Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

2 files changed, 477 insertions, 47 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index b2e12893e3f..f7ba099049e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -40,6 +40,7 @@
 #include <linux/kvm_para.h>
 #include <linux/pagemap.h>
 #include <linux/mman.h>
+#include <linux/swap.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -59,7 +60,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
 
 static __read_mostly struct preempt_ops kvm_preempt_ops;
 
-static struct dentry *debugfs_dir;
+struct dentry *kvm_debugfs_dir;
 
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
@@ -119,6 +120,29 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	smp_call_function_mask(cpus, ack_flush, NULL, 1);
 }
 
+void kvm_reload_remote_mmus(struct kvm *kvm)
+{
+	int i, cpu;
+	cpumask_t cpus;
+	struct kvm_vcpu *vcpu;
+
+	cpus_clear(cpus);
+	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+		vcpu = kvm->vcpus[i];
+		if (!vcpu)
+			continue;
+		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
+			continue;
+		cpu = vcpu->cpu;
+		if (cpu != -1 && cpu != raw_smp_processor_id())
+			cpu_set(cpu, cpus);
+	}
+	if (cpus_empty(cpus))
+		return;
+	smp_call_function_mask(cpus, ack_flush, NULL, 1);
+}
+
+
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 {
 	struct page *page;
@@ -170,6 +194,7 @@ static struct kvm *kvm_create_vm(void)
 	mutex_init(&kvm->lock);
 	kvm_io_bus_init(&kvm->mmio_bus);
 	init_rwsem(&kvm->slots_lock);
+	atomic_set(&kvm->users_count, 1);
 	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	spin_unlock(&kvm_lock);
@@ -189,9 +214,13 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		vfree(free->dirty_bitmap);
 
+	if (!dont || free->lpage_info != dont->lpage_info)
+		vfree(free->lpage_info);
+
 	free->npages = 0;
 	free->dirty_bitmap = NULL;
 	free->rmap = NULL;
+	free->lpage_info = NULL;
 }
 
 void kvm_free_physmem(struct kvm *kvm)
@@ -215,11 +244,25 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	mmdrop(mm);
 }
 
+void kvm_get_kvm(struct kvm *kvm)
+{
+	atomic_inc(&kvm->users_count);
+}
+EXPORT_SYMBOL_GPL(kvm_get_kvm);
+
+void kvm_put_kvm(struct kvm *kvm)
+{
+	if (atomic_dec_and_test(&kvm->users_count))
+		kvm_destroy_vm(kvm);
+}
+EXPORT_SYMBOL_GPL(kvm_put_kvm);
+
+
 static int kvm_vm_release(struct inode *inode, struct file *filp)
 {
 	struct kvm *kvm = filp->private_data;
 
-	kvm_destroy_vm(kvm);
+	kvm_put_kvm(kvm);
 	return 0;
 }
 
@@ -301,6 +344,25 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		new.user_alloc = user_alloc;
 		new.userspace_addr = mem->userspace_addr;
 	}
+	if (npages && !new.lpage_info) {
+		int largepages = npages / KVM_PAGES_PER_HPAGE;
+		if (npages % KVM_PAGES_PER_HPAGE)
+			largepages++;
+		if (base_gfn % KVM_PAGES_PER_HPAGE)
+			largepages++;
+
+		new.lpage_info = vmalloc(largepages * sizeof(*new.lpage_info));
+
+		if (!new.lpage_info)
+			goto out_free;
+
+		memset(new.lpage_info, 0, largepages * sizeof(*new.lpage_info));
+
+		if (base_gfn % KVM_PAGES_PER_HPAGE)
+			new.lpage_info[0].write_count = 1;
+		if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE)
+			new.lpage_info[largepages-1].write_count = 1;
+	}
 
 	/* Allocate page dirty bitmap if needed */
 	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
@@ -397,6 +459,12 @@ int is_error_page(struct page *page)
 }
 EXPORT_SYMBOL_GPL(is_error_page);
 
