diff options
Diffstat (limited to 'include/linux/kvm_host.h')
| -rw-r--r-- | include/linux/kvm_host.h | 1650 |
1 files changed, 1387 insertions, 263 deletions
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7f2e2a09ebbd..3bde4fb5c6aa 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -10,7 +10,9 @@ #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> +#include <linux/sched/stat.h> #include <linux/bug.h> +#include <linux/minmax.h> #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/preempt.h> @@ -26,6 +28,13 @@ #include <linux/rcuwait.h> #include <linux/refcount.h> #include <linux/nospec.h> +#include <linux/notifier.h> +#include <linux/ftrace.h> +#include <linux/hashtable.h> +#include <linux/instrumentation.h> +#include <linux/interval_tree.h> +#include <linux/rbtree.h> +#include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -34,21 +43,22 @@ #include <linux/kvm_types.h> #include <asm/kvm_host.h> +#include <linux/kvm_dirty_ring.h> -#ifndef KVM_MAX_VCPU_ID -#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS +#ifndef KVM_MAX_VCPU_IDS +#define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif /* - * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used - * in kvm, other bits are visible for userspace which are defined in + * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally + * used in kvm, other bits are visible for userspace which are defined in * include/linux/kvm_h. */ #define KVM_MEMSLOT_INVALID (1UL << 16) /* * Bit 63 of the memslot generation number is an "update in-progress flag", - * e.g. is temporarily set for the duration of install_new_memslots(). + * e.g. is temporarily set for the duration of kvm_swap_active_memslots(). * This flag effectively creates a unique generation number that is used to * mark cached memslot data, e.g. MMIO accesses, as potentially being stale, * i.e. may (or may not) have come from the previous memslots generation. @@ -70,8 +80,8 @@ /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 -#ifndef KVM_ADDRESS_SPACE_NUM -#define KVM_ADDRESS_SPACE_NUM 1 +#ifndef KVM_MAX_NR_ADDRESS_SPACES +#define KVM_MAX_NR_ADDRESS_SPACES 1 #endif /* @@ -86,6 +96,8 @@ #define KVM_PFN_ERR_FAULT (KVM_PFN_ERR_MASK) #define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1) #define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2) +#define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3) +#define KVM_PFN_ERR_NEEDS_IO (KVM_PFN_ERR_MASK + 4) /* * error pfns indicate that the gfn is in slot but faild to @@ -97,6 +109,15 @@ static inline bool is_error_pfn(kvm_pfn_t pfn) } /* + * KVM_PFN_ERR_SIGPENDING indicates that fetching the PFN was interrupted + * by a pending signal. Note, the signal may or may not be fatal. + */ +static inline bool is_sigpending_pfn(kvm_pfn_t pfn) +{ + return pfn == KVM_PFN_ERR_SIGPENDING; +} + +/* * error_noslot pfns indicate that the gfn can not be * translated to pfn - it is not in slot or failed to * translate it to pfn. @@ -128,25 +149,34 @@ static inline bool kvm_is_error_hva(unsigned long addr) #endif -#define KVM_ERR_PTR_BAD_PAGE (ERR_PTR(-ENOENT)) - -static inline bool is_error_page(struct page *page) +static inline bool kvm_is_error_gpa(gpa_t gpa) { - return IS_ERR(page); + return gpa == INVALID_GPA; } #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) +#define KVM_REQUEST_NO_ACTION BIT(10) /* * Architecture-independent vcpu->requests bit members - * Bits 4-7 are reserved for more arch-independent bits. + * Bits 3-7 are reserved for more arch-independent bits. + */ +#define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_UNBLOCK 2 +#define KVM_REQ_DIRTY_RING_SOFT_FULL 3 +#define KVM_REQUEST_ARCH_BASE 8 + +/* + * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to + * OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick" + * in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing + * on. A kick only guarantees that the vCPU is on its way out, e.g. a previous + * kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no + * guarantee the vCPU received an IPI and has actually exited guest mode. */ -#define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_PENDING_TIMER 2 -#define KVM_REQ_UNHALT 3 -#define KVM_REQUEST_ARCH_BASE 8 +#define KVM_REQ_OUTSIDE_GUEST_MODE (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ @@ -154,6 +184,10 @@ static inline bool is_error_page(struct page *page) }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) +bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap); +bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); + #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -179,6 +213,7 @@ enum kvm_bus { KVM_PIO_BUS, KVM_VIRTIO_CCW_NOTIFY_BUS, KVM_FAST_MMIO_BUS, + KVM_IOCSR_BUS, KVM_NR_BUSES }; @@ -190,8 +225,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); -void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, - struct kvm_io_device *dev); +int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev); struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr); @@ -201,7 +236,6 @@ struct kvm_async_pf { struct list_head link; struct list_head queue; struct kvm_vcpu *vcpu; - struct mm_struct *mm; gpa_t cr2_or_gpa; unsigned long addr; struct kvm_arch_async_pf arch; @@ -216,6 +250,30 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER +union kvm_mmu_notifier_arg { + unsigned long attributes; +}; + +enum kvm_gfn_range_filter { + KVM_FILTER_SHARED = BIT(0), + KVM_FILTER_PRIVATE = BIT(1), +}; + +struct kvm_gfn_range { + struct kvm_memory_slot *slot; + gfn_t start; + gfn_t end; + union kvm_mmu_notifier_arg arg; + enum kvm_gfn_range_filter attr_filter; + bool may_block; + bool lockless; +}; +bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); +bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); +bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); +#endif + enum { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, @@ -223,21 +281,19 @@ enum { READING_SHADOW_PAGE_TABLES, }; -#define KVM_UNMAPPED_PAGE ((void *) 0x500 + POISON_POINTER_DELTA) - struct kvm_host_map { /* * Only valid if the 'pfn' is managed by the host kernel (i.e. There is * a 'struct page' for it. When using mem= kernel parameter some memory * can be used as guest memory but they are not managed by host * kernel). - * If 'pfn' is not managed by the host kernel, this field is - * initialized to KVM_UNMAPPED_PAGE. */ + struct page *pinned_page; struct page *page; void *hva; kvm_pfn_t pfn; kvm_pfn_t gfn; + bool writable; }; /* @@ -249,6 +305,11 @@ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) return !!map->hva; } +static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) +{ + return single_task_running() && !need_resched() && ktime_before(cur, stop); +} + /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. @@ -266,23 +327,25 @@ struct kvm_vcpu { #endif int cpu; int vcpu_id; /* id given by userspace at creation */ - int vcpu_idx; /* index in kvm->vcpus array */ - int srcu_idx; + int vcpu_idx; /* index into kvm->vcpu_array */ + int ____srcu_idx; /* Don't use this directly. You've been warned. */ +#ifdef CONFIG_PROVE_RCU + int srcu_depth; +#endif int mode; u64 requests; unsigned long guest_debug; - int pre_pcpu; - struct list_head blocked_vcpu_list; - struct mutex mutex; struct kvm_run *run; +#ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; - struct pid __rcu *pid; +#endif + struct pid *pid; + rwlock_t pid_lock; int sigset_active; sigset_t sigset; - struct kvm_vcpu_stat stat; unsigned int halt_poll_ns; bool valid_wakeup; @@ -316,11 +379,182 @@ struct kvm_vcpu { bool dy_eligible; } spin_loop; #endif + bool wants_to_run; bool preempted; bool ready; + bool scheduled_out; struct kvm_vcpu_arch arch; + struct kvm_vcpu_stat stat; + char stats_id[KVM_STATS_NAME_SIZE]; + struct kvm_dirty_ring dirty_ring; + + /* + * The most recently used memslot by