#include <linux/spinlock.h>
#include <linux/signal.h>
#include <linux/sched.h>
+#include <linux/bug.h>
#include <linux/mm.h>
#include <linux/mmu_notifier.h>
#include <linux/preempt.h>
#define KVM_MMIO_SIZE 8
#endif
+/*
+ * If we support unaligned MMIO, at most one fragment will be split into two:
+ */
+#ifdef KVM_UNALIGNED_MMIO
+# define KVM_EXTRA_MMIO_FRAGMENTS 1
+#else
+# define KVM_EXTRA_MMIO_FRAGMENTS 0
+#endif
+
+#define KVM_USER_MMIO_SIZE 8
+
+#define KVM_MAX_MMIO_FRAGMENTS \
+ (KVM_MMIO_SIZE / KVM_USER_MMIO_SIZE + KVM_EXTRA_MMIO_FRAGMENTS)
+
/*
* vcpu->requests bit members
*/
struct kvm_io_device *dev;
};
+#define NR_IOBUS_DEVS 1000
+
struct kvm_io_bus {
int dev_count;
-#define NR_IOBUS_DEVS 300
- struct kvm_io_range range[NR_IOBUS_DEVS];
+ struct kvm_io_range range[];
};
enum kvm_bus {
enum {
OUTSIDE_GUEST_MODE,
IN_GUEST_MODE,
- EXITING_GUEST_MODE
+ EXITING_GUEST_MODE,
+ READING_SHADOW_PAGE_TABLES,
+};
+
+/*
+ * Sometimes a large or cross-page mmio needs to be broken up into separate
+ * exits for userspace servicing.
+ */
+struct kvm_mmio_fragment {
+ gpa_t gpa;
+ void *data;
+ unsigned len;
};
struct kvm_vcpu {
int mmio_needed;
int mmio_read_completed;
int mmio_is_write;
- int mmio_size;
- int mmio_index;
- unsigned char mmio_data[KVM_MMIO_SIZE];
- gpa_t mmio_phys_addr;
+ int mmio_cur_fragment;
+ int mmio_nr_fragments;
+ struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS];
#endif
#ifdef CONFIG_KVM_ASYNC_PF
} async_pf;
#endif
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+ /*
+ * Cpu relax intercept or pause loop exit optimization
+ * in_spin_loop: set when a vcpu does a pause loop exit
+ * or cpu relax intercepted.
+ * dy_eligible: indicates whether vcpu is eligible for directed yield.
+ */
+ struct {
+ bool in_spin_loop;
+ bool dy_eligible;
+ } spin_loop;
+#endif
struct kvm_vcpu_arch arch;
};
*/
#define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)
-struct kvm_lpage_info {
- unsigned long rmap_pde;
- int write_count;
-};
-
struct kvm_memory_slot {
gfn_t base_gfn;
unsigned long npages;
unsigned long flags;
unsigned long *rmap;
unsigned long *dirty_bitmap;
- unsigned long *dirty_bitmap_head;
- unsigned long nr_dirty_pages;
- struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
+ struct kvm_arch_memory_slot arch;
unsigned long userspace_addr;
int user_alloc;
int id;
struct hlist_head irq_ack_notifier_list;
#endif
-#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
struct mmu_notifier mmu_notifier;
unsigned long mmu_notifier_seq;
long mmu_notifier_count;
long tlbs_dirty;
};
-/* The guest did something we don't support. */
-#define pr_unimpl(vcpu, fmt, ...) \
- pr_err_ratelimited("kvm: %i: cpu%i " fmt, \
- current->tgid, (vcpu)->vcpu_id , ## __VA_ARGS__)
+#define kvm_err(fmt, ...) \
+ pr_err("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
+#define kvm_info(fmt, ...) \
+ pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
+#define kvm_debug(fmt, ...) \
+ pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
+#define kvm_pr_unimpl(fmt, ...) \
+ pr_err_ratelimited("kvm [%i]: " fmt, \
+ task_tgid_nr(current), ## __VA_ARGS__)
-#define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt)
-#define vcpu_printf(vcpu, fmt...) kvm_printf(vcpu->kvm, fmt)
+/* The guest did something we don't support. */
+#define vcpu_unimpl(vcpu, fmt, ...) \
+ kvm_pr_unimpl("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
{
return slot;
}
-#define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
-#define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB)
-static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; }
-
extern struct page *bad_page;
-extern struct page *fault_page;
-
-extern pfn_t bad_pfn;
-extern pfn_t fault_pfn;
int is_error_page(struct page *page);
int is_error_pfn(pfn_t pfn);
int is_hwpoison_pfn(pfn_t pfn);
-int is_fault_pfn(pfn_t pfn);
int is_noslot_pfn(pfn_t pfn);
int is_invalid_pfn(pfn_t pfn);
int kvm_is_error_hva(unsigned long addr);
int __kvm_set_memory_region(struct kvm *kvm,
struct kvm_userspace_memory_region *mem,
int user_alloc);
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+ struct kvm_memory_slot *dont);
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages);
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_memory_slot old,
struct kvm_userspace_memory_region *mem,
struct kvm_memory_slot old,
int user_alloc);
+bool kvm_largepages_enabled(void);
void kvm_disable_largepages(void);
void kvm_arch_flush_shadow(struct kvm *kvm);
int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
int nr_pages);
+struct page *get_bad_page(void);
struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
void kvm_release_page_clean(struct page *page);
void kvm_set_page_dirty(struct page *page);
void kvm_set_page_accessed(struct page *page);
-pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr);
+pfn_t hva_to_pfn_atomic(unsigned long addr);
pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn);
pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async,
bool write_fault, bool *writable);
pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable);
-pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
- struct kvm_memory_slot *slot, gfn_t gfn);
+pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
void kvm_release_pfn_dirty(pfn_t);
void kvm_release_pfn_clean(pfn_t pfn);