+int is_error_pfn(pfn_t pfn)
+{
+	return pfn == bad_pfn;
+}
+EXPORT_SYMBOL_GPL(is_error_pfn);
+
 static inline unsigned long bad_hva(void)
 {
 	return PAGE_OFFSET;
@@ -444,7 +512,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
-static unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
+unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *slot;
 
@@ -454,11 +522,12 @@ static unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 		return bad_hva();
 	return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
 }
+EXPORT_SYMBOL_GPL(gfn_to_hva);
 
 /*
  * Requires current->mm->mmap_sem to be held
  */
-struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 {
 	struct page *page[1];
 	unsigned long addr;
@@ -469,7 +538,7 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 	addr = gfn_to_hva(kvm, gfn);
 	if (kvm_is_error_hva(addr)) {
 		get_page(bad_page);
-		return bad_page;
+		return page_to_pfn(bad_page);
 	}
 
 	npages = get_user_pages(current, current->mm, addr, 1, 1, 1, page,
@@ -477,27 +546,71 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 
 	if (npages != 1) {
 		get_page(bad_page);
-		return bad_page;
+		return page_to_pfn(bad_page);
 	}
 
-	return page[0];
+	return page_to_pfn(page[0]);
+}
+
+EXPORT_SYMBOL_GPL(gfn_to_pfn);
+
+struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+{
+	return pfn_to_page(gfn_to_pfn(kvm, gfn));
 }
 
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
 void kvm_release_page_clean(struct page *page)
 {
-	put_page(page);
+	kvm_release_pfn_clean(page_to_pfn(page));
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
+void kvm_release_pfn_clean(pfn_t pfn)
+{
+	put_page(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
+
 void kvm_release_page_dirty(struct page *page)
 {
+	kvm_release_pfn_dirty(page_to_pfn(page));
+}
+EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
+
+void kvm_release_pfn_dirty(pfn_t pfn)
+{
+	kvm_set_pfn_dirty(pfn);
+	kvm_release_pfn_clean(pfn);
+}
+EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
+
+void kvm_set_page_dirty(struct page *page)
+{
+	kvm_set_pfn_dirty(page_to_pfn(page));
+}
+EXPORT_SYMBOL_GPL(kvm_set_page_dirty);
+
+void kvm_set_pfn_dirty(pfn_t pfn)
+{
+	struct page *page = pfn_to_page(pfn);
 	if (!PageReserved(page))
 		SetPageDirty(page);
-	put_page(page);
 }
-EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
+EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
+
+void kvm_set_pfn_accessed(pfn_t pfn)
+{
+	mark_page_accessed(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
+
+void kvm_get_pfn(pfn_t pfn)
+{
+	get_page(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_get_pfn);
 
 static int next_segment(unsigned long len, int offset)
 {
@@ -554,7 +667,9 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
 	addr = gfn_to_hva(kvm, gfn);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
+	pagefault_disable();
 	r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len);
+	pagefault_enable();
 	if (r)
 		return -EFAULT;
 	return 0;
@@ -651,6 +766,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	 * We will block until either an interrupt or a signal wakes us up
 	 */
 	while (!kvm_cpu_has_interrupt(vcpu)
+	       && !kvm_cpu_has_pending_timer(vcpu)
 	       && !signal_pending(current)
 	       && !kvm_arch_vcpu_runnable(vcpu)) {
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -678,8 +794,10 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	if (vmf->pgoff == 0)
 		page = virt_to_page(vcpu->run);
+#ifdef CONFIG_X86
 	else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->arch.pio_data);
+#endif
 	else
 		return VM_FAULT_SIGBUS;
 	get_page(page);
@@ -701,11 +819,11 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp)
 {
 	struct kvm_vcpu *vcpu = filp->private_data;
 