this vCPU and the slots generation + * for which it is valid. + * No wraparound protection is needed since generations won't overflow in + * thousands of years, even assuming 1M memslot operations per second. + */ + struct kvm_memory_slot *last_used_slot; + u64 last_used_slot_gen; }; +/* + * Start accounting time towards a guest. + * Must be called before entering guest context. + */ +static __always_inline void guest_timing_enter_irqoff(void) +{ + /* + * This is running in ioctl context so its safe to assume that it's the + * stime pending cputime to flush. + */ + instrumentation_begin(); + vtime_account_guest_enter(); + instrumentation_end(); +} + +/* + * Enter guest context and enter an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_enter_irqoff(void) +{ + /* + * KVM does not hold any references to rcu protected data when it + * switches CPU into a guest mode. In fact switching to a guest mode + * is very similar to exiting to userspace from rcu point of view. In + * addition CPU may stay in a guest mode for quite a long time (up to + * one time slice). Lets treat guest mode as quiescent state, just like + * we do with user-mode execution. + */ + if (!context_tracking_guest_enter()) { + instrumentation_begin(); + rcu_virt_note_context_switch(); + instrumentation_end(); + } +} + +/* + * Deprecated. Architectures should move to guest_timing_enter_irqoff() and + * guest_state_enter_irqoff(). + */ +static __always_inline void guest_enter_irqoff(void) +{ + guest_timing_enter_irqoff(); + guest_context_enter_irqoff(); +} + +/** + * guest_state_enter_irqoff - Fixup state when entering a guest + * + * Entry to a guest will enable interrupts, but the kernel state is interrupts + * disabled when this is invoked. Also tell RCU about it. + * + * 1) Trace interrupts on state + * 2) Invoke context tracking if enabled to adjust RCU state + * 3) Tell lockdep that interrupts are enabled + * + * Invoked from architecture specific code before entering a guest. + * Must be called with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_enter_irqoff() before this. + * + * Note: this is analogous to exit_to_user_mode(). + */ +static __always_inline void guest_state_enter_irqoff(void) +{ + instrumentation_begin(); + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(); + instrumentation_end(); + + guest_context_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +/* + * Exit guest context and exit an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_exit_irqoff(void) +{ + /* + * Guest mode is treated as a quiescent state, see + * guest_context_enter_irqoff() for more details. + */ + if (!context_tracking_guest_exit()) { + instrumentation_begin(); + rcu_virt_note_context_switch(); + instrumentation_end(); + } +} + +/* + * Stop accounting time towards a guest. + * Must be called after exiting guest context. + */ +static __always_inline void guest_timing_exit_irqoff(void) +{ + instrumentation_begin(); + /* Flush the guest cputime we spent on the guest */ + vtime_account_guest_exit(); + instrumentation_end(); +} + +/* + * Deprecated. Architectures should move to guest_state_exit_irqoff() and + * guest_timing_exit_irqoff(). + */ +static __always_inline void guest_exit_irqoff(void) +{ + guest_context_exit_irqoff(); + guest_timing_exit_irqoff(); +} + +static inline void guest_exit(void) +{ + unsigned long flags; + + local_irq_save(flags); + guest_exit_irqoff(); + local_irq_restore(flags); +} + +/** + * guest_state_exit_irqoff - Establish state when returning from guest mode + * + * Entry from a guest disables interrupts, but guest mode is traced as + * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. + * + * 1) Tell lockdep that interrupts are disabled + * 2) Invoke context tracking if enabled to reactivate RCU + * 3) Trace interrupts off state + * + * Invoked from architecture specific code after exiting a guest. + * Must be invoked with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_exit_irqoff() after this. + * + * Note: this is analogous to enter_from_user_mode(). + */ +static __always_inline void guest_state_exit_irqoff(void) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + guest_context_exit_irqoff(); + + instrumentation_begin(); + trace_hardirqs_off_finish(); + instrumentation_end(); +} + static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* @@ -338,7 +572,26 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) +/* + * Since at idle each memslot belongs to two memslot sets it has to contain + * two embedded nodes for each data structure that it forms a part of. + * + * Two memslot sets (one active and one inactive) are necessary so the VM + * continues to run on one memslot set while the other is being modified. + * + * These two memslot sets normally point to the same set of memslots. + * They can, however, be desynchronized when performing a memslot management + * operation by replacing the memslot to be modified by its copy. + * After the operation is complete, both memslot sets once again point to + * the same, common set of memslot data. + * + * The memslots themselves are independent of each other so they can be + * individually added or deleted. + */ struct kvm_memory_slot { + struct hlist_node id_node[2]; + struct interval_tree_node hva_node[2]; + struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; @@ -347,8 +600,30 @@ struct kvm_memory_slot { u32 flags; short id; u16 as_id; + +#ifdef CONFIG_KVM_PRIVATE_MEM + struct { + /* + * Writes protected by kvm->slots_lock. Acquiring a + * reference via kvm_gmem_get_file() is protected by + * either kvm->slots_lock or kvm->srcu. + */ + struct file *file; + pgoff_t pgoff; + } gmem; +#endif }; +static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot) +{ + return slot && (slot->flags & KVM_MEM_GUEST_MEMFD); +} + +static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) +{ + return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; +} + static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) { return ALIGN(memslot->npages, BITS_PER_LONG) / 8; @@ -378,6 +653,13 @@ struct kvm_hv_sint { u32 sint; }; +struct kvm_xen_evtchn { + u32 port; + u32 vcpu_id; + int vcpu_idx; + u32 priority; +}; + struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; @@ -398,6 +680,7 @@ struct kvm_kernel_irq_routing_entry { } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; + struct kvm_xen_evtchn xen_evtchn; }; struct hlist_node link; }; @@ -410,19 +693,25 @@ struct kvm_irq_routing_table { * Array indexed by gsi. Each entry contains list of irq chips * the gsi is connected to. */ - struct hlist_head map[]; + struct hlist_head map[] __counted_by(nr_rt_entries); }; #endif -#ifndef KVM_PRIVATE_MEM_SLOTS -#define KVM_PRIVATE_MEM_SLOTS 0 -#endif +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm); -#ifndef KVM_MEM_SLOTS_NUM -#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) +#ifndef KVM_INTERNAL_MEM_SLOTS +#define KVM_INTERNAL_MEM_SLOTS 0 #endif -#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +#define KVM_MEM_SLOTS_NUM SHRT_MAX +#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS) + +#if KVM_MAX_NR_ADDRESS_SPACES == 1 +static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm) +{ + return KVM_MAX_NR_ADDRESS_SPACES; +} + static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) { return 0; @@ -430,25 +719,78 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) #endif /* - * Note: - * memslots are not sorted by id anymore, please use id_to_memslot() - * to get the memslot by its id. + * Arch code must define kvm_arch_has_private_mem if support for private memory + * is enabled. */ +#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) +static inline bool kvm_arch_has_private_mem(struct kvm *kvm) +{ + return false; +} +#endif + +#ifndef kvm_arch_has_readonly_mem +static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +} +#endif + struct kvm_memslots { u64 generation; - /* The mapping table from slot id to the index in memslots[]. */ - short id_to_index[KVM_MEM_SLOTS_NUM]; - atomic_t lru_slot; - int used_slots; - struct kvm_memory_slot memslots[]; + atomic_long_t last_used_slot; + struct rb_root_cached hva_tree; + struct rb_root gfn_tree; + /* + * The mapping table from slot id to memslot. + * + * 7-bit bucket count matches the size of the old id to index array for + * 512 slots, while giving good performance with this slot count. + * Higher bucket counts bring only small performance improvements but + * always result in higher memory usage (even for lower memslot counts). + */ + DECLARE_HASHTABLE(id_hash, 7); + int node_idx; }; struct kvm { +#ifdef KVM_HAVE_MMU_RWLOCK + rwlock_t mmu_lock; +#else spinlock_t mmu_lock; +#endif /* KVM_HAVE_MMU_RWLOCK */ + struct mutex slots_lock; + + /* + * Protects the arch-specific fields of struct kvm_memory_slots in + * use by the VM. To be used under the slots_lock (above) or in a + * kvm->srcu critical section where acquiring the slots_lock would + * lead to deadlock with the synchronize_srcu in + * kvm_swap_active_memslots(). + */ + struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ - struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; - struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + unsigned long nr_memslot_pages; + /* The two memslot sets - active and inactive (per address space) */ + struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2]; + /* The current active memslot set for each address space */ + struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES]; + struct xarray vcpu_array; + /* + * Protected by slots_lock, but can be read outside if an + * incorrect answer is acceptable. + */ + atomic_t nr_memslots_dirty_logging; + + /* Used to wait for completion of MMU notifiers. */ + spinlock_t mn_invalidate_lock; + unsigned long mn_active_invalidate_count; + struct rcuwait mn_memslots_update_rcuwait; + + /* For management / invalidation of gfn_to_pfn_caches */ + spinlock_t gpc_lock; + struct list_head gpc_list; /* * created_vcpus is protected by kvm->lock, and is incremented @@ -457,20 +799,22 @@ struct kvm { * and is accessed atomically. */ atomic_t online_vcpus; + int max_vcpus; int created_vcpus; int last_boosted_vcpu; struct list_head vm_list; struct mutex lock; struct kvm_io_bus __rcu *buses[KVM_NR_BUSES]; -#ifdef CONFIG_HAVE_KVM_EVENTFD +#ifdef CONFIG_HAVE_KVM_IRQCHIP struct { spinlock_t lock; struct list_head items; + /* resampler_list update side is protected by resampler_lock. */ struct list_head resampler_list; struct mutex resampler_lock; } irqfds; - struct list_head ioeventfds; #endif + struct list_head ioeventfds; struct kvm_vm_stat stat; struct kvm_arch arch; refcount_t users_count; @@ -486,17 +830,17 @@ struct kvm { * Update side is protected by irq_lock. */ struct kvm_irq_routing_table __rcu *irq_routing; -#endif -#ifdef CONFIG_HAVE_KVM_IRQFD + struct hlist_head irq_ack_notifier_list; #endif -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER struct mmu_notifier mmu_notifier; - unsigned long mmu_notifier_seq; - long mmu_notifier_count; + unsigned long mmu_invalidate_seq; + long mmu_invalidate_in_progress; + gfn_t mmu_invalidate_range_start; + gfn_t mmu_invalidate_range_end; #endif - long tlbs_dirty; struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; @@ -504,7 +848,21 @@ struct kvm { struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; + bool override_halt_poll_ns; unsigned int max_halt_poll_ns; + u32 dirty_ring_size; + bool dirty_ring_with_bitmap; + bool vm_bugged; + bool vm_dead; + +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER + struct notifier_block pm_notifier; +#endif +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + /* Protected by slots_locks (for writes) and RCU (for reads) */ + struct xarray mem_attr_array; +#endif + char stats_id[KVM_STATS_NAME_SIZE]; }; #define kvm_err(fmt, ...) \ @@ -533,6 +891,75 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline void kvm_vm_dead(struct kvm *kvm) +{ + kvm->vm_dead = true; + kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD); +} + +static inline void kvm_vm_bugged(struct kvm *kvm) +{ + kvm->vm_bugged = true; + kvm_vm_dead(kvm); +} + + +#define KVM_BUG(cond, kvm, fmt...) \ +({ \ + bool __ret = !!(cond); \ + \ + if (WARN_ONCE(__ret && !(kvm)->vm_bugged, fmt)) \ + kvm_vm_bugged(kvm); \ + unlikely(__ret); \ +}) + +#define KVM_BUG_ON(cond, kvm) \ +({ \ + bool __ret = !!(cond); \ + \ + if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ + kvm_vm_bugged(kvm); \ + unlikely(__ret); \ +}) + +/* + * Note, "data corruption" refers to corruption of host kernel data structures, + * not guest data. Guest data corruption, suspected or confirmed, that is tied + * and contained to a single VM should *never* BUG() and potentially panic the + * host, i.e. use this variant of KVM_BUG() if and only if a KVM data structure + * is corrupted and that corruption can have a cascading effect to other parts + * of the hosts and/or to other VMs. + */ +#define KVM_BUG_ON_DATA_CORRUPTION(cond, kvm) \ +({ \ + bool __ret = !!(cond); \ + \ + if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) \ + BUG_ON(__ret); \ + else if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ + kvm_vm_bugged(kvm); \ + unlikely(__ret); \ +}) + +static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(vcpu->srcu_depth++, + "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); +#endif + vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) +{ + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); + +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(--vcpu->srcu_depth, + "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); +#endif +} + static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); @@ -548,23 +975,31 @@ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { int num_vcpus = atomic_read(&kvm->online_vcpus); + + /* + * Explicitly verify the target vCPU is online, as the anti-speculation + * logic only limits the CPU's ability to speculate, e.g. given a "bad" + * index, clamping the index to 0 would return vCPU0, not NULL. + */ + if (i >= num_vcpus) + return NULL; + i = array_index_nospec(i, num_vcpus); /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); - return kvm->vcpus[i]; + return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - for (idx = 0; \ - idx < atomic_read(&kvm->online_vcpus) && \ - (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ - idx++) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + if (atomic_read(&kvm->online_vcpus)) \ + xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ + (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (id < 0) return NULL; @@ -578,18 +1013,11 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) -{ - return vcpu->vcpu_idx; -} +void kvm_destroy_vcpus(struct kvm *kvm); -#define kvm_for_each_memslot(memslot, slots) \ - for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + slots->used_slots; memslot++) \ - if (WARN_ON_ONCE(!memslot->npages)) { \ - } else - -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); +int kvm_trylock_all_vcpus(struct kvm *kvm); +int kvm_lock_all_vcpus(struct kvm *kvm); +void kvm_unlock_all_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); @@ -606,7 +1034,7 @@ static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm) } #endif -#ifdef CONFIG_HAVE_KVM_IRQFD +#ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd_init(void); void kvm_irqfd_exit(void); #else @@ -619,17 +1047,18 @@ static inline void kvm_irqfd_exit(void) { } #endif -int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, - struct module *module); +int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); +bool kvm_get_kvm_safe(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); +bool