1 files changed, 458 insertions, 172 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5186e728c53e..96ebc0679415 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5,7 +5,7 @@
  * machines without emulation or binary translation.
  *
  * Copyright (C) 2006 Qumranet, Inc.
- * Copyright 2010 Red Hat, Inc. and/or its affilates.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
  *
  * Authors:
  *   Avi Kivity   <avi@qumranet.com>
@@ -30,7 +30,7 @@
 #include <linux/debugfs.h>
 #include <linux/highmem.h>
 #include <linux/file.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
 #include <linux/cpumask.h>
@@ -52,9 +52,9 @@
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm-generic/bitops/le.h>
 
 #include "coalesced_mmio.h"
+#include "async_pf.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
@@ -68,7 +68,7 @@ MODULE_LICENSE("GPL");
  *              kvm->lock --> kvm->slots_lock --> kvm->irq_lock
  */
 
-DEFINE_SPINLOCK(kvm_lock);
+DEFINE_RAW_SPINLOCK(kvm_lock);
 LIST_HEAD(vm_list);
 
 static cpumask_var_t cpus_hardware_enabled;
@@ -89,7 +89,8 @@ static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
 
-static bool kvm_rebooting;
+bool kvm_rebooting;
+EXPORT_SYMBOL_GPL(kvm_rebooting);
 
 static bool largepages_enabled = true;
 
@@ -102,8 +103,26 @@ static pfn_t fault_pfn;
 inline int kvm_is_mmio_pfn(pfn_t pfn)
 {
         if (pfn_valid(pfn)) {
-                struct page *page = compound_head(pfn_to_page(pfn));
-                return PageReserved(page);
+                int reserved;
+                struct page *tail = pfn_to_page(pfn);
+                struct page *head = compound_trans_head(tail);
+                reserved = PageReserved(head);
+                if (head != tail) {
+                        /*
+                         * "head" is not a dangling pointer
+                         * (compound_trans_head takes care of that)
+                         * but the hugepage may have been splitted
+                         * from under us (and we may not hold a
+                         * reference count on the head page so it can
+                         * be reused before we run PageReferenced), so
+                         * we've to check PageTail before returning
+                         * what we just read.
+                         */
+                        smp_rmb();
+                        if (PageTail(tail))
+                                return reserved;
+                }
+                return PageReserved(tail);
         }
 
         return true;
@@ -117,6 +136,14 @@ void vcpu_load(struct kvm_vcpu *vcpu)
         int cpu;
 
         mutex_lock(&vcpu->mutex);
+        if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) {
+                /* The thread running this VCPU changed. */
+                struct pid *oldpid = vcpu->pid;
+                struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
+                rcu_assign_pointer(vcpu->pid, newpid);
+                synchronize_rcu();
+                put_pid(oldpid);
+        }
         cpu = get_cpu();
         preempt_notifier_register(&vcpu->preempt_notifier);
         kvm_arch_vcpu_load(vcpu, cpu);
@@ -145,13 +172,16 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 
         zalloc_cpumask_var(&cpus, GFP_ATOMIC);
 
-        raw_spin_lock(&kvm->requests_lock);
-        me = smp_processor_id();
+        me = get_cpu();
         kvm_for_each_vcpu(i, vcpu, kvm) {
-                if (kvm_make_check_request(req, vcpu))
-                        continue;
+                kvm_make_request(req, vcpu);
                 cpu = vcpu->cpu;
-                if (cpus != NULL && cpu != -1 && cpu != me)
+
+                /* Set ->requests bit before we read ->mode */
+                smp_mb();
+
+                if (cpus != NULL && cpu != -1 && cpu != me &&
+                      kvm_vcpu_exiting_guest_mode(vcpu) != OUTSIDE_GUEST_MODE)
                         cpumask_set_cpu(cpu, cpus);
         }
         if (unlikely(cpus == NULL))
@@ -160,15 +190,19 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
                 smp_call_function_many(cpus, ack_flush, NULL, 1);
         else
                 called = false;
-        raw_spin_unlock(&kvm->requests_lock);
+        put_cpu();
         free_cpumask_var(cpus);
         return called;
 }
 
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
+        int dirty_count = kvm->tlbs_dirty;
+
+        smp_mb();
         if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
                 ++kvm->stat.remote_tlb_flush;
+        cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
 
 void kvm_reload_remote_mmus(struct kvm *kvm)
@@ -185,7 +219,9 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
         vcpu->cpu = -1;
         vcpu->kvm = kvm;
         vcpu->vcpu_id = id;
+        vcpu->pid = NULL;
         init_waitqueue_head(&vcpu->wq);
+        kvm_async_pf_vcpu_init(vcpu);
 
         page = alloc_page(GFP_KERNEL | __GFP_ZERO);
         if (!page) {
@@ -208,6 +244,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_init);
 