-	fput(vcpu->kvm->filp);
+	kvm_put_kvm(vcpu->kvm);
 	return 0;
 }
 
-static struct file_operations kvm_vcpu_fops = {
+static const struct file_operations kvm_vcpu_fops = {
 	.release        = kvm_vcpu_release,
 	.unlocked_ioctl = kvm_vcpu_ioctl,
 	.compat_ioctl   = kvm_vcpu_ioctl,
@@ -717,15 +835,9 @@ static struct file_operations kvm_vcpu_fops = {
  */
 static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 {
-	int fd, r;
-	struct inode *inode;
-	struct file *file;
-
-	r = anon_inode_getfd(&fd, &inode, &file,
-			     "kvm-vcpu", &kvm_vcpu_fops, vcpu);
-	if (r)
-		return r;
-	atomic_inc(&vcpu->kvm->filp->f_count);
+	int fd = anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu);
+	if (fd < 0)
+		kvm_put_kvm(vcpu->kvm);
 	return fd;
 }
 
@@ -760,6 +872,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
 	mutex_unlock(&kvm->lock);
 
 	/* Now it's all set up, let userspace reach it */
+	kvm_get_kvm(kvm);
 	r = create_vcpu_fd(vcpu);
 	if (r < 0)
 		goto unlink;
@@ -802,28 +915,39 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
 		break;
 	case KVM_GET_REGS: {
-		struct kvm_regs kvm_regs;
+		struct kvm_regs *kvm_regs;
 
-		memset(&kvm_regs, 0, sizeof kvm_regs);
-		r = kvm_arch_vcpu_ioctl_get_regs(vcpu, &kvm_regs);
-		if (r)
+		r = -ENOMEM;
+		kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
+		if (!kvm_regs)
 			goto out;
+		r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs);
+		if (r)
+			goto out_free1;
 		r = -EFAULT;
-		if (copy_to_user(argp, &kvm_regs, sizeof kvm_regs))
-			goto out;
+		if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs)))
+			goto out_free1;
 		r = 0;
+out_free1:
+		kfree(kvm_regs);
 		break;
 	}
 	case KVM_SET_REGS: {
-		struct kvm_regs kvm_regs;
+		struct kvm_regs *kvm_regs;
 
-		r = -EFAULT;
-		if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs))
+		r = -ENOMEM;
+		kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
+		if (!kvm_regs)
 			goto out;
-		r = kvm_arch_vcpu_ioctl_set_regs(vcpu, &kvm_regs);
+		r = -EFAULT;
+		if (copy_from_user(kvm_regs, argp, sizeof(struct kvm_regs)))
+			goto out_free2;
+		r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs);
 		if (r)
-			goto out;
+			goto out_free2;
 		r = 0;
+out_free2:
+		kfree(kvm_regs);
 		break;
 	}
 	case KVM_GET_SREGS: {
@@ -851,6 +975,30 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_GET_MP_STATE: {
+		struct kvm_mp_state mp_state;
+
+		r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state);
+		if (r)
+			goto out;
+		r = -EFAULT;
+		if (copy_to_user(argp, &mp_state, sizeof mp_state))
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_SET_MP_STATE: {
+		struct kvm_mp_state mp_state;
+
+		r = -EFAULT;
+		if (copy_from_user(&mp_state, argp, sizeof mp_state))
+			goto out;
+		r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
 	case KVM_TRANSLATE: {
 		struct kvm_translation tr;
 
@@ -1005,7 +1153,7 @@ static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-static struct file_operations kvm_vm_fops = {
+static const struct file_operations kvm_vm_fops = {
 	.release        = kvm_vm_release,
 	.unlocked_ioctl = kvm_vm_ioctl,
 	.compat_ioctl   = kvm_vm_ioctl,
@@ -1014,21 +1162,15 @@ static struct file_operations kvm_vm_fops = {
 
 static int kvm_dev_ioctl_create_vm(void)
 {
-	int fd, r;
-	struct inode *inode;
-	struct file *file;
+	int fd;
 	struct kvm *kvm;
 
