr_err("kvm: failed to shrink bus, removing it completely\n"); - goto broken; + if (new_bus) { + memcpy(new_bus, bus, struct_size(bus, range, i)); + new_bus->dev_count--; + memcpy(new_bus->range + i, bus->range + i + 1, + flex_array_size(new_bus, range, new_bus->dev_count - i)); } - memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); - new_bus->dev_count--; - memcpy(new_bus->range + i, bus->range + i + 1, - (new_bus->dev_count - i) * sizeof(struct kvm_io_range)); - -broken: rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); + + /* Destroy the old bus _after_ installing the (null) bus. */ + if (!new_bus) { + pr_err("kvm: failed to shrink bus, removing it completely\n"); + for (j = 0; j < bus->dev_count; j++) { + if (j == i) + continue; + kvm_iodevice_destructor(bus->range[j].dev); + } + } + kfree(bus); - return; + return new_bus ? 0 : -ENOMEM; } struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, @@ -4086,26 +5412,25 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { + int ret; struct kvm_stat_data *stat_data = (struct kvm_stat_data *) inode->i_private; - /* The debugfs files are a reference to the kvm struct which - * is still valid when kvm_destroy_vm is called. - * To avoid the race between open and the removal of the debugfs - * directory we test against the users count. + /* + * The debugfs files are a reference to the kvm struct which + * is still valid when kvm_destroy_vm is called. kvm_get_kvm_safe + * avoids the race between open and the removal of the debugfs directory. */ - if (!refcount_inc_not_zero(&stat_data->kvm->users_count)) + if (!kvm_get_kvm_safe(stat_data->kvm)) return -ENOENT; - if (simple_attr_open(inode, file, get, - KVM_DBGFS_GET_MODE(stat_data->dbgfs_item) & 0222 - ? set : NULL, - fmt)) { + ret = simple_attr_open(inode, file, get, + kvm_stats_debugfs_mode(stat_data->desc) & 0222 + ? set : NULL, fmt); + if (ret) kvm_put_kvm(stat_data->kvm); - return -ENOMEM; - } - return 0; + return ret; } static int kvm_debugfs_release(struct inode *inode, struct file *file) @@ -4121,38 +5446,38 @@ static int kvm_debugfs_release(struct inode *inode, struct file *file) static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val) { - *val = *(ulong *)((void *)kvm + offset); + *val = *(u64 *)((void *)(&kvm->stat) + offset); return 0; } static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) { - *(ulong *)((void *)kvm + offset) = 0; + *(u64 *)((void *)(&kvm->stat) + offset) = 0; return 0; } static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; *val = 0; kvm_for_each_vcpu(i, vcpu, kvm) - *val += *(u64 *)((void *)vcpu + offset); + *val += *(u64 *)((void *)(&vcpu->stat) + offset); return 0; } static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) - *(u64 *)((void *)vcpu + offset) = 0; + *(u64 *)((void *)(&vcpu->stat) + offset) = 0; return 0; } @@ -4162,14 +5487,14 @@ static int kvm_stat_data_get(void *data, u64 *val) int r = -EFAULT; struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data; - switch (stat_data->dbgfs_item->kind) { + switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_get_stat_per_vm(stat_data->kvm, - stat_data->dbgfs_item->offset, val); + stat_data->desc->desc.offset, val); break; case KVM_STAT_VCPU: r = kvm_get_stat_per_vcpu(stat_data->kvm, - stat_data->dbgfs_item->offset, val); + stat_data->desc->desc.offset, val); break; } @@ -4184,14 +5509,14 @@ static int kvm_stat_data_clear(void *data, u64 val) if (val) return -EINVAL; - switch (stat_data->dbgfs_item->kind) { + switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_clear_stat_per_vm(stat_data->kvm, - stat_data->dbgfs_item->offset); + stat_data->desc->desc.offset); break; case KVM_STAT_VCPU: r = kvm_clear_stat_per_vcpu(stat_data->kvm, - stat_data->dbgfs_item->offset); + stat_data->desc->desc.offset); break; } @@ -4248,6 +5573,7 @@ static int vm_stat_clear(void *_offset, u64 val) } DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%llu\n"); static int vcpu_stat_get(void *_offset, u64 *val) { @@ -4284,11 +5610,7 @@ static int vcpu_stat_clear(void *_offset, u64 val) DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear, "%llu\n"); - -static const struct file_operations *stat_fops[] = { - [KVM_STAT_VCPU] = &vcpu_stat_fops, - [KVM_STAT_VM] = &vm_stat_fops, -}; +DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n"); static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) { @@ -4324,7 +5646,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) } add_uevent_var(env, "PID=%d", kvm->userspace_pid); - if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) { + if (!IS_ERR(kvm->debugfs_dentry)) { char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT); if (p) { @@ -4342,15 +5664,32 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) static void kvm_init_debug(void) { - struct kvm_stats_debugfs_item *p; + const struct file_operations *fops; + const struct _kvm_stats_desc *pdesc; + int i; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); - kvm_debugfs_num_entries = 0; - for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) { - debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p), - kvm_debugfs_dir, (void *)(long)p->offset, - stat_fops[p->kind]); + for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { + pdesc = &kvm_vm_stats_desc[i]; + if (kvm_stats_debugfs_mode(pdesc) & 0222) + fops = &vm_stat_fops; + else + fops = &vm_stat_readonly_fops; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm_debugfs_dir, + (void *)(long)pdesc->desc.offset, fops); + } + + for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { + pdesc = &kvm_vcpu_stats_desc[i]; + if (kvm_stats_debugfs_mode(pdesc) & 0222) + fops = &vcpu_stat_fops; + else + fops = &vcpu_stat_readonly_fops; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm_debugfs_dir, + (void *)(long)pdesc->desc.offset, fops); } } @@ -4364,9 +5703,7 @@ static int kvm_suspend(void) static void kvm_resume(void) { if (kvm_usage_count) { -#ifdef CONFIG_LOCKDEP - WARN_ON(lockdep_is_held(&kvm_count_lock)); -#endif + lockdep_assert_not_held(&kvm_count_lock); hardware_enable_nolock(NULL); } } @@ -4399,7 +5736,7 @@ static void kvm_sched_out(struct preempt_notifier *pn, { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); - if (current->state == TASK_RUNNING) { + if (current->on_rq) { WRITE_ONCE(vcpu->preempted, true); WRITE_ONCE(vcpu->ready, true); } @@ -4426,6 +5763,7 @@ struct kvm_vcpu *kvm_get_running_vcpu(void) return vcpu; } +EXPORT_SYMBOL_GPL(kvm_get_running_vcpu); /** * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus. @@ -4435,14 +5773,66 @@ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) return &kvm_running_vcpu; } -static void check_processor_compat(void *rtn) +#ifdef CONFIG_GUEST_PERF_EVENTS +static unsigned int kvm_guest_state(void) +{ + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + unsigned int state; + + if (!kvm_arch_pmi_in_guest(vcpu)) + return 0; + + state = PERF_GUEST_ACTIVE; + if (!kvm_arch_vcpu_in_kernel(vcpu)) + state |= PERF_GUEST_USER; + + return state; +} + +static unsigned long kvm_guest_get_ip(void) { - *(int *)rtn = kvm_arch_check_processor_compat(); + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + + /* Retrieving the IP must be guarded by a call to kvm_guest_state(). */ + if (WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu))) + return 0; + + return kvm_arch_vcpu_get_ip(vcpu); +} + +static struct perf_guest_info_callbacks kvm_guest_cbs = { + .state = kvm_guest_state, + .get_ip = kvm_guest_get_ip, + .handle_intel_pt_intr = NULL, +}; + +void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)) +{ + kvm_guest_cbs.handle_intel_pt_intr = pt_intr_handler; + perf_register_guest_info_callbacks(&kvm_guest_cbs); +} +void kvm_unregister_perf_callbacks(void) +{ + perf_unregister_guest_info_callbacks(&kvm_guest_cbs); +} +#endif + +struct kvm_cpu_compat_check { + void *opaque; + int *ret; +}; + +static void check_processor_compat(void *data) +{ + struct kvm_cpu_compat_check *c = data; + + *c->ret = kvm_arch_check_processor_compat(c->opaque); } int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, struct module *module) { + struct kvm_cpu_compat_check c; int r; int cpu; @@ -4466,12 +5856,14 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, goto out_free_0; } - r = kvm_arch_hardware_setup(); + r = kvm_arch_hardware_setup(opaque); if (r < 0) goto out_free_1; + c.ret = &r; + c.opaque = opaque; for_each_online_cpu(cpu) { - smp_call_function_single(cpu, check_processor_compat, &r, 1); + smp_call_function_single(cpu, check_processor_compat, &c, 1); if (r < 0) goto out_free_2; } @@ -4489,20 +5881,27 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align, SLAB_ACCOUNT, offsetof(struct kvm_vcpu, arch), - sizeof_field(struct kvm_vcpu, arch), + offsetofend(struct kvm_vcpu, stats_id) + - offsetof(struct kvm_vcpu, arch), NULL); if (!kvm_vcpu_cache) { r = -ENOMEM; goto out_free_3; } + for_each_possible_cpu(cpu) { + if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), + GFP_KERNEL, cpu_to_node(cpu))) { + r = -ENOMEM; + goto out_free_4; + } + } + r = kvm_async_pf_init(); if (r) - goto out_free; + goto out_free_4; kvm_chardev_ops.owner = module; - kvm_vm_fops.owner = module; - kvm_vcpu_fops.owner = module; r = misc_register(&kvm_dev); if (r) { @@ -4524,7 +5923,9 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, out_unreg: kvm_async_pf_deinit(); -out_free: +out_free_4: + for_each_possible_cpu(cpu) + free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); @@ -4544,8 +5945,12 @@ EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { + int cpu; + debugfs_remove_recursive(kvm_debugfs_dir); misc_deregister(&kvm_dev); + for_each_possible_cpu(cpu) + free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); @@ -4576,6 +5981,7 @@ static int kvm_vm_worker_thread(void *context) * we have to locally copy anything that is needed beyond initialization */ struct kvm_vm_worker_thread_context *init_context = context; + struct task_struct *parent; struct kvm *kvm = init_context->kvm; kvm_vm_thread_fn_t thread_fn = init_context->thread_fn; uintptr_t data = init_context->data; @@ -4602,7 +6008,7 @@ init_complete: init_context = NULL; if (err) - return err; + goto out; /* Wait to be woken up by the spawner before proceeding. */ kthread_parkme(); @@ -4610,6 +6016,25 @@ init_complete: if (!kthread_should_stop()) err = thread_fn(kvm, data); +out: + /* + * Move kthread back to its original cgroup to prevent it lingering in + * the cgroup of the VM process, after the latter finishes its + * execution. + * + * kthread_stop() waits on the 'exited' completion condition which is + * set in exit_mm(), via mm_release(), in do_exit(). However, the + * kthread is removed from the cgroup in the cgroup_exit() which is + * called after the exit_mm(). This causes the kthread_stop() to return + * before the kthread actually quits the cgroup. + */ + rcu_read_lock(); + parent = rcu_dereference(current->real_parent); + get_task_struct(parent); + rcu_read_unlock(); + cgroup_attach_task_all(parent, current); + put_task_struct(parent); + return err; } |