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
+        put_pid(vcpu->pid);
         kvm_arch_vcpu_uninit(vcpu);
         free_page((unsigned long)vcpu->run);
 }
@@ -247,7 +284,7 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
         idx = srcu_read_lock(&kvm->srcu);
         spin_lock(&kvm->mmu_lock);
         kvm->mmu_notifier_seq++;
-        need_tlb_flush = kvm_unmap_hva(kvm, address);
+        need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty;
         spin_unlock(&kvm->mmu_lock);
         srcu_read_unlock(&kvm->srcu, idx);
 
@@ -291,6 +328,7 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
         kvm->mmu_notifier_count++;
         for (; start < end; start += PAGE_SIZE)
                 need_tlb_flush |= kvm_unmap_hva(kvm, start);
+        need_tlb_flush |= kvm->tlbs_dirty;
         spin_unlock(&kvm->mmu_lock);
         srcu_read_unlock(&kvm->srcu, idx);
 
@@ -344,6 +382,22 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
         return young;
 }
 
+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);
+
+        return young;
+}
+
 static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
                                      struct mm_struct *mm)
 {
@@ -360,6 +414,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
         .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,
+        .test_young             = kvm_mmu_notifier_test_young,
         .change_pte             = kvm_mmu_notifier_change_pte,
         .release                = kvm_mmu_notifier_release,
 };
@@ -381,11 +436,15 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 
 static struct kvm *kvm_create_vm(void)
 {
-        int r = 0, i;
-        struct kvm *kvm = kvm_arch_create_vm();
+        int r, i;
+        struct kvm *kvm = kvm_arch_alloc_vm();
 
-        if (IS_ERR(kvm))
-                goto out;
+        if (!kvm)
+                return ERR_PTR(-ENOMEM);
+
+        r = kvm_arch_init_vm(kvm);
+        if (r)
+                goto out_err_nodisable;
 
         r = hardware_enable_all();
         if (r)
@@ -399,49 +458,61 @@ static struct kvm *kvm_create_vm(void)
         r = -ENOMEM;
         kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
         if (!kvm->memslots)
-                goto out_err;
+                goto out_err_nosrcu;
         if (init_srcu_struct(&kvm->srcu))
-                goto out_err;
+                goto out_err_nosrcu;
         for (i = 0; i < KVM_NR_BUSES; i++) {
                 kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
                                         GFP_KERNEL);
-                if (!kvm->buses[i]) {
-                        cleanup_srcu_struct(&kvm->srcu);
+                if (!kvm->buses[i])
                         goto out_err;
-                }
-        }
-
-        r = kvm_init_mmu_notifier(kvm);
-        if (r) {
-                cleanup_srcu_struct(&kvm->srcu);
-                goto out_err;
         }
 
+        spin_lock_init(&kvm->mmu_lock);
         kvm->mm = current->mm;
         atomic_inc(&kvm->mm->mm_count);
-        spin_lock_init(&kvm->mmu_lock);
-        raw_spin_lock_init(&kvm->requests_lock);
         kvm_eventfd_init(kvm);
         mutex_init(&kvm->lock);
         mutex_init(&kvm->irq_lock);
         mutex_init(&kvm->slots_lock);
         atomic_set(&kvm->users_count, 1);
-        spin_lock(&kvm_lock);
+
+        r = kvm_init_mmu_notifier(kvm);
+        if (r)
+                goto out_err;
+
+        raw_spin_lock(&kvm_lock);
         list_add(&kvm->vm_list, &vm_list);
-        spin_unlock(&kvm_lock);
-out:
+        raw_spin_unlock(&kvm_lock);
+
         return kvm;
 
 out_err:
+        cleanup_srcu_struct(&kvm->srcu);
+out_err_nosrcu:
         hardware_disable_all();
 out_err_nodisable:
         for (i = 0; i < KVM_NR_BUSES; i++)
                 kfree(kvm->buses[i]);
         kfree(kvm->memslots);
-        kfree(kvm);
+        kvm_arch_free_vm(kvm);
         return ERR_PTR(r);
 }
 
+static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
+{
+        if (!memslot->dirty_bitmap)
+                return;
+
+        if (2 * kvm_dirty_bitmap_bytes(memslot) > PAGE_SIZE)
+                vfree(memslot->dirty_bitmap_head);
+        else
+                kfree(memslot->dirty_bitmap_head);
+
+        memslot->dirty_bitmap = NULL;
+        memslot->dirty_bitmap_head = NULL;
+}
+
 /*
  * Free any memory in @free but not in @dont.
  */
@@ -454,7 +525,7 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
                 vfree(free->rmap);
 
         if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
-                vfree(free->dirty_bitmap);
+                kvm_destroy_dirty_bitmap(free);
 
 
         for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
@@ -465,7 +536,6 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
         }
 
         free->npages = 0;
-        free->dirty_bitmap = NULL;
         free->rmap = NULL;
 }
 