 	kvm = kvm_create_vm();
 	if (IS_ERR(kvm))
 		return PTR_ERR(kvm);
-	r = anon_inode_getfd(&fd, &inode, &file, "kvm-vm", &kvm_vm_fops, kvm);
-	if (r) {
-		kvm_destroy_vm(kvm);
-		return r;
-	}
-
-	kvm->filp = file;
+	fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm);
+	if (fd < 0)
+		kvm_put_kvm(kvm);
 
 	return fd;
 }
@@ -1059,7 +1201,15 @@ static long kvm_dev_ioctl(struct file *filp,
 		r = -EINVAL;
 		if (arg)
 			goto out;
-		r = 2 * PAGE_SIZE;
+		r = PAGE_SIZE;     /* struct kvm_run */
+#ifdef CONFIG_X86
+		r += PAGE_SIZE;    /* pio data page */
+#endif
+		break;
+	case KVM_TRACE_ENABLE:
+	case KVM_TRACE_PAUSE:
+	case KVM_TRACE_DISABLE:
+		r = kvm_trace_ioctl(ioctl, arg);
 		break;
 	default:
 		return kvm_arch_dev_ioctl(filp, ioctl, arg);
@@ -1232,9 +1382,9 @@ static void kvm_init_debug(void)
 {
 	struct kvm_stats_debugfs_item *p;
 
-	debugfs_dir = debugfs_create_dir("kvm", NULL);
+	kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
 	for (p = debugfs_entries; p->name; ++p)
-		p->dentry = debugfs_create_file(p->name, 0444, debugfs_dir,
+		p->dentry = debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
 						(void *)(long)p->offset,
 						stat_fops[p->kind]);
 }
@@ -1245,7 +1395,7 @@ static void kvm_exit_debug(void)
 
 	for (p = debugfs_entries; p->name; ++p)
 		debugfs_remove(p->dentry);
-	debugfs_remove(debugfs_dir);
+	debugfs_remove(kvm_debugfs_dir);
 }
 
 static int kvm_suspend(struct sys_device *dev, pm_message_t state)
@@ -1272,6 +1422,7 @@ static struct sys_device kvm_sysdev = {
 };
 
 struct page *bad_page;
+pfn_t bad_pfn;
 
 static inline
 struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
@@ -1313,6 +1464,8 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 		goto out;
 	}
 
+	bad_pfn = page_to_pfn(bad_page);
+
 	r = kvm_arch_hardware_setup();
 	if (r < 0)
 		goto out_free_0;
@@ -1386,6 +1539,7 @@ EXPORT_SYMBOL_GPL(kvm_init);
 