void kvm_set_pfn_dirty(pfn_t pfn);
void kvm_set_pfn_accessed(pfn_t pfn);
void kvm_get_pfn(pfn_t pfn);
+pfn_t get_fault_pfn(void);
int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
int len);
gfn_t gfn);
void kvm_vcpu_block(struct kvm_vcpu *vcpu);
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
+bool kvm_vcpu_yield_to(struct kvm_vcpu *target);
void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
void kvm_resched(struct kvm_vcpu *vcpu);
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
struct
kvm_userspace_memory_region *mem,
int user_alloc);
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level);
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
void kvm_arch_hardware_unsetup(void);
void kvm_arch_check_processor_compat(void *rtn);
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
void kvm_free_physmem(struct kvm *kvm);
+void *kvm_kvzalloc(unsigned long size);
+void kvm_kvfree(const void *addr);
+
#ifndef __KVM_HAVE_ARCH_VM_ALLOC
static inline struct kvm *kvm_arch_alloc_vm(void)
{
}
#endif
+static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
+{
+#ifdef __KVM_HAVE_ARCH_WQP
+ return vcpu->arch.wqp;
+#else
+ return &vcpu->wq;
+#endif
+}
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
void kvm_arch_destroy_vm(struct kvm *kvm);
void kvm_free_all_assigned_devices(struct kvm *kvm);
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
-int kvm_is_mmio_pfn(pfn_t pfn);
+bool kvm_is_mmio_pfn(pfn_t pfn);
struct kvm_irq_ack_notifier {
struct hlist_node link;
unsigned int entries_nr;
int host_irq;
bool host_irq_disabled;
+ bool pci_2_3;
struct msix_entry *host_msix_entries;
int guest_irq;
struct msix_entry *guest_msix_entries;
struct pci_dev *dev;
struct kvm *kvm;
spinlock_t intx_lock;
+ spinlock_t intx_mask_lock;
char irq_name[32];
struct pci_saved_state *pci_saved_state;
};
#ifdef CONFIG_IOMMU_API
int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
+void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
int kvm_iommu_map_guest(struct kvm *kvm);
int kvm_iommu_unmap_guest(struct kvm *kvm);
int kvm_assign_device(struct kvm *kvm,
return 0;
}
+static inline void kvm_iommu_unmap_pages(struct kvm *kvm,
+ struct kvm_memory_slot *slot)
+{
+}
+
static inline int kvm_iommu_map_guest(struct kvm *kvm)
{
return -ENODEV;
current->flags &= ~PF_VCPU;
}
+/*
+ * 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.
+ */
+static inline struct kvm_memory_slot *
+search_memslots(struct kvm_memslots *slots, gfn_t gfn)
+{
+ struct kvm_memory_slot *memslot;
+
+ kvm_for_each_memslot(memslot, slots)
+ if (gfn >= memslot->base_gfn &&
+ gfn < memslot->base_gfn + memslot->npages)
+ return memslot;
+
+ return NULL;
+}
+
+static inline struct kvm_memory_slot *
+__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
+{
+ return search_memslots(slots, gfn);
+}
+
static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
{
return gfn_to_memslot(kvm, gfn)->id;
}
+static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
+{
+ /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
+ return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
+ (base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
+}
+
+static inline gfn_t
+hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
+{
+ gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT;
+
+ return slot->base_gfn + gfn_offset;
+}
+
static inline unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
gfn_t gfn)
{
extern struct kvm_stats_debugfs_item debugfs_entries[];
extern struct dentry *kvm_debugfs_dir;
-#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_seq)
{
if (unlikely(vcpu->kvm->mmu_notifier_count))
}
#endif
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
+#ifdef KVM_CAP_IRQ_ROUTING
#define KVM_MAX_IRQ_ROUTES 1024
unsigned flags);
void kvm_free_irq_routing(struct kvm *kvm);
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
+
#else
static inline void kvm_free_irq_routing(struct kvm *kvm) {}
#ifdef CONFIG_HAVE_KVM_EVENTFD
void kvm_eventfd_init(struct kvm *kvm);
-int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags);
+int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
void kvm_irqfd_release(struct kvm *kvm);
void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
static inline void kvm_eventfd_init(struct kvm *kvm) {}
-static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
+static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
{
return -EINVAL;
}
{
return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id;
}
+
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu);
+
+#else
+
+static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }
+
#endif
#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT
}
}
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+
+static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
+{
+ vcpu->spin_loop.in_spin_loop = val;
+}
+static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
+{
+ vcpu->spin_loop.dy_eligible = val;
+}
+
+#else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
+
+static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
+{
+}
+
+static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
+{
+}
+
+static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
+{
+ return true;
+}
+
+#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
#endif