@@ -486,9 +556,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
         struct mm_struct *mm = kvm->mm;
 
         kvm_arch_sync_events(kvm);
-        spin_lock(&kvm_lock);
+        raw_spin_lock(&kvm_lock);
         list_del(&kvm->vm_list);
-        spin_unlock(&kvm_lock);
+        raw_spin_unlock(&kvm_lock);
         kvm_free_irq_routing(kvm);
         for (i = 0; i < KVM_NR_BUSES; i++)
                 kvm_io_bus_destroy(kvm->buses[i]);
@@ -499,6 +569,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
         kvm_arch_flush_shadow(kvm);
 #endif
         kvm_arch_destroy_vm(kvm);
+        kvm_free_physmem(kvm);
+        cleanup_srcu_struct(&kvm->srcu);
+        kvm_arch_free_vm(kvm);
         hardware_disable_all();
         mmdrop(mm);
 }
@@ -527,6 +600,29 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
         return 0;
 }
 
+#ifndef CONFIG_S390
+/*
+ * Allocation size is twice as large as the actual dirty bitmap size.
+ * This makes it possible to do double buffering: see x86's
+ * kvm_vm_ioctl_get_dirty_log().
+ */
+static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
+{
+        unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
+
+        if (dirty_bytes > PAGE_SIZE)
+                memslot->dirty_bitmap = vzalloc(dirty_bytes);
+        else
+                memslot->dirty_bitmap = kzalloc(dirty_bytes, GFP_KERNEL);
+
+        if (!memslot->dirty_bitmap)
+                return -ENOMEM;
+
+        memslot->dirty_bitmap_head = memslot->dirty_bitmap;
+        return 0;
+}
+#endif /* !CONFIG_S390 */
+
 /*
  * Allocate some memory and give it an address in the guest physical address
  * space.
@@ -539,7 +635,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
                             struct kvm_userspace_memory_region *mem,
                             int user_alloc)
 {
-        int r, flush_shadow = 0;
+        int r;
         gfn_t base_gfn;
         unsigned long npages;
         unsigned long i;
@@ -553,7 +649,12 @@ int __kvm_set_memory_region(struct kvm *kvm,
                 goto out;
         if (mem->guest_phys_addr & (PAGE_SIZE - 1))
                 goto out;
-        if (user_alloc && (mem->userspace_addr & (PAGE_SIZE - 1)))
+        /* We can read the guest memory with __xxx_user() later on. */
+        if (user_alloc &&
+            ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
+             !access_ok(VERIFY_WRITE,
+                        (void __user *)(unsigned long)mem->userspace_addr,
+                        mem->memory_size)))
                 goto out;
         if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
                 goto out;
@@ -604,13 +705,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
         /* Allocate if a slot is being created */
 #ifndef CONFIG_S390
         if (npages && !new.rmap) {
-                new.rmap = vmalloc(npages * sizeof(*new.rmap));
+                new.rmap = vzalloc(npages * sizeof(*new.rmap));
 
                 if (!new.rmap)
                         goto out_free;
 
-                memset(new.rmap, 0, npages * sizeof(*new.rmap));
-
                 new.user_alloc = user_alloc;
                 new.userspace_addr = mem->userspace_addr;
         }
@@ -633,14 +732,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
                              >> KVM_HPAGE_GFN_SHIFT(level));
                 lpages -= base_gfn >> KVM_HPAGE_GFN_SHIFT(level);
 
-                new.lpage_info[i] = vmalloc(lpages * sizeof(*new.lpage_info[i]));
+                new.lpage_info[i] = vzalloc(lpages * sizeof(*new.lpage_info[i]));
 
                 if (!new.lpage_info[i])
                         goto out_free;
 
-                memset(new.lpage_info[i], 0,
-                       lpages * sizeof(*new.lpage_info[i]));
-
                 if (base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
                         new.lpage_info[i][0].write_count = 1;
                 if ((base_gfn+npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
@@ -661,15 +757,9 @@ skip_lpage:
 