file_is_kvm(struct file *file); void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { - as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM); + as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES); return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); @@ -647,21 +1076,130 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) return __kvm_memslots(vcpu->kvm, as_id); } +static inline bool kvm_memslots_empty(struct kvm_memslots *slots) +{ + return RB_EMPTY_ROOT(&slots->gfn_tree); +} + +bool kvm_are_all_memslots_empty(struct kvm *kvm); + +#define kvm_for_each_memslot(memslot, bkt, slots) \ + hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ + if (WARN_ON_ONCE(!memslot->npages)) { \ + } else + static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { - int index = slots->id_to_index[id]; struct kvm_memory_slot *slot; + int idx = slots->node_idx; - if (index < 0) - return NULL; + hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { + if (slot->id == id) + return slot; + } + + return NULL; +} + +/* Iterator used for walking memslots that overlap a gfn range. */ +struct kvm_memslot_iter { + struct kvm_memslots *slots; + struct rb_node *node; + struct kvm_memory_slot *slot; +}; + +static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) +{ + iter->node = rb_next(iter->node); + if (!iter->node) + return; + + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); +} + +static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, + struct kvm_memslots *slots, + gfn_t start) +{ + int idx = slots->node_idx; + struct rb_node *tmp; + struct kvm_memory_slot *slot; + + iter->slots = slots; + + /* + * Find the so called "upper bound" of a key - the first node that has + * its key strictly greater than the searched one (the start gfn in our case). + */ + iter->node = NULL; + for (tmp = slots->gfn_tree.rb_node; tmp; ) { + slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); + if (start < slot->base_gfn) { + iter->node = tmp; + tmp = tmp->rb_left; + } else { + tmp = tmp->rb_right; + } + } + + /* + * Find the slot with the lowest gfn that can possibly intersect with + * the range, so we'll ideally have slot start <= range start + */ + if (iter->node) { + /* + * A NULL previous node means that the very first slot + * already has a higher start gfn. + * In this case slot start > range start. + */ + tmp = rb_prev(iter->node); + if (tmp) + iter->node = tmp; + } else { + /* a NULL node below means no slots */ + iter->node = rb_last(&slots->gfn_tree); + } - slot = &slots->memslots[index]; + if (iter->node) { + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); - WARN_ON(slot->id != id); - return slot; + /* + * It is possible in the slot start < range start case that the + * found slot ends before or at range start (slot end <= range start) + * and so it does not overlap the requested range. + * + * In such non-overlapping case the next slot (if it exists) will + * already have slot start > range start, otherwise the logic above + * would have found it instead of the current slot. + */ + if (iter->slot->base_gfn + iter->slot->npages <= start) + kvm_memslot_iter_next(iter); + } } +static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) +{ + if (!iter->node) + return false; + + /* + * If this slot starts beyond or at the end of the range so does + * every next one + */ + return iter->slot->base_gfn < end; +} + +/* Iterate over each memslot at least partially intersecting [start, end) range */ +#define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ + for (kvm_memslot_iter_start(iter, slots, start); \ + kvm_memslot_iter_is_valid(iter, end); \ + kvm_memslot_iter_next(iter)) + +struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); +struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); +struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); + /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot @@ -671,7 +1209,7 @@ struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) * -- just change its flags * * Since flags can be changed by some of these operations, the following - * differentiation is the best we can do for __kvm_set_memory_region(): + * differentiation is the best we can do for kvm_set_memory_region(): */ enum kvm_mr_change { KVM_MR_CREATE, @@ -680,18 +1218,15 @@ enum kvm_mr_change { KVM_MR_FLAGS_ONLY, }; -int kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); -int __kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); +int kvm_set_internal_memslot(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); @@ -701,35 +1236,70 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm); void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); -int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, - struct page **pages, int nr_pages); +int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn, + struct page **pages, int nr_pages); + +struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write); +static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) +{ + return __gfn_to_page(kvm, gfn, true); +} -struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable); unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn); unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable); + +static inline void kvm_release_page_unused(struct page *page) +{ + if (!page) + return; + + put_page(page); +} + void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); -void kvm_set_page_accessed(struct page *page); - -kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, - bool *writable); -kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, - bool atomic, bool *async, bool write_fault, - bool *writable); - -void kvm_release_pfn_clean(kvm_pfn_t pfn); -void kvm_release_pfn_dirty(kvm_pfn_t pfn); -void kvm_set_pfn_dirty(kvm_pfn_t pfn); -void kvm_set_pfn_accessed(kvm_pfn_t pfn); -void kvm_get_pfn(kvm_pfn_t pfn); - -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); + +static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page, + bool unused, bool dirty) +{ + lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused); + + if (!page) + return; + + /* + * If the page that KVM got from the *primary MMU* is writable, and KVM + * installed or reused a SPTE, mark the page/folio dirty. Note, this + * may mark a folio dirty even if KVM created a read-only SPTE, e.g. if + * the GFN is write-protected. Folios can't be safely marked dirty + * outside of mmu_lock as doing so could race with writeback on the + * folio. As a result, KVM can't mark folios dirty in the fast page + * fault handler, and so KVM must (somewhat) speculatively mark the + * folio dirty if KVM could locklessly make the SPTE writable. + */ + if (unused) + kvm_release_page_unused(page); + else if (dirty) + kvm_release_page_dirty(page); + else + kvm_release_page_clean(page); +} + +kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn, + unsigned int foll, bool *writable, + struct page **refcounted_page); + +static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, + bool write, bool *writable, + struct page **refcounted_page) +{ + return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, + write ? FOLL_WRITE : 0, writable, refcounted_page); +} + int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); @@ -792,26 +1362,29 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, offset_in_page(__gpa), v); \ }) -int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); -struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); -void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); -struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); -struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); -int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic); -struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); -void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic); +int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map, + bool