 void kvm_exit(void)
 {
+	kvm_trace_cleanup();
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
 	sysdev_unregister(&kvm_sysdev);
diff --git a/virt/kvm/kvm_trace.c b/virt/kvm/kvm_trace.c
new file mode 100644
index 00000000000..0e495470788
--- /dev/null
+++ b/virt/kvm/kvm_trace.c
@@ -0,0 +1,276 @@
+/*
+ * kvm trace
+ *
+ * It is designed to allow debugging traces of kvm to be generated
+ * on UP / SMP machines.  Each trace entry can be timestamped so that
+ * it's possible to reconstruct a chronological record of trace events.
+ * The implementation refers to blktrace kernel support.
+ *
+ * Copyright (c) 2008 Intel Corporation
+ * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
+ *
+ * Authors: Feng(Eric) Liu, eric.e.liu@intel.com
+ *
+ * Date:    Feb 2008
+ */
+
+#include <linux/module.h>
+#include <linux/relay.h>
+#include <linux/debugfs.h>
+
+#include <linux/kvm_host.h>
+
+#define KVM_TRACE_STATE_RUNNING 	(1 << 0)
+#define KVM_TRACE_STATE_PAUSE 		(1 << 1)
+#define KVM_TRACE_STATE_CLEARUP 	(1 << 2)
+
+struct kvm_trace {
+	int trace_state;
+	struct rchan *rchan;
+	struct dentry *lost_file;
+	atomic_t lost_records;
+};
+static struct kvm_trace *kvm_trace;
+
+struct kvm_trace_probe {
+	const char *name;
+	const char *format;
+	u32 cycle_in;
+	marker_probe_func *probe_func;
+};
+
+static inline int calc_rec_size(int cycle, int extra)
+{
+	int rec_size = KVM_TRC_HEAD_SIZE;
+
+	rec_size += extra;
+	return cycle ? rec_size += KVM_TRC_CYCLE_SIZE : rec_size;
+}
+
+static void kvm_add_trace(void *probe_private, void *call_data,
+			  const char *format, va_list *args)
+{
+	struct kvm_trace_probe *p = probe_private;
+	struct kvm_trace *kt = kvm_trace;
+	struct kvm_trace_rec rec;
+	struct kvm_vcpu *vcpu;
+	int    i, extra, size;
+
+	if (unlikely(kt->trace_state != KVM_TRACE_STATE_RUNNING))
+		return;
+
+	rec.event	= va_arg(*args, u32);
+	vcpu		= va_arg(*args, struct kvm_vcpu *);
+	rec.pid		= current->tgid;
+	rec.vcpu_id	= vcpu->vcpu_id;
+
+	extra   	= va_arg(*args, u32);
+	WARN_ON(!(extra <= KVM_TRC_EXTRA_MAX));
+	extra 		= min_t(u32, extra, KVM_TRC_EXTRA_MAX);
+	rec.extra_u32   = extra;
+
+	rec.cycle_in 	= p->cycle_in;
+
+	if (rec.cycle_in) {
+		u64 cycle = 0;
+
+		cycle = get_cycles();
+		rec.u.cycle.cycle_lo = (u32)cycle;
+		rec.u.cycle.cycle_hi = (u32)(cycle >> 32);
+
+		for (i = 0; i < rec.extra_u32; i++)
+			rec.u.cycle.extra_u32[i] = va_arg(*args, u32);
+	} else {
+		for (i = 0; i < rec.extra_u32; i++)
+			rec.u.nocycle.extra_u32[i] = va_arg(*args, u32);
+	}
+
+	size = calc_rec_size(rec.cycle_in, rec.extra_u32 * sizeof(u32));
+	relay_write(kt->rchan, &rec, size);
+}
+
+static struct kvm_trace_probe kvm_trace_probes[] = {
+	{ "kvm_trace_entryexit", "%u %p %u %u %u %u %u %u", 1, kvm_add_trace },
+	{ "kvm_trace_handler", "%u %p %u %u %u %u %u %u", 0, kvm_add_trace },
+};
+
+static int lost_records_get(void *data, u64 *val)
+{
+	struct kvm_trace *kt = data;
+
+	*val = atomic_read(&kt->lost_records);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(kvm_trace_lost_ops, lost_records_get, NULL, "%llu\n");
+
+/*
+ *  The relay channel is used in "no-overwrite" mode, it keeps trace of how
+ *  many times we encountered a full subbuffer, to tell user space app the
+ *  lost records there were.
+ */
+static int kvm_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