         /* Allocate page dirty bitmap if needed */
         if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
-                unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(&new);
-
-                new.dirty_bitmap = vmalloc(dirty_bytes);
-                if (!new.dirty_bitmap)
+                if (kvm_create_dirty_bitmap(&new) < 0)
                         goto out_free;
-                memset(new.dirty_bitmap, 0, dirty_bytes);
                 /* destroy any largepage mappings for dirty tracking */
-                if (old.npages)
-                        flush_shadow = 1;
         }
 #else  /* not defined CONFIG_S390 */
         new.user_alloc = user_alloc;
@@ -685,6 +775,7 @@ skip_lpage:
                 memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
                 if (mem->slot >= slots->nmemslots)
                         slots->nmemslots = mem->slot + 1;
+                slots->generation++;
                 slots->memslots[mem->slot].flags |= KVM_MEMSLOT_INVALID;
 
                 old_memslots = kvm->memslots;
@@ -705,14 +796,12 @@ skip_lpage:
         if (r)
                 goto out_free;
 
-#ifdef CONFIG_DMAR
         /* map the pages in iommu page table */
         if (npages) {
                 r = kvm_iommu_map_pages(kvm, &new);
                 if (r)
                         goto out_free;
         }
-#endif
 
         r = -ENOMEM;
         slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
@@ -721,6 +810,7 @@ skip_lpage:
         memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
         if (mem->slot >= slots->nmemslots)
                 slots->nmemslots = mem->slot + 1;
+        slots->generation++;
 
         /* actual memory is freed via old in kvm_free_physmem_slot below */
         if (!npages) {
@@ -740,9 +830,6 @@ skip_lpage:
         kvm_free_physmem_slot(&old, &new);
         kfree(old_memslots);
 
-        if (flush_shadow)
-                kvm_arch_flush_shadow(kvm);
-
         return 0;
 
 out_free:
@@ -851,10 +938,10 @@ int kvm_is_error_hva(unsigned long addr)
 }
 EXPORT_SYMBOL_GPL(kvm_is_error_hva);
 
-struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
+static struct kvm_memory_slot *__gfn_to_memslot(struct kvm_memslots *slots,
+                                                gfn_t gfn)
 {
         int i;
-        struct kvm_memslots *slots = kvm_memslots(kvm);
 
         for (i = 0; i < slots->nmemslots; ++i) {
                 struct kvm_memory_slot *memslot = &slots->memslots[i];
@@ -865,6 +952,11 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
         }
         return NULL;
 }
+
+struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
+{
+        return __gfn_to_memslot(kvm_memslots(kvm), gfn);
+}
 EXPORT_SYMBOL_GPL(gfn_to_memslot);
 
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
@@ -910,97 +1002,203 @@ out:
         return size;
 }
 
-int memslot_id(struct kvm *kvm, gfn_t gfn)
+static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
+                                     gfn_t *nr_pages)
 {
-        int i;
-        struct kvm_memslots *slots = kvm_memslots(kvm);
-        struct kvm_memory_slot *memslot = NULL;
+        if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
+                return bad_hva();
 
-        for (i = 0; i < slots->nmemslots; ++i) {
-                memslot = &slots->memslots[i];
+        if (nr_pages)
+                *nr_pages = slot->npages - (gfn - slot->base_gfn);
 
-                if (gfn >= memslot->base_gfn
-                    && gfn < memslot->base_gfn + memslot->npages)
-                        break;
-        }
+        return gfn_to_hva_memslot(slot, gfn);
+}
 
-        return memslot - slots->memslots;
+unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
+{
+        return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL);
 }
+EXPORT_SYMBOL_GPL(gfn_to_hva);
 
-static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
+static pfn_t get_fault_pfn(void)
 {
-        return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
+        get_page(fault_page);
+        return fault_pfn;
 }
 
-unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
+int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
+        unsigned long start, int write, struct page **page)
 {
-        struct kvm_memory_slot *slot;
+        int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET;
 
-        slot = gfn_to_memslot(kvm, gfn);
-        if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
-                return bad_hva();
-        return gfn_to_hva_memslot(slot, gfn);
+        if (write)
+                flags |= FOLL_WRITE;
+
+        return __get_user_pages(tsk, mm, start, 1, flags, page, NULL, NULL);
 }
-EXPORT_SYMBOL_GPL(gfn_to_hva);
 
-static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr)
+static inline int check_user_page_hwpoison(unsigned long addr)
+{
+        int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE;
+
+        rc = __get_user_pages(current, current->mm, addr, 1,
+                              flags, NULL, NULL, NULL);
+        return rc == -EHWPOISON;
+}
+
+static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic,
+                        bool *async, bool write_fault, bool *writable)
 {
         struct page *page[1];
-        int npages;
+        int npages = 0;
         pfn_t pfn;
 
-        might_sleep();
+        /* we can do it either atomically or asynchronously, not both */
+        BUG_ON(atomic && async);
+
+        BUG_ON(!write_fault && !writable);
 