writable); +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map); + +static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, + struct kvm_host_map *map) +{ + return __kvm_vcpu_map(vcpu, gpa, map, true); +} + +static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa, + struct kvm_host_map *map) +{ + return __kvm_vcpu_map(vcpu, gpa, map, false); +} + unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, @@ -826,35 +1399,146 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); +/** + * kvm_gpc_init - initialize gfn_to_pfn_cache. + * + * @gpc: struct gfn_to_pfn_cache object. + * @kvm: pointer to kvm instance. + * + * This sets up a gfn_to_pfn_cache by initializing locks and assigning the + * immutable attributes. Note, the cache must be zero-allocated (or zeroed by + * the caller before init). + */ +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm); + +/** + * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest + * physical address. + * + * @gpc: struct gfn_to_pfn_cache object. + * @gpa: guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * This primes a gfn_to_pfn_cache and links it into the @gpc->kvm's list for + * invalidations to be processed. Callers are required to use kvm_gpc_check() + * to ensure that the cache is valid before accessing the target page. + */ +int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len); + +/** + * kvm_gpc_activate_hva - prepare a cached kernel mapping and HPA for a given HVA. + * + * @gpc: struct gfn_to_pfn_cache object. + * @hva: userspace virtual address to map. + * @len: sanity check; the range being access must fit a single page. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * The semantics of this function are the same as those of kvm_gpc_activate(). It + * merely bypasses a layer of address translation. + */ +int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long hva, unsigned long len); + +/** + * kvm_gpc_check - check validity of a gfn_to_pfn_cache. + * + * @gpc: struct gfn_to_pfn_cache object. + * @len: sanity check; the range being access must fit a single page. + * + * @return: %true if the cache is still valid and the address matches. + * %false if the cache is not valid. + * + * Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock + * while calling this function, and then continue to hold the lock until the + * access is complete. + * + * Callers in IN_GUEST_MODE may do so without locking, although they should + * still hold a read lock on kvm->scru for the memslot checks. + */ +bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len); + +/** + * kvm_gpc_refresh - update a previously initialized cache. + * + * @gpc: struct gfn_to_pfn_cache object. + * @len: sanity check; the range being access must fit a single page. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * This will attempt to refresh a gfn_to_pfn_cache. Note that a successful + * return from this function does not mean the page can be immediately + * accessed because it may have raced with an invalidation. Callers must + * still lock and check the cache status, as this function does not return + * with the lock still held to permit access. + */ +int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len); + +/** + * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. + * + * @gpc: struct gfn_to_pfn_cache object. + * + * This removes a cache from the VM's list to be processed on MMU notifier + * invocation. + */ +void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc); + +static inline bool kvm_gpc_is_gpa_active(struct gfn_to_pfn_cache *gpc) +{ + return gpc->active && !kvm_is_error_gpa(gpc->gpa); +} + +static inline bool kvm_gpc_is_hva_active(struct gfn_to_pfn_cache *gpc) +{ + return gpc->active && kvm_is_error_gpa(gpc->gpa); +} + void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); -void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_vcpu_halt(struct kvm_vcpu *vcpu); +bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); -void kvm_vcpu_kick(struct kvm_vcpu *vcpu); + +#ifndef CONFIG_S390 +void __kvm_vcpu_kick(struct kvm_vcpu *vcpu, bool wait); + +static inline void kvm_vcpu_kick(struct kvm_vcpu *vcpu) +{ + __kvm_vcpu_kick(vcpu, false); +} +#endif + int kvm_vcpu_yield_to(struct kvm_vcpu *target); -void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode); void kvm_flush_remote_tlbs(struct kvm *kvm); -void kvm_reload_remote_mmus(struct kvm *kvm); +void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); +void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, + const struct kvm_memory_slot *memslot); #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min); +int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min); int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc); void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); #endif -bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except, - unsigned long *vcpu_bitmap, cpumask_var_t tmp); -bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); -bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except); -bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, - unsigned long *vcpu_bitmap); +void kvm_mmu_invalidate_begin(struct kvm *kvm); +void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end); +void kvm_mmu_invalidate_end(struct kvm *kvm); +bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -870,10 +1554,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, unsigned long mask); void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot); -#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT -void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, - struct kvm_memory_slot *memslot); -#else /* !CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ +#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty, struct kvm_memory_slot **memslot); @@ -883,8 +1564,9 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg); +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); @@ -906,11 +1588,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); -int kvm_arch_init(void *opaque); -void kvm_arch_exit(void); - -void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); @@ -918,21 +1595,43 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); +#endif + #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); +#else +static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif -int kvm_arch_hardware_enable(void); -void kvm_arch_hardware_disable(void); -int kvm_arch_hardware_setup(void *opaque); -void kvm_arch_hardware_unsetup(void); -int kvm_arch_check_processor_compat(void *opaque); +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +/* + * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under + * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of + * kvm_usage_count, i.e. at the beginning of the generic hardware enabling + * sequence, and at the end of the generic hardware disabling sequence. + */ +void kvm_arch_enable_virtualization(void); +void kvm_arch_disable_virtualization(void); +/* + * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to + * do the actual twiddling of hardware bits. The hooks are called on all + * online CPUs when KVM enables/disabled virtualization, and on a single CPU + * when that CPU is onlined/offlined (including for Resume/Suspend). + */ +int kvm_arch_enable_virtualization_cpu(void); +void kvm_arch_disable_virtualization_cpu(void); +#endif +bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); -int kvm_arch_post_init_vm(struct kvm *kvm); +bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu); void kvm_arch_pre_destroy_vm(struct kvm *kvm); +void kvm_arch_create_vm_debugfs(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* @@ -941,20 +1640,39 