+				     void *prev_subbuf, size_t prev_padding)
+{
+	struct kvm_trace *kt;
+
+	if (!relay_buf_full(buf))
+		return 1;
+
+	kt = buf->chan->private_data;
+	atomic_inc(&kt->lost_records);
+
+	return 0;
+}
+
+static struct dentry *kvm_create_buf_file_callack(const char *filename,
+						 struct dentry *parent,
+						 int mode,
+						 struct rchan_buf *buf,
+						 int *is_global)
+{
+	return debugfs_create_file(filename, mode, parent, buf,
+				   &relay_file_operations);
+}
+
+static int kvm_remove_buf_file_callback(struct dentry *dentry)
+{
+	debugfs_remove(dentry);
+	return 0;
+}
+
+static struct rchan_callbacks kvm_relay_callbacks = {
+	.subbuf_start 		= kvm_subbuf_start_callback,
+	.create_buf_file 	= kvm_create_buf_file_callack,
+	.remove_buf_file 	= kvm_remove_buf_file_callback,
+};
+
+static int do_kvm_trace_enable(struct kvm_user_trace_setup *kuts)
+{
+	struct kvm_trace *kt;
+	int i, r = -ENOMEM;
+
+	if (!kuts->buf_size || !kuts->buf_nr)
+		return -EINVAL;
+
+	kt = kzalloc(sizeof(*kt), GFP_KERNEL);
+	if (!kt)
+		goto err;
+
+	r = -EIO;
+	atomic_set(&kt->lost_records, 0);
+	kt->lost_file = debugfs_create_file("lost_records", 0444, kvm_debugfs_dir,
+					    kt, &kvm_trace_lost_ops);
+	if (!kt->lost_file)
+		goto err;
+
+	kt->rchan = relay_open("trace", kvm_debugfs_dir, kuts->buf_size,
+				kuts->buf_nr, &kvm_relay_callbacks, kt);
+	if (!kt->rchan)
+		goto err;
+
+	kvm_trace = kt;
+
+	for (i = 0; i < ARRAY_SIZE(kvm_trace_probes); i++) {
+		struct kvm_trace_probe *p = &kvm_trace_probes[i];
+
+		r = marker_probe_register(p->name, p->format, p->probe_func, p);
+		if (r)
+			printk(KERN_INFO "Unable to register probe %s\n",
+			       p->name);
+	}
+
+	kvm_trace->trace_state = KVM_TRACE_STATE_RUNNING;
+
+	return 0;
+err:
+	if (kt) {
+		if (kt->lost_file)
+			debugfs_remove(kt->lost_file);
+		if (kt->rchan)
+			relay_close(kt->rchan);
+		kfree(kt);
+	}
+	return r;
+}
+
+static int kvm_trace_enable(char __user *arg)
+{
+	struct kvm_user_trace_setup kuts;
+	int ret;
+
+	ret = copy_from_user(&kuts, arg, sizeof(kuts));
+	if (ret)
+		return -EFAULT;
+
+	ret = do_kvm_trace_enable(&kuts);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int kvm_trace_pause(void)
+{
+	struct kvm_trace *kt = kvm_trace;
+	int r = -EINVAL;
+
+	if (kt == NULL)
+		return r;
+
+	if (kt->trace_state == KVM_TRACE_STATE_RUNNING) {
+		kt->trace_state = KVM_TRACE_STATE_PAUSE;
+		relay_flush(kt->rchan);
+		r = 0;
+	}
+
+	return r;
+}
+
+void kvm_trace_cleanup(void)
+{
+	struct kvm_trace *kt = kvm_trace;
+	int i;
+
+	if (kt == NULL)
+		return;
+
+	if (kt->trace_state == KVM_TRACE_STATE_RUNNING ||
+	    kt->trace_state == KVM_TRACE_STATE_PAUSE) {
+
+		kt->trace_state = KVM_TRACE_STATE_CLEARUP;
+
+		for (i = 0; i < ARRAY_SIZE(kvm_trace_probes); i++) {
+			struct kvm_trace_probe *p = &kvm_trace_probes[i];
+			marker_probe_unregister(p->name, p->probe_func, p);
+		}
+
+		relay_close(kt->rchan);
+		debugfs_remove(kt->lost_file);
+		kfree(kt);
+	}
+}
+
+int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	long r = -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (ioctl) {
+	case KVM_TRACE_ENABLE:
+		r = kvm_trace_enable(argp);
+		break;
+	case KVM_TRACE_PAUSE:
+		r = kvm_trace_pause();
+		break;
+	case KVM_TRACE_DISABLE:
+		r = 0;
+		kvm_trace_cleanup();
+		break;
+	}
+
+	return r;
+}