-        npages = get_user_pages_fast(addr, 1, 1, page);
+        if (writable)
+                *writable = true;
+
+        if (atomic || async)
+                npages = __get_user_pages_fast(addr, 1, 1, page);
+
+        if (unlikely(npages != 1) && !atomic) {
+                might_sleep();
+
+                if (writable)
+                        *writable = write_fault;
+
+                if (async) {
+                        down_read(&current->mm->mmap_sem);
+                        npages = get_user_page_nowait(current, current->mm,
+                                                     addr, write_fault, page);
+                        up_read(&current->mm->mmap_sem);
+                } else
+                        npages = get_user_pages_fast(addr, 1, write_fault,
+                                                     page);
+
+                /* map read fault as writable if possible */
+                if (unlikely(!write_fault) && npages == 1) {
+                        struct page *wpage[1];
+
+                        npages = __get_user_pages_fast(addr, 1, 1, wpage);
+                        if (npages == 1) {
+                                *writable = true;
+                                put_page(page[0]);
+                                page[0] = wpage[0];
+                        }
+                        npages = 1;
+                }
+        }
 
         if (unlikely(npages != 1)) {
                 struct vm_area_struct *vma;
 
+                if (atomic)
+                        return get_fault_pfn();
+
                 down_read(&current->mm->mmap_sem);
-                if (is_hwpoison_address(addr)) {
+                if (npages == -EHWPOISON ||
+                        (!async && check_user_page_hwpoison(addr))) {
                         up_read(&current->mm->mmap_sem);
                         get_page(hwpoison_page);
                         return page_to_pfn(hwpoison_page);
                 }
 
-                vma = find_vma(current->mm, addr);
-
-                if (vma == NULL || addr < vma->vm_start ||
-                    !(vma->vm_flags & VM_PFNMAP)) {
-                        up_read(&current->mm->mmap_sem);
-                        get_page(fault_page);
-                        return page_to_pfn(fault_page);
+                vma = find_vma_intersection(current->mm, addr, addr+1);
+
+                if (vma == NULL)
+                        pfn = get_fault_pfn();
+                else if ((vma->vm_flags & VM_PFNMAP)) {
+                        pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) +
+                                vma->vm_pgoff;
+                        BUG_ON(!kvm_is_mmio_pfn(pfn));
+                } else {
+                        if (async && (vma->vm_flags & VM_WRITE))
+                                *async = true;
+                        pfn = get_fault_pfn();
                 }
-
-                pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
                 up_read(&current->mm->mmap_sem);
-                BUG_ON(!kvm_is_mmio_pfn(pfn));
         } else
                 pfn = page_to_pfn(page[0]);
 
         return pfn;
 }
 
-pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
+pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr)
+{
+        return hva_to_pfn(kvm, addr, true, NULL, true, NULL);
+}
+EXPORT_SYMBOL_GPL(hva_to_pfn_atomic);
+
+static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async,
+                          bool write_fault, bool *writable)
 {
         unsigned long addr;
 
+        if (async)
+                *async = false;
+
         addr = gfn_to_hva(kvm, gfn);
         if (kvm_is_error_hva(addr)) {
                 get_page(bad_page);
                 return page_to_pfn(bad_page);
         }
 
-        return hva_to_pfn(kvm, addr);
+        return hva_to_pfn(kvm, addr, atomic, async, write_fault, writable);
+}
+
+pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
+{
+        return __gfn_to_pfn(kvm, gfn, true, NULL, true, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic);
+
+pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async,
+                       bool write_fault, bool *writable)
+{
+        return __gfn_to_pfn(kvm, gfn, false, async, write_fault, writable);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_async);
+
+pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
+{
+        return __gfn_to_pfn(kvm, gfn, false, NULL, true, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn);
 
+pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
+                      bool *writable)
+{
+        return __gfn_to_pfn(kvm, gfn, false, NULL, write_fault, writable);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
+
 pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
                          struct kvm_memory_slot *slot, gfn_t gfn)
 {
         unsigned long addr = gfn_to_hva_memslot(slot, gfn);
-        return hva_to_pfn(kvm, addr);
+        return hva_to_pfn(kvm, addr, false, NULL, true, NULL);
+}
+
+int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
+                                                                  int nr_pages)
+{
+        unsigned long addr;
+        gfn_t entry;
+
+        addr = gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, &entry);
+        if (kvm_is_error_hva(addr))
+                return -1;
+
+        if (entry < nr_pages)
+                return 0;
+
+        return __get_user_pages_fast(addr, nr_pages, 1, pages);
 }
+EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
 
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {
@@ -1091,7 +1289,7 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
         addr = gfn_to_hva(kvm, gfn);
         if (kvm_is_error_hva(addr))
                 return -EFAULT;
-        r = copy_from_user(data, (void __user *)addr + offset, len);
+        r = __copy_from_user(data, (void __user *)addr + offset, len);
         if (r)
                 return -EFAULT;
         return 0;
@@ -1175,9 +1373,51 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
         return 0;
 }
 