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm); */ static inline struct kvm *kvm_arch_alloc_vm(void) { - return kzalloc(sizeof(struct kvm), GFP_KERNEL); + return kzalloc(sizeof(struct kvm), GFP_KERNEL_ACCOUNT); } +#endif +static inline void __kvm_arch_free_vm(struct kvm *kvm) +{ + kvfree(kvm); +} + +#ifndef __KVM_HAVE_ARCH_VM_FREE static inline void kvm_arch_free_vm(struct kvm *kvm) { - kfree(kvm); + __kvm_arch_free_vm(kvm); } #endif -#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB -static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) +#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS +static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { return -ENOTSUPP; } +#else +int kvm_arch_flush_remote_tlbs(struct kvm *kvm); +#endif + +#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE +static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, + gfn_t gfn, u64 nr_pages) +{ + return -EOPNOTSUPP; +} +#else +int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); #endif #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA @@ -988,7 +1706,7 @@ static inline void kvm_arch_end_assignment(struct kvm *kvm) { } -static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } @@ -1003,6 +1721,20 @@ static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) #endif } +/* + * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns + * true if the vCPU was blocking and was awakened, false otherwise. + */ +static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) +{ + return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); +} + +static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) +{ + return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); +} + #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and @@ -1017,16 +1749,21 @@ static inline bool kvm_arch_intc_initialized(struct kvm *kvm) } #endif +#ifdef CONFIG_GUEST_PERF_EVENTS +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu); + +void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)); +void kvm_unregister_perf_callbacks(void); +#else +static inline void kvm_register_perf_callbacks(void *ign) {} +static inline void kvm_unregister_perf_callbacks(void) {} +#endif /* CONFIG_GUEST_PERF_EVENTS */ + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); -void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); -bool kvm_is_reserved_pfn(kvm_pfn_t pfn); -bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn); - struct kvm_irq_ack_notifier { struct hlist_node link; unsigned gsi; @@ -1056,55 +1793,91 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* - * search_memslots() and __gfn_to_memslot() are here because they are - * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c. - * gfn_to_memslot() itself isn't here as an inline because that would - * bloat other code too much. - * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! + * Returns a pointer to the memslot if it contains gfn. + * Otherwise returns NULL. */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn) +try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->lru_slot); - struct kvm_memory_slot *memslots = slots->memslots; + if (!slot) + return NULL; - if (unlikely(!slots->used_slots)) + if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) + return slot; + else return NULL; +} - if (gfn >= memslots[slot].base_gfn && - gfn < memslots[slot].base_gfn + memslots[slot].npages) - return &memslots[slot]; +/* + * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. + * + * With "approx" set returns the memslot also when the address falls + * in a hole. In that case one of the memslots bordering the hole is + * returned. + */ +static inline struct kvm_memory_slot * +search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) +{ + struct kvm_memory_slot *slot; + struct rb_node *node; + int idx = slots->node_idx; + + slot = NULL; + for (node = slots->gfn_tree.rb_node; node; ) { + slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); + if (gfn >= slot->base_gfn) { + if (gfn < slot->base_gfn + slot->npages) + return slot; + node = node->rb_right; + } else + node = node->rb_left; + } - while (start < end) { - slot = start + (end - start) / 2; + return approx ? slot : NULL; +} - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } +static inline struct kvm_memory_slot * +____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) +{ + struct kvm_memory_slot *slot; - if (start < slots->used_slots && gfn >= memslots[start].base_gfn && - gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->lru_slot, start); - return &memslots[start]; + slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); + slot = try_get_memslot(slot, gfn); + if (slot) + return slot; + + slot = search_memslots(slots, gfn, approx); + if (slot) { + atomic_long_set(&slots->last_used_slot, (unsigned long)slot); + return slot; } return NULL; } +/* + * __gfn_to_memslot() and its descendants are here to allow arch code to inline + * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline + * because that would bloat other code too much. + */ static inline struct kvm_memory_slot * __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) { - return search_memslots(slots, gfn); + return ____gfn_to_memslot(slots, gfn, false); } static inline unsigned long -__gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +__gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { - return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE; + /* + * The index was checked originally in search_memslots. To avoid + * that a malicious guest builds a Spectre gadget out of e.g. page + * table walks, do not let the processor speculate loads outside + * the guest's registered memslots. + */ + unsigned long offset = gfn - slot->base_gfn; + offset = array_index_nospec(offset, slot->npages); + return slot->userspace_addr + offset * PAGE_SIZE; } static inline int memslot_id(struct kvm *kvm, gfn_t gfn) @@ -1135,17 +1908,21 @@ static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) return (hpa_t)pfn << PAGE_SHIFT; } -static inline struct page *kvm_vcpu_gpa_to_page(struct kvm_vcpu *vcpu, - gpa_t gpa) +static inline bool kvm_is_gpa_in_memslot(struct kvm *kvm, gpa_t gpa) { - return kvm_vcpu_gfn_to_page(vcpu, gpa_to_gfn(gpa)); + unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); + + return !kvm_is_error_hva(hva); } -static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa) +static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc) { - unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); + lockdep_assert_held(&gpc->lock); - return kvm_is_error_hva(hva); + if (!gpc->memslot) + return; + + mark_page_dirty_in_slot(gpc->kvm, gpc->memslot, gpa_to_gfn(gpc->gpa)); } enum kvm_stat_kind { @@ -1155,47 +1932,259 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - struct kvm_stats_debugfs_item *dbgfs_item; + const struct _kvm_stats_desc *desc; + enum kvm_stat_kind kind; }; -struct kvm_stats_debugfs_item { - const char *name; - int offset; - enum kvm_stat_kind kind; - int mode; +struct _kvm_stats_desc { + struct kvm_stats_desc desc; + char name[KVM_STATS_NAME_SIZE]; }; -#define KVM_DBGFS_GET_MODE(dbgfs_item) \ - ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) +#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = sz, \ + .bucket_size = bsz + +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, stat) \ + }, \ + .name = #stat, \ + } +/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ +#define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ + SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) + +#define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, \ + unit, base, exponent, 1, 0) +#define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, \ + unit, base, exponent, 1, 0) +#define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, \ + unit, base, exponent, 