+int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+                              gpa_t gpa)
+{
+        struct kvm_memslots *slots = kvm_memslots(kvm);
+        int offset = offset_in_page(gpa);
+        gfn_t gfn = gpa >> PAGE_SHIFT;
+
+        ghc->gpa = gpa;
+        ghc->generation = slots->generation;
+        ghc->memslot = __gfn_to_memslot(slots, gfn);
+        ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL);
+        if (!kvm_is_error_hva(ghc->hva))
+                ghc->hva += offset;
+        else
+                return -EFAULT;
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
+
+int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+                           void *data, unsigned long len)
+{
+        struct kvm_memslots *slots = kvm_memslots(kvm);
+        int r;
+
+        if (slots->generation != ghc->generation)
+                kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+
+        if (kvm_is_error_hva(ghc->hva))
+                return -EFAULT;
+
+        r = copy_to_user((void __user *)ghc->hva, data, len);
+        if (r)
+                return -EFAULT;
+        mark_page_dirty_in_slot(kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT);
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_guest_cached);
+
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
 {
-        return kvm_write_guest_page(kvm, gfn, empty_zero_page, offset, len);
+        return kvm_write_guest_page(kvm, gfn, (const void *) empty_zero_page,
+                                    offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
 
@@ -1200,18 +1440,24 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
+void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
+                             gfn_t gfn)
 {
-        struct kvm_memory_slot *memslot;
-
-        memslot = gfn_to_memslot(kvm, gfn);
         if (memslot && memslot->dirty_bitmap) {
                 unsigned long rel_gfn = gfn - memslot->base_gfn;
 
-                generic___set_le_bit(rel_gfn, memslot->dirty_bitmap);
+                __set_bit_le(rel_gfn, memslot->dirty_bitmap);
         }
 }
 
+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(kvm, memslot, gfn);
+}
+
 /*
  * The vCPU has executed a HLT instruction with in-kernel mode enabled.
  */
@@ -1245,18 +1491,55 @@ void kvm_resched(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_resched);
 
-void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu)
+void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
-        ktime_t expires;
-        DEFINE_WAIT(wait);
-
-        prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
-
-        /* Sleep for 100 us, and hope lock-holder got scheduled */
-        expires = ktime_add_ns(ktime_get(), 100000UL);
-        schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
+        struct kvm *kvm = me->kvm;
+        struct kvm_vcpu *vcpu;
+        int last_boosted_vcpu = me->kvm->last_boosted_vcpu;
+        int yielded = 0;
+        int pass;
+        int i;
 
-        finish_wait(&vcpu->wq, &wait);
+        /*
+         * We boost the priority of a VCPU that is runnable but not
+         * currently running, because it got preempted by something
+         * else and called schedule in __vcpu_run.  Hopefully that
+         * VCPU is holding the lock that we need and will release it.
+         * We approximate round-robin by starting at the last boosted VCPU.
+         */
+        for (pass = 0; pass < 2 && !yielded; pass++) {
+                kvm_for_each_vcpu(i, vcpu, kvm) {
+                        struct task_struct *task = NULL;
+                        struct pid *pid;
+                        if (!pass && i < last_boosted_vcpu) {
+                                i = last_boosted_vcpu;
+                                continue;
+                        } else if (pass && i > last_boosted_vcpu)
+                                break;
+                        if (vcpu == me)
+                                continue;
+                        if (waitqueue_active(&vcpu->wq))
+                                continue;
+                        rcu_read_lock();
+                        pid = rcu_dereference(vcpu->pid);
+                        if (pid)
+                                task = get_pid_task(vcpu->pid, PIDTYPE_PID);
+                        rcu_read_unlock();
+                        if (!task)
+                                continue;
+                        if (task->flags & PF_VCPU) {
+                                put_task_struct(task);
+                                continue;
+                        }
+                        if (yield_to(task, 1)) {
+                                put_task_struct(task);
+                                kvm->last_boosted_vcpu = i;
+                                yielded = 1;
+                                break;
+                        }
+                        put_task_struct(task);
+                }
+        }
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
 
@@ -1305,6 +1588,7 @@ static struct file_operations kvm_vcpu_fops = {
         .unlocked_ioctl = kvm_vcpu_ioctl,
         .compat_ioctl   = kvm_vcpu_ioctl,
         .mmap           = kvm_vcpu_mmap,
+        .llseek         = noop_llseek,
 };
 