1, 0) +#define STATS_DESC_LINEAR_HIST(SCOPE, name, unit, base, exponent, sz, bsz) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LINEAR_HIST, \ + unit, base, exponent, sz, bsz) +#define STATS_DESC_LOG_HIST(SCOPE, name, unit, base, exponent, sz) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LOG_HIST, \ + unit, base, exponent, sz, 0) + +/* Cumulative counter, read/write */ +#define STATS_DESC_COUNTER(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Instantaneous counter, read only */ +#define STATS_DESC_ICOUNTER(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Peak counter, read/write */ +#define STATS_DESC_PCOUNTER(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) + +/* Instantaneous boolean value, read only */ +#define STATS_DESC_IBOOLEAN(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) +/* Peak (sticky) boolean value, read/write */ +#define STATS_DESC_PBOOLEAN(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) + +/* Cumulative time in nanosecond */ +#define STATS_DESC_TIME_NSEC(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9) +/* Linear histogram for time in nanosecond */ +#define STATS_DESC_LINHIST_TIME_NSEC(SCOPE, name, sz, bsz) \ + STATS_DESC_LINEAR_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9, sz, bsz) +/* Logarithmic histogram for time in nanosecond */ +#define STATS_DESC_LOGHIST_TIME_NSEC(SCOPE, name, sz) \ + STATS_DESC_LOG_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9, sz) + +#define KVM_GENERIC_VM_STATS() \ + STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush), \ + STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush_requests) + +#define KVM_GENERIC_VCPU_STATS() \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns), \ + STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_success_hist, \ + HALT_POLL_HIST_COUNT), \ + STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ + HALT_POLL_HIST_COUNT), \ + STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ + HALT_POLL_HIST_COUNT), \ + STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) + +ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, + const struct _kvm_stats_desc *desc, + void *stats, size_t size_stats, + char __user *user_buffer, size_t size, loff_t *offset); + +/** + * kvm_stats_linear_hist_update() - Update bucket value for linear histogram + * statistics data. + * + * @data: start address of the stats data + * @size: the number of bucket of the stats data + * @value: the new value used to update the linear histogram's bucket + * @bucket_size: the size (width) of a bucket + */ +static inline void kvm_stats_linear_hist_update(u64 *data, size_t size, + u64 value, size_t bucket_size) +{ + size_t index = div64_u64(value, bucket_size); + + index = min(index, size - 1); + ++data[index]; +} + +/** + * kvm_stats_log_hist_update() - Update bucket value for logarithmic histogram + * statistics data. + * + * @data: start address of the stats data + * @size: the number of bucket of the stats data + * @value: the new value used to update the logarithmic histogram's bucket + */ +static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) +{ + size_t index = fls64(value); + + index = min(index, size - 1); + ++data[index]; +} -#define VM_STAT(n, x, ...) \ - { n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ } -#define VCPU_STAT(n, x, ...) \ - { n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ } +#define KVM_STATS_LINEAR_HIST_UPDATE(array, value, bsize) \ + kvm_stats_linear_hist_update(array, ARRAY_SIZE(array), value, bsize) +#define KVM_STATS_LOG_HIST_UPDATE(array, value) \ + kvm_stats_log_hist_update(array, ARRAY_SIZE(array), value) -extern struct kvm_stats_debugfs_item debugfs_entries[]; -extern struct dentry *kvm_debugfs_dir; -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) -static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) +extern const struct kvm_stats_header kvm_vm_stats_header; +extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; +extern const struct kvm_stats_header kvm_vcpu_stats_header; +extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; + +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER +static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { - if (unlikely(kvm->mmu_notifier_count)) + if (unlikely(kvm->mmu_invalidate_in_progress)) return 1; /* - * Ensure the read of mmu_notifier_count happens before the read - * of mmu_notifier_seq. This interacts with the smp_wmb() in - * mmu_notifier_invalidate_range_end to make sure that the caller - * either sees the old (non-zero) value of mmu_notifier_count or - * the new (incremented) value of mmu_notifier_seq. - * PowerPC Book3s HV KVM calls this under a per-page lock - * rather than under kvm->mmu_lock, for scalability, so - * can't rely on kvm->mmu_lock to keep things ordered. + * Ensure the read of mmu_invalidate_in_progress happens before + * the read of mmu_invalidate_seq. This interacts with the + * smp_wmb() in mmu_notifier_invalidate_range_end to make sure + * that the caller either sees the old (non-zero) value of + * mmu_invalidate_in_progress or the new (incremented) value of + * mmu_invalidate_seq. + * + * PowerPC Book3s HV KVM calls this under a per-page lock rather + * than under kvm->mmu_lock, for scalability, so can't rely on + * kvm->mmu_lock to keep things ordered. */ smp_rmb(); - if (kvm->mmu_notifier_seq != mmu_seq) + if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } + +static inline int mmu_invalidate_retry_gfn(struct kvm *kvm, + unsigned long mmu_seq, + gfn_t gfn) +{ + lockdep_assert_held(&kvm->mmu_lock); + /* + * If mmu_invalidate_in_progress is non-zero, then the range maintained + * by kvm_mmu_notifier_invalidate_range_start contains all addresses + * that might be being invalidated. Note that it may include some false + * positives, due to shortcuts when handing concurrent invalidations. + */ + if (unlikely(kvm->mmu_invalidate_in_progress)) { + /* + * Dropping mmu_lock after bumping mmu_invalidate_in_progress + * but before updating the range is a KVM bug. + */ + if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA || + kvm->mmu_invalidate_range_end == INVALID_GPA)) + return 1; + + if (gfn >= kvm->mmu_invalidate_range_start && + gfn < kvm->mmu_invalidate_range_end) + return 1; + } + + if (kvm->mmu_invalidate_seq != mmu_seq) + return 1; + return 0; +} + +/* + * This lockless version of the range-based retry check *must* be paired with a + * call to the locked version after acquiring mmu_lock, i.e. this is safe to + * use only as a pre-check to avoid contending mmu_lock. This version *will* + * get false negatives and false positives. + */ +static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, + unsigned long mmu_seq, + gfn_t gfn) +{ + /* + * Use READ_ONCE() to ensure the in-progress flag and sequence counter + * are always read from memory, e.g. so that checking for retry in a + * loop won't result in an infinite retry loop. Don't force loads for + * start+end, as the key to avoiding infinite retry loops is observing + * the 1=>0 transition of in-progress, i.e. getting false negatives + * due to stale start+end values is acceptable. + */ + if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) && + gfn >= kvm->mmu_invalidate_range_start && + gfn < kvm->mmu_invalidate_range_end) + return true; + + return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq; +} #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING @@ -1207,6 +2196,7 @@ int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); +int kvm_init_irq_routing(struct kvm *kvm); int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); @@ -1216,18 +2206,24 @@ void kvm_free_irq_routing(struct kvm *kvm); static inline void kvm_free_irq_routing(struct kvm *kvm) {} +static inline int kvm_init_irq_routing(struct kvm *kvm) +{ + return 0; +} + #endif