 /*
@@ -1412,6 +1696,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
                 if (arg)
                         goto out;
                 r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
+                trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
                 break;
         case KVM_GET_REGS: {
                 struct kvm_regs *kvm_regs;
@@ -1774,11 +2059,12 @@ static struct file_operations kvm_vm_fops = {
         .compat_ioctl   = kvm_vm_compat_ioctl,
 #endif
         .mmap           = kvm_vm_mmap,
+        .llseek         = noop_llseek,
 };
 
 static int kvm_dev_ioctl_create_vm(void)
 {
-        int fd, r;
+        int r;
         struct kvm *kvm;
 
         kvm = kvm_create_vm();
@@ -1791,11 +2077,11 @@ static int kvm_dev_ioctl_create_vm(void)
                 return r;
         }
 #endif
-        fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
-        if (fd < 0)
+        r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+        if (r < 0)
                 kvm_put_kvm(kvm);
 
-        return fd;
+        return r;
 }
 
 static long kvm_dev_ioctl_check_extension_generic(long arg)
@@ -1867,6 +2153,7 @@ out:
 static struct file_operations kvm_chardev_ops = {
         .unlocked_ioctl = kvm_dev_ioctl,
         .compat_ioctl   = kvm_dev_ioctl,
+        .llseek         = noop_llseek,
 };
 
 static struct miscdevice kvm_dev = {
@@ -1875,7 +2162,7 @@ static struct miscdevice kvm_dev = {
         &kvm_chardev_ops,
 };
 
-static void hardware_enable(void *junk)
+static void hardware_enable_nolock(void *junk)
 {
         int cpu = raw_smp_processor_id();
         int r;
@@ -1895,7 +2182,14 @@ static void hardware_enable(void *junk)
         }
 }
 
-static void hardware_disable(void *junk)
+static void hardware_enable(void *junk)
+{
+        raw_spin_lock(&kvm_lock);
+        hardware_enable_nolock(junk);
+        raw_spin_unlock(&kvm_lock);
+}
+
+static void hardware_disable_nolock(void *junk)
 {
         int cpu = raw_smp_processor_id();
 
@@ -1905,32 +2199,39 @@ static void hardware_disable(void *junk)
         kvm_arch_hardware_disable(NULL);
 }
 
+static void hardware_disable(void *junk)
+{
+        raw_spin_lock(&kvm_lock);
+        hardware_disable_nolock(junk);
+        raw_spin_unlock(&kvm_lock);
+}
+
 static void hardware_disable_all_nolock(void)
 {
         BUG_ON(!kvm_usage_count);
 
         kvm_usage_count--;
         if (!kvm_usage_count)
-                on_each_cpu(hardware_disable, NULL, 1);
+                on_each_cpu(hardware_disable_nolock, NULL, 1);
 }
 
 static void hardware_disable_all(void)
 {
-        spin_lock(&kvm_lock);
+        raw_spin_lock(&kvm_lock);
         hardware_disable_all_nolock();
-        spin_unlock(&kvm_lock);
+        raw_spin_unlock(&kvm_lock);
 }
 
 static int hardware_enable_all(void)
 {
         int r = 0;
 
-        spin_lock(&kvm_lock);
+        raw_spin_lock(&kvm_lock);
 
         kvm_usage_count++;
         if (kvm_usage_count == 1) {
                 atomic_set(&hardware_enable_failed, 0);
-                on_each_cpu(hardware_enable, NULL, 1);
+                on_each_cpu(hardware_enable_nolock, NULL, 1);
 
                 if (atomic_read(&hardware_enable_failed)) {
                         hardware_disable_all_nolock();
@@ -1938,7 +2239,7 @@ static int hardware_enable_all(void)
                 }
         }
 
-        spin_unlock(&kvm_lock);
+        raw_spin_unlock(&kvm_lock);
 
         return r;
 }
@@ -1968,18 +2269,12 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 }
 
 
-asmlinkage void kvm_handle_fault_on_reboot(void)
+asmlinkage void kvm_spurious_fault(void)
 {
-        if (kvm_rebooting) {
-                /* spin while reset goes on */
-                local_irq_enable();
-                while (true)
-                        ;
-        }
         /* Fault while not rebooting.  We want the trace. */
         BUG();
 }
-EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot);
+EXPORT_SYMBOL_GPL(kvm_spurious_fault);
 
 static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
                       void *v)
@@ -1992,7 +2287,7 @@ static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
          */
         printk(KERN_INFO "kvm: exiting hardware virtualization\n");
         kvm_rebooting = true;
-        on_each_cpu(hardware_disable, NULL, 1);
+        on_each_cpu(hardware_disable_nolock, NULL, 1);
         return NOTIFY_OK;
 }
 
@@ -2106,10 +2401,10 @@ static int vm_stat_get(void *_offset, u64 *val)
         struct kvm *kvm;
 
         *val = 0;
-        spin_lock(&kvm_lock);
+        raw_spin_lock(&kvm_lock);
         list_for_each_entry(kvm, &vm_list, vm_list)
                 *val += *(u32 *)((void *)kvm + offset);
-        spin_unlock(&kvm_lock);
+        raw_spin_unlock(&kvm_lock);
         return 0;
 }
 
@@ -2123,12 +2418,12 @@ static int vcpu_stat_get(void *_offset, u64 *val)
         int i;
 
         *val = 0;
-        spin_lock(&kvm_lock);
+        raw_spin_lock(&kvm_lock);
         list_for_each_entry(kvm, &vm_list, vm_list)
                 kvm_for_each_vcpu(i, vcpu, kvm)
                         *val += *(u32 *)((void *)vcpu + offset);
 
-        spin_unlock(&kvm_lock);
+        raw_spin_unlock(&kvm_lock);
         return 0;
 }
 
@@ -2159,31 +2454,26 @@ static void kvm_exit_debug(void)
         debugfs_remove(kvm_debugfs_dir);
 }
 
-static int kvm_suspend(struct sys_device *dev, pm_message_t state)
+static int kvm_suspend(void)
 {
         if (kvm_usage_count)
-                hardware_disable(NULL);
+                hardware_disable_nolock(NULL);
         return 0;
 }
 
-static int kvm_resume(struct sys_device *dev)
+static void kvm_resume(void)
 {
-        if (kvm_usage_count)
-                hardware_enable(NULL);
-        return 0;
+        if (kvm_usage_count) {
+                WARN_ON(raw_spin_is_locked(&kvm_lock));
+                hardware_enable_nolock(NULL);
+        }
 }
 
-static struct sysdev_class kvm_sysdev_class = {
-        .name = "kvm",
+static struct syscore_ops kvm_syscore_ops = {
         .suspend = kvm_suspend,
         .resume = kvm_resume,
 };
 
-static struct sys_device kvm_sysdev = {
-        .id = 0,
-        .cls = &kvm_sysdev_class,
-};
-
 struct page *bad_page;
 pfn_t bad_pfn;
 
@@ -2267,14 +2557,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
                 goto out_free_2;
         register_reboot_notifier(&kvm_reboot_notifier);
 
-        r = sysdev_class_register(&kvm_sysdev_class);
-        if (r)
-                goto out_free_3;
-
-        r = sysdev_register(&kvm_sysdev);
-        if (r)
-                goto out_free_4;
-
         /* A kmem cache lets us meet the alignment requirements of fx_save. */
         if (!vcpu_align)
                 vcpu_align = __alignof__(struct kvm_vcpu);
@@ -2282,9 +2564,13 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
                                            0, NULL);
         if (!kvm_vcpu_cache) {
                 r = -ENOMEM;
-                goto out_free_5;
+                goto out_free_3;
         }
 
+        r = kvm_async_pf_init();
+        if (r)
+                goto out_free;
+
         kvm_chardev_ops.owner = module;
         kvm_vm_fops.owner = module;
         kvm_vcpu_fops.owner = module;
@@ -2292,9 +2578,11 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
         r = misc_register(&kvm_dev);
         if (r) {
                 printk(KERN_ERR "kvm: misc device register failed\n");
-                goto out_free;
+                goto out_unreg;
         }
 
+        register_syscore_ops(&kvm_syscore_ops);
+
         kvm_preempt_ops.sched_in = kvm_sched_in;
         kvm_preempt_ops.sched_out = kvm_sched_out;
 
@@ -2302,12 +2590,10 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
         return 0;
 
+out_unreg:
+        kvm_async_pf_deinit();
 out_free:
         kmem_cache_destroy(kvm_vcpu_cache);
-out_free_5:
-        sysdev_unregister(&kvm_sysdev);
-out_free_4:
-        sysdev_class_unregister(&kvm_sysdev_class);
 out_free_3:
         unregister_reboot_notifier(&kvm_reboot_notifier);
         unregister_cpu_notifier(&kvm_cpu_notifier);
@@ -2334,11 +2620,11 @@ void kvm_exit(void)
         kvm_exit_debug();
         misc_deregister(&kvm_dev);
         kmem_cache_destroy(kvm_vcpu_cache);
-        sysdev_unregister(&kvm_sysdev);
-        sysdev_class_unregister(&kvm_sysdev_class);
+        kvm_async_pf_deinit();
+        unregister_syscore_ops(&kvm_syscore_ops);
         unregister_reboot_notifier(&kvm_reboot_notifier);
         unregister_cpu_notifier(&kvm_cpu_notifier);
-        on_each_cpu(hardware_disable, NULL, 1);
+        on_each_cpu(hardware_disable_nolock, NULL, 1);
         kvm_arch_hardware_unsetup();
         kvm_arch_exit();
         free_cpumask_var(cpus_hardware_enabled);