int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); -#ifdef CONFIG_HAVE_KVM_EVENTFD - void kvm_eventfd_init(struct kvm *kvm); int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); -#ifdef CONFIG_HAVE_KVM_IRQFD +#ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); +bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) @@ -1236,35 +2232,18 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) } static inline void kvm_irqfd_release(struct kvm *kvm) {} -#endif - -#else - -static inline void kvm_eventfd_init(struct kvm *kvm) {} - -static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) -{ - return -EINVAL; -} - -static inline void kvm_irqfd_release(struct kvm *kvm) {} - -#ifdef CONFIG_HAVE_KVM_IRQCHIP -static inline void kvm_irq_routing_update(struct kvm *kvm) -{ -} -#endif -static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) +static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin) { - return -ENOSYS; + return false; } - -#endif /* CONFIG_HAVE_KVM_EVENTFD */ +#endif /* CONFIG_HAVE_KVM_IRQCHIP */ void kvm_arch_irq_routing_update(struct kvm *kvm); -static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Ensure the rest of the request is published to kvm_check_request's @@ -1274,6 +2253,27 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } +static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +{ + /* + * Request that don't require vCPU action should never be logged in + * vcpu->requests. The vCPU won't clear the request, so it will stay + * logged indefinitely and prevent the vCPU from entering the guest. + */ + BUILD_BUG_ON(!__builtin_constant_p(req) || + (req & KVM_REQUEST_NO_ACTION)); + + __kvm_make_request(req, vcpu); +} + +#ifndef CONFIG_S390 +static inline void kvm_make_request_and_kick(int req, struct kvm_vcpu *vcpu) +{ + kvm_make_request(req, vcpu); + __kvm_vcpu_kick(vcpu, req & KVM_REQUEST_WAIT); +} +#endif + static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->requests); @@ -1305,7 +2305,10 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) } } +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +extern bool enable_virt_at_load; extern bool kvm_rebooting; +#endif extern unsigned int halt_poll_ns; extern unsigned int halt_poll_ns_grow; @@ -1363,8 +2366,6 @@ struct kvm_device_ops { int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma); }; -void kvm_device_get(struct kvm_device *dev); -void kvm_device_put(struct kvm_device *dev); struct kvm_device *kvm_device_from_filp(struct file *filp); int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type); @@ -1404,7 +2405,7 @@ static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot) struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); -#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS +#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) bool kvm_arch_has_irq_bypass(void); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); @@ -1414,6 +2415,8 @@ void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *); void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); +bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *, + struct kvm_kernel_irq_routing_entry *); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ #ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS @@ -1452,8 +2455,7 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ -void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end); +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); @@ -1464,12 +2466,6 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ -typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data); - -int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, - uintptr_t data, const char *name, - struct task_struct **thread_ptr); - #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) { @@ -1478,4 +2474,132 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) } #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ +/* + * If more than one page is being (un)accounted, @virt must be the address of + * the first page of a block of pages what were allocated together (i.e + * accounted together). + * + * kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state() + * is thread-safe. + */ +static inline void kvm_account_pgtable_pages(void *virt, int nr) +{ + mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, nr); +} + +/* + * This defines how many reserved entries we want to keep before we + * kick the vcpu to the userspace to avoid dirty ring full. This + * value can be tuned to higher if e.g. PML is enabled on the host. + */ +#define KVM_DIRTY_RING_RSVD_ENTRIES 64 + +/* Max number of entries allowed for each kvm dirty ring */ +#define KVM_DIRTY_RING_MAX_ENTRIES 65536 + +static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + gpa_t gpa, gpa_t size, + bool is_write, bool is_exec, + bool is_private) +{ + vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT; + vcpu->run->memory_fault.gpa = gpa; + vcpu->run->memory_fault.size = size; + + /* RWX flags are not (yet) defined or communicated to userspace. */ + vcpu->run->memory_fault.flags = 0; + if (is_private) + vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE; +} + +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn) +{ + return xa_to_value(xa_load(&kvm->mem_attr_array, gfn)); +} + +bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long mask, unsigned long attrs); +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range); +bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range); + +static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) +{ + return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) && + kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE; +} +#else +static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) +{ + return false; +} +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ + +#ifdef CONFIG_KVM_PRIVATE_MEM +int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t *pfn, struct page **page, + int *max_order); +#else +static inline int kvm_gmem_get_pfn(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn, + kvm_pfn_t *pfn, struct page **page, + int *max_order) +{ + KVM_BUG_ON(1, kvm); + return -EIO; +} +#endif /* CONFIG_KVM_PRIVATE_MEM */ + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE +int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM +/** + * kvm_gmem_populate() - Populate/prepare a GPA range with guest data + * + * @kvm: KVM instance + * @gfn: starting GFN to be populated + * @src: userspace-provided buffer containing data to copy into GFN range + * (passed to @post_populate, and incremented on each iteration + * if not NULL) + * @npages: number of pages to copy from userspace-buffer + * @post_populate: callback to issue for each gmem page that backs the GPA + * range + * @opaque: opaque data to pass to @post_populate callback + * + * This is primarily intended for cases where a gmem-backed GPA range needs + * to be initialized with userspace-provided data prior to being mapped into + * the guest as a private page. This should be called with the slots->lock + * held so that caller-enforced invariants regarding the expected memory + * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES. + * + * Returns the number of pages that were populated. + */ +typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + void __user *src, int order, void *opaque); + +long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, + kvm_gmem_populate_cb post_populate, void *opaque); +#endif + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range); +#endif + +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +int kvm_enable_virtualization(void); +void kvm_disable_virtualization(void); +#else +static inline int kvm_enable_virtualization(void) { return 0; } +static inline void kvm_disable_virtualization(void) { } +